A method for precise light and heat regulation of wheat cultivation seedlings

Abstract

The present application relates to the field of crop cultivation technology, and more particularly to a method for precise light and heat regulation of wheat seedling cultivation. Through multi-dimensional data acquisition, time series analysis, classification prediction and feedback cycle mechanism, a mapping model of light and heat environment and physiological signals is constructed, the health status and abnormal mode are accurately identified, and real-time regulation instruction sequence is generated, the light and temperature parameters are dynamically adjusted, and the environmental conditions are continuously met the needs of seedlings, realizing the fine management of wheat seedling growth environment, significantly improving the adaptability of seedlings to light and heat conditions, reducing the influence of environmental stress on growth, and providing an efficient and intelligent solution for agricultural production.

Description

Technical Field

[0001] This invention relates to the field of crop cultivation technology, and in particular to a method for precise control of light and heat in wheat seedlings. Background Technology

[0002] In agricultural production, the management of the growth environment of wheat seedlings has a crucial impact on yield and quality. Light and temperature, as key factors affecting seedling growth, directly relate to the efficiency of photosynthesis and metabolic activities. Ensuring the healthy growth of seedlings in a dynamically changing environment is a critical issue that modern agriculture urgently needs to address, especially given the context of variable climate and limited resources, making precise control of environmental conditions particularly urgent.

[0003] However, current wheat seedling management often suffers from insufficient monitoring of environmental factors and the seedling's own condition. Many methods focus only on adjusting a single environmental parameter, neglecting the interaction between light and temperature, and the combined impact of these factors on seedling physiological responses. This one-sidedness leads to environmental regulation often failing to adapt to the actual needs of the seedlings in a timely manner, thus affecting growth outcomes.

[0004] A deeper technical challenge lies in the fact that the effects of changes in light and temperature, as two core environmental factors, on seedlings are not simply linear but involve complex interactions. For example, when light intensity is too high, if the temperature is not lowered in time, seedlings may wilt due to overheating or even experience inhibited photosynthesis; conversely, in low-temperature environments, insufficient light may lead to slow seedling growth and weakened metabolic activity. The dynamic and uncertain nature of this interaction makes relying solely on experience or fixed rules for environmental adjustments extremely difficult, often failing to meet the individualized needs of seedlings at different growth stages. In actual planting, farmers or systems often face the following dilemma: when light suddenly intensifies, the temperature also rises, but due to a lack of real-time feedback on seedling leaf condition or growth rate, adjustments may be delayed, leading to heat stress and even irreversible damage to seedlings. On cloudy days or in low-temperature environments, failure to supplement light or raise the temperature in time can also cause seedlings to miss the optimal growth window, affecting their overall development.

[0005] Therefore, how to capture the physiological responses of seedlings in real time under constantly changing light and temperature conditions, and dynamically adjust environmental parameters based on these responses to ensure that seedlings are always in a suitable growth state, has become a key problem that urgently needs to be solved. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a method for precise control of light and heat in wheat seedling cultivation. It addresses the differences in growth requirements of wheat seedlings under different light and heat environments by integrating environmental data acquisition, physiological signal analysis, and dynamic environmental control to solve business scenario problems, forming a complete logical chain from data perception to precise control.

[0007] To achieve the above objectives, the technical solution of the present invention is as follows: A method for precise control of light and heat in wheat seedling cultivation, the method comprising: The light intensity and temperature data in the photothermal environment are collected by a sensor array, and the leaf temperature changes and photosynthetic rate indicators of wheat seedlings are recorded simultaneously to obtain the initial response dataset. Based on the initial response dataset, the correlation between photothermal environment and physiological signals was analyzed, a mapping model was constructed, and the response characteristics of wheat seedlings under different environments were determined. The response features are processed using a classification algorithm to generate health status categories and abnormal pattern classification results. Real-time features are extracted from the classification results to predict dynamic adaptation trends and generate adaptation curve data. Based on the adaptation curve data, determine the deviation status of photothermal conditions, adjust the light intensity and temperature parameters, and obtain the optimized parameter set; The optimized parameter set is verified through a feedback loop mechanism to determine the final fine management parameter set. Based on the fine management parameter set, a continuous monitoring instruction sequence is generated to dynamically optimize environmental control.

[0008] Furthermore, the process involves collecting light intensity and temperature data from the photothermal environment using a sensor array, simultaneously recording changes in leaf temperature and photosynthetic rate indices of wheat seedlings, and obtaining an initial response dataset, including: The sensor array acquires light intensity and ambient temperature data in real time, and records the dynamic changes in wheat seedling leaf temperature and photosynthetic rate index values ​​to form a preliminary physiological signal dataset. For the preliminary physiological signal dataset, time series analysis is used to determine the dynamic pattern of leaf temperature change. If the leaf temperature change in the dynamic pattern exceeds the preset threshold range, outliers are removed by data filtering technology to generate a corrected temperature change dataset. Based on the corrected temperature change dataset and the photosynthetic rate index, the correlation between the two is analyzed to determine the degree of influence of the photothermal environment on photosynthetic efficiency.

[0009] Furthermore, based on the initial response dataset, the correlation between photothermal environment and physiological signals is analyzed, a mapping model is constructed, and the response characteristics of wheat seedlings under different environments are determined, including: Based on the initial response dataset, fluctuation data of light intensity and ambient temperature were extracted. Combined with leaf temperature changes and photosynthetic rate indicators, the influence pattern of photothermal conditions on physiological signals was analyzed. Based on the influence pattern, a mapping model between photothermal environment and physiological signals was constructed for different combinations of light intensity and temperature. Based on the mapping model, response characteristic data of wheat seedlings under various environmental conditions are obtained. Through the response characteristic data, the adaptability of wheat seedlings to light and heat conditions is analyzed, and an environmental response characteristic set is generated.

[0010] Furthermore, the step of processing the response features using a classification algorithm to generate health status categories and abnormal pattern classification results includes: Based on the response characteristics, the physiological signals of wheat seedlings are classified using the support vector machine algorithm to determine the health status categories under different light and heat conditions. If the amount of data in a certain health status category is lower than the preset proportion, the sample is expanded through data augmentation technology to generate a balanced classification dataset. For balanced classification datasets, the random forest algorithm is used to extract abnormal pattern features and classify the abnormal types of physiological signals. If the photosynthetic rate index is lower than a preset threshold, it is determined to be a photoinhibition response, and a specific response type label is generated.

[0011] Furthermore, the step of extracting real-time features from the classification results, predicting dynamic adaptation trends, and generating adaptation curve data includes: The light suppression response data were filtered from the classification results, real-time perception-related features were extracted, and the real-time perception-related features were standardized to generate a normalized feature set. For the normalized feature set, the support vector machine algorithm is applied to predict the dynamic adaptation trend and generate the adaptation trend prediction result. Based on the adaptive trend prediction results, key node data are extracted and an adaptive trend curve representation is constructed. If there are missing data in the adaptive trend curve representation, the missing parts are supplemented by interpolation to generate complete adaptive curve data.

