Environment adaptive control method and system based on crop growth monitoring

Abstract

This invention provides an environmental adaptive control method and system based on crop growth monitoring, belonging to the field of smart agriculture technology. First, it captures crop growth status data and multi-element data of the growth environment. Then, it identifies crop growth potential characteristics from the crop growth status data. Based on the dynamic relationship between these crop growth potential characteristics and the multi-element environmental data, it constructs an environmental evolution path. An environmental coordinated regulation sequence is generated according to the environmental evolution path. The sequence is executed to regulate the environment in stages, while simultaneously and continuously capturing the regulated data. The growth potential characteristics are updated based on the new data, and the environmental evolution path is optimized. This invention can adjust environmental parameters in real time according to the crop growth status, achieving environmental adaptive control, fully stimulating crop growth potential, improving yield and quality, and reducing costs.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture technology, and more specifically, to an environmental adaptive control method and system based on crop growth monitoring. Background Technology

[0002] In the field of agricultural planting, precisely controlling the crop growth environment to achieve high yields and quality has long been a goal. Traditional methods of controlling the crop growth environment are mostly based on setting fixed environmental parameters, such as controlling the greenhouse environment according to predetermined values ​​for temperature, humidity, and light intensity. However, crop growth is a dynamic process; its growth status changes continuously over time, and the environmental requirements differ at different growth stages. Moreover, crop growth is influenced by a combination of environmental factors, which are interconnected and interact with each other, jointly affecting crop growth and development.

[0003] Existing environmental control technologies often consider only one or a few environmental factors, lacking a comprehensive analysis of the complex relationships between crop growth status and multiple environmental factors. For example, when adjusting light intensity, the impact of light on crop water evaporation and gas exchange may not be taken into account; when adjusting temperature, the effects of temperature on crop physiological metabolism and growth rhythms may be ignored. These isolated environmental control methods are insufficient to meet the dynamic needs of crops at different growth stages, resulting in the crop's growth potential not being fully realized, thus affecting crop yield and quality. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide an environmental adaptive control method based on crop growth monitoring, the method comprising:

[0005] The system captures crop growth status data and multi-element data of the crop growth environment. The crop growth status data includes static parameters of crop organ morphology, dynamic processes of physiological metabolism, and characteristics of growth rhythm fluctuations. The multi-element data of the crop growth environment includes environmental composition data related to light, water, gas, and temperature within the crop growth space.

[0006] Identify crop growth potential characteristics from the crop growth status data. These characteristics are core features related to the upper limit of crop growth and its evolutionary direction under suitable environmental conditions.

[0007] Based on the dynamic interaction between the crop growth potential characteristics and the multi-element data of the crop growth environment, an environmental evolution path is constructed. The environmental evolution path is a phased environmental change scheme that guides the current environment to gradually transition towards adapting to the crop growth potential characteristics.

[0008] An environmental coordination regulation sequence is generated based on the environmental evolution path. The environmental coordination regulation sequence includes the regulation methods, transition rhythms, and inter-element linkage logic of environmental elements at each stage of environmental evolution.

[0009] The environmental coordinated regulation sequence is executed to regulate the crop growth environment in stages, and the crop growth status data and environmental multi-factor data after regulation are captured simultaneously and continuously. The crop growth potential characteristics are updated based on the crop growth status data after regulation, and the environmental evolution path is optimized using the updated crop growth potential characteristics.

[0010] Furthermore, embodiments of the present invention also provide an environmental adaptive control system based on crop growth monitoring, characterized in that it includes:

[0011] A processor; a machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to execute the above-described environmental adaptive control method based on crop growth monitoring by executing the machine-executable instructions.

[0012] In another aspect, embodiments of the present invention also provide a computer program product, the computer program product including machine-executable instructions, the machine-executable instructions being stored in a computer-readable storage medium, a processor of an environmental adaptive control system based on crop growth monitoring reading the machine-executable instructions from the computer-readable storage medium, the processor executing the machine-executable instructions, causing the environmental adaptive control system based on crop growth monitoring to execute the above-described environmental adaptive control method based on crop growth monitoring.

[0013] Based on the above, by capturing crop growth status data and multi-element data of the crop growth environment, and identifying crop growth potential characteristics from the crop growth status data, it is possible to accurately grasp the upper limit of crop growth and evolution direction under suitable environmental conditions. Based on the dynamic interaction between crop growth potential characteristics and multi-element environmental data, an environmental evolution path is constructed, enabling the scientific planning and orderly guidance of environmental regulation, allowing the environment to gradually transition towards a direction suitable for crop growth potential. An environmental synergistic regulation sequence is generated based on the environmental evolution path, clarifying the regulation methods, transition rhythms, and inter-element linkage logic of environmental elements at each stage of environmental evolution. Executing the environmental synergistic regulation sequence and continuously monitoring and updating the crop growth environment and status allows for real-time optimization of the environmental evolution path based on the actual crop growth situation, fully stimulating crop growth potential, improving crop yield and quality, while reducing energy consumption and production costs. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the execution flow of the environmental adaptive control method based on crop growth monitoring provided in an embodiment of the present invention.

[0015] Figure 2 This is a schematic diagram of exemplary hardware and software components of an environmental adaptive control system based on crop growth monitoring provided in an embodiment of the present invention. Detailed Implementation

[0016] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating an environmental adaptive control method based on crop growth monitoring, provided in one embodiment of the present invention. The following is a detailed description of this environmental adaptive control method based on crop growth monitoring.

[0017] Step S110: Capture crop growth status data and crop growth environment multi-element data. The crop growth status data includes static parameters of crop organ morphology, dynamic processes of physiological metabolism, and characteristics of growth rhythm fluctuations. The crop growth environment multi-element data includes environmental composition data related to light, water, gas, and temperature within the crop growth space.

[0018] In this embodiment, a digital rice platform is used as the application scenario to capture the growth status and environmental data of rice crops. This can be achieved by deploying multispectral cameras, lidar, and physiological monitoring sensors in the rice planting area. Multispectral cameras are used to acquire information such as the color and texture of rice leaves, and then extract static parameters of organ morphology, such as leaf length, width, and leaf area index. LiDAR is used to scan the three-dimensional structure of the rice plant to acquire parameters such as stem height, diameter, and number of tillers. Physiological monitoring sensors are implanted in the rice leaves and stems to monitor dynamic physiological metabolic processes such as photosynthetic rate, transpiration intensity, and sugar content in real time. Growth rhythm fluctuations are obtained by periodically recording parameters such as rice plant height, number of tillers, and leaf growth rate over a continuous period of time, for example, recording data at a fixed time each day for continuous monitoring throughout a growing season.

[0019] Furthermore, environmental monitoring stations are set up in the paddy fields according to a certain spatial distribution. Light element data is collected through light sensors, recording the light intensity (in lux) and light duration (in hours) at different time periods; moisture element data is obtained through soil moisture sensors and water level monitoring devices, including soil moisture content (in percentage) and irrigation water replenishment frequency (in days / times); gas element data is monitored through gas sensors, mainly including changes in carbon dioxide concentration (in ppm) and oxygen concentration (in percentage); temperature element data is collected through temperature sensors, recording the distribution of air temperature and soil temperature and the temperature fluctuation range (in degrees Celsius). All of the above data is uploaded to the database of the digital rice platform in real time through the Internet of Things transmission module, with the data sampling frequency set to once every 10 minutes to ensure the continuity and timeliness of the data.

[0020] Step S120: Identify crop growth potential characteristics from the crop growth status data. The crop growth potential characteristics are the core features related to the upper limit of crop growth and evolution direction under suitable environmental conditions.

[0021] Step S121: Separate the organ morphology data, physiological metabolism data, and growth rhythm data from the crop growth status data. The organ morphology data records the structural morphology and size correlation information of the crop roots, stems, leaves, flowers, and fruits. The physiological metabolism data records the dynamic process information of crop nutrient synthesis, material transport, and energy conversion. The growth rhythm data records the growth activity level and periodic fluctuation information of the crop at different time periods.

[0022] In the digital rice platform, the crop growth status data captured in step S110 is processed by breaking it down. Regarding organ morphology data, structural morphology and size correlation information related to rice roots, stems, leaves, flowers, and fruits are extracted from data acquired by multispectral cameras and lidar. For example, root morphology data includes root length, diameter, distribution depth, and number of lateral roots; stem morphology data includes stem height, internode length, stem diameter, and tillering angle; leaf morphology data includes leaf length, width, leaf area, leaf inclination angle, and leaf color value; flower morphology data includes the number of spikelets, flowering time, and anther morphology; and fruit morphology data includes grain length, width, and thousand-grain weight. This data is stored in a structured data table, with each record corresponding to the observation value of a rice plant or a specific organ at a specific time point.

[0023] The physiological metabolic data was broken down into its components. From the raw data acquired by physiological monitoring sensors, dynamic process information related to nutrient synthesis, substance transport, and energy conversion was extracted. Data on nutrient synthesis included photosynthetic rate, chlorophyll content, and carotenoid content during photosynthesis. Data on substance transport included the transport rate of sucrose in the phloem and the distribution ratio of mineral elements such as nitrogen, phosphorus, and potassium within the plant. Data on energy conversion included respiration intensity and ATP production rate. This data was stored in time series format, with each time series corresponding to the change of a specific physiological metabolic indicator over time.

[0024] The decomposition of growth rhythm data extracts information reflecting the level of growth activity and cyclical fluctuations at different times from continuously recorded rice growth parameters. Growth activity is characterized by parameters such as daily increase in plant height, leaf growth rate, and tillering rate; cyclical fluctuations are obtained by analyzing the changes in these parameters at different times of the day (e.g., morning, noon, evening) and at different growth stages (e.g., tillering stage, jointing stage, heading stage, grain-filling stage). For example, during the tillering stage, the number of tillers grown by the rice plant at different times each day is statistically analyzed to form growth rhythm data.

[0025] Step S122: Extract the structural integrity features and growth spatial layout features of each organ from the organ morphology data. The structural integrity features reflect the completeness of the development and the functional integrity of each organ. The growth spatial layout features reflect the distribution pattern of each organ in the growth environment and the ease of resource acquisition.

[0026] Based on the organ morphology data obtained in step S121, structural integrity features and growth space layout features are further extracted. For structural integrity features, taking rice leaves as an example, the completeness of development and functional integrity are assessed by analyzing the leaf morphological parameters. Specifically, leaf integrity is calculated as the ratio of the actual leaf area to the standard area of ​​a healthy leaf of the same variety; the presence of lesions, insect damage, or other damage is detected, and the proportion of damaged area to the total leaf area is calculated; leaf color uniformity is assessed by calculating the color parameter differences in different regions of the leaf using multispectral data. Smaller differences indicate more uniform color and higher structural integrity. These indicators are combined to form a leaf structural integrity feature vector, which includes parameters across multiple dimensions such as leaf integrity, proportion of damaged area, and color uniformity.

[0027] Regarding the spatial layout characteristics of the plant, taking rice plants as an example again, we analyze the distribution patterns of various organs in the growth environment and their accessibility to resources. For example, the spatial layout characteristics of the stem include the height distribution of the stem, the spatial arrangement of tillers (such as whether they are evenly distributed), and the distance between the stem and surrounding plants; the spatial layout characteristics of the leaves include the spatial distribution of the leaf area index, the leaf tilt angle distribution (the proportion of leaves at different angles), and the vertical distribution position of the leaves in the canopy. By calculating these parameters, a spatial layout characteristic vector is formed, which can reflect the spatial distribution of various organs of the rice plant and the impact of the above distribution on the access to resources such as light and water.

[0028] Step S123: Extract the nutrient synthesis efficiency characteristics, material transport smoothness characteristics, and energy conversion stability characteristics from the physiological metabolic data. The nutrient synthesis efficiency characteristics reflect the crop's ability to synthesize the nutrients it needs using environmental resources. The material transport smoothness characteristics reflect the smoothness of nutrient transport between organs. The energy conversion stability characteristics reflect the crop's ability to continuously convert environmental energy into growth energy.

