Plant phenotype automatic acquisition and feature processing method for multi-element environment

Abstract

The present application relates to the technical field of plant phenotype data processing, in particular to a plant phenotype automatic collection and feature processing method for multiple environments. The present application synchronously collects plant multi-modal phenotype data through Internet of Things nodes, calculates coupling strength in combination with environmental factors, divides phenotype parameters into two categories of environment-sensitive and steady-state, and improves data classification accuracy. The growth trend field is constructed by using phenology stage decoupling analysis and geographical space superposition, and the abnormal section is dynamically removed in combination with physiological coordination degree and mutation detection algorithm, thereby enhancing the stability of trend analysis. The phenotype-environment response atlas is generated through standardization processing and environment equivalent value model, key environment-sensitive windows are identified, and cross-environment regulation schemes in different regions and stages are output, thereby realizing intelligent and accurate management of crop growth environment and being suitable for agricultural yield increase and breeding optimization.

Description

Technical Field

[0001] This invention relates to the field of plant phenotypic data processing technology, specifically to an automated method for collecting and processing plant phenotypic features in diverse environments. Background Technology

[0002] Plant phenotype is a comprehensive reflection of the interaction between plant genes and the environment. Accurately analyzing the dynamic characteristics of plant phenotypes under diverse environments is of great significance for crop breeding, cultivation regulation, and environmental adaptability research. However, the natural environment is highly heterogeneous, and environmental factors such as light, temperature, water, and soil nutrients vary complexly in time and space, resulting in significant dynamics and environmental dependence of plant phenotypes.

[0003] In the current field of plant phenotyping research, although numerous techniques have been developed to analyze the relationship between plant phenotypic characteristics and the environment, significant shortcomings remain. For example, application number CN202510509758.6 provides a plant phenotyping method that focuses only on single or a few visible morphological features of plants, such as relying solely on visual characteristics like leaf color and shape to judge plant growth status. However, the natural environment is complex and ever-changing; environmental factors such as light intensity, temperature, humidity, and soil fertility are constantly in flux, making it difficult for traditional methods to comprehensively capture the integrated responses of plant phenotypes under diverse environmental conditions. Furthermore, when processing environmentally sensitive phenotypic features, traditional image recognition technology, lacking in-depth analysis of the coupling relationship between environmental factors and phenotypic parameters, cannot accurately distinguish between phenotypic changes caused by environmental changes and those caused by the plant's own growth and development. This leads to biases in the judgment of abnormal phenotypes, making it difficult to accurately identify key environmentally sensitive windows, and resulting in regulatory schemes generated based on phenotypic analysis lacking specificity and effectiveness.

[0004] While some deep learning-based plant phenotypic analysis models have improved the accuracy of phenotypic identification to some extent, these models are mostly black-box models with complex and opaque internal operating mechanisms. In diverse environments, these models struggle to explain how environmental factors affect the extraction and identification of phenotypic features, and cannot effectively filter and process phenotypic data based on environmental adaptability principles. Furthermore, deep learning models rely on large amounts of high-quality labeled data for training. However, in real-world diverse environments, plant phenotypic data is severely affected by environmental noise, making data labeling difficult and inaccurate. This results in poor model training performance, making it difficult to construct reliable phenotypic-environment response models and providing a scientific and accurate basis for formulating cross-environmental regulation strategies. Summary of the Invention

[0005] To address the problems mentioned in the background art, such as insufficient analysis of the coupling relationship between environmental factors and phenotypic characteristics, lack of targeted data processing, and difficulty in constructing accurate environmental adaptability maps, this invention provides an automated method for collecting and processing plant phenotypic data in diverse environments. By automating the processing of plant phenotypic data in diverse environments, accurately analyzing the relationship between phenotypic and environmental response, and assisting in the generation of regulatory schemes, this invention achieves efficient processing of phenotypic data, accurate construction of environmental adaptability maps, and intelligent output of cross-environmental regulatory schemes.

[0006] The specific technical solution of the present invention is as follows:

[0007] The technical solution of this invention is to provide an automated method for collecting and processing plant phenotypic features in diverse environments, including:

[0008] Based on the synchronous collection of plant multimodal phenotypic data by IoT nodes, the coupling strength between multimodal phenotypic data and environmental factors is calculated. According to the coupling strength, the multimodal phenotypic data is divided into two categories: environmentally sensitive phenotypic group and environmentally stable phenotypic group.

[0009] The growth trend benchmark values ​​of the environmentally sensitive phenotype group and the environmentally stable phenotype group were identified through phenological stage decoupling analysis. Using geospatial coordinates as a framework, the environmental gradient data and the growth trend benchmark values ​​were spatiotemporally superimposed to generate the growth trend fields of the environmentally sensitive phenotype group and the environmentally stable phenotype group, respectively.