[0012] Furthermore, the step of determining the deviation state of photothermal conditions based on the adaptation curve data, adjusting the light intensity and temperature parameters, and obtaining an optimized parameter set includes: Based on the adaptation curve data, analyze the current deviation status of the photothermal conditions. If the deviation status exceeds the preset threshold, trigger the light intensity parameter adjustment process and generate a preliminary adjustment plan. For the initial adjustment plan, the optimized light intensity value is determined through iterative calculation. Based on the optimized light intensity value, parameter adjustment instructions are generated. Combined with target interval calibration, a calibrated parameter set is generated. By analyzing the real-time state of photothermal conditions using the calibrated parameter set, it can be determined whether the target interval constraints are met.

[0013] Furthermore, the optimized parameter set is verified through a feedback loop mechanism to determine the final fine-grained management parameter set, including: Based on the optimized parameter set, combined with temperature data, environmental control commands are generated and sent to environmental equipment to collect real-time blade temperature change data. By continuously monitoring the blade temperature change data using a feedback loop mechanism, if the temperature change exceeds the preset threshold range, an adjustment signal is triggered, a new temperature adjustment value is calculated, and an update control command is generated. According to the updated control command, the blade temperature change is monitored synchronously to obtain the adjusted temperature data. If the adjusted temperature data tends to be stable, the final set of temperature adjustment parameters is determined.

[0014] Furthermore, the step of generating a continuous monitoring instruction sequence based on the fine-grained management parameter set and dynamically optimizing environmental control includes: Based on the refined management parameter set, an environmental control basic data set is constructed, an initial management instruction sequence is generated, and combined with the wheat seedling growth stage, the real-time demand for environmental control is analyzed to obtain data on the changes in environmental variables in stages. Based on the phased changes in environmental variables, real-time monitoring instructions are generated and transmitted to environmental control equipment. Through these instructions, the environmental adaptation of wheat seedlings is analyzed, and the deviation range is determined. If the deviation range exceeds a preset threshold, an adjustment signal is generated, the instruction sequence is updated, the details of the dynamic adjustment operation are recorded, and a structured control log is generated.

[0015] The technical effects and advantages of this invention are as follows: 1. This application provides a method for precise control of light and heat in wheat seedling cultivation. Through multi-dimensional data collection, time-series analysis, classification prediction, and feedback loop mechanism, a mapping model between light and heat environment and physiological signals is constructed. This model accurately identifies healthy states and abnormal patterns, generates real-time control command sequences, and dynamically adjusts light and temperature parameters to ensure that environmental conditions continuously meet the needs of seedlings. This achieves refined management of the wheat seedling growth environment, significantly improves the adaptability of seedlings to light and heat conditions, reduces the impact of environmental stress on growth, and provides an efficient and intelligent solution for agricultural production. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the process for precise control of light and heat in wheat seedlings according to the present invention; Figure 2 This is a schematic diagram of the physiological signal mapping model of seedlings with different light and heat combinations.

[0017] Figure 3This is a classification diagram of the health status and abnormal patterns of wheat seedlings. Detailed Implementation

[0018] The present invention will be further described in detail below with reference to the embodiments given in the accompanying drawings.

[0019] See Figure 1 As shown, this invention provides a method for precise control of light and heat in wheat seedling cultivation. The aim is to achieve dynamic optimization management of the growth environment by collecting and analyzing light and heat environment data, combined with the physiological signal characteristics of wheat seedlings. The technical solution of this invention will be described in detail below with reference to specific embodiments to make the objectives, technical solutions, and advantages of this invention clearer.

[0020] The method provided by this invention mainly targets the growth needs of wheat seedlings under different light and heat conditions. Through multi-dimensional data collection and analysis, it constructs a correlation model between environmental and physiological signals, thereby achieving precise environmental regulation. The entire method includes multiple steps such as data collection, correlation analysis, classification processing, trend prediction, and parameter adjustment, gradually realizing refined management of the wheat seedling growth environment. The specific implementation process is as follows: Step S1: Collect light intensity and temperature data in the photothermal environment through a sensor array, and simultaneously record the leaf temperature changes and photosynthetic rate indicators of wheat seedlings to obtain the initial response dataset.

[0021] This step is fundamental to the entire implementation process and aims to obtain raw information about the wheat seedlings' growth environment and physiological state. Sensor arrays are typically deployed within the wheat seedling planting area, covering different light and temperature distribution zones to ensure data comprehensiveness. Light intensity data is primarily acquired through light sensors, usually measured in lux, to characterize the intensity of ambient light; temperature data is collected using high-precision temperature sensors, accurate to 0.1 degrees Celsius, to reflect subtle changes in ambient temperature. Simultaneously, infrared thermometers monitor real-time temperature changes in wheat seedling leaves, recording their dynamic fluctuations over different time periods. Furthermore, photosynthetic rate indicators are obtained using a portable photosynthesis meter, reflecting the photosynthetic efficiency of the wheat seedlings under the current environment. These data collectively constitute the initial response dataset. The specific execution process of this step is as follows: Step S11: Real-time acquisition of light intensity and ambient temperature data through sensor array, while recording dynamic changes in wheat seedling leaf temperature and photosynthetic rate index values ​​to form a preliminary physiological signal dataset.

[0022] In practice, the sensor array can include multiple light and temperature sensors, installed at different locations within the planting area, such as above the field, near seedlings, and in shaded areas, to capture spatial differences in light and heat conditions. The light sensors record data every 5 minutes, while the temperature sensors collect ambient and leaf temperatures every 2 minutes, ensuring sufficiently high temporal resolution. Photosynthetic rate measurements are typically performed at fixed times each day, such as 9:00 AM to 11:00 AM, to avoid interference from changes in the angle of sunlight. The collected data is uploaded in real-time to a data processing center via a wireless transmission module, forming a preliminary physiological signal dataset containing multi-dimensional information such as timestamps, light intensity values, ambient temperature values, leaf temperature values, and photosynthetic rate values.

[0023] Step S12: Based on the preliminary physiological signal dataset, time series analysis is used to determine the dynamic pattern of leaf temperature changes. Time series analysis is a method for processing data that changes over time, aiming to uncover periodic, trend, and anomalous features in the data.

[0024] In this embodiment, the blade temperature data is first smoothed to reduce noise interference. For example, a moving average method is used to average every 10 consecutive data points to obtain a smoothed temperature change curve. The calculation formula is as follows:

[0025] in, for The blade temperature after time smoothing. The moving average window size (n=10 in this example) is used. For the first The raw blade temperature data at that moment.

[0026] Then, the periodic characteristics of temperature changes are analyzed, such as observing the daily temperature fluctuations during the morning and evening to determine whether they are synchronized with changes in light intensity. Furthermore, trend characteristics of temperature changes are extracted, such as whether leaf temperature shows a continuous upward trend under sustained high temperatures. Through these analyses, a dynamic pattern of leaf temperature changes is obtained, which is used to subsequently assess the impact of the environment on wheat seedlings.

[0027] Step S13: If the blade temperature change in the dynamic mode exceeds the preset threshold range, outliers are removed by data filtering technology to generate a corrected temperature change dataset.