[0029] From the physiological metabolic data obtained in step S121, nutrient synthesis efficiency characteristics, substance transport smoothness characteristics, and energy conversion stability characteristics are extracted. Taking photosynthesis as an example, nutrient synthesis efficiency characteristics are calculated based on the acquired photosynthetic rate data, combined with environmental data such as light intensity and carbon dioxide concentration, to determine indicators such as light energy utilization efficiency (the ratio of photosynthetic rate to light intensity) and carbon dioxide fixation efficiency (the ratio of photosynthetic rate to carbon dioxide concentration). Simultaneously, considering the impact of chlorophyll content on photosynthesis, a correlation analysis is performed between chlorophyll content and photosynthetic rate to form a nutrient synthesis efficiency feature vector. This feature vector includes parameters such as light energy utilization efficiency, carbon dioxide fixation efficiency, and the correlation coefficient between chlorophyll content and photosynthetic rate.

[0030] To assess the fluidity of sucrose transport within rice plants, using sucrose transport as an example, the transport rate of sucrose in the phloem and the gradient changes in sucrose concentration between different organs are monitored. The transport rate of sucrose from leaves (source organs) to stems and fruits (sink organs) is calculated, and the rate fluctuations during transport are analyzed. Simultaneously, the differences in sucrose concentration between different organs are calculated; a larger difference indicates stronger transport dynamics and better fluidity. These parameters are then integrated into a feature vector for fluidity of sucrose transport.

[0031] For the stability characteristics of energy conversion, data such as respiration intensity and ATP production rate are used. The variation of respiration intensity at different times (e.g., day and night) and at different growth stages is analyzed, and its coefficient of variation is calculated. The smaller the coefficient of variation, the more stable the energy conversion. Simultaneously, the ratio of ATP production rate to respiration intensity is analyzed to assess the efficiency and stability of energy conversion. These indicators are combined into an energy conversion stability feature vector.

[0032] Step S124: Extract the distribution characteristics of active growth periods and the fluctuation amplitude characteristics of growth cycles from the growth rhythm data. The distribution characteristics of active growth periods reflect the concentrated growth activity of crops at different times of the day, and the fluctuation amplitude characteristics of growth cycles reflect the smooth change of crop growth status within a continuous growth cycle.

[0033] For the growth rhythm data obtained in step S121, the distribution characteristics of active growth periods and the fluctuation amplitude characteristics of the growth cycle are extracted. Taking the daily increase in rice plant height as an example, the day is divided into multiple equal time periods (e.g., every 2 hours), and the proportion of plant height increase in each time period to the total daily increase is calculated. By analyzing these proportions, the main active growth periods of rice are determined. For example, if the proportion of plant height increase between 6-8 am and 4-6 pm is significantly higher than in other time periods, these two time periods are considered active growth periods. The proportion of growth in each time period is used as a feature parameter to form a distribution feature vector of active growth periods.

[0034] To assess the fluctuation range of the growth cycle, taking the variation in tillering rate across different growth stages (such as the tillering stage and jointing stage) as an example, the difference between the maximum and minimum tillering rates within each growth cycle, and the ratio of this difference to the average tillering rate within that cycle, are calculated and used as an indicator of fluctuation range. Simultaneously, the change in tillering rate between adjacent growth cycles is analyzed, and the absolute value of this change is calculated as the ratio of the tillering rate of the previous cycle, serving as an indicator of inter-cycle fluctuation. These indicators are integrated into a growth cycle fluctuation range feature vector, which reflects the smoothness of changes in the growth status of rice within a continuous growth cycle.

[0035] Step S125: Based on the features extracted from the organ morphology data and the features extracted from the physiological metabolism data, establish the correlation between the two, and obtain the correlation between structural integrity features and nutrient synthesis efficiency features, as well as the correlation between growth space layout features and material transport smoothness features.

[0036] Step S1251: The structural integrity features and growth spatial layout features extracted from the organ morphology data are used as the first feature group, and the nutrient synthesis efficiency features and material transport smoothness features extracted from the physiological metabolism data are used as the second feature group. Both sets of features retain the time dimension information and quantification parameters in the original data.

[0037] In the digital rice platform, the structural integrity features and growth spatial layout features extracted in step S122 are integrated into a first feature group. Each feature in this first feature group contains corresponding timestamp information and specific quantitative parameter values. For example, the leaf integrity value over time in the structural integrity features, and the spatial distribution parameter of leaf area index in the growth spatial layout features. Similarly, the nutrient synthesis efficiency features and material transport smoothness features extracted in step S123 are integrated into a second feature group, which also retains time dimension information and quantitative parameters, such as light energy utilization efficiency and sucrose transport rate at different time points.

[0038] Step S1252: Based on the crop growth status data, obtain the dynamic change data of the first feature group and the second feature group during the continuous monitoring period to form time series data of two sets of features, wherein each time node in the time series data corresponds to a set of feature parameters.

[0039] Crop growth status data related to the first and second feature groups are retrieved from the database of the digital rice platform. This data covers a continuous monitoring period (e.g., from rice transplanting to the end of the grain-filling stage). For each feature in the first feature group, its quantified parameter values ​​at different monitoring time points are arranged in chronological order to form a time series of structural integrity features and a time series of growth spatial layout features. Similarly, for each feature in the second feature group, its quantified parameter values ​​are also arranged in chronological order to form a time series of nutrient synthesis efficiency features and a time series of material transport smoothness features. Each time point in each time series corresponds to the specific parameter value of that feature at that time point.

[0040] Step S1253: Perform correlation analysis on the time series of structural integrity features in the first feature group and the time series of nutrient synthesis efficiency features in the second feature group to obtain the time lag relationship and co-change relationship between the changes in structural integrity features and the changes in the response of nutrient synthesis efficiency features.

[0041] Time series correlation analysis was employed to analyze the time series data of structural integrity characteristics and nutrient synthesis efficiency characteristics. First, stationarity tests were performed on both time series to ensure the data met the requirements of correlation analysis. Then, the cross-correlation coefficient between the two time series was calculated. By analyzing the changes in the cross-correlation coefficient with time lags, the time lag relationship between changes in structural integrity characteristics and changes in the response of nutrient synthesis efficiency characteristics was determined. For example, after a change in structural integrity characteristics, how long did it take for the nutrient synthesis efficiency characteristics to begin to show a response change? Simultaneously, the trends of the two time series were analyzed to determine whether they changed in the same direction (simultaneous increase or decrease) or in opposite directions, thereby identifying the accompanying relationship.

[0042] Step S1254: Perform correlation analysis on the time series of growth spatial layout features in the first feature group and the time series of material transport flow features in the second feature group to obtain the time lag relationship and change correlation information between the changes in growth spatial layout features and the changes in material transport flow feature response.

[0043] Similar to step S1253, a correlation analysis is performed on the time series of growth spatial layout characteristics and the time series of material transport flow characteristics. The cross-correlation coefficient between the two is calculated to determine the time lag relationship, i.e., how long it takes for the material transport flow characteristics to respond after a change in the growth spatial layout characteristics. Simultaneously, the relationship between the magnitude of change in the growth spatial layout characteristics and the magnitude of change in the material transport flow characteristics is analyzed. For example, whether an improvement in the growth spatial layout characteristics (such as a more rational leaf distribution) leads to an increase in the material transport flow characteristics, and to what extent, thereby obtaining information on the correlation of changes.

[0044] Step S1255: Based on the results of the two sets of association analysis, divide the association into direct association and indirect association. The direct association is that the change of one set of features directly leads to the change of another set of features. The indirect association is that one set of features leads to the change of another set of features by influencing other intermediate factors.

[0045] Based on the correlation analysis results of steps S1253 and S1254, and combined with physiological knowledge of rice growth, direct and indirect correlations are distinguished. For example, if the leaf integrity in the structural integrity feature increases, it directly leads to an increase in photosynthetic area, thereby increasing the photosynthetic rate in the nutrient synthesis efficiency feature; this correlation is a direct correlation. However, if the leaf area index in the growth space layout feature is too large, it leads to poor ventilation and increased humidity inside the plant, causing pests and diseases, which in turn affects nutrient synthesis efficiency. In the above case, the correlation between the growth space layout feature and the nutrient synthesis efficiency feature is an indirect correlation, with pests and diseases being an intermediate influencing factor.

[0046] Step S1256: For the directly associated feature pairs, define the preceding feature and the subsequent feature, and obtain the correspondence between the response change trend of the subsequent feature when the preceding feature undergoes a specific change trend. The preceding feature is the feature that triggers the change, and the subsequent feature is the feature that produces the response change.

[0047] For example, step S12561: determine a set of feature pairs from the directly associated feature pairs, which includes an organ morphology-related feature and a physiological metabolism-related feature.

[0048] In the digital rice platform, we selected leaf integrity (a structural integrity feature) and photosynthetic rate (a nutrient synthesis efficiency feature) as directly related features for analysis. Leaf integrity is an organ morphology-related feature, while photosynthetic rate is a physiological metabolism-related feature.

[0049] Step S12562: Obtain the time series data of the feature pair during the continuous monitoring period. The time series data includes the specific parameter values ​​of the preceding and subsequent features at each time node.

[0050] Time series data of leaf integrity and photosynthetic rate were retrieved from the database for a continuous monitoring period (e.g., 30 days). Each time point (e.g., each day) had a corresponding leaf integrity value (e.g., 0.85, 0.88, etc.) and photosynthetic rate value (e.g., 15 μmol / m²·s, 16 μmol / m²·s, etc.).

[0051] Step S12563: Compare the parameter values ​​of the preceding feature at adjacent time nodes. If the absolute value of the difference exceeds the preset change threshold, then the time node is determined as the change time node, and the change magnitude of the time node and the preceding feature is recorded.

[0052] The threshold for leaf integrity variation is set to 0.05. Leaf integrity values ​​at adjacent time points are compared. If the absolute value of the difference between the leaf integrity of a later time point and that of a previous time point is greater than 0.05, the later time point is determined as the time point of change. For example, if the leaf integrity is 0.80 on day 5 and 0.86 on day 6, the difference is 0.06, exceeding the threshold of 0.05. Therefore, day 6 is the time point of change, with a variation of 0.06.

[0053] Step S12564: Track the changes of subsequent features after the time node, identify the response time node from the time series data where the subsequent features begin to show a response change, and record the time difference between the response time node and the preceding feature change time node.

[0054] After determining the time point of change (e.g., day 6), the photosynthetic rate changes at subsequent time points (day 7, day 8, etc.). When the change in photosynthetic rate compared to the stable value before the time point exceeds a preset response threshold (e.g., a change in photosynthetic rate exceeding 1 μmol / m²·s), that time point is determined as the response time point. For example, if the photosynthetic rate begins to exceed the response threshold on day 7, then day 7 is the response time point, with a time difference of 1 day.

[0055] Step S12565: Calculate the magnitude of change of subsequent features after the response change.

[0056] Using the photosynthetic rate at the response time point (day 7) as a baseline, the ratio of the maximum change in photosynthetic rate over a subsequent period (e.g., from day 7 to day 10) to the photosynthetic rate at the response time point is calculated as the magnitude of the subsequent characteristic change. For example, if the photosynthetic rate is 15 μmol / m²·s on day 7 and reaches 18 μmol / m²·s on day 10, the change is 3 μmol / m²·s, and the magnitude of the change is 3 / 15 = 0.2.

[0057] Step S12566: Repeat the above tracking, identification and calculation process for all time points of change of the feature pair to obtain the corresponding data of the change amplitude of the preceding feature and the change amplitude of the subsequent feature.

[0058] Repeat steps S12563 to S12565 for all time points of change in the characteristic pair of leaf integrity and photosynthetic rate (such as day 6, day 12, day 20, etc.) to obtain multiple sets of corresponding data for the change range of leaf integrity and photosynthetic rate, such as (0.06, 0.2), (0.08, 0.25), (0.04, 0.15), etc.

[0059] Step S12567: Based on multiple sets of corresponding data, analyze the changing trends of the amplitude of change of the preceding feature and the amplitude of change of the subsequent feature, and define the type of correspondence between the two.

[0060] Trend analysis was performed on multiple sets of corresponding data. A scatter plot was created to observe the relationship between changes in leaf integrity and photosynthetic rate. If the scatter plot roughly resembles a straight line, the relationship is linear; if it shows a curve, it is non-linear. In this example, it is assumed that the scatter plot approximates a linear relationship.