[0010] For the growth trend field of the environmentally sensitive phenotype group, the physiological response synergy among the parameters of the same group is calculated in real time to detect and remove abnormal growth segments; for the growth trend field of the environmentally stable phenotype group, anomaly detection based on phenological stage constraints is implemented to identify and remove abnormal growth segments.

[0011] After removing anomalous segments, the growth trend fields of the environmentally sensitive phenotype group and the environmentally stable phenotype group are standardized and processed to construct an environmental equivalent value mapping model to generate a phenotype-environmental response map. Based on the phenotype-environmental response map, key environmentally sensitive windows are identified, and cross-environmental regulation schemes are output.

[0012] As a further optimization of the present invention, the multimodal phenotypic data includes morphological features, physiological indicators, and growth dynamics. The morphological features include height, leaf area, and stem diameter. The physiological indicators include chlorophyll content, photosynthetic rate, and transpiration rate. The growth dynamics include growth rate, flowering time, and maturity stage. The Internet of Things node adopts a multimodal sensor array composed of a spectral imager, a thermal imaging camera, and a laser scanner, and realizes synchronous acquisition of multi-source data at nanosecond-level time resolution through a high-precision timestamp module.

[0013] As a further optimization of the present invention, the method for calculating the coupling strength between the multimodal phenotypic data and environmental factors is as follows: for a given synchronization time, the phenotypic parameters... and environmental factors Its coupling strength Represented as:

[0014] ;

[0015] in, yes The joint probability distribution, and They are The marginal probability distribution.

[0016] As a further optimization of the present invention, the multimodal phenotypic data is divided into an environment-sensitive phenotypic group and an environment-steady-state phenotypic group. The division criteria are as follows: a coupling strength threshold is set, and parameters with coupling strength greater than or equal to the coupling strength threshold are classified into the environment-sensitive phenotypic group, while parameters with coupling strength less than the coupling strength threshold are classified into the environment-steady-state phenotypic group.

[0017] As a further optimization of the present invention, the phenological stages are divided as follows: a dataset with time series is constructed using morphological features, physiological indicators and growth dynamics collected by multimodal sensors; the phenological stages are divided based on the similarity of growth curves between different plants.

[0018] The growth trend baseline values ​​for the environmentally sensitive phenotype group and the environmentally stable phenotype group are calculated as follows: Let the time interval of a certain phenological stage be... The corresponding phenotypic parameter sequence is Then its growth trend benchmark value Represented as:

[0019] ;

[0020] in, This indicates the number of samples within that phenological stage. express Samples in The phenotypic parameter value at that location.

[0021] As a further optimization of the present invention, the geospatial coordinate framework adopts a GIS-based multi-layer spatial index structure to spatiotemporally overlay environmental gradient data with growth trend benchmark values.

[0022] The spatiotemporal superposition steps include:

[0023] The growth trend baseline values ​​are arranged according to the time series and mapped to the geospatial coordinate system;

[0024] The environmental gradient data are arranged according to time series and mapped to the same geospatial coordinate system;

[0025] By integrating growth trend benchmarks and environmental gradient data in both time and space dimensions, a growth trend field is constructed.

[0026] As a further optimization of the present invention, the growth trend field calculation method is as follows: a certain spatial unit Growth trend value at Represented as:

[0027] ;

[0028] in, express Given the baseline value of the growth trend, The weight of the benchmark value to the target spatial cell is calculated using a power function of the inverse distance, i.e.: , Representing the target space unit and The Euclidean distance between spatial units containing the growth trend baseline value. The distance decay exponent is 2.

[0029] As a further optimization of the present invention, the calculation method for the physiological response synergy degree corresponding to the growth trend field of the environmentally sensitive phenotype group is as follows: for two parameters in a certain environmentally sensitive phenotype group and Its physiological response coordination The calculation formula is:

[0030] ;

[0031] in, and Representing time points The parameter value at that location, and Representing parameters respectively and The average value, The length of the time series;

[0032] The anomaly detection method for the growth trend field of the environmental steady-state phenotype group is as follows: Let the time interval of a certain phenological stage be... The corresponding phenotypic parameter sequence is ,in If there is a certain point in time within this period; , making exist If the trend of change before and after the event differs significantly, then that point in time is considered a mutation point; mutation intensity The calculation formula is:

[0033] .

[0034] As a further optimization of the present invention, the environmental equivalent value mapping model is as follows:

[0035] ;

[0036] in, This is the standardized environmental equivalent value. For spatial coordinates, For time, Environmental factors The weight, These are the normalized phenotypic parameter values.