[0028] In actual planting environments, leaf temperature data may exhibit outliers due to sensor malfunctions, external interference, or sudden weather changes. For example, the temperature might suddenly jump to a value far exceeding the normal range. To ensure data reliability, a reasonable threshold range needs to be set. For instance, the normal leaf temperature range could be set to 15 to 35 degrees Celsius. If a data point exceeds this range, it should be marked as an outlier. Data filtering techniques can employ median filtering, which involves taking the time point before and after the outlier as the center. The median value replaces outliers in a data set, thus smoothing the data curve. The formula for median filtering is as follows:

[0029] in, for The blade temperature after real-time correction. The median filter window radius is k=3 in this embodiment, and median{} represents taking the median of the data within the brackets.

[0030] Furthermore, contextual data can be used for validation. For example, if outliers occur during periods of continuous high temperatures, they may be genuine data and should be retained. Through the above processing, a corrected temperature change dataset is generated, ensuring the accuracy and consistency of the data.

[0031] Step S14: Based on the corrected temperature change dataset and the photosynthetic rate index, analyze the correlation between the two to determine the degree of influence of the photothermal environment on photosynthetic efficiency.

[0032] This step focuses on analyzing the relationship between leaf temperature changes and photosynthetic rate to reveal the impact of the photothermal environment on the physiological state of wheat seedlings. Specifically, firstly, the corrected temperature change data and photosynthetic rate data are aligned by time to form a unified time-series dataset. Then, the Pearson correlation coefficient between the two at different time periods is calculated to quantify their correlation. The calculation formula is as follows:

[0033] Where r is the Pearson correlation coefficient (with a value range of [-1,1]). m For the number of data samples, For the first i The blade temperature after real-time correction. This is the average value of the corrected blade temperature. P(i) For the first i The photosynthetic rate at any given time This represents the average photosynthetic rate. r >0 indicates a positive correlation. r <0 indicates a negative correlation. |r| The closer the correlation is to 1, the stronger the correlation.

[0034] In addition, the impact of temperature change rate on photosynthetic efficiency will be analyzed. For example, if leaf temperature rises rapidly in a short period of time, will it lead to a sharp decrease in photosynthetic rate? Through these analyses, the extent to which the light and heat environment affects the photosynthetic efficiency of wheat seedlings will be preliminarily determined, providing data support for the subsequent construction of a mapping model.

[0035] In one possible implementation, analysis of seedling data from a wheat planting base revealed that when the ambient temperature exceeded 30 degrees Celsius and the light intensity was higher than 80,000 lux, the leaf temperature rose by more than 5 degrees Celsius within half an hour, and the photosynthetic rate decreased by about 30%.

[0036] The changes in physiological indicators of wheat seedlings under different light and heat conditions are shown in Table 1 below: Table 1

[0037] Further analysis revealed that this decline was primarily due to stomatal closure caused by high temperature and light, which reduced carbon dioxide absorption and thus inhibited photosynthetic efficiency. This finding indicates that the effect of the photothermal environment on photosynthetic efficiency has a significant nonlinear characteristic, requiring further steps to construct a more accurate model for quantitative description.

[0038] In another embodiment, data were collected from different wheat seedling varieties. It was found that varieties with stronger heat tolerance showed a smaller increase in leaf temperature and a decrease in photosynthetic rate of only about 10% under high-temperature conditions, while varieties with weaker heat tolerance showed a more significant decrease, reaching up to 40%. The comparison of heat tolerance among different wheat seedling varieties is shown in Table 2 below: Table 2

[0039] Comparative analysis reveals that wheat seedlings exhibit varietal differences in their adaptability to light and heat environments. Therefore, differentiated management strategies should be developed for different varieties in subsequent environmental control to improve overall growth performance.

[0040] Step S2: Based on the initial response dataset, analyze the correlation between photothermal environment and physiological signals, construct a mapping model, and determine the response characteristics of wheat seedlings under different environments.

[0041] This step is one of the core components of the entire method, aiming to establish a quantitative relationship between the light and heat environment and the physiological signals of wheat seedlings through data analysis, providing a theoretical basis for subsequent classification and prediction. The construction of the mapping model requires comprehensive consideration of multi-dimensional data such as light intensity, ambient temperature, leaf temperature changes, and photosynthetic rate. Multivariate analysis methods are used to uncover their intrinsic correlations and generate a model that can characterize the response features of wheat seedlings. The specific execution process of this step is as follows: Step S21: Based on the initial response dataset, extract the fluctuation data of light intensity and ambient temperature, and combine the leaf temperature change and photosynthetic rate index to analyze the influence pattern of light and heat conditions on physiological signals.

[0042] In practice, the initial response dataset is first preprocessed. Firstly, the light intensity and ambient temperature data are standardized to eliminate dimensional differences. The standardization formula is as follows:

[0043] in, The values ​​are standardized. X The original data, This is the minimum value of the indicator. This represents the maximum value of the indicator.

[0044] Then, the fluctuation characteristics of light intensity and ambient temperature were extracted, such as calculating the daily peak, mean, and rate of change of light intensity, and the daily average temperature difference and extreme values ​​of ambient temperature. Next, these fluctuation characteristics were correlated with leaf temperature changes and photosynthetic rate indicators to observe the physiological signal manifestations of wheat seedlings under different combinations of light and heat conditions. For example, under conditions of sustained high light intensity and rapid temperature rise, did leaf temperature show an accelerated upward trend, and did the photosynthetic rate show a significant decrease? Through these analyses, the influence pattern of light and heat conditions on physiological signals was preliminarily determined, providing a data foundation for subsequent model construction.

[0045] Step S22: By using the influence mode, a mapping model between photothermal environment and physiological signals is constructed for different combinations of light intensity and temperature.

[0046] See Figure 2As shown in the figure, the physiological response regions of four types of wheat seedlings are divided into different colored blocks, corresponding to the growth status under different light and heat combinations. This is used to intuitively quantify the correspondence between different light and heat combinations and the physiological response of wheat seedlings, providing a modeling basis for subsequent trend prediction and precise regulation. The green zone represents the optimal growth zone, characterized by a combination of low to medium light intensity and medium to high temperature. Physiologically, wheat seedlings are in their optimal growth range, exhibiting high photosynthetic rates, stable leaf temperatures, and no stress damage; this is the target zone for cultivation regulation. The red zone represents the photoinhibition zone, characterized by a combination of high light intensity and medium to high temperature. Physiologically, light intensity exceeds the seedlings' tolerance threshold, causing photoinhibition and a significant decrease in photosynthetic rates; this is a stress zone requiring regulation through shading and supplemental lighting. The blue zone represents the heat stress zone, characterized by a combination of low to medium light intensity and low temperature. Physiologically, excessively high ambient temperatures exceed the suitable growth temperature for seedlings, causing heat stress, abnormally high leaf temperatures, and suppressed photosynthetic rates; this requires regulation through cooling. The yellow zone represents the low-temperature inhibition zone, characterized by a combination of high light intensity and low temperature. Physiologically, excessively low ambient temperatures cause low-temperature stress; even with sufficient light, photosynthetic rates are still suppressed; this requires regulation through heating. The mapping model was constructed to quantify the relationship between light and heat conditions and physiological signals in wheat seedlings, enabling it to predict physiological responses under specific conditions.