[0061] Step S12568: If the correspondence type is linear, obtain the change ratio between the two; if the correspondence type is nonlinear, obtain the change law and key turning points of the correspondence.

[0062] Since this example shows a linear relationship, the ratio between the change in leaf integrity and the change in photosynthetic rate is calculated using linear regression analysis. Assume that the regression analysis yields a photosynthetic rate change of 3.5 × leaf integrity change, i.e., a ratio of 3.5.

[0063] Step S12569: Integrate the response lag time of the feature pair, multiple sets of corresponding data and the corresponding relationship type to generate corresponding relationship data between the change magnitude of the preceding feature and the subsequent feature, and supplement the corresponding relationship data into the feature association mapping framework.

[0064] Leaf integrity was used as a leading feature and photosynthetic rate as a subsequent feature, with a response lag time of 1 day, a linear relationship type, a change ratio of 3.5, and multiple sets of corresponding data (0.06, 0.2), (0.08, 0.25), (0.04, 0.15), etc., were integrated to generate corresponding relationship data, which was then added to the feature association mapping framework for subsequent feature association network construction.

[0065] Step S1257: For the indirectly associated feature pairs, identify intermediate influencing factors and obtain the transmission path of the leading feature to the subsequent feature through the intermediate influencing factors. The intermediate influencing factors are crop growth-related features between the leading feature and the subsequent feature.

[0066] Taking the indirect correlation between leaf area index (a characteristic of growth space layout) and photosynthetic rate (a characteristic of nutrient synthesis efficiency) as an example, we identify intermediate influencing factors. Analysis of the rice growth process reveals that an excessively high leaf area index may lead to poor ventilation and light penetration between plants, thereby reducing the carbon dioxide concentration on the leaf surface. Since carbon dioxide concentration is a crucial factor affecting photosynthetic rate, the intermediate influencing factor is the carbon dioxide concentration on the leaf surface. The transmission pathway is: increased leaf area index → ​​poor ventilation and light penetration → decreased carbon dioxide concentration on the leaf surface → decreased photosynthetic rate.

[0067] Step S1258: Integrate the correspondence between the directly associated feature pairs and the transmission path of the indirectly associated feature pairs to form a preliminary feature association mapping framework. The feature association mapping framework includes the association type and association information between each group of features.

[0068] The correspondences of directly related feature pairs obtained in steps S1256 and S1257 (such as the linear relationship between leaf integrity and photosynthetic rate, response lag time, etc.) and the transmission paths of indirectly related feature pairs (such as the path by which leaf area index affects photosynthetic rate through carbon dioxide concentration) are integrated to construct a preliminary feature association mapping framework. This feature association mapping framework is represented in the form of a directed graph, where nodes are the various features, directed edges represent the association relationships between features, and the edges are labeled with association information such as association type (direct or indirect), correspondence (such as linear proportion, change law), or transmission path (intermediate influencing factors).

[0069] Step S1259: Compare the preliminary feature association mapping framework with the basic physiological mechanisms of crop growth, and output mapping results that conform to the intrinsic laws of organ morphology and physiological metabolism during crop growth.

[0070] Based on fundamental theories of organ morphology and physiological metabolism in rice physiology, a preliminary feature correlation mapping framework was compared and validated. For example, it was verified whether the direct correlation between leaf integrity and photosynthetic rate conformed to the basic principles of photosynthesis, and whether the transmission pathway of leaf area index affecting photosynthetic rate through carbon dioxide concentration correctly reflected the physiological characteristics of the plant population. Correlation relationships that did not conform to basic physiological mechanisms were corrected or eliminated, ultimately outputting mapping results that conformed to the intrinsic laws of crop growth.

[0071] Step S12510: Supplement the mapping results with the triggering conditions and duration information of each association to form an association mapping between organ morphological features and physiological metabolic features.

[0072] For each association in the mapping results, information on triggering conditions and duration is added. Triggering conditions refer to the degree of change required in the preceding feature to trigger a response in the subsequent feature; for example, a change in leaf integrity exceeding 0.05 is required to significantly affect photosynthetic rate. Duration refers to the duration of the subsequent feature's response; for example, an increase in photosynthetic rate after leaf integrity improves can last for 5 days. Adding this information to the association mapping makes the relationship between organ morphology features and physiological metabolic features more complete and specific.

[0073] Step S126: Based on the correlation and the features extracted from the growth rhythm data, establish a constraint relationship to obtain the constraint relationship between the distribution features of active growth periods and the correlation between the structural integrity features and the nutrient synthesis efficiency features, as well as the constraint relationship between the growth cycle fluctuation amplitude features and the correlation between the growth spatial layout features and the material transport smoothness features.

[0074] Combining the distribution characteristics of active growth periods and the amplitude characteristics of growth cycle fluctuations extracted in step S124, and the correlation established in step S125, a constraint relationship is established. For example, the distribution characteristics of active growth periods indicate that rice grows actively in the morning and evening. During these periods, the correlation between structural integrity characteristics and nutrient synthesis efficiency characteristics may be stronger. Specifically, during the active growth period in the morning, the promoting effect of improved leaf integrity on photosynthetic rate may be more significant than at other times. This is the constraint relationship between the distribution characteristics of active growth periods and the correlation between the two.

[0075] A large value for the amplitude of growth cycle fluctuations indicates that the rice growth status fluctuates drastically across different cycles. Under such circumstances, the relationship between the spatial layout characteristics of growth and the smoothness of material transport may be affected. For example, during the vigorous growth period, the dependence of material transport smoothness on the spatial layout of growth may be stronger, while during the stagnant growth period, this dependence may be weaker, thus forming a constraint relationship between the amplitude of growth cycle fluctuations and the relationship between the two.

[0076] Step S127: Based on the association and constraint relationship, a feature association network is formed, and core feature combinations located at core topological positions or logical hub positions are selected from the feature association network. The change trajectory of the core feature combination in the crop growth status data is tracked, and the change status of the feature parameters and interactions between features in the core feature combination at different monitoring periods is recorded.

[0077] The associations established in step S125 and the constraints established in step S126 are integrated to construct a feature association network containing nodes (features) and edges (associations and constraints). Using network analysis algorithms (such as centrality analysis), the degree centrality, betweenness centrality, and proximity centrality of each feature node are calculated. Feature nodes with higher values ​​are selected; these nodes are the features located in the core topology or logical hub positions. These core features are then combined to form core feature combinations, such as leaf integrity, photosynthetic rate, leaf area index, sucrose translocation rate, and distribution of active growth periods.

[0078] Then, feature parameters of each feature in the core feature combination at different monitoring periods are extracted from the crop growth status data, such as daily leaf integrity values ​​and photosynthetic rate values. The changing state of the interaction between these features is analyzed, such as the change in the correlation strength between leaf integrity and photosynthetic rate over time. The above information is recorded in chronological order to form the change trajectory of the core feature combination.

[0079] Step S128: Based on the change trajectory of the core feature combination, deduce the upper limit parameter of crop growth under no environmental restrictions. The upper limit parameter is the optimal development state that the morphology, physiological metabolism and growth rhythm of various organs of the crop can reach.

[0080] Analyzing the changing trajectories of core characteristic combinations identifies the trends and potential growth space of each characteristic under existing environmental conditions. It is assumed that under ideal, unrestricted environmental conditions (such as sufficient light, suitable temperature, and optimal nutrient supply), each core characteristic will reach a stable optimal value according to its inherent growth law. Through curve fitting and trend extrapolation, the changing trajectories of each core characteristic are extended to predict its limit value under unrestricted environmental conditions. For example, by fitting the exponential growth curve of the photosynthetic rate change trajectory, its final stable maximum value is extrapolated, which is one of the upper limit parameters for physiological metabolism. Similarly, similar derivations are made for organ morphology characteristics (such as plant height and leaf area index) and growth rhythm characteristics (such as the length of the active growth period) to obtain the upper limit parameters for each aspect, which together constitute the set of upper limit parameters for crop growth.

[0081] Step S129: Integrate the change trajectory of the growth upper limit parameter and the core feature combination to form the crop growth potential feature.

[0082] The growth upper limit parameter derived in step S128 is integrated with the change trajectory of the core feature combination recorded in step S127. The growth upper limit parameter reflects the optimal development state of the crop under ideal conditions, while the change trajectory of the core feature combination reflects the growth dynamics of the crop under actual environmental conditions. By combining the two, a feature that comprehensively reflects the crop's growth potential is formed, namely, the crop growth potential feature. This crop growth potential feature not only includes the growth upper limit that the crop can reach, but also the process and dynamic change law of achieving these upper limits.

[0083] Step S130: Based on the dynamic interaction between the crop growth potential characteristics and the multi-element data of the crop growth environment, construct an environmental evolution path. The environmental evolution path is a phased environmental change scheme that guides the current environment to gradually transition towards adapting to the crop growth potential characteristics.

[0084] Step S131: Separate the light element data, water element data, gas element data, and temperature element data from the multi-element data of the crop growth environment. The light element data records the changes in light intensity and the distribution of light duration in the growth environment. The water element data records the water content and water replenishment frequency in the growth environment. The gas element data records the changes in carbon dioxide concentration and oxygen concentration in the growth environment. The temperature element data records the temperature distribution and temperature fluctuation range in the growth environment.

[0085] In the digital rice platform, the multi-element data of crop growth environment captured in step S110 are broken down. For light element data, the data collected by light sensors is used to extract the light intensity variation curve over time (e.g., light intensity values ​​at different times of day) and light duration distribution information (e.g., daily sunshine duration, duration of different light intensity intervals, etc.). For moisture element data, the data obtained from soil moisture sensors and water level monitoring devices is used to separate the time series data of soil moisture content and the frequency data of irrigation water replenishment (e.g., number of irrigations per week, time interval between irrigations, etc.). For gas element data, the data is used to extract hourly variation data of carbon dioxide and oxygen concentrations from gas sensor data. For temperature element data, the data is used to obtain the spatial distribution data of air temperature and soil temperature (e.g., temperature values ​​in different field areas) and temperature fluctuation amplitude data (e.g., the difference between the highest and lowest temperatures of the day) from temperature sensor data.

[0086] Step S132: Analyze the relationship between the core features of the crop growth potential characteristics and the light element data, and generate the demand form information of the optimal state of organ morphology for light intensity changes and light duration distribution, as well as the dependence pattern information of the optimal state of physiological metabolism on light elements in the upper limit parameters of growth.

[0087] Taking core characteristics of crop growth potential (such as leaf area and photosynthetic rate) as examples, this paper analyzes their relationship with light element data. For optimal organ morphology, such as the upper limit of leaf area growth, by analyzing leaf growth data under different light intensities and durations, the paper determines the required light intensity range (e.g., 30,000-50,000 lux) and light duration (e.g., 10-12 hours per day) for achieving optimal leaf area, generating demand-based information. For optimal physiological metabolism, such as the upper limit of photosynthetic rate, the paper analyzes the relationship curve between photosynthetic rate and light intensity, determines the light intensity at which the photosynthetic rate reaches its maximum value (light saturation point), and the variation law of photosynthetic rate under different light intensities, generating dependency pattern information. For example, the photosynthetic rate increases linearly with increasing light intensity below the light saturation point and remains stable above the light saturation point.

[0088] Step S133: Analyze the relationship between the core features of the crop growth potential characteristics and the water element data, and generate the demand form information of the optimal state of organ morphology on water content and water replenishment frequency, the dependence pattern information of the optimal state of physiological metabolism on water elements, and the response form information of the optimal state of growth rhythm to changes in water elements.