[0037] As a further optimization of the present invention, the key environmental sensitive window analyzes the correlation between phenotypic parameters and environmental factors in different phenological stages, and combines dynamic query function to identify key environmental factors and their corresponding sensitive windows in the budding, flowering and maturity stages, and outputs cross-environmental regulation schemes by region and stage.

[0038] The beneficial effects of the technical solutions provided in this application include at least the following:

[0039] This technical solution achieves high-precision synchronous acquisition and classification optimization of plant phenotypic data through the collaboration of multimodal sensors and IoT nodes, significantly improving the intelligence level of data processing. Phenotypic parameters are divided into environmentally sensitive and steady-state types through coupling strength calculation. Combining phenological stage decoupling analysis and spatiotemporal overlay of a geospatial coordinate framework, a dynamic growth trend field model is constructed. This effectively solves the error problems caused by environmental interference and differences in growth stages in traditional phenotypic analysis, providing an innovative technical path for the comparability of phenotypic data under cross-environmental conditions.

[0040] This technical solution innovatively introduces anomaly detection mechanisms based on physiological response synergy detection and phenological stage constraints. It accurately identifies and eliminates anomalous segments in both environmentally sensitive and steady-state phenotypic groups, significantly improving the stability and reliability of the growth trend field. Through the construction of an environmental equivalent value mapping model and a phenotypic-environmental response map, it achieves multidimensional correlation analysis between phenotypic characteristics and environmental factors, providing a visualization tool for revealing key environmentally sensitive windows in plant growth and overcoming the limitations of traditional static analysis methods.

[0041] The final cross-environmental regulation strategy output by this technical solution possesses precise management capabilities in stages and regions, and can dynamically adapt to environmental needs under different phenological stages and geographical conditions. The regulation scheme based on a multi-objective optimization model integrates environmental factor weights and cost constraints, achieving closed-loop management from data-driven to decision optimization. This provides a scientific basis for precise agricultural regulation, crop yield improvement, and efficient resource utilization, and has significant industrial application value. Attached Figure Description

[0042] Figure 1 A schematic diagram of the overall process for an automated method of plant phenotypic acquisition and feature processing for diverse environments; Figure 2 S100 step flowchart for an automated method for collecting and processing plant phenotypes in diverse environments; Figure 3 S200 step flowchart for automated plant phenotyping and feature processing method for diverse environments; Figure 4 Detailed flowchart of the S300 method for automated collection and feature processing of plant phenotypes in diverse environments; Figure 5 S400 flowchart of automated plant phenotyping and feature processing method for diverse environments; Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0044] Traditional plant phenotypic analysis methods largely rely on manual measurements or static observations under single environments, resulting in low efficiency, high cost, and difficulty in reflecting the dynamic coupling relationship between phenotype and environment. While some studies have introduced automated monitoring equipment, systematic methods are still lacking in areas such as environmental adaptation processing of phenotypic data, outlier removal, and standardization of cross-environmental phenotypic characteristics, thus limiting the efficiency of phenotypic data utilization and the accuracy of environmental adaptation analysis. For solutions to these problems, please refer to [link to relevant documentation]. Figure 1 This illustrates an embodiment of the present invention providing an automated method for collecting and processing plant phenotypic features in diverse environments. The method includes:

[0045] S100: Based on the synchronous collection of plant multimodal phenotypic data by IoT nodes, calculate the coupling strength between multimodal phenotypic data and environmental factors, and divide the multimodal phenotypic data into two categories according to the coupling strength: environmentally sensitive phenotypic group and environmentally stable phenotypic group.

[0046] S200: The environmentally sensitive phenotype group and the environmentally stable phenotype group respectively identify the growth trend benchmark values ​​through phenological stage decoupling analysis. Using geospatial coordinates as a framework, the environmental gradient data and the growth trend benchmark values ​​are spatiotemporally superimposed to generate the growth trend fields of the environmentally sensitive phenotype group and the environmentally stable phenotype group, respectively.

[0047] S300: For the growth trend field of environmentally sensitive phenotype groups, the physiological response synergy among parameters of the same group is calculated in real time to detect and remove abnormal growth segments; for the growth trend field of environmentally stable phenotype groups, anomaly detection based on phenological stage constraints is implemented to identify and remove abnormal growth segments.

[0048] S400: Standardize the growth trend fields of environmentally sensitive phenotype groups and environmentally stable phenotype groups after removing abnormal segments, construct an environmental equivalent value mapping model to generate a phenotype-environmental response map; identify key environmentally sensitive windows based on the phenotype-environmental response map, and output cross-environmental control schemes.