[0047] In this embodiment, a mapping model is constructed using multivariate regression analysis, with input variables including light intensity (…). L ), ambient temperature ( T ) and its fluctuation characteristics, with the output variable being the leaf temperature change rate ( ) and photosynthetic rate value ( P ).

[0048] The regression model for the rate of change of leaf temperature is as follows:

[0049] The regression model for photosynthetic rate is as follows:

[0050] in, and For regression coefficients, and This is the random error term.

[0051] Specifically, the dataset is first divided into multiple subsets, each corresponding to a specific combination of light and heat conditions, such as high temperature and high light, medium temperature and medium light, and low temperature and low light. Then, a regression model is fitted to each subset to obtain parameter values ​​under each condition, such as the influence coefficient of light intensity on leaf temperature change and the inhibition coefficient of ambient temperature on photosynthetic rate. Finally, the regression results from all subsets are integrated to form a comprehensive mapping model used to describe the physiological response patterns of wheat seedlings under different light and heat conditions.

[0052] Step S23: Based on the mapping model, obtain response characteristic data of wheat seedlings under various environmental conditions. After constructing the mapping model, use this model to simulate various combinations of light and heat conditions to generate response characteristic data of wheat seedlings. For example, set the light intensity range from 20,000 lux to 100,000 lux and the ambient temperature range from 15 degrees Celsius to 35 degrees Celsius, input them into the model respectively, and calculate the corresponding leaf temperature change rate and photosynthetic rate values. In this way, a response characteristic dataset containing multiple environmental conditions is generated, covering the physiological performance of wheat seedlings in different light and heat environments. These data not only reflect the adaptability of wheat seedlings to the environment but also reveal their stress response characteristics under extreme conditions, laying the foundation for subsequent analysis.

[0053] Step S24: Analyze the adaptability of wheat seedlings to light and heat conditions through response feature data, and generate an environmental response feature set.

[0054] This step focuses on analyzing the adaptability of wheat seedlings under different environmental conditions. For example, in high temperature and high light conditions, can they maintain a stable photosynthetic rate by adjusting leaf temperature? Or in low temperature and low light conditions, do they exhibit slow growth?

[0055] Specifically, firstly, cluster analysis was performed on the response feature data using the K-means clustering algorithm, dividing it into three categories: highly adaptable, moderately adaptable, and poorly adaptable. Then, for each category, key features were extracted; for example, the highly adaptable category exhibited characteristics such as a lower leaf temperature change rate and a higher photosynthetic rate. Finally, these features were integrated into an environmental response feature set to characterize the overall adaptability of wheat seedlings under different light and heat conditions, providing a basis for subsequent classification and regulation.

[0056] In one possible implementation, analysis of data from a specific wheat-growing region revealed that when the ambient temperature was between 20 and 25 degrees Celsius and the light intensity was between 40,000 and 60,000 lux, the leaf temperature change rate of wheat seedlings remained at a low level, while the photosynthetic rate reached its daily peak, demonstrating strong adaptability. However, when the temperature exceeded 30 degrees Celsius and the light intensity exceeded 80,000 lux, the leaf temperature change rate increased significantly, and the photosynthetic rate decreased by more than 25%, indicating weaker adaptability. This analysis can clarify the optimal growth environment range for wheat seedlings, providing a direct reference for subsequent environmental regulation.

[0057] In another embodiment, response characteristic analysis was conducted on wheat seedlings at different growth stages. It was found that seedlings in the tillering stage showed weak tolerance to high temperature and high light, with a higher rate of leaf temperature change and a significant decrease in photosynthetic rate. In contrast, seedlings in the jointing stage exhibited strong adaptability, maintaining a certain photosynthetic efficiency even under high temperatures. The comparison of the adaptability of wheat seedlings at different growth stages is shown in Table 3 below. Table 3

[0058] This finding suggests that environmental regulation needs to be dynamically adjusted in conjunction with the growth stages of wheat seedlings to ensure that suitable growth conditions can be provided at different stages.

[0059] Step S3: Use a classification algorithm to process the response features and generate health status category and abnormal pattern classification results.

[0060] This step aims to classify the physiological signals of wheat seedlings based on the aforementioned set of environmental response characteristics, distinguishing between their healthy states and abnormal patterns, thus providing a basis for subsequent prediction and regulation. The classification process comprehensively considers the performance of wheat seedlings under different light and heat conditions, generating accurate classification results through multi-dimensional feature analysis. The specific execution process of this step is as follows: Step S31: Based on the response characteristics, the physiological signals of wheat seedlings are classified using the Support Vector Machine (SVM) algorithm to determine the health status category under different light and heat conditions. SVM is a statistical learning-based classification method suitable for processing multi-dimensional feature data and effectively distinguishing data samples of different categories.

[0061] In this embodiment, the environmental response feature set is used as input data, and the features include the leaf temperature change rate (…). ), photosynthetic rate value ( P ), light intensity ( LThe classification objective is to categorize the physiological signals of wheat seedlings into three main categories: good health, fair health, and poor health. Specifically, the feature data is first standardized to ensure consistency in the dimensions of each feature. Then, a classification model is constructed using a support vector machine (SVM) algorithm. By finding the optimal hyperplane in the feature space, data samples of different health states are separated. Finally, the classification results are generated, clearly defining the health status category of wheat seedlings under different light and heat conditions. For example, under suitable light and heat conditions, the seedlings exhibit good health, while under extreme high temperature and high light conditions, they exhibit poor health.

[0062] See Figure 3 As shown, each group of three columns of bars corresponds to an abnormality pattern. The height of each column represents the proportion / severity of that health level. The color-coded layers clearly show the classification criteria. In the light inhibition group, "Good" (green) indicates a large baseline proportion, suggesting that seedlings can recover through self-regulation under mild light inhibition; "Average" (yellow) indicates moderate light inhibition leading to decreased photosynthetic efficiency; and "Poor" (red) indicates severe light inhibition causing irreversible damage. In the heat stress group, "Good" (green) indicates a lower proportion than the light inhibition group, suggesting that heat stress has a more direct impact on seedlings; "Average" (yellow) indicates moderate heat stress causing excessive leaf temperature; and "Poor" (red) indicates severe heat stress causing heat damage. In the low temperature inhibition group, "Good" (green) indicates the highest proportion, suggesting that the inhibitory effect of low temperature on seedlings is relatively delayed; "Average" (yellow) indicates moderate low temperature inhibiting photosynthetic rate; and "Poor" (red) indicates severe low temperature stress causing growth stagnation. Figure 3 It can intuitively display the classification results of the health level and abnormal patterns of wheat seedlings under different light and heat stresses using the support vector machine algorithm, providing a basis for subsequent trend prediction and precise regulation.