[0089] This study analyzes the interaction between core characteristics of crop growth potential, such as root depth (organ morphology), transpiration rate (physiological metabolism), and tillering rhythm (growth rhythm), and water element data. Regarding optimal organ morphology, achieving optimal root depth requires a suitable soil moisture content range (e.g., 60%-80% of field capacity) and a reasonable water replenishment frequency (e.g., irrigation every 3-5 days), generating demand pattern information accordingly. For optimal physiological metabolism, transpiration rate is closely related to soil moisture content and air humidity (related to water elements). By analyzing changes in transpiration rate under different water conditions, the optimal water conditions for transpiration rate are determined, generating dependency pattern information, such as the optimal transpiration rate at 70% soil moisture content. Regarding the optimal state of growth rhythm, the tillering rhythm is quite sensitive to changes in water content. Water deficit can lead to delayed or reduced tillering. Analyzing the impact of water replenishment frequency and timing on tillering time and quantity can generate response form information. For example, maintaining stable soil moisture content during the tillering period can promote uniform tillering.

[0090] Step S134: Analyze the relationship between the core features of the crop growth potential characteristics and the gas element data, and generate information on the demand form of the optimal nutrient synthesis efficiency state for changes in carbon dioxide and oxygen concentrations, as well as the dependence pattern information of the optimal material transport smoothness state on gas elements.

[0091] For the optimal state of nutrient synthesis efficiency (e.g., photosynthetic efficiency), the relationship with carbon dioxide concentration was analyzed. Experimental data showed that within a certain range, photosynthetic efficiency increased with increasing carbon dioxide concentration; however, once the carbon dioxide concentration reached a certain value, photosynthetic efficiency no longer increased. Therefore, information on the carbon dioxide concentration requirement for the optimal state of nutrient synthesis efficiency was generated, such as maintaining a carbon dioxide concentration of 800-1000 ppm. Simultaneously, oxygen concentration affects root respiration, thus influencing nutrient absorption. Information on the oxygen concentration requirement was generated, such as requiring a soil oxygen concentration higher than 10%. For the optimal state of mass transport efficiency (e.g., sucrose transport), oxygen concentration in the gaseous element affects energy supply (through respiration), thus affecting the driving force of mass transport. The changes in sucrose transport rate under different oxygen concentrations were analyzed, generating dependency pattern information, such as the optimal sucrose transport rate at an oxygen concentration of 15%-20%.

[0092] Step S135: Analyze the relationship between the core features of the crop growth potential characteristics and the temperature element data, and generate the demand form information of the optimal state of energy conversion stability for temperature distribution and temperature fluctuation amplitude, as well as the response form information of the optimal state of growth cycle fluctuation to changes in temperature elements.

[0093] The optimal state of energy conversion stability (such as stable respiration) is closely related to temperature. Respiration increases with rising temperature within a certain temperature range, but decreases beyond the optimum temperature. Therefore, information on the required temperature distribution for the optimal state of energy conversion stability is generated, such as a suitable air temperature range of 25-30 degrees Celsius and a soil temperature range of 20-25 degrees Celsius. Simultaneously, excessive temperature fluctuations can affect the activity of respiratory enzymes, leading to energy conversion instability. Information on the required temperature fluctuation range is generated, such as a diurnal temperature range not exceeding 10 degrees Celsius. The optimal state of growth cycle fluctuation (such as stable duration of each growth stage) is sensitive to temperature changes. Different growth stages have different temperature requirements. Analyzing the impact of temperature changes on the duration of key growth stages such as the jointing and heading stages generates response information. For example, during the heading stage, for every 1 degree Celsius increase in temperature, the heading period may be shortened by 1-2 days.

[0094] Step S136: Integrate the demand form information, dependency pattern information and response form information of each core feature and each environmental element data to form an action relationship network. The action relationship network includes the action priority and mutual cooperation logic of various environmental elements in the process of achieving the crop growth potential characteristics.

[0095] The core features obtained in steps S132 to S135 are integrated with the demand form information, dependency pattern information, and response form information of the light, water, gas, and temperature element data. Core features and environmental elements are represented by nodes, and their interactions are represented by directed edges. The edges are labeled with the interaction type (demand, dependency, response) and specific information (such as the numerical range of demand, the curve characteristics of dependency patterns, etc.). By analyzing the intensity and frequency of the effects of each environmental element on the core features in the network, the priority of each type of environmental element is determined. For example, during the tillering stage of rice, the priority of water and temperature elements may be higher than that of light and gas elements. Simultaneously, the mutual influence between environmental elements is analyzed. For example, increased light intensity leads to increased temperature and accelerated water evaporation, thus forming a logic of mutual cooperation between environmental elements. The above priorities and cooperation logic are integrated into the interaction relationship network.

[0096] Step S137: Based on the interaction network, divide the environmental evolution stages and obtain the environmental evolution stage division results. Each environmental evolution stage corresponds to a key development node in the process of achieving the crop growth potential characteristics. The environmental element configuration focus is different in different environmental evolution stages.

[0097] Step S1371: Extract the upper limit parameter of growth from the crop growth potential characteristics, clarify the optimal development state of the crop in terms of organ morphology, physiological metabolism, and growth rhythm, and decompose the optimal development state into multiple continuous development goals, each development goal corresponding to a key node in the process of achieving the crop growth potential characteristics.

[0098] Growth ceiling parameters are extracted from crop growth potential characteristics, such as maximum plant height and maximum leaf area index in terms of organ morphology, maximum photosynthetic rate and maximum sucrose translocation rate in terms of physiological metabolism, and minimum growth period and most stable tillering frequency in terms of growth rhythm, thus clarifying these optimal development states. Then, based on the growth and development patterns of rice, these optimal development states are decomposed into multiple continuous development goals. For example, the goal during the tillering stage is to achieve a certain number of tillers and plant height; the goal during the jointing stage is to have thick stems and suitable internode length; and the goal during the heading stage is to have uniform heading and sufficient number of spikelets. Each development goal is a key node.

[0099] Step S1372: Determine the crop growth status requirements corresponding to each key node, and obtain the organ morphological characteristics, physiological metabolic characteristics and growth rhythm characteristics that the crop needs to possess at the key node.

[0100] For each key node (such as the tillering stage), the corresponding crop growth requirements are determined. Regarding organ morphology, the tillering stage requires 8-10 tillers per plant, a plant height of 30-40 cm, and a leaf area index of 2.0-2.5. Regarding physiological and metabolic characteristics, the photosynthetic rate is required to reach 15-20 μmol / m²·s, and the nitrogen uptake rate must reach a certain level. Regarding growth rhythm characteristics, the tillering rate must be stable, with an average of one tiller produced every 2-3 days. These requirements are then specified as parameter ranges for the organ morphology, physiological and metabolic characteristics, and growth rhythm characteristics corresponding to that key node.

[0101] Step S1373: Based on the interaction network, determine the core environmental element support required for each key node to achieve its goal. The core environmental element support is the configuration of environmental elements that plays a decisive role in the achievement of the key node.

[0102] Based on the interaction network, we analyze which environmental factors play a decisive role in the achievement of each key node. For example, for the tillering stage, moisture and temperature are the core environmental factors; suitable soil moisture content (60%-70% of field capacity) and temperature (20-25 degrees Celsius) are crucial for promoting tillering. Therefore, the core environmental factors required for this key node are specific ranges of moisture content and temperature. For the heading stage, light duration and temperature are the core environmental factors; sufficient light duration (more than 10 hours per day) and suitable temperature (25-30 degrees Celsius) are needed to ensure successful heading.

[0103] Step S1374: Compare the core environmental element support corresponding to adjacent key nodes. If the difference between the core environmental element configurations of two adjacent key nodes exceeds a preset configuration difference threshold, then the latter key node is determined as a change node.

[0104] Preset difference thresholds, such as a moisture content difference threshold of 10% (percentage of field water holding capacity) and a temperature difference threshold of 5 degrees Celsius. Compare the core environmental element configurations of adjacent key nodes (such as the tillering stage and the jointing stage). If the core moisture content is 65% during the tillering stage and 50% during the jointing stage, the difference is 15%, exceeding the 10% threshold. Then, the key node during the jointing stage is identified as a change node.

[0105] Step S1375: Using the change nodes as boundaries, the transition process from the current environment to the optimal environment is divided into multiple continuous environmental evolution stages. Each environmental evolution stage contains one or more key nodes, and the configuration of core environmental elements remains relatively stable within each environmental evolution stage.

[0106] Using the points of change as boundaries, the entire environmental transition process is divided into environmental evolution stages. For example, the first environmental evolution stage is from the current environment to the key node of the tillering stage (a non-change node), during which the configuration of core environmental elements (such as moisture and temperature) remains stable to support tillering; the second environmental evolution stage is from the key node of the tillering stage to the change node of the jointing stage, during which the configuration of core environmental elements will gradually adjust to adapt to the needs of the jointing stage; and so on, forming multiple consecutive environmental evolution stages.

[0107] Step S1376: For each environmental evolution stage, define the core environmental element types and configuration priorities within that stage. The configuration priorities are set based on the degree of dependence of key nodes within that stage on environmental elements.

[0108] For each stage of environmental evolution, the types of core environmental elements and their allocation priorities are defined based on the degree of dependence on environmental factors at each key node. For example, in the tillering stage, the core environmental elements are water and temperature. Since tillering is slightly more dependent on water than on temperature, water has a higher allocation priority than temperature. In the jointing stage, the core environmental elements may be light and water, with light having a higher allocation priority than water.

[0109] Step S1377: Analyze the interaction between core environmental elements and non-core environmental elements in each stage of environmental evolution, obtain information on the auxiliary role of non-core environmental elements on core environmental elements, and formulate a configuration scheme for non-core environmental elements based on this auxiliary role information.

[0110] At each stage of environmental evolution, we analyze how non-core environmental factors assist core environmental factors in fulfilling their functions. For example, in the tillering stage, where water and temperature are core environmental factors, carbon dioxide concentration is a non-core environmental factor. Appropriately increasing the carbon dioxide concentration can enhance photosynthesis and indirectly promote tillering growth, thus playing a supporting role to the core environmental factors. Based on this information about supporting roles, we formulate a configuration scheme for non-core environmental factors, such as controlling the carbon dioxide concentration at around 800 ppm.

[0111] Step S1378: Determine the duration of each environmental evolution stage, the duration of which is set based on the difficulty of achieving key nodes within the environmental evolution stage, the transition rhythm of environmental element changes, and the natural cycle of crop growth.

[0112] Taking into account the difficulty of achieving key milestones (e.g., the tillering stage is relatively easy to achieve and can therefore have a shorter duration), the transitional pace of environmental changes (e.g., adjusting from the current moisture content to the target content takes time), and the natural cycle of rice growth (e.g., the tillering stage typically lasts 20-30 days), the duration of each environmental evolution stage is set. For example, the duration of the environmental evolution stage, including the tillering stage, is set to 25 days.

[0113] Step S1379: Set stage goals for each environmental evolution stage. The stage goals are the state that environmental elements should reach and the degree of development that crop growth potential should achieve at the end of the environmental evolution stage. The stage goals correspond to the key nodes within the environmental evolution stage.

[0114] Based on the key nodes within the environmental evolution stage, stage goals are set. For example, the stage goals for the tillering stage are: soil moisture content reaches 65%, temperature stabilizes at 22 degrees Celsius, the number of tillers per rice plant reaches 9, plant height reaches 35 cm, and leaf area index reaches 2.3. These stage goals correspond to the requirements of the key nodes in the tillering stage.

[0115] Step S13710: Integrate the core environmental elements, configuration priorities, duration and stage objectives of each environmental evolution stage to form the environmental evolution stage division result.

[0116] The core environmental elements, configuration priorities, duration, and stage objectives of each environmental evolution stage are integrated to form the environmental evolution stage division results, which are presented in the form of tables or structured documents.

[0117] Step S138: For each stage of environmental evolution, configure the initial combination of environmental elements based on the current crop growth environment multi-factor data and the potential achievement requirements of that stage of environmental evolution.

[0118] For each stage of environmental evolution, the initial combination of environmental elements is determined based on current multi-factor data of crop growth environment (such as current light intensity, soil moisture content, carbon dioxide concentration, temperature, etc.) and the potential achievement requirements of this stage (i.e., the state of environmental elements in the stage objective). For example, if the current soil moisture content is 50%, and the stage objective for this environmental evolution stage is 65% soil moisture content, then the initial value of the water element in the initial combination of environmental elements is 50%, which needs to be gradually adjusted to 65% during this stage. At the same time, the initial combination of environmental elements, including the initial values ​​of each element such as light, water, gases, and temperature, is configured in conjunction with the current state of other environmental elements and the stage objective.