[0049] The specific plan is as follows:

[0050] In the automated collection and feature processing method of plant phenotypes for diverse environments, the S100 synchronously collects multimodal phenotypic data of plants through IoT nodes and calculates the coupling strength between phenotypic parameters and environmental factors. Based on the coupling strength, the phenotypic data is divided into two categories: environmentally sensitive and environmentally stable, providing basic data support for subsequent environmental adaptability analysis.

[0051] Please refer to Figure 2 It illustrates a flowchart of an exemplary automated plant phenotypic acquisition and feature processing method S100 for diverse environments according to this application, the contents of which include:

[0052] S110: Synchronously collect multimodal phenotypic data of plants based on IoT nodes.

[0053] Multimodal phenotypic data includes plant morphological characteristics such as height, leaf area, and stem diameter; physiological indicators such as chlorophyll content, photosynthetic rate, and transpiration rate; and growth dynamics such as growth rate, flowering time, and maturity stage. In one possible implementation, IoT nodes employ multimodal sensors, including spectral imagers, thermal imaging cameras, and laser scanners, to capture plant morphological characteristics, physiological indicators, and growth dynamics.

[0054] Because plant growth and environmental changes are time-dependent, data collected by different sensors must be aligned on the same timescale to ensure the accuracy of subsequent analysis. In one possible implementation, IoT nodes are equipped with high-precision timestamp modules to ensure that each collected data point carries accurate time information.

[0055] S120: Calculate the coupling strength between multimodal phenotypic data and environmental factors, and divide the phenotypic group into environmentally sensitive phenotypic group and environmentally stable phenotypic group based on the coupling strength.

[0056] The coupling strength between the multimodal phenotypic data collected in S110 and environmental factors is calculated to identify which phenotypic parameters are highly sensitive to environmental changes and which are relatively stable.

[0057] In one possible implementation, for a given synchronization time, the phenotypic parameters and environmental factors Its coupling strength Represented as:

[0058] ;

[0059] in, yes The joint probability distribution, and and They are The marginal probability distribution. The stronger the coupling, the stronger the correlation between the two variables, i.e., the phenotypic parameters. Affected by environmental factors The greater the impact.

[0060] Based on the calculated coupling strength, the multimodal phenotypic data are divided into two categories: environmentally sensitive phenotypic groups and environmentally stable phenotypic groups. The environmentally sensitive phenotypic groups consist of parameter clusters that are strongly coupled with environmental factors, while the environmentally stable phenotypic groups contain independent parameters that are less affected by the environment.

[0061] In one possible implementation, a coupling strength threshold is set, and parameters with coupling strength greater than or equal to the coupling strength threshold are classified as environmentally sensitive phenotypes, while parameters with coupling strength less than the coupling strength threshold are classified as environmentally stable phenotypes.

[0062] In an automated method for collecting and processing plant phenotypes in diverse environments, the S200 system generates growth trend fields for both environmentally sensitive and environmentally stable phenotype groups by combining the mapping relationships of environmental factors with baseline values ​​obtained from decoupling analysis of phenological stages. The S200 system not only reveals plant growth patterns under different environmental conditions but also provides support for subsequent detection of growth anomalies and analysis of environmental adaptability.

[0063] Please refer to Figure 3 The diagram illustrates a flowchart of an exemplary automated plant phenotypic acquisition and feature processing method S200 for diverse environments, which includes:

[0064] S210: Identify growth trend benchmark values ​​based on phenological stage decoupling analysis.

[0065] During plant growth, changes in phenotypic characteristics are influenced by phenological stages. Phenological stages refer to the different developmental stages that plants experience in their life cycle, such as budding, flowering, and maturity. The division of phenological stages directly affects the dynamic change patterns of phenotypic data.

[0066] Specifically, this step first uses known phenological information to divide the multimodal phenotypic data into stages, and then calculates the baseline value for each phenological stage to eliminate the interference of growth stage differences on trend analysis.

[0067] In one possible implementation, the division of phenological stages utilizes a time-series dataset constructed from morphological features, physiological indicators, and growth dynamics collected by multimodal sensors. Phenological stages are then defined based on the similarity of growth curves among different plants.

[0068] After the phenological stages are divided, the growth trend baseline values ​​are calculated for each phenological stage for both the environmentally sensitive phenotype group and the environmentally stable phenotype group. The growth trend baseline value refers to the average trend of phenotypic parameters within a specific phenological stage. In one possible implementation, the growth trend baseline value is calculated as follows: Let the time interval of a certain phenological stage be... The corresponding phenotypic parameter sequence is Then its growth trend benchmark value Represented as:

[0069] ;

[0070] in, This indicates the number of samples within that phenological stage. express Samples in The phenotypic parameter value at that location.