[0063] Step S32: If the data volume of a certain health status category is lower than a preset proportion, data augmentation techniques are used to expand the sample and generate a balanced classification dataset. In actual data analysis, due to the possibility of insufficient data samples under certain light and heat conditions, such as insufficient data volume under extreme low temperature and low light conditions, the classification model's ability to identify that category may be weak. To solve this problem, a preset proportion of data volume is set, for example, requiring that the data volume of each health status category accounts for no less than 20% of the total data. If the data volume of a certain category is lower than this proportion, data augmentation techniques are used to expand the sample. Specifically, a Gaussian noise-based data augmentation method can be used to generate new samples, as shown in the following formula:

[0064] in, For the enhanced new sample, For the original sample, Noise intensity (in this embodiment) N(0,1) is a standard normally distributed random number.

[0065] Furthermore, interpolation methods can be used to generate intermediate state data, such as interpolating between a normal and a poor health state to create transitional data samples. These methods generate a balanced classification dataset, ensuring the accuracy and robustness of subsequent classification models.

[0066] Step S33: For the balanced classification dataset, the random forest algorithm is used to extract abnormal pattern features and classify the abnormal types of physiological signals. Random forest is an ensemble learning method that classifies data by constructing multiple decision trees, effectively identifying abnormal patterns in complex data.

[0067] In this step, a balanced classification dataset is input into a random forest model to extract abnormal pattern features from the physiological signals of wheat seedlings, such as a persistently lower photosynthetic rate than normal, and abnormally high or low leaf temperature change rates. The classification objective is to categorize abnormal patterns into types such as light-induced suppression response, heat stress response, and low-temperature suppression response. Specifically, the random forest model analyzes the importance of each feature to the classification result. For example, if the photosynthetic rate decreases significantly and the light intensity is extremely high, it tends to be classified as a light-induced suppression response; if the leaf temperature continues to rise and the ambient temperature is far above the normal range, it tends to be classified as a heat stress response. In this way, the abnormal type classification results of the physiological signals of wheat seedlings are generated, providing a basis for subsequent targeted regulation. The feature judgment criteria for different abnormal types are shown in Table 4 below: Table 4

[0068] Step S34: If the photosynthetic rate index is lower than a preset threshold, it is determined to be a photoinhibition response, and a specific response type label is generated. Under certain light and heat conditions, wheat seedlings may experience photoinhibition due to excessive light intensity, leading to a significant decrease in photosynthetic rate. To accurately identify this abnormal pattern, a preset threshold for photosynthetic rate is set, for example, setting the lower limit of the normal photosynthetic rate to 70% of the daily average. That is:

[0069] in, A preset threshold is set for the photosynthetic rate. This represents the average photosynthetic rate for that day.

[0070] If the photosynthetic rate index remains below a certain threshold for a given period, it is identified as a photoinhibition response, and a corresponding response type label is generated, such as "photoinhibition - high light intensity". Furthermore, it is verified in conjunction with light intensity data; for example, if the light intensity exceeds 80,000 lux, the possibility of a photoinhibition response is further confirmed. In this way, specific response type labels are generated, providing accurate anomaly information for subsequent environmental regulation.

[0071] In one possible implementation, classification analysis of seedling data from a wheat-growing region revealed that when light intensity exceeded 90,000 lux for more than 2 hours, the photosynthetic rate dropped to below 60% of normal levels, consistent with the characteristics of photoinhibition response. Further analysis using a random forest model confirmed that this abnormal pattern was primarily caused by photosystem damage due to excessive light, generating a "photoinhibition-high light intensity" label. This label helps in subsequent targeted reduction of light intensity to prevent further decline in photosynthetic efficiency.

[0072] In another embodiment, anomaly pattern analysis was performed on wheat seedlings with different planting densities. It was found that seedlings in high-density planting areas were more prone to heat stress responses, characterized by leaf temperatures consistently above 35 degrees Celsius and photosynthetic rates decreasing to below 50% of normal levels. Seedlings in low-density planting areas showed fewer such anomalies, indicating that planting density has a significant impact on heat stress response. The incidence of anomaly patterns under different planting densities is compared in Table 5 below. Table 5

[0073] The analysis generated a "heat stress-high density" label, providing a reference for subsequent optimization of planting layout and environmental control. This analysis also revealed the importance of rationally adjusting planting density, which helps improve the overall health of wheat seedlings.

[0074] It should be noted that the above classification process can not only identify the health status and abnormal patterns of wheat seedlings, but also provide data support for subsequent dynamic prediction and environmental regulation. In-depth analysis of the classification results can clarify the specific impact pathways of light and heat conditions on wheat seedlings, thereby enabling the development of more precise management strategies.

[0075] In one embodiment, supplementary analysis of the classification results of wheat seedlings under different soil moisture conditions revealed that seedlings were more prone to heat stress responses when soil moisture was low. Even if the ambient temperature did not reach extreme values, leaf temperature would rise rapidly, leading to a decrease in photosynthetic rate. This phenomenon indicates that the interaction between soil moisture and light and heat conditions has a significant impact on the physiological signals of wheat seedlings. By generating a "heat stress-low humidity" tag, environmental conditions can be optimized in subsequent regulation by combining irrigation measures, avoiding the exacerbation of heat stress due to insufficient water.

[0076] For example, in a wheat experimental field, during the high temperatures of summer, soil moisture dropped to below 60% of normal levels, and seedling leaf temperature rose to 38 degrees Celsius in a short period, with photosynthetic rate decreasing by about 35%. Classification model analysis confirmed this abnormal pattern as a heat stress response, and a corresponding label was generated. Based on this result, subsequent control measures included timed irrigation, which restored soil moisture to a suitable level, lowered seedling leaf temperature to 32 degrees Celsius, and restored photosynthetic rate to over 85% of normal levels. This case demonstrates that the accuracy of classification results directly affects the effectiveness of environmental control, and appropriate label generation can significantly improve management efficiency.

[0077] In another possible approach, analysis of wheat seedling classification results under different light shading conditions revealed that some seedlings experienced insufficient light intensity due to shading from surrounding crops, resulting in a persistently lower photosynthetic rate than normal, exhibiting a low-temperature inhibition response. Anomaly pattern features were extracted using a random forest model to generate a "low-temperature inhibition - low light intensity" label. This label helps in subsequent regulation by adjusting planting layouts or increasing artificial lighting measures to improve photosynthetic efficiency and ensure healthy seedling growth.

[0078] It should be noted that the above steps, through multi-dimensional data analysis and classification, comprehensively revealed the physiological signal characteristics of wheat seedlings under different light and heat conditions, laying a solid foundation for subsequent dynamic prediction and environmental regulation. The classification results not only reflect the health status of the seedlings but also clarify the causes and manifestations of abnormal patterns, providing important references for precision management.