[0119] Step S139: Based on the mutual cooperation logic in the interaction network, construct transition rules for the initial combination of environmental elements in each environmental evolution stage. The transition rules include the change order and mutual linkage mode of various environmental elements in the environmental evolution stage.

[0120] Referring to the interaction logic of environmental elements in the network of relationships, transition rules are constructed for the initial combination of environmental elements at each stage of environmental evolution. For example, at a certain stage of environmental evolution, it is necessary to simultaneously increase light intensity and temperature. According to the interaction logic, an increase in light intensity will lead to an increase in temperature. Therefore, light regulation can be initiated first. After the light intensity reaches a certain level, temperature fine-tuning can be initiated based on the actual temperature changes to avoid excessive temperature. This is the sequence of changes in environmental elements. Regarding the interaction mechanism, when the light intensity increases by 10,000 lux, the temperature should be adjusted by 0.5 degrees Celsius to maintain a suitable growth temperature. The above sequence of changes and interaction mechanism are integrated into transition rules.

[0121] Step S1310: Integrate the initial environmental element combinations, transition rules, and connection logic between environmental evolution stages to form the environmental evolution path.

[0122] This process integrates the initial environmental element combinations, transition rules, and connection logic between environmental evolution stages (such as how the environmental state at the end of the previous stage serves as the initial state for the next stage, and whether buffering and adjustment are needed between stages) to form a complete environmental evolution path. This path describes the entire process of transitioning from the current environment through various environmental evolution stages to an optimal environment that suits the crop's growth potential characteristics.

[0123] Step S140: Generate an environmental coordinated regulation sequence based on the environmental evolution path. The environmental coordinated regulation sequence includes the regulation methods, transition rhythms, and inter-element linkage logic of environmental elements at each stage of environmental evolution.

[0124] Step S141: Analyze each environmental evolution stage in the environmental evolution path, and extract the target state of environmental elements, duration of environmental evolution stage, and rhythm of environmental element changes within each environmental evolution stage.

[0125] The environmental evolution path is analyzed, and for each stage of environmental evolution, the target state of environmental elements (such as light intensity reaching 50,000 lux, soil moisture content reaching 65%), the duration of the stage (such as 25 days), and the rate of change of environmental elements (such as moisture content increasing by 0.6% per day) are extracted.

[0126] Step S142: For each environmental evolution stage, calculate the difference between the target state of environmental elements in that environmental evolution stage and the initial state of environmental elements in the current environmental evolution stage, and obtain information on the gap between environmental element states.

[0127] For each stage of environmental evolution, the target state of environmental elements is compared with the initial state of environmental elements at that stage, and the difference is calculated. For example, if the initial light intensity is 30,000 lux and the target state is 50,000 lux, the difference is 20,000 lux; if the initial soil moisture content is 50% and the target state is 65%, the difference is 15%. These differences are summarized to form the environmental element state difference information.

[0128] Step S143: Based on the environmental element state gap information, determine the adjustment direction of various environmental elements in each environmental evolution stage.

[0129] Based on the information on the differences in the states of environmental elements, the adjustment direction is determined. If the target state value is greater than the initial state value, the adjustment direction is to increase; if the target state value is less than the initial state value, the adjustment direction is to decrease. For example, if the difference in light intensity is positive, the adjustment direction is to increase light intensity; if the target state of a certain environmental element is lower than the initial state, the adjustment direction is to decrease that element.

[0130] Step S144: Based on the duration of the environmental evolution stage and the rhythm of change of the environmental elements, determine the adjustment rate of various environmental elements in each environmental evolution stage, wherein the adjustment rate is the magnitude of change of the environmental elements per unit time.

[0131] The adjustment rate is calculated by combining the duration of the environmental evolution stage and the rhythm of environmental factor changes. For example, if the difference in light intensity is 20,000 lux, lasts for 25 days, and the rhythm of change requires a uniform increase, then the adjustment rate is 20,000 lux / 25 days = 800 lux / day. For soil moisture content, if the difference is 15% and lasts for 25 days, the adjustment rate is 15% / 25 days = 0.6% / day.

[0132] Step S145: For each stage of environmental evolution, analyze the mutual influence of various environmental elements in the process of regulation, identify the influence relationship of one environmental element regulation on the state changes of other environmental elements, and construct a regulation logic to avoid adverse interference between elements based on the identified influence relationship.

[0133] Step S1451: Determine an environmental evolution stage, obtain the types of environmental elements and their initial configuration states for that stage, and define the various environmental elements that need to be regulated within that stage and their respective regulation objectives.

[0134] Select an environmental evolution stage, such as the jointing stage of rice. The environmental factors at this stage include light, moisture, temperature, and carbon dioxide concentration. The initial configuration is: light intensity 35,000 lux, soil moisture content 55%, temperature 23 degrees Celsius, and carbon dioxide concentration 600 ppm. The environmental factors to be adjusted and the adjustment targets are: light intensity adjusted to 45,000 lux, soil moisture content adjusted to 60%, temperature adjusted to 28 degrees Celsius, and carbon dioxide concentration adjusted to 800 ppm.

[0135] Step S1452: For each type of environmental element in the environmental evolution stage, simulate the process of its adjustment according to the preset adjustment direction and adjustment rate, and obtain the state change curve of the environmental element in the adjustment process. The state change curve includes the element state value at different time points.

[0136] Taking light intensity as an example, the preset adjustment direction is increase, the adjustment rate is 400 lux / day, and the duration is 10 days. Starting from an initial 35,000 lux, the intensity is increased by 400 lux each day, simulating the state change curve of light intensity. This state change curve includes the daily light intensity values, such as 35,400 lux on day 1, 35,800 lux on day 2, until reaching 45,000 lux on day 10. Similarly, similar simulations are performed for moisture, temperature, and carbon dioxide concentration, obtaining their respective state change curves.

[0137] Step S1453: Fix the adjustment process of the above-mentioned environmental elements, simulate the state change curves when other types of environmental elements are adjusted individually, and identify the differences between the two by comparing the individual adjustment curves with the common adjustment curves that include the adjustment of fixed elements.

[0138] The light intensity was adjusted according to the aforementioned state change curve. Then, the temperature adjustment process was simulated separately (increasing at a rate of 0.5 degrees Celsius per day for 10 days) to obtain a temperature adjustment curve. Next, the temperature state change curve was simulated when light and temperature were adjusted together (since increased light leads to a temperature rise). By comparing the two temperature curves, differences in temperature values ​​at the same time points were identified; for example, the temperature on day 5 under combined adjustment might be 0.3 degrees Celsius higher than under individual adjustment.

[0139] Step S1454: Based on the differences, determine the nature and direction of the impact of this type of environmental element regulation on the state changes of other types of environmental elements.

[0140] Based on the differences identified in step S1453, the nature and direction of the influence are determined. For example, if light regulation leads to a higher temperature under combined regulation than under individual regulation, it indicates that light regulation has a positive effect on temperature change (promoting temperature increase). Similarly, analyzing the effect of moisture regulation on temperature, it is possible that increased moisture may lead to a slight decrease in temperature (negative effect).

[0141] Step S1455: Analyze the underlying mechanisms of the influence properties and directions to obtain the specific ways in which this type of environmental element regulates and changes the state of other environmental elements.

[0142] The mechanism by which light regulation positively affects temperature is that increased light intensity leads to increased light energy absorption by plants, some of which is converted into heat, resulting in a rise in ambient temperature. The mechanism by which water regulation negatively affects temperature is that increased soil moisture content leads to increased evaporation, which absorbs heat from the environment, resulting in a decrease in temperature. By analyzing these mechanisms, we can clarify the specific ways in which environmental factors regulate and influence the state changes of other factors.

[0143] Step S1456: Divide the positive and negative impacts, wherein the positive impacts are those that promote other environmental elements to move closer to the adjustment target, and the negative impacts are those that hinder other environmental elements from moving closer to the adjustment target.

[0144] The nature of the influence must be determined to determine whether it is beneficial for other environmental factors to achieve the regulatory target. For example, during the jointing stage, the temperature regulation target is 28 degrees Celsius. The current co-regulation effect of sunlight on temperature brings the temperature closer to the target, thus it is a beneficial influence. If the negative influence of moisture regulation on temperature causes the temperature to deviate from the target, it is an adverse influence.

[0145] Step S1457: For the aforementioned adverse effects, obtain information on the conditions under which they occur, their manifestations, and their interference with the regulatory effects on other environmental factors.

[0146] Assuming the negative impact of moisture regulation on temperature is detrimental, the conditions under which it occurs are analyzed as follows: when soil moisture content increases beyond a certain threshold (e.g., 60%), the temperature decrease becomes more pronounced. This manifests as a linear decrease in temperature with increasing moisture content. A potential interference factor is that in the later stages of moisture regulation, the target temperature of 28 degrees Celsius may not be achieved.

[0147] Step S1458: Repeat the above simulation, comparison and analysis process for all environmental elements in this environmental evolution stage to establish a table of mutual influence relationships between various environmental elements.

[0148] For all environmental factors such as light, moisture, temperature, and carbon dioxide concentration, perform the operations from steps S1452 to S1457, analyze the impact of each type of factor regulation on other factors, and establish a table of mutual influence relationships. The table includes information such as the source factor, the affected factor, the nature of the influence, the direction of the influence, the mechanism of action, and the judgment of whether it is beneficial or detrimental.

[0149] Step S1459: Based on the mutual influence relationship table, filter out the combinations of environmental elements that have adverse effects, and obtain the transmission direction information of the adverse effects in each combination.

[0150] Select combinations of adverse effects from the interaction table, such as the effect of water regulation on temperature, and the inhibitory effect of excessive carbon dioxide concentration on photosynthesis (under specific conditions), and record the transmission direction of the adverse effects in each combination, such as water → temperature (negative effect).

[0151] Step S14510: Based on the mutual influence relationship table and the screening results, output the mutual influence analysis results of environmental element regulation within this environmental evolution stage, and construct the regulation logic to avoid adverse interference between elements accordingly.

[0152] Based on the results of the interaction analysis and the combination of adverse effects, a regulation logic to avoid adverse interference is constructed. For example, regarding the adverse effect of moisture regulation on temperature, the regulation logic could be: while regulating moisture, appropriately increase the rate of temperature regulation to offset the temperature decrease caused by the increase in moisture; or after moisture regulation reaches a certain level, pause moisture regulation, complete the temperature regulation target first, and then continue moisture regulation.

[0153] Step S146: Based on the analysis results of the mutual influence, construct the regulation sequence of various environmental elements in each stage of environmental evolution, wherein the regulation sequence includes the order in which different environmental elements initiate regulation.

[0154] Based on the analysis of the interactions between environmental elements, especially the favorable and unfavorable effects, the order of regulation should be determined. For example, regulation of elements that have a smaller impact on other elements or produce a favorable impact should be initiated first. During the jointing stage, light regulation has a favorable effect on temperature, so light regulation can be initiated first, followed by temperature regulation after a period of time; moisture regulation has an unfavorable effect on temperature, so moisture regulation can be initiated last, or it can be initiated when temperature regulation is close to the target.

[0155] Step S147: For each environmental evolution stage, an environmental regulation subsequence for that stage is generated based on the regulation direction, the regulation rate, and the regulation sequence. The environmental regulation subsequence includes regulation schemes for various environmental elements within that environmental evolution stage.

[0156] By comprehensively considering the direction, rate, and sequence of regulation, environmental regulation sub-sequences are generated for each stage of environmental evolution. For example, the environmental regulation sub-sequence for the jointing stage could be: Days 1-10, increase light intensity by 400 lux per day; Days 3-12, increase temperature by 0.5 degrees Celsius per day; Days 5-15, increase soil moisture content by 0.5% per day; Days 7-17, increase carbon dioxide concentration by 20 ppm per day. Each factor's regulation scheme includes information such as start time, duration, direction, and rate of regulation.

[0157] Step S148: Analyze the connection relationship between the environmental regulation sub-sequences in adjacent environmental evolution stages, obtain the connection logic, and construct a transition scheme between environmental evolution stages based on the connection logic.