[0071] S220: Based on the geospatial coordinate framework, environmental gradient data and growth trend benchmark values ​​are spatiotemporally overlaid to generate growth trend fields for environmentally sensitive phenotype groups and environmentally stable phenotype groups.

[0072] In S210, growth trend baseline values ​​for the environmentally sensitive phenotype group and the environmentally stable phenotype group were extracted through phenological stage decoupling analysis. In S220, the growth trend baseline values ​​were spatiotemporally overlaid with environmental gradient data to generate growth trend fields for the environmentally sensitive phenotype group and the environmentally stable phenotype group.

[0073] A geospatial coordinate frame is the foundation for spatiotemporal overlay, its function being to map growth trend baseline values ​​and environmental gradient data to a unified spatial coordinate system. In one possible implementation, the geospatial coordinate frame employs Geographic Information System (GIS) technology to map growth trend baseline values ​​and environmental gradient data to the same geospatial coordinate system, thereby achieving spatial alignment.

[0074] After spatial alignment, the environmental gradient data and the growth trend benchmark value are spatiotemporally overlaid. That is, the growth trend benchmark value and the environmental gradient data are mapped to the same geospatial coordinate system, and combined with time series data, a spatial distribution model that can reflect the growth trend of plants under different environmental conditions is constructed.

[0075] In one possible implementation, the specific steps of spatiotemporal superposition include:

[0076] The growth trend baseline values ​​are arranged according to the time series and mapped to the geospatial coordinate system;

[0077] The environmental gradient data are arranged according to time series and mapped to the same geospatial coordinate system;

[0078] By integrating growth trend benchmarks and environmental gradient data in both time and space dimensions, a growth trend field is constructed.

[0079] Based on the above implementation methods, in one possible implementation, the growth trend field calculation method is as follows: a certain spatial unit Growth trend value at Represented as:

[0080] ;

[0081] in, express Given the baseline value of the growth trend, The weight of the benchmark value to the target spatial cell is calculated using a power function of the inverse distance, i.e.: , Representing the target space unit and The Euclidean distance between spatial units containing the growth trend baseline value. The distance decay exponent is 2.

[0082] In the automated acquisition and feature processing method for plant phenotypes in diverse environments, S300 performs anomaly detection on the growth trend fields of environmentally sensitive phenotype groups and environmentally stable phenotype groups generated in S200, respectively, to remove abnormal segments and improve the accuracy of subsequent phenotype-environment response surface construction.

[0083] Please refer to Figure 4 The diagram illustrates a flowchart of an exemplary automated plant phenotypic acquisition and feature processing method S300 for diverse environments, which includes:

[0084] S310: Detection and removal of abnormal segments in the growth trend field of environmentally sensitive phenotype groups.

[0085] The environment-sensitive phenotype group consists of a cluster of parameters strongly coupled with environmental factors, and its growth trend is significantly influenced by these factors. Therefore, the growth trend field of the environment-sensitive phenotype group may exhibit significant fluctuations under different environmental conditions, and may even show anomalous segments. This step identifies and removes these anomalous segments by calculating the physiological response synergy among parameters within the same group in real time, ensuring the stability and reliability of the growth trend field.

[0086] In environmentally sensitive phenotype groups, due to the high sensitivity of parameters to environmental factors, changes in the synergy of physiological responses exhibit complex synergistic relationships. Therefore, calculating the synergy of physiological responses among parameters within the same group helps identify anomalous segments. In one possible implementation, for two parameters in a given environmentally sensitive phenotype group... and Its physiological response coordination The calculation formula is:

[0087] ;

[0088] in, and Representing time points The parameter value at that location, and Representing parameters respectively and The average value, This represents the length of the time series.

[0089] After calculating the physiological response synergy among parameters in the same group, anomaly detection is performed. An anomaly segment refers to a region within a specific time or space where the parameter's trend differs significantly from the normal trend. In one possible implementation, the anomaly detection method uses a threshold judgment based on statistical analysis. If the physiological response synergy within a certain time period... If the set threshold is exceeded, the time period is determined to be an abnormal period.

[0090] Once an abnormal segment is detected, it is removed to ensure the accuracy of the growth trend field.

[0091] S320: Detection and removal of abnormal segments in the growth trend field of environmentally stable phenotype groups.

[0092] The environmentally stable phenotypic group consists of independent parameters that are less affected by the environment, and its growth trend is relatively stable. However, since plant growth can be affected by various factors, such as pests and diseases, and mechanical damage, there may still be anomalous segments in the growth trend field of the environmentally stable phenotypic group. Therefore, for the growth trend field of the environmentally stable phenotypic group, anomaly detection with phenological stage constraints is implemented, and when anomalies are detected, environmental data of that spatial location is correlated to identify and remove environmentally abnormal segments.