[0079] In one embodiment, a comparative analysis of classification results for wheat seedlings at different growth stages revealed that seedlings in the tillering stage were highly sensitive to light and heat conditions, with over 30% of the seedlings classified as "poorly healthy" in the health status category. However, the sensitivity of seedlings in the jointing stage decreased, with the proportion falling below 15%. This result indicates that the growth cycle significantly impacts the adaptability of wheat seedlings. By generating classification labels for different growth stages, phased management strategies can be developed for subsequent regulation. For example, monitoring and adjusting light and heat conditions during the tillering stage can be strengthened to reduce the probability of abnormal patterns.

[0080] For example, in experimental data from a wheat planting base, tillering seedlings exhibited a significant heat stress response under high temperature and high light conditions, with leaf temperature change rates reaching as high as 3 degrees Celsius per hour and photosynthetic rates dropping to below 60% of normal levels. By generating a "heat stress-tillering stage" label using a classification model, subsequent control measures specifically reduced light intensity and ambient temperature, lowering the leaf temperature change rate to 1.5 degrees Celsius per hour and restoring the photosynthetic rate to over 80% of normal levels. This case demonstrates that combining growth cycle classification analysis can significantly improve the targeting and effectiveness of environmental control, providing strong support for the healthy growth of wheat seedlings.

[0081] In another embodiment, classification analysis of wheat seedling planting data at different geographical locations revealed that seedlings in high-altitude areas were more prone to low-temperature inhibition, characterized by a persistently lower photosynthetic rate than normal, while seedlings in low-altitude areas exhibited more heat stress responses. By generating "low-temperature inhibition - high altitude" and "heat stress - low altitude" labels, differentiated management plans can be developed in subsequent regulation based on geographical characteristics. For example, insulation measures can be increased in high-altitude areas, while cooling measures can be strengthened in low-altitude areas to optimize the seedling growth environment.

[0082] Step S4: Extract real-time features from the classification results, predict the dynamic adaptation trend, and generate adaptation curve data.

[0083] This step, based on the aforementioned classification results, further analyzes the dynamic adaptability of wheat seedlings under different light and heat conditions. The aim is to generate curve data reflecting seedling adaptability through real-time feature extraction and trend prediction, providing a basis for subsequent environmental regulation. Predicting dynamic adaptation trends requires comprehensive consideration of health status categories and abnormal pattern characteristics from the classification results, combined with real-time data analysis, to capture the response patterns of wheat seedlings to environmental changes. The specific execution process of this step is as follows: Step S41: Filter the light-inhibition response data from the classification results and extract real-time perception-related features. In specific implementation, firstly, data samples labeled as light-inhibition responses are filtered from the classification results. These data typically exhibit a photosynthetic rate significantly lower than normal and light intensity exceeding the normal range. Next, for these data samples, real-time perception-related features are extracted, such as the rate of decrease in photosynthetic rate (…). ), the rate of increase in leaf temperature ( ) and the instantaneous value of light intensity ( ), etc. The formula for calculating the rate of decline in photosynthetic rate is as follows:

[0084] in, This represents the rate of decrease in photosynthetic rate (a negative value indicates a decrease). The photosynthetic rate at the initial moment. for t 1 Photosynthetic rate at any given time For time intervals.

[0085] These features reflect the immediate physiological state of wheat seedlings at the onset of photoinhibition response, aiding in the subsequent prediction of their adaptation trends to environmental changes. Furthermore, temporal features are extracted, such as the duration of the photoinhibition response and its distribution across time periods within a day. This feature extraction creates a real-time feature dataset characterizing the photoinhibition response, laying the foundation for subsequent analysis.

[0086] Step S42 involves standardizing the real-time perception-related features to generate a normalized feature set. Since the extracted real-time perception-related features may have different dimensions and numerical ranges—for example, the numerical ranges of the photosynthetic rate decline rate and the instantaneous light intensity differ significantly—direct use may lead to biases in subsequent prediction models. Therefore, these features need to be standardized and converted into dimensionless numerical forms. Specifically, a linear normalization method is used to map the value of each feature to the range of 0 to 1, ensuring a balanced weighting of the influence of different features on the prediction results. Furthermore, the feature data is smoothed, for example, by using a moving average method to reduce noise interference in the data and ensure the stability of the feature values. Through these processes, a normalized feature set is generated, providing high-quality data support for subsequent trend prediction.

[0087] Step S43: For the normalized feature set, apply the Support Vector Machine (SVM) algorithm to predict the dynamic adaptation trend and generate the adaptation trend prediction result. The SVM algorithm is a statistical learning-based prediction method suitable for processing multi-dimensional feature data. It can predict data trends by constructing optimal decision boundaries.

[0088] In this step, the normalized feature set is used as input data, and the prediction target is the adaptive trend of wheat seedlings over a future period, such as whether the photosynthetic rate will continue to decline or whether the leaf temperature will continue to rise. The output of the prediction model is the future... t The photosynthetic rate and leaf temperature at any given time are given by the following formula:

[0089] in, for t Predict the photosynthetic rate in real time. for t Predicting leaf temperature in real time For the feature weight vector, For bias terms, This is the normalized feature set.

[0090] Specifically, the feature set is first divided into training data and test data. A support vector machine (SVM) prediction model is constructed using the training data to determine the mapping relationship between features and adaptation trends. Then, the model's prediction accuracy is verified using test data to ensure that the model can adapt to data changes under different light and heat conditions. Mean squared error (MSE) is used. MSE The model performance is evaluated using the following formula:

[0091] in, This is the actual value. For predicted values, n This represents the number of test samples. MSE The smaller the value, the higher the accuracy of the model's predictions.

[0092] The final result is an adaptation trend prediction, which characterizes the dynamic adaptability of wheat seedlings in the current environment.

[0093] Step S44: Based on the adaptation trend prediction results, extract key node data and construct an adaptation trend curve representation. Based on the prediction results, focus on extracting key node data, such as the time node when the photosynthetic rate drops to its lowest point. The time point when the blade temperature reaches its peak The formula for extracting key node data is as follows:

[0094] in, To predict the start time, To predict the termination time, for t The photosynthetic rate predicted at any time, for t Predicted leaf temperature at all times.

[0095] These key node data points reflect important turning points in the adaptation trend of wheat seedlings, helping to visually demonstrate their dynamic changes. Next, these key node data are used to construct adaptation trend curves, for example, plotting time on the horizontal axis and photosynthetic rate or leaf temperature on the vertical axis to create a graph reflecting the adaptation trend. In this way, the physiological state changes of wheat seedlings at different time periods can be clearly observed, providing a direct basis for subsequent environmental regulation.

[0096] Step S45: If the adaptation trend curve indicates missing data, interpolation is used to fill in the missing parts, generating complete adaptation curve data. In actual data processing, due to limitations in sensor acquisition frequency or data transmission interruptions, data gaps may exist in the adaptation trend curve, such as photosynthetic rate data not being recorded for a certain time period. To ensure the integrity and continuity of the curve, interpolation is used to fill in the missing parts. Specifically, a linear interpolation method is used to calculate approximate values ​​for the missing points based on data values ​​at several time points before and after the missing data points, and these approximate values ​​are then filled into the curve. Furthermore, if the time span of the missing data is long, interpolation estimation can be combined with historical data trends to ensure the rationality of the supplemented data. Through the above processing, complete adaptation curve data is generated, providing comprehensive support for subsequent analysis and control.