[0158] By comparing the environmental regulation subsequences of two adjacent environmental evolution stages, the relationship between the environmental element states at the end of the previous stage and the environmental element states at the beginning of the next stage is analyzed. If the state at the end of the previous stage is consistent with the initial state of the next stage, the transition logic is a direct transition; if there are differences, a transition scheme needs to be constructed, such as setting a short buffer period before the start of the next stage to fine-tune the environmental elements to meet the initial state requirements of the next stage.

[0159] Step S149: Based on the aforementioned connection relationship, supplement the environmental element buffering and regulation steps between the environmental regulation sub-sequences in adjacent environmental evolution stages to generate the final transition scheme.

[0160] Based on the connection relationship, if there are differences in the state of environmental elements in adjacent environmental evolution stages, a buffer adjustment step is added. For example, if the temperature at the end of the previous stage is 25 degrees Celsius, and the initial temperature requirement for the next stage is 26 degrees Celsius, then a 1-day buffer adjustment step is added between the two stages to adjust the temperature from 25 degrees Celsius to 26 degrees Celsius, with an adjustment rate of 1 degree Celsius / day.

[0161] Step S1410: Integrate the environmental regulation sub-sequences of all environmental evolution stages and the buffer regulation steps between the environmental evolution stages to form the environmental coordinated regulation sequence.

[0162] The environmental regulation subsequences of all stages of environmental evolution and the buffer regulation steps between stages are integrated in chronological order to form a complete environmental synergistic regulation sequence. This environmental synergistic regulation sequence details the regulation methods, transition rhythms, and inter-element linkage logic of each environmental element at different times throughout the entire crop growth cycle.

[0163] Step S150: Execute the environmental coordinated regulation sequence to regulate the crop growth environment in stages, simultaneously and continuously capture the regulated crop growth status data and the regulated environmental multi-element data, update the crop growth potential characteristics based on the regulated crop growth status data, and optimize the environmental evolution path using the updated crop growth potential characteristics.

[0164] Step S151: According to the environmental evolution stage division and regulation logic in the environmental coordinated regulation sequence, start the corresponding environmental regulation device, first execute the environmental regulation sub-sequence of the first environmental evolution stage, and perform regulation operations on various environmental elements according to the regulation direction, regulation rate and regulation order in the environmental regulation sub-sequence.

[0165] In the digital rice platform, corresponding environmental regulation devices are activated according to the instructions of the environmental coordinated regulation sequence. For example, the first environmental evolution stage is the tillering stage, and the regulation subsequence requires increased light intensity, higher temperature, and increased soil moisture content. Supplemental lighting equipment is activated to increase light intensity according to the regulation rate, heating equipment is activated to increase temperature according to the regulation rate, and the irrigation system is activated to increase soil moisture content according to the regulation rate. The operation is strictly carried out in the regulation sequence, such as activating the supplemental lighting equipment first, then the heating equipment two days later, and finally the irrigation system three days later.

[0166] Step S152: During the execution of the environmental regulation subsequence in the first environmental evolution stage, the regulated crop growth status data and regulated environmental multi-element data are continuously captured according to the set capture interval.

[0167] The capture interval was set to once every 2 hours. During the first environmental evolution phase (lasting 25 days), the adjusted crop growth status data (such as plant height, number of tillers, leaf color, photosynthetic rate, etc.) and environmental multi-element data (such as light intensity, soil moisture content, temperature, carbon dioxide concentration, etc.) were collected every 2 hours through sensors and uploaded to the digital rice platform database in real time.

[0168] Step S153: After the environmental regulation sub-sequence of the first environmental evolution stage is completed, based on the crop growth status data after regulation in the first environmental evolution stage, re-extract organ morphology, physiological metabolism, and growth rhythm related features, establish a feature association network, screen core feature combinations, derive new growth upper limit parameters, and generate crop growth potential features after regulation in the first environmental evolution stage.

[0169] After the first environmental evolution stage is completed, organ morphology features (such as number of tillers and plant height), physiological and metabolic features (such as photosynthetic rate), and growth rhythm features (such as tillering rate) are re-extracted from the captured adjusted crop growth status data according to the methods in steps S121 to S129. A new feature association network is established, core feature combinations are screened, and new growth upper limit parameters (such as the maximum number of tillers may be increased from the original 10 to 12) are derived to generate adjusted crop growth potential features.

[0170] Step S154: Compare the crop growth potential characteristics after adjustment in the first environmental evolution stage with the crop growth potential characteristics before adjustment, record the changing trend of the upper limit parameter of growth and the changes in the logical relationship between the core feature combinations, and construct the data on the stimulation effect of crop growth potential.

[0171] The adjusted crop growth potential characteristics are compared with those before adjustment to analyze changes in upper growth limit parameters, such as an increase in the upper limit of tiller number and an increase in the upper limit of photosynthetic rate, and to record the trend of these changes (increase or decrease). Simultaneously, the changes in the logical relationships between core characteristic combinations are analyzed, such as whether the correlation between leaf integrity and photosynthetic rate has strengthened. These changes are recorded to form data on the activation effect of crop growth potential.

[0172] Step S155: Based on the environmental multi-element data after adjustment in the first environmental evolution stage, analyze the actual execution effect of the environmental adjustment sub-sequence in the first environmental evolution stage of the environmental coordinated adjustment sequence, and generate a matching parameter record of the actual environmental changes and the set changes of the environmental adjustment sub-sequence.

[0173] From the adjusted multi-element environmental data, the actual change curve of each environmental element is extracted and compared with the change curve set by the environmental adjustment subsequence. Fit parameters between the actual and set changes are calculated, such as the ratio of the actual increase to the set increase in light intensity, and the difference between the temperature fluctuation amplitude and the set fluctuation amplitude, generating a fit parameter record.

[0174] Step S156: Combining the data on the activation effect of crop growth potential and the actual execution effect data of the environmental regulation subsequence of the first environmental evolution stage, identify the discrepancies between the target state, transition rules and actual regulation effects set in the first environmental evolution stage of the environmental evolution path.

[0175] Step S1561: Extract the upper limit parameter of growth and the combination of core features from the crop growth potential characteristics after adjustment in the first environmental evolution stage, and compare them with the crop growth potential characteristics before adjustment to obtain the changing trend of the upper limit parameter and the changes in the logical relationship between the core feature combinations. The changing trend and changes constitute the data of the activation effect of the crop growth potential.

[0176] As described in step S154, the adjusted growth limit parameters (such as the maximum number of tillers of 12) and core feature combinations (such as the number of tillers, photosynthetic rate, and temperature) are extracted and compared with those before adjustment (maximum number of tillers of 10) to obtain the trend of the increase in growth limit parameters and the changes in the logical relationship between core feature combinations (such as the enhanced correlation between temperature and the number of tillers), thus forming the stimulation effect data.

[0177] Step S1562: Compare the excitation effect data with the environmental evolution target set for the first environmental evolution stage in the environmental evolution path to obtain the gap information between the actual excitation effect and the target excitation effect.

[0178] The environmental evolution target set for the first stage of the environmental evolution path was to reach an upper limit of 11 tillers and increase the upper limit of photosynthetic rate by 15%. The actual effect was an upper limit of 12 tillers (exceeding the target) and an increase of 10% in the upper limit of photosynthetic rate (below the target). The gap information is that the increase in the upper limit of photosynthetic rate was 5% less than the target.

[0179] Step S1563: Extract the actual environmental state from the environmental multi-element data after adjustment in the first environmental evolution stage, and compare it with the target environmental state set for the first environmental evolution stage in the environmental evolution path to obtain the deviation values ​​between the actual state and the target state of various environmental elements. The deviation values ​​constitute the actual execution effect data of the environmental adjustment subsequence of the first environmental evolution stage.

[0180] The environmental evolution path sets the target environmental state at the end of the first environmental evolution stage as: light intensity 45,000 lux, soil moisture content 65%, and temperature 25 degrees Celsius. The actual environmental state is: light intensity 45,000 lux (no deviation), soil moisture content 63% (deviation -2%), and temperature 24 degrees Celsius (deviation -1 degree Celsius). The above deviation values ​​constitute the actual execution effect data.

[0181] Step S1564: Compare the actual execution effect data with the transition rules set for the first environmental evolution stage in the environmental evolution path to obtain the difference information between the actual environmental element change rhythm, linkage mode and the set rules.

[0182] The transition rules set for the environmental evolution path are: light intensity increases by 800 lux per day, and temperature increases by 0.5 degrees Celsius per day. The linkage between light and temperature is that for every 10,000 lux increase in light intensity, the temperature increases by 2 degrees Celsius. The actual change rate is: light intensity increases by 800 lux per day (compliant), and temperature increases by 0.4 degrees Celsius per day (lower than the set 0.5). Regarding the linkage, when light intensity increases by 20,000 lux, the actual temperature increase is 3.5 degrees Celsius, while the set value should be 4 degrees Celsius. The difference is that the temperature increase is 0.5 degrees Celsius less than the set value.

[0183] Step S1565: Based on the gap information between the actual stimulation effect and the target stimulation effect, determine the compatibility between the target environmental state set in the first environmental evolution stage and the crop growth potential characteristics. If the compatibility is insufficient, then the target state is determined to be inconsistent.

[0184] The actual increase in the upper limit of photosynthetic rate was lower than the target, possibly because the carbon dioxide concentration in the target environment was not set sufficiently (currently set at 700 ppm, but may require a higher concentration), resulting in insufficient compatibility between the target environment and the characteristics of crop growth potential. Therefore, the target carbon dioxide concentration was identified as the inconsistency.

[0185] Step S1566: Based on the difference information between the actual changes in environmental elements and the set rules, determine the validity of the transition rules set in the first environmental evolution stage. If the transition rules cannot guide the environmental elements to change as expected, then the transition rules are determined to be inconsistent.

[0186] The discrepancy between the actual temperature change rhythm and linkage mode and the set rules indicates that the transition rules for temperature regulation (such as the power setting of the heating device) may be unreasonable and unable to guide the temperature to change as expected. Therefore, the transition rules for temperature regulation are identified as non-compliant.

[0187] Step S1567: Analyze the causes of the deviation between the actual state and the target state of environmental elements. After excluding the influence of uncontrollable external factors, the target state or transition rule corresponding to the deviation caused by the environmental evolution path setting problem is identified as the non-conforming part.

[0188] The analysis revealed that the actual soil moisture content (63%) was lower than the target moisture content (65%). After excluding uncontrollable external factors such as rainy days, it was found that the problem was caused by insufficient flow settings in the irrigation system. This is a problem with the setting of irrigation transition rules in the environmental evolution path. Therefore, the irrigation transition rules were identified as the non-compliant part.

[0189] Step S1568: For the determined non-target state, analyze the mismatch points between it and the crop growth potential characteristics, and obtain the environmental element configuration information in the target state that does not match the development needs of crop growth potential.

[0190] For the non-compliant target state of carbon dioxide concentration (700 ppm), the analysis found that further improvement of the upper limit of photosynthetic rate in the crop growth potential characteristics requires a higher carbon dioxide concentration (such as 800 ppm). The current target state configuration cannot meet the requirements, and there is a mismatch. The configuration information of this environmental element was obtained.

[0191] Step S1569: For the determined non-compliant transition rules, analyze their logical defects in guiding the change of environmental elements, and obtain information on the change rhythm or linkage mode that the non-compliant transition rules cannot achieve effective transition of environmental elements.

[0192] Analysis revealed that the temperature regulation did not conform to the transition rules. The change rhythm setting (increasing by 0.5 degrees Celsius per day) did not take into account the actual temperature increase effect of increased light, resulting in a logical defect in the linkage method and failing to achieve effective temperature transition. Specific defect information of the change rhythm and linkage method was obtained.

[0193] Step S15610: Integrate the non-conforming target state and its adaptation contradictions, as well as the non-conforming transition rules and their logical defects, to form a detailed identification result of the non-conforming part in the environmental evolution path.

[0194] By integrating the discrepancies in the target carbon dioxide concentration (adaptation contradiction: insufficient concentration), temperature regulation transition rules (logical flaw: unreasonable change rhythm and linkage method), and irrigation transition rules (logical flaw: insufficient flow rate setting), detailed discrepancy identification results are formed.