[0093] In one possible implementation, the method for detecting abnormal segments in the growth trend field of an environmentally stable phenotype group is as follows: Let the time interval of a certain phenological stage be... The corresponding phenotypic parameter sequence is ,in If there exists a certain point in time within this time period. , making exist If the trend of change before and after a significant difference occurs, that point in time is considered a mutation point. Mutation intensity. The calculation formula is:

[0094] .

[0095] In one possible implementation, the outlier detection method uses a threshold judgment based on statistical analysis. This threshold is determined by the intensity of abrupt changes within a certain time period. If the set threshold is exceeded, the time period is determined to be an abnormal period.

[0096] After detecting mutation points, it is further determined whether they belong to an abnormal growth segment, and these are then removed. Specifically, if the occurrence of a mutation point is related to known changes in environmental factors, the mutation can be considered reasonable, and the data is retained. However, if the occurrence of a mutation point lacks a reasonable environmental explanation and is inconsistent with the evolution of phenological stages, the mutation is considered to be caused by abnormal factors and is removed.

[0097] In the automated collection and feature processing method of plant phenotypes for diverse environments, S400 achieves standardized processing of plant phenotype data and output of precise control schemes under cross-environmental conditions by mapping environmental equivalent values ​​and constructing phenotype-environmental response maps, combined with the identification of key environmental sensitive windows.

[0098] Please refer to Figure 5The diagram illustrates a flowchart of an exemplary automated plant phenotypic acquisition and feature processing method S400 for diverse environments, which includes:

[0099] S410: Based on the standardization of the growth trend field, construct an environmental equivalent value mapping model.

[0100] The growth trend fields of the environmentally sensitive phenotypic group and the environmentally stable phenotypic group, after removing outliers, were standardized to eliminate data bias under different environmental conditions. An environmental equivalent value mapping model was constructed to achieve cross-environmental comparability of phenotypic features. By combining the gradient distribution of environmental factors and the baseline values ​​of phenological stages, a multidimensional mapping relationship was established to convert actual observations into equivalent values ​​under standard environmental conditions, providing a foundation for the subsequent generation of phenotypic-environmental response maps.

[0101] Standardization of the growth trend field for environmentally sensitive phenotype groups involves converting the values ​​of parameters highly sensitive to environmental factors into relative values ​​under standard conditions, making them comparable across different environmental conditions. Standardization of the growth trend field for environmentally stable phenotype groups eliminates the influence of minor differences in environmental factors on the data, ensuring its stability under different environmental conditions.

[0102] In one possible implementation, a dynamic normalization method is used for the growth trend field of the environmentally sensitive phenotype group, whose growth trend is significantly affected by environmental factors. For the growth trend field of the environmentally stable phenotype group, whose growth trend is mainly regulated by phenological stages, a static normalization method is used.

[0103] Based on the above standardization process, in one possible implementation, the standardization of the two types of growth trend fields is carried out under a unified environmental factor framework to ensure that the standardization results of environmentally sensitive and environmentally stable parameters are comparable.

[0104] With the support of a geographic information system, the standardized phenotypic data of the growth trend fields of the environmentally sensitive phenotypic group and the environmentally stable phenotypic group are mapped to a unified spatial coordinate system along with the environmental gradient data. An environmental equivalent value mapping model is then constructed.

[0105] In one possible implementation, the environmental equivalent value mapping model is as follows:

[0106] ;

[0107] in, This is the standardized environmental equivalent value. For spatial coordinates, For time, Environmental factors The weight, These are the normalized phenotypic parameter values.

[0108] S420: Construct a phenotypic-environmental response map based on the environmental equivalent value mapping model.

[0109] Phenotypic-environmental response mapping is a visualization tool used to show the changing trends of plant phenotypic parameters under different environmental conditions and their relationship with environmental factors. By using phenotypic-environmental response mapping, we can intuitively analyze plant growth patterns under different environmental conditions, identify the impact of key environmental factors on phenotypes, and provide a basis for subsequent regulatory strategies.

[0110] The phenotypic-environmental response map is constructed based on an environmental equivalent value mapping model, which maps phenotypic data under different environmental conditions to a standard environment and visualizes them in a geospatial coordinate system.

[0111] In one possible implementation, the steps for constructing a phenotypic-environmental response map include:

[0112] The standardized environmental equivalent values ​​are integrated with the geospatial coordinate system to ensure that the phenotypic data and environmental factors are spatially aligned.

[0113] The discrete environmental equivalent data points are interpolated into a continuous spatial distribution.

[0114] A gradient color scheme is used to convert environmental equivalent values ​​into visual colors, intuitively displaying the changing trends of phenotypic parameters in different regions.