[0097] In one possible implementation, trend prediction was performed on seedling data from a wheat-growing area. It was found that the photoinhibition response peaked between 12 PM and 2 PM daily, with the photosynthetic rate dropping to below 50% of normal. By constructing an adaptation trend curve, it was clearly observed that the photosynthetic rate gradually decreased over time, reaching its lowest point at 13:45. h), the blade temperature reached its peak at 14:15 (h), The pattern of h) was observed. For the 10-minute data gap caused by equipment failure in the curve, linear interpolation was used to fill in the missing values, ensuring the continuity of the curve. This complete adaptation curve data provides an important reference for subsequent judgment of light and heat condition deviations.

[0098] In another embodiment, adaptation trend prediction was performed on wheat seedlings of different varieties. It was found that varieties with stronger light tolerance showed a more gradual decline in photosynthetic rate under high light intensity, with smaller fluctuations in their adaptation trend curves. In contrast, varieties with weaker light tolerance showed a significant decline, with larger fluctuations in their curves. A comparison of key parameters in the adaptation trend curves of different wheat seedling varieties is shown in Table 6 below. Table 6

[0099] By comparing and analyzing the adaptation curve data of different varieties, we can clarify the differences in their adaptability to light and heat conditions, providing a basis for subsequent targeted regulation.

[0100] Step S5: Based on the adaptation curve data, determine the deviation status of the photothermal conditions, adjust the light intensity and temperature parameters, and obtain the optimized parameter set.

[0101] This step, based on the aforementioned adaptation curve data, analyzes whether the current light and heat conditions deviate from the optimal growth requirements of wheat seedlings. It then generates an optimized set of environmental parameters through parameter adjustments, providing specific guidance for subsequent regulation. Determining deviations in light and heat conditions and adjusting parameters are crucial for achieving precision management, requiring comprehensive consideration of the seedlings' dynamic adaptation trends and actual environmental data. The specific execution process of this step is as follows: Step S51: Analyze the current deviation of light and heat conditions based on the adaptation curve data. In specific implementation, the adaptation curve data is first analyzed to extract key trends in photosynthetic rate and leaf temperature, such as a continuous decrease in photosynthetic rate or a leaf temperature consistently above the normal range. Next, these trends are compared with the optimal growth environment range for wheat seedlings. In this embodiment, the optimal light intensity range is... lx, the optimal ambient temperature range is ℃. The quantitative determination of deviation status uses the deviation rate formula, as follows:

[0102] in, The light intensity deviation rate, Given the current light intensity, lx is the median value of the optimal light intensity; The environmental temperature deviation rate, The current ambient temperature. ℃ represents the median of the optimal ambient temperature.

[0103] If the current light intensity or ambient temperature exceeds the above range, and the adaptation curve data shows a significant abnormal trend, such as a decrease in photosynthetic rate exceeding 30%, it is determined that there is a deviation in photothermal conditions. Furthermore, the duration and severity of the deviation will be analyzed to determine the urgency of subsequent adjustments.

[0104] In one possible implementation, the current light intensity lx, ambient temperature ℃, calculated , The photosynthetic rate dropped to 60% of the normal level, and the adaptation curve data showed a clear trend of light inhibition, indicating a serious deviation in photothermal conditions.

[0105] Step S52: If the deviation exceeds a preset threshold, the light intensity parameter adjustment process is triggered to generate a preliminary adjustment plan. To ensure the suitability of the wheat seedling growth environment, a preset threshold for the deviation is set; for example, in this embodiment, the light intensity deviation threshold is... Ambient temperature deviation threshold If the current deviation exceeds these thresholds, the light intensity parameter adjustment process will be triggered.

[0106] Specifically, firstly, based on the decrease in photosynthetic rate in the adaptation curve data... Preliminary estimate of the required adjustment value of light intensity The estimation formula is as follows:

[0107] in, Light intensity adjustment coefficient (in this embodiment) ), The rate of decrease in photosynthetic rate, ,in, This represents the current photosynthetic rate. The optimal photosynthetic rate.

[0108] Next, based on the current environmental conditions, a preliminary adjustment plan is generated. For example, adjusting the coverage area of ​​the shade net or the power of the artificial lighting equipment can reduce or increase the light intensity. In this way, it is ensured that the adjustment plan can specifically alleviate the deviation in light and heat conditions.

[0109] Step S53: Based on the initial adjustment plan, the optimized light intensity value is determined through iterative calculation. Further optimization of the light intensity value is needed to ensure that the adjusted environmental conditions can best meet the growth needs of wheat seedlings. The goal of the iterative calculation is to restore the photosynthetic rate to more than 80% of the normal level. The iterative formula is as follows:

[0110] in, For the first The illumination intensity of the next iteration For the first The illumination intensity of the next iteration The learning rate (in this embodiment) ), For the target photosynthetic rate, Current light intensity The photosynthetic rate was calculated using a mapping model.

[0111] An iterative calculation method was employed to gradually adjust the light intensity value based on the photosynthetic rate variation trend in the adaptation curve data. Through multiple iterations, the light intensity value was determined until the photosynthetic rate recovered to more than 80% of its normal level, or the leaf temperature dropped to a suitable range. This process ensures the accuracy and effectiveness of the adjustment results.

[0112] Step S54: Based on the optimized illumination intensity value, generate parameter adjustment instructions, and combine this with target interval calibration to generate a calibrated parameter set. The calibrated illumination intensity must meet the following constraints, and calibration is performed using the interval projection method:

[0113] in, For the calibrated light intensity, The optimized light intensity value, lx is the lower limit of the optimal light intensity. lx is the upper limit of the optimal light intensity.

[0114] After adjusting the light intensity, the ambient temperature needs to be calibrated simultaneously. Considering the indirect effects of sunlight on temperature (such as the cooling effect of shading), a linear correction model is adopted:

[0115] in, The current ambient temperature. The light-temperature correlation coefficient (in this embodiment) lx - ¹·℃ - ¹), used to characterize the expected decrease in ambient temperature for every 10,000 lx decrease in light intensity.

[0116] Through the above calibration, a set of calibration parameters for different scenarios is generated, as shown in Table 7 below: Table 7

[0117] Step S55: Analyze the real-time state of the photothermal conditions using the calibrated parameter set to determine whether the target range constraints are met. After the parameter adjustment command is issued, the actual changes in the photothermal conditions need to be monitored in real time to verify the effectiveness of the calibrated parameter set.

[0118] Specifically, the system collects adjusted light intensity and ambient temperature data using a sensor array and analyzes whether these data fall within the target range. For example, it checks whether the light intensity is stable between 40,000 and 60,000 lux and whether the ambient temperature is maintained between 20 and 25 degrees Celsius. If the real-time conditions meet the target range constraints, the parameter set is confirmed to be valid; if deviations still exist, the deviation values ​​are recorded and fed back to the adjustment process to regenerate optimized parameters. In this way, it is ensured that the real-time light and heat conditions continuously meet the growth requirements of wheat seedlings.