[0195] Step S157: For the discrepancies, based on the crop growth potential characteristics and environmental multi-element data after adjustment in the first environmental evolution stage, adjust the initial environmental element combination, transition rules and environmental evolution stage connection logic of the subsequent environmental evolution stages in the environmental evolution path to generate an optimized environmental evolution path.

[0196] Based on the identified discrepancies, adjust the initial environmental element combinations for subsequent environmental evolution stages, such as increasing the initial value of carbon dioxide concentration; modify transition rules, such as adjusting the rate and linkage of temperature regulation and increasing the flow rate of the irrigation system; optimize the connection logic between environmental evolution stages, such as adding temperature buffer regulation steps between adjacent stages, and generate an optimized environmental evolution path.

[0197] Step S158: According to the optimized environmental evolution path, adjust the environmental regulation sub-sequences of subsequent environmental evolution stages and the buffer regulation steps between environmental evolution stages in the environmental coordinated regulation sequence.

[0198] Based on the optimized environmental evolution path, the environmental regulation subsequences of subsequent environmental evolution stages are adjusted accordingly, such as modifying the regulation rate and target value of carbon dioxide concentration, and adjusting the regulation schemes for temperature and irrigation; at the same time, the buffer regulation steps between stages are adjusted to adapt to the new environmental evolution path.

[0199] Step S159: Initiate the optimized second environmental evolution stage environmental regulation subsequence, and repeat the process of capturing regulated data, updating crop growth potential characteristics, identifying discrepancies, optimizing environmental evolution paths, and adjusting environmental co-regulation sequences until regulation of all environmental evolution stages is completed.

[0200] Initiate the optimized second environmental evolution stage (such as the jointing stage) environmental regulation subsequence, and continuously capture data, update crop growth potential characteristics, identify discrepancies, optimize environmental evolution path and adjust regulation sequence according to the process of steps S152 to S158, and execute the regulation of each environmental evolution stage in sequence.

[0201] Step S1510: After the environmental regulation subsequences of all environmental evolution stages have been executed, based on the finally captured regulated crop growth status data and regulated environmental multi-factor data, the final crop growth potential characteristics and optimized environmental evolution path are generated.

[0202] Once all environmental evolution stages have been regulated, the final crop growth potential characteristics (such as the maximum yield potential and optimal quality parameters) and the optimized environmental evolution path are generated based on the final captured crop growth status data and environmental multi-factor data. This environmental evolution path can serve as a reference scheme for environmental control in future similar rice cultivation processes.

[0203] In one exemplary embodiment, an environmental adaptive control system based on crop growth monitoring is provided. This system can be a terminal, server, etc., and its internal structure diagram can be as follows: Figure 2As shown, this crop growth monitoring-based environmental adaptive control system includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, near-field communication, or other technologies. When the computer program is executed by the processor, it implements an environmental adaptive control method based on crop growth monitoring. The display unit is used to generate a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, or a button, trackball, or touchpad set on the shell of the environmental adaptive control system based on crop growth monitoring, or an external keyboard, touchpad, or mouse, etc.

[0204] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. An environmental adaptive control method based on crop growth monitoring, characterized in that, The method includes: The system captures crop growth status data and multi-element data of the crop growth environment. The crop growth status data includes static parameters of crop organ morphology, dynamic processes of physiological metabolism, and characteristics of growth rhythm fluctuations. The multi-element data of the crop growth environment includes environmental composition data related to light, water, gas, and temperature within the crop growth space. Identify crop growth potential characteristics from the crop growth status data. These characteristics are core features related to the upper limit of crop growth and its evolutionary direction under suitable environmental conditions. Based on the dynamic interaction between the crop growth potential characteristics and the multi-element data of the crop growth environment, an environmental evolution path is constructed. The environmental evolution path is a phased environmental change scheme that guides the current environment to gradually transition towards adapting to the crop growth potential characteristics. An environmental coordination and regulation sequence is generated based on the environmental evolution path. The environmental coordination and regulation sequence includes the regulation methods, transition rhythms, and inter-element linkage logic of environmental elements at each stage of environmental evolution. The environmental coordinated regulation sequence is executed to regulate the crop growth environment in stages, and the crop growth status data and environmental multi-factor data after regulation are captured simultaneously and continuously. The crop growth potential characteristics are updated based on the crop growth status data after regulation, and the environmental evolution path is optimized using the updated crop growth potential characteristics. The step of generating an environmental coordinated regulation sequence based on the environmental evolution path includes: The environmental evolution path is analyzed, and the target state of environmental elements, duration of environmental evolution stage, and rhythm of environmental element changes within each environmental evolution stage are extracted. For each stage of environmental evolution, the difference between the target state of environmental elements in that stage and the initial state of environmental elements in the current stage is calculated to obtain information on the gap between environmental element states. Based on the environmental element state gap information, the adjustment direction of various environmental elements in each stage of environmental evolution is determined; Based on the duration of the environmental evolution stage and the rhythm of change of the environmental elements, the adjustment rate of various environmental elements in each environmental evolution stage is determined, whereby the adjustment rate is the magnitude of change of the environmental elements per unit time. For each stage of environmental evolution, the interaction between various environmental elements in the process of regulation is analyzed, the influence relationship of one environmental element regulation on the state changes of other environmental elements is identified, and a regulation logic to avoid adverse interference between elements is constructed based on the identified influence relationship. Based on the analysis results of the mutual influence, the regulation sequence of various environmental elements in each stage of environmental evolution is constructed, and the regulation sequence includes the order in which different environmental elements initiate regulation. For each stage of environmental evolution, an environmental regulation subsequence for that stage is generated based on the regulation direction, the regulation rate, and the regulation sequence. The environmental regulation subsequence includes regulation schemes for various environmental elements within that stage of environmental evolution. The connection relationship between the environmental regulation sub-sequences in adjacent environmental evolution stages is analyzed to obtain the connection logic, and a transition scheme between environmental evolution stages is constructed based on the connection logic. Based on the aforementioned connection relationship, environmental element buffering and regulation steps are added between the environmental regulation sub-sequences in adjacent environmental evolution stages to generate the final transition scheme. The environmental regulation subsequences of all environmental evolution stages and the buffer regulation steps between environmental evolution stages are integrated to form the environmental coordinated regulation sequence; For each stage of environmental evolution, the interaction between various environmental elements during their regulation processes is analyzed. The influence of one environmental element's regulation on the state changes of other environmental elements is identified. Based on the identified influence relationships, a regulation logic to avoid adverse interference between elements is constructed, including: Identify an environmental evolution stage, obtain the types of environmental elements and their initial configuration states for that stage, and define the various environmental elements that need to be regulated within that stage and their respective regulation objectives. For each type of environmental element in this environmental evolution stage, the process of its adjustment according to a preset adjustment direction and adjustment rate is simulated to obtain the state change curve of the environmental element in the adjustment process. The state change curve includes the element state value at different time points. The adjustment process of the above-mentioned environmental elements is fixed, and the state change curves of other types of environmental elements are simulated when they are adjusted individually. By comparing the state change curves when they are adjusted individually with the common adjustment curve including the adjustment of fixed elements, the differences between the two are identified. Based on the aforementioned differences, determine the nature and direction of the impact of this type of environmental element regulation on the state changes of other types of environmental elements; Analyze the underlying mechanisms of the nature and direction of the aforementioned influences to obtain the specific ways in which this type of environmental element regulates and alters the state changes of other environmental elements; The impacts are divided into beneficial and adverse impacts. The beneficial impacts are those that promote the convergence of other environmental factors toward the adjustment target, and the adverse impacts are those that hinder the convergence of other environmental factors toward the adjustment target. To address the aforementioned adverse effects, information is obtained regarding the conditions under which they occur, their manifestations, and their interference with the regulatory effects on other environmental factors. The above simulation, comparison, and analysis process was repeated for all environmental elements within this stage of environmental evolution to establish a table of mutual influence relationships among various environmental elements; Based on the aforementioned mutual influence relationship table, combinations of environmental elements with adverse effects are selected, and the transmission direction information of the adverse effects in each combination is obtained. Based on the aforementioned mutual influence relationship table and screening results, the analysis results of the mutual influence of environmental element regulation within this environmental evolution stage are output, and a regulation logic to avoid adverse interference between elements is constructed accordingly.

2. The environmental adaptive control method based on crop growth monitoring according to claim 1, characterized in that, The process of identifying crop growth potential characteristics from the crop growth status data includes: The crop growth status data is broken down into organ morphology data, physiological metabolism data, and growth rhythm data. The organ morphology data records the structural morphology and size correlation information of crop roots, stems, leaves, flowers, and fruits. The physiological metabolism data records the dynamic process information of crop nutrient synthesis, material transport, and energy conversion. The growth rhythm data records the growth activity level and periodic fluctuation information of crops at different time periods. The structural integrity features and growth spatial layout features of each organ are extracted from the organ morphology data. The structural integrity features reflect the degree of development and functional integrity of each organ, and the growth spatial layout features reflect the distribution pattern of each organ in the growth environment and the ease of resource acquisition. The nutrient synthesis efficiency feature, material transport smoothness feature, and energy conversion stability feature are extracted from the physiological metabolic data. The nutrient synthesis efficiency feature reflects the crop's ability to synthesize the nutrients it needs using environmental resources. The material transport smoothness feature reflects the smoothness of nutrient transport between organs. The energy conversion stability feature reflects the crop's ability to continuously convert environmental energy into growth energy. Extract the distribution characteristics of active growth periods and the fluctuation amplitude characteristics of growth cycles from the growth rhythm data. The distribution characteristics of active growth periods reflect the concentrated growth activity of crops at different times of the day, and the fluctuation amplitude characteristics of growth cycles reflect the smooth changes in the growth status of crops within a continuous growth cycle. Based on the features extracted from the organ morphology data and the features extracted from the physiological metabolism data, the correlation between the two is established to obtain the correlation between structural integrity features and nutrient synthesis efficiency features, as well as the correlation between growth space layout features and material transport smoothness features. Based on the aforementioned correlation and the features extracted from the growth rhythm data, a constraint relationship is established to obtain the constraint relationship between the distribution features of active growth periods and the structural integrity features and nutrient synthesis efficiency features, as well as the constraint relationship between the growth cycle fluctuation amplitude features and the growth spatial layout features and material transport smoothness features. Based on the aforementioned correlation and constraint relationships, a feature association network is formed, and core feature combinations located at core topological positions or logical hub positions are selected from the feature association network. The change trajectory of the core feature combinations in the crop growth status data is tracked, and the change status of the feature parameters of each feature in the core feature combination and the interaction between features is recorded at different monitoring periods. Based on the change trajectory of the core feature combination, the upper limit parameter of crop growth under no environmental restrictions is derived. The upper limit parameter of growth is the optimal development state that the morphology, physiological metabolism and growth rhythm of various organs of the crop can reach. The variation trajectory of the combination of the growth upper limit parameter and the core feature is used to form the crop growth potential feature.