[0115] A dynamic query function was built, allowing users to click on a region to view detailed data, adjust the weights of environmental factors, or compare growth trends over different time periods.

[0116] S430: Identify critical environmental sensitive windows.

[0117] The critical environmental sensitivity window refers to the environmental factors and corresponding growth stages that play a dominant role in changes in plant phenotypic parameters under specific environmental conditions. By identifying the critical environmental sensitivity window, the plant growth environment can be precisely controlled to improve crop yield and quality.

[0118] The identification of critical environmentally sensitive windows is based on the analysis of phenotypic-environmental response profiles.

[0119] In one possible implementation, the identification step of the critical environment-sensitive window includes:

[0120] Based on the division of phenological stages (S210) and combined with phenotypic-environmental response maps, key environmental factors at different growth stages are analyzed. For example, key environmental factors may change at different phenological stages such as budding, flowering, and maturity.

[0121] By analyzing phenotypic-environmental response maps, we can identify the key environmental factors that have the greatest impact on phenotypic parameters during specific phenological stages and determine the corresponding key environmental sensitivity windows.

[0122] S440: Output cross-environmental regulation schemes based on phenotypic-environmental response maps.

[0123] Cross-environmental regulation schemes improve the growth stability and adaptability of plants under different environmental conditions by optimizing environmental management measures.

[0124] In one possible implementation, the basic principles followed in formulating cross-environmental control schemes are:

[0125] Ensure that regulatory measures can effectively mitigate the adverse effects of critical environmental windows on plant growth;

[0126] The control plan should have a certain degree of flexibility to adapt to changes under different environmental conditions;

[0127] Control measures should be based on scientific evidence to ensure their positive impact on plant growth.

[0128] Based on the above principles, in one possible implementation, a phased and regional cross-environmental regulation plan is formulated for the key environmentally sensitive windows identified in the phenotypic-environmental response map.

[0129] An example of a phased cross-environmental regulation scheme is as follows:

[0130] The environmental sensitivity window during the germination period indicates insufficient water supply and excessively low soil temperature.

[0131] The control measures are as follows: optimize the irrigation system to ensure that the soil moisture is maintained within a suitable range; adopt mulch film covering or greenhouse insulation measures to raise the soil temperature to the optimal germination temperature.

[0132] Environmental sensitivity during the growth period indicates insufficient light intensity and uneven nutrient supply.

[0133] Control measures include: using intelligent supplemental lighting systems to supplement light, and dynamically adjusting fertilization plans based on soil sensor data to ensure a balanced supply of key nutrients such as nitrogen, phosphorus, and potassium.

[0134] The environmental sensitivity during the flowering period is indicated by temperature fluctuations and abnormal air humidity.

[0135] The control measures are as follows: stabilize temperature and humidity through an environmental control system, and implement artificial pollination or assisted pollination measures for sensitive varieties to improve the fruit setting rate.

[0136] The environmental sensitivity window during the maturity period is characterized by large diurnal temperature differences and high risk of pests and diseases.

[0137] The control measures include: optimizing the harvesting time to avoid periods of extreme temperature differences; and implementing precise pesticide application based on pest and disease monitoring data.

[0138] An example of a regional cross-environmental regulation scheme is as follows:

[0139] The environmental sensitivity window in highly sensitive areas shows the significant impact of local environmental factors on plant growth.

[0140] The control measures are as follows: in areas with high salinity and alkalinity, soil improvement technology is used to reduce soil salinity; in areas with significant microclimate differences, geographic information systems are used to optimize planting layout to avoid the adverse effects of environmental differences on growth.

[0141] The environmental sensitivity window in low-sensitivity areas indicates that environmental factors have a relatively small impact on plant growth, but there may be potential risks.

[0142] The control measures include: implementing crop rotation or intercropping systems to improve soil fertility and ecological stability; and accumulating long-term monitoring data to provide early warnings of environmental risks and formulate preventive control plans.

[0143] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0144] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features of the invention herein.

[0145] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An automated method for collecting and processing plant phenotypic features in diverse environments, characterized in that, include: Based on the synchronous collection of plant multimodal phenotypic data by IoT nodes, the coupling strength between multimodal phenotypic data and environmental factors is calculated. According to the coupling strength, the multimodal phenotypic data is divided into two categories: environmentally sensitive phenotypic group and environmentally stable phenotypic group. The growth trend benchmark values ​​of the environmentally sensitive phenotype group and the environmentally stable phenotype group were identified through phenological stage decoupling analysis. Using geospatial coordinates as a framework, the environmental gradient data and the growth trend benchmark values ​​were spatiotemporally superimposed to generate the growth trend fields of the environmentally sensitive phenotype group and the environmentally stable phenotype group, respectively. For the growth trend field of the environmentally sensitive phenotype group, the physiological response synergy among the parameters of the same group is calculated in real time to detect and remove abnormal growth segments; for the growth trend field of the environmentally stable phenotype group, anomaly detection based on phenological stage constraints is implemented to identify and remove abnormal growth segments. After removing anomalous segments, the growth trend fields of the environmentally sensitive phenotype group and the environmentally stable phenotype group are standardized and processed to construct an environmental equivalent value mapping model to generate a phenotype-environmental response map. Based on the phenotype-environmental response map, key environmentally sensitive windows are identified, and cross-environmental regulation schemes are output.

2. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 1, characterized in that, The multimodal phenotypic data includes morphological features, physiological indicators, and growth dynamics. The morphological features include height, leaf area, and stem diameter. The physiological indicators include chlorophyll content, photosynthetic rate, and transpiration rate. The growth dynamics include growth rate, flowering time, and maturity stage. The IoT node uses a multimodal sensor array composed of a spectral imager, a thermal imaging camera, and a laser scanner. It achieves synchronous acquisition of multi-source data at nanosecond-level time resolution through a high-precision timestamp module.

3. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 2, characterized in that, The method for calculating the coupling strength between the multimodal phenotypic data and environmental factors is as follows: for a given synchronization time, the phenotypic parameters... and environmental factors Its coupling strength Represented as: ； in, yes The joint probability distribution, and and They are The marginal probability distribution.

4. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 3, characterized in that, The multimodal phenotypic data are divided into an environment-sensitive phenotypic group and an environment-steady-state phenotypic group. The division criteria are as follows: a coupling strength threshold is set, and parameters with a coupling strength greater than or equal to the coupling strength threshold are classified into the environment-sensitive phenotypic group, while parameters with a coupling strength less than the coupling strength threshold are classified into the environment-steady-state phenotypic group.

5. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 1, characterized in that, The phenological stages are divided as follows: a time-series dataset is constructed using morphological features, physiological indicators, and growth dynamics collected by multimodal sensors; the phenological stages are divided based on the similarity of growth curves among different plants. The growth trend baseline values ​​for the environmentally sensitive phenotype group and the environmentally stable phenotype group are calculated as follows: Let the time interval of a certain phenological stage be... The corresponding phenotypic parameter sequence is Then its growth trend benchmark value Represented as: ； in, This indicates the number of samples within that phenological stage. express Samples in The phenotypic parameter value at that location.

6. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 1, characterized in that, The geospatial coordinate framework adopts a GIS-based multi-layer spatial index structure, which spatiotemporally overlays environmental gradient data with growth trend benchmark values. The spatiotemporal superposition steps include: The growth trend baseline values ​​are arranged according to the time series and mapped to the geospatial coordinate system; The environmental gradient data are arranged according to time series and mapped to the same geospatial coordinate system; By integrating growth trend benchmarks and environmental gradient data in both time and space dimensions, a growth trend field is constructed.

7. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 6, characterized in that, The growth trend field calculation method is as follows: a certain spatial unit Growth trend value at Represented as: ； in, express Given the baseline value of the growth trend, The weight of the benchmark value to the target spatial cell is calculated using a power function of the inverse distance, i.e.: , Representing the target space unit and The Euclidean distance between spatial units containing the growth trend baseline value. The distance decay exponent is 2.

8. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 1, characterized in that, The physiological response synergy degree corresponding to the growth trend field of the environmentally sensitive phenotype group is calculated as follows: for two parameters in a certain environmentally sensitive phenotype group... and Its physiological response coordination The calculation formula is: ； in, and Representing time points The parameter value at that location, and Representing parameters respectively and The average value, The length of the time series; The anomaly detection method for the growth trend field of the environmental steady-state phenotype group is as follows: Let the time interval of a certain phenological stage be... The corresponding phenotypic parameter sequence is ,in If there is a certain point in time within this period; , making exist If the trend of change before and after the event differs significantly, then that point in time is considered a mutation point; mutation intensity The calculation formula is: 。 9. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 1, characterized in that, The environmental equivalent value mapping model is as follows: ； in, This is the standardized environmental equivalent value. For spatial coordinates, For time, Environmental factors The weight, These are the normalized phenotypic parameter values.

10. The method for automated collection and feature processing of plant phenotypes in diverse environments according to claim 9, characterized in that, The key environmental sensitive window analyzes the correlation between phenotypic parameters and environmental factors in different phenological stages, and combines dynamic query function to identify key environmental factors and their corresponding sensitive windows in the budding, flowering and maturity stages, and outputs cross-environmental regulation schemes by region and stage.

Images