3. The environmental adaptive control method based on crop growth monitoring according to claim 1, characterized in that, The construction of an environmental evolution path based on the dynamic interaction between the crop growth potential characteristics and multi-factor data of the crop growth environment includes: The crop growth environment multi-element data is broken down into light element data, water element data, gas element data, and temperature element data. The light element data records the changes in light intensity and the distribution of light duration in the growth environment. The water element data records the water content and water replenishment frequency in the growth environment. The gas element data records the changes in carbon dioxide and oxygen concentrations in the growth environment. The temperature element data records the temperature distribution and temperature fluctuation range in the growth environment. The relationship between the core features of the crop growth potential characteristics and the light element data is analyzed to generate the demand form information of the optimal state of organ morphology on light intensity changes and light duration distribution, as well as the dependence pattern information of the optimal state of physiological metabolism on light elements in the upper limit parameters of growth. The relationship between the core features of the crop growth potential characteristics and the water element data is analyzed to generate information on the demand form of the optimal organ morphology state for water content and water replenishment frequency, the dependence pattern of the optimal physiological metabolism state on water elements, and the response form of the optimal growth rhythm state to changes in water elements. The interaction between the core features of the crop growth potential characteristics and the gas element data is analyzed to generate information on the demand form of carbon dioxide and oxygen concentration changes for the optimal state of nutrient synthesis efficiency, as well as the dependence pattern of gas elements for the optimal state of material transport smoothness. The interaction between the core features of the crop growth potential characteristics and the temperature element data is analyzed to generate information on the demand form of the optimal state of energy conversion stability for temperature distribution and temperature fluctuation amplitude, as well as information on the response form of the optimal state of growth cycle fluctuation to changes in temperature elements. The demand form information, dependency pattern information and response form information of each core feature and each environmental element data are integrated to form an action relationship network. The action relationship network includes the action priority and mutual cooperation logic of various environmental elements in the process of achieving the crop growth potential characteristics. Based on the aforementioned interaction network, environmental evolution stages are divided to obtain environmental evolution stage division results. Each environmental evolution stage corresponds to a key development node in the process of achieving the crop growth potential characteristics. The focus of environmental element configuration is different in different environmental evolution stages. For each stage of environmental evolution, an initial combination of environmental elements is configured based on multi-factor data of the current crop growth environment and the potential achievement requirements of that stage of environmental evolution. Based on the mutual cooperation logic in the aforementioned interaction network, transition rules are constructed for the initial combination of environmental elements in each environmental evolution stage. The transition rules include the change sequence and mutual linkage mode of various environmental elements within the environmental evolution stage. The environmental evolution path is formed by integrating the initial environmental element combinations, transition rules, and connection logic between environmental evolution stages at each stage.

4. The environmental adaptive control method based on crop growth monitoring according to claim 1, characterized in that, The execution of the environmental coordinated regulation sequence to regulate the crop growth environment in stages, simultaneously and continuously capturing regulated crop growth status data and regulated environmental multi-factor data, updating the crop growth potential characteristics based on the regulated crop growth status data, and optimizing the environmental evolution path using the updated crop growth potential characteristics, includes: According to the environmental evolution stage division and regulation logic in the environmental coordinated regulation sequence, the corresponding environmental regulation device is activated. First, the environmental regulation sub-sequence of the first environmental evolution stage is executed, and various environmental elements are regulated according to the regulation direction, regulation rate and regulation order in the environmental regulation sub-sequence. During the execution of the environmental regulation subsequence in the first environmental evolution stage, crop growth status data and environmental multi-factor data after regulation are continuously captured according to the set capture interval; Once the environmental regulation subsequence of the first environmental evolution stage is completed, based on the captured crop growth status data after regulation in the first environmental evolution stage, organ morphology, physiological metabolism, and growth rhythm-related features are re-extracted, a feature association network is established, core feature combinations are screened, new growth upper limit parameters are derived, and crop growth potential features after regulation in the first environmental evolution stage are generated. By comparing the crop growth potential characteristics after adjustment in the first environmental evolution stage with the crop growth potential characteristics before adjustment, the changing trend of the upper limit parameter of growth and the changes in the logical relationship between the core feature combinations are recorded to constitute the data on the stimulation effect of crop growth potential. Based on the environmental multi-element data after adjustment in the first environmental evolution stage, the actual execution effect of the environmental adjustment sub-sequence in the first environmental evolution stage of the environmental coordinated adjustment sequence is analyzed, and a matching parameter record of the actual environmental changes and the set changes of the environmental adjustment sub-sequence is generated. By combining the data on the activation effect of crop growth potential and the actual execution effect data of the environmental regulation subsequence of the first environmental evolution stage, discrepancies between the target state, transition rules and actual regulation effects set in the first environmental evolution stage of the environmental evolution path are identified. For the discrepancies, based on the crop growth potential characteristics and environmental multi-element data after adjustment in the first environmental evolution stage, the initial environmental element combinations, transition rules, and environmental evolution stage connection logic in the subsequent environmental evolution stages in the environmental evolution path are adjusted to generate an optimized environmental evolution path. According to the optimized environmental evolution path, adjust the environmental regulation sub-sequences of subsequent environmental evolution stages and the buffer regulation steps between environmental evolution stages in the environmental coordinated regulation sequence; Initiate the optimized second environmental evolution stage environmental regulation subsequence, and repeat the process of capturing regulated crop growth status data, updating crop growth potential characteristics, identifying discrepancies, optimizing environmental evolution paths, and adjusting environmental co-regulation sequences until regulation of all environmental evolution stages is completed. After all environmental regulation subsequences in all stages of environmental evolution have been executed, the final crop growth potential characteristics and optimized environmental evolution path are generated based on the finally captured regulated crop growth status data and regulated environmental multi-factor data.

5. The environmental adaptive control method based on crop growth monitoring according to claim 2, characterized in that, The features extracted from the organ morphology data and the features extracted from the physiological metabolic data are used to establish a correlation between the two, obtaining the correlation between structural integrity features and nutrient synthesis efficiency features, and the correlation between growth spatial layout features and material transport smoothness features, including: The structural integrity features and growth spatial layout features extracted from the organ morphology data are used as the first feature group, and the nutrient synthesis efficiency features and material transport smoothness features extracted from the physiological metabolism data are used as the second feature group. Both sets of features retain the time dimension information and quantitative parameters in the original data. Based on the crop growth status data, dynamic change data of the first feature group and the second feature group are obtained during the continuous monitoring period, forming time series data of two sets of features, where each time node in the time series data corresponds to a set of feature parameters. Correlation analysis was performed on the time series of structural integrity features in the first feature group and the time series of nutrient synthesis efficiency features in the second feature group to obtain the time lag relationship and co-change relationship between changes in structural integrity features and changes in the response of nutrient synthesis efficiency features; A correlation analysis was performed on the time series of growth spatial layout features in the first feature group and the time series of material transport smoothness features in the second feature group to obtain the time lag relationship and change correlation information between the changes in growth spatial layout features and the changes in the response of material transport smoothness features. Based on the results of the two sets of association analysis, direct association and indirect association are distinguished. Direct association is when a change in one set of features directly leads to a change in another set of features. Indirect association is when a set of features leads to a change in another set of features by influencing other intermediate factors. For the directly associated feature pairs, a leading feature and a subsequent feature are defined, and the correspondence between the response change trend of the subsequent feature when the leading feature undergoes a specific change trend is obtained. The leading feature is the feature that triggers the change, and the subsequent feature is the feature that produces the response change. For the indirectly associated feature pairs, intermediate influencing factors are identified, and the transmission path of the leading feature to the subsequent feature through the intermediate influencing factors is obtained. The intermediate influencing factors are crop growth-related features between the leading feature and the subsequent feature. By integrating the correspondence between the directly associated feature pairs and the transmission path of the indirectly associated feature pairs, a preliminary feature association mapping framework is formed. The feature association mapping framework includes the association type and association information between each group of features. The preliminary feature association mapping framework is compared with the basic physiological mechanisms of crop growth, and the mapping results are output that conform to the intrinsic laws of organ morphology and physiological metabolism during crop growth. The mapping results are supplemented with information on the triggering conditions and duration of each association to form an association mapping between organ morphological features and physiological metabolic features.

6. The environmental adaptive control method based on crop growth monitoring according to claim 3, characterized in that, The process of dividing environmental evolution stages based on the aforementioned interaction network to obtain environmental evolution stage division results includes: Extract the upper limit parameter of growth potential characteristics of the crop to determine the optimal development state of the crop in terms of organ morphology, physiological metabolism and growth rhythm. Decompose the optimal development state into multiple continuous development goals, and each development goal corresponds to a key node in the process of achieving the crop growth potential characteristics. Determine the crop growth status requirements corresponding to each key node, and obtain the organ morphological characteristics, physiological metabolic characteristics and growth rhythm characteristics that the crop needs to possess at that key node; Based on the aforementioned network of interactions, the core environmental elements required for the achievement of each key node are determined. These core environmental elements are the configuration of environmental elements that play a decisive role in the achievement of the key node. The core environmental element support corresponding to adjacent key nodes is compared. If the difference between the core environmental element configurations of two adjacent key nodes exceeds a preset configuration difference threshold, the latter key node is determined as a change node. Using the aforementioned change nodes as boundaries, the transition process from the current environment to the optimal environment is divided into multiple consecutive environmental evolution stages. Each environmental evolution stage contains one or more key nodes, and the configuration of core environmental elements remains relatively stable within each environmental evolution stage. For each stage of environmental evolution, the types of core environmental elements and their configuration priorities are defined. The configuration priorities are set based on the degree of dependence of key nodes on environmental elements within that stage of environmental evolution. Analyze the interaction between core environmental elements and non-core environmental elements in each stage of environmental evolution, obtain information on the auxiliary role of non-core environmental elements on core environmental elements, and formulate configuration schemes for non-core environmental elements based on this auxiliary role information. The duration of each environmental evolution stage is determined based on the difficulty of achieving key nodes within that stage, the transitional rhythm of environmental element changes, and the natural cycle of crop growth. Each stage of environmental evolution is given a stage objective, which is the state that environmental elements should reach and the degree of development that crop growth potential should achieve by the end of the stage. The stage objective corresponds to the key nodes within the stage of environmental evolution. The core environmental elements, configuration priorities, durations, and stage objectives of each environmental evolution stage are integrated to form the environmental evolution stage division result.

7. The environmental adaptive control method based on crop growth monitoring according to claim 4, characterized in that, The method combines the data on the stimulating effect of crop growth potential with the actual execution effect data of the environmental regulation subsequence of the first environmental evolution stage to identify discrepancies between the target state, transition rules, and actual regulation effects set in the first environmental evolution stage of the environmental evolution path, including: Extract the upper limit parameter and core feature combination from the crop growth potential characteristics after adjustment in the first environmental evolution stage, and compare them with the crop growth potential characteristics before adjustment to obtain the changing trend of the upper limit parameter and the changes in the logical relationship between the core feature combinations. The changing trend and changes constitute the data of the activation effect of the crop growth potential. The stimulation effect data is compared with the environmental evolution target set for the first environmental evolution stage in the environmental evolution path to obtain the gap information between the actual stimulation effect and the target stimulation effect. Extract the actual environmental state from the environmental multi-element data after the adjustment of the first environmental evolution stage, and compare it with the target environmental state set for the first environmental evolution stage in the environmental evolution path to obtain the deviation values ​​between the actual state and the target state of various environmental elements. The deviation values ​​constitute the actual execution effect data of the environmental adjustment subsequence of the first environmental evolution stage. The actual execution effect data is compared with the transition rules set for the first environmental evolution stage in the environmental evolution path to obtain information on the differences between the actual environmental element change rhythm, linkage mode and the set rules. Based on the gap between the actual stimulation effect and the target stimulation effect, the compatibility between the target environmental state set in the first environmental evolution stage and the crop growth potential characteristics is determined. If the compatibility is insufficient, the target state is determined to be a mismatch. Based on the difference information between the actual changes in environmental elements and the set rules, the validity of the transition rules set in the first environmental evolution stage is determined. If the transition rules cannot guide the environmental elements to change as expected, the transition rules are identified as non-compliant. Analyze the causes of the deviation between the actual state and the target state of environmental elements. After excluding the influence of uncontrollable external factors, identify the target state or transition rule corresponding to the deviation caused by the setting problem of the environmental evolution path as the non-conforming part. For the identified non-target states, analyze the points of mismatch between them and the characteristics of crop growth potential, and obtain the configuration information of environmental elements in the target states that do not match the development needs of crop growth potential. For the identified non-compliant transition rules, analyze their logical defects in guiding changes in environmental elements, and obtain information on the change rhythm or linkage mode that cannot achieve effective transition of environmental elements in the non-compliant transition rules. By integrating the non-target states and their adaptation contradictions, as well as the non-conforming transition rules and their logical defects, a detailed identification result of the non-conforming parts in the environmental evolution path is formed.

8. An environmental adaptive control system based on crop growth monitoring, characterized in that, include: processor; A machine-readable storage medium for storing machine-executable instructions of the processor; The processor is configured to execute the environmental adaptive control method based on crop growth monitoring as described in any one of claims 1 to 7 by executing the machine-executable instructions.

Images