[0119] In one possible implementation, deviation analysis was performed on seedling data from a wheat-growing area. The analysis revealed that the current light intensity was as high as 85,000 lux, with the photosynthetic rate dropping to below 60% of normal, and the adaptation curve data showing a clear trend of photoinhibition. By triggering a light intensity parameter adjustment process, the initial plan was to reduce the light intensity to 60,000 lux, and through iterative calculations, it was ultimately determined to be 55,000 lux. After adjustment, the photosynthetic rate recovered to over 85% of normal, and the leaf temperature dropped to a suitable range, indicating that the parameter adjustment was effective. This process helps to quickly alleviate photoinhibition and ensure the healthy growth of seedlings.

[0120] In another embodiment, parameter adjustments were made to wheat seedlings grown in different environments. It was found that in greenhouse cultivation areas, due to the higher controllability of light intensity, the adjusted light intensity value quickly reached the target range. However, in open-field cultivation areas, the adjustment effect was delayed due to weather changes. Comparative analysis shows the impact of the planting environment on the effectiveness of parameter adjustments. Therefore, differentiated adjustment strategies should be developed based on environmental characteristics in subsequent control measures to improve overall management efficiency.

[0121] Step S6: Verify the optimized parameter set through a feedback loop mechanism to determine the final fine-grained management parameter set.

[0122] This step aims to verify, through actual environmental control and data feedback, whether the optimized parameter set can continuously meet the growth needs of wheat seedlings, and ultimately generate a refined management parameter set to provide a basis for long-term environmental management. The feedback loop mechanism is an important means of achieving dynamic control, ensuring the applicability and stability of the parameter set through real-time monitoring and adjustment. The specific execution process of this step is as follows: Step S61: Based on the optimized parameter set and combined with temperature data, generate environmental control commands and send them to environmental equipment to collect real-time blade temperature change data.

[0123] In practice, the optimized parameter set is first translated into specific environmental control commands, such as instructing cooling equipment to adjust the ambient temperature to 23 degrees Celsius, or instructing shading equipment to maintain light intensity at 55,000 lux. These commands are then sent to the corresponding environmental devices, such as the greenhouse's air conditioning system and shading net control system, to ensure that environmental conditions are adjusted according to the commands. Simultaneously, a sensor array collects real-time data on leaf temperature changes in wheat seedlings, recording the temperature value every 5 minutes after adjustment to observe the actual impact of parameter adjustments on the seedlings' physiological state. This approach forms a closed-loop process from parameter adjustment to data acquisition, providing data support for subsequent feedback analysis.

[0124] Step S62 involves continuously monitoring leaf temperature changes using a feedback loop mechanism. After the parameter adjustment command is executed, the leaf temperature changes of wheat seedlings need to be continuously monitored to verify whether the adjustment effect meets expectations.

[0125] Specifically, a feedback loop mechanism is employed, analyzing leaf temperature data every 30 minutes to observe whether it remains stable within a suitable range, such as 20 to 30 degrees Celsius. Furthermore, the trend of leaf temperature changes is analyzed, such as whether it shows a continuous upward or downward trend, to determine whether environmental adjustments have a positive impact on the seedling's physiological state. If an anomaly is detected during monitoring, such as a sudden increase in leaf temperature, the abnormal data is recorded and subsequent adjustment procedures are triggered. Continuous monitoring ensures the real-time nature and effectiveness of environmental control.

[0126] Step S63: If the temperature change exceeds a preset threshold range, an adjustment signal is triggered, a new temperature adjustment value is calculated, and based on the new temperature adjustment value, the updated ambient temperature is obtained, generating an update control command. The temperature adjustment value is calculated using a proportional-integral (PI) control algorithm, as shown in the following formula:

[0127] in, This is the temperature adjustment value. The scaling factor (in this embodiment) ), The integral coefficient (in this embodiment) ), for Temperature deviation at any time , The target temperature value for the blade (in this embodiment) ℃), for The actual blade temperature at that moment. From time 1 to Sum of time deviations.

[0128] The updated formula for calculating ambient temperature is: ,in, For the updated ambient temperature, This represents the current ambient temperature.

[0129] This step ensures the stability of the wheat seedlings' growth environment by setting a preset threshold range for leaf temperature changes, for example, allowing fluctuations of ±2 degrees Celsius. If the leaf temperature change exceeds this range during monitoring, such as a temperature rise of more than 2 degrees Celsius within 30 consecutive minutes, an adjustment signal is triggered, indicating that the current parameter set may not be fully applicable. Next, based on the magnitude and trend of the leaf temperature change, a new temperature adjustment value is calculated. For example, if the temperature is too high, a 1-degree Celsius reduction in ambient temperature is planned, and a corresponding update control command is generated, such as instructing the cooling equipment to increase its cooling capacity. In this way, it is ensured that environmental conditions can respond promptly to changes in the physiological needs of the seedlings.

[0130] Step S64: According to the update control command, synchronously monitor the leaf temperature changes and obtain the adjusted temperature data. After the update control command is issued, it is necessary to synchronously monitor the leaf temperature changes of wheat seedlings to verify the adjustment effect.

[0131] Specifically, a sensor array collects blade temperature data every 5 minutes, recording temperature changes over a continuous 2-hour period after adjustment. Next, the system analyzes whether the adjusted temperature data has stabilized, for example, whether it has returned to the target value within a suitable range. Furthermore, the amplitude of temperature fluctuations is observed; for example, whether the temperature fluctuation after adjustment is less than 0.5 degrees Celsius, to determine the effectiveness of the updated control commands. This synchronous monitoring obtains the adjusted temperature data, providing a basis for subsequent parameter confirmation.

[0132] Step S65: If the adjusted temperature data tends to stabilize, the final set of temperature adjustment parameters is determined. Based on continuous monitoring, if the adjusted temperature data remains stable for two consecutive hours, for example, leaf temperature fluctuations are less than 0.5 degrees Celsius, and the average value remains between 22 and 25 degrees Celsius, then the current parameter adjustment is confirmed to be effective. Next, the adjusted light intensity and temperature values ​​are integrated into the final set of temperature adjustment parameters, for example, the final light intensity is determined to be 55,000 lux and the ambient temperature to be 23 degrees Celsius. This parameter set, as part of the fine-grained management parameter group, is used to guide subsequent long-term environmental regulation. In this way, it is ensured that the parameter set can continuously meet the growth needs of wheat seedlings.

[0133] In one possible implementation, feedback loop monitoring was performed on seedling data in a wheat-growing area. It was found that leaf temperature continued to rise after initial adjustments, exceeding a preset threshold. An adjustment signal was triggered, a new temperature adjustment value was calculated, and the ambient temperature was reduced from 25 degrees Celsius to 23 degrees Celsius, generating an updated control command. After adjustment, leaf temperature dropped to 24 degrees Celsius within one hour and remained stable in subsequent monitoring, indicating that the parameter adjustment was effective. The final set of temperature adjustment parameters was determined to be an ambient temperature of 23 degrees Celsius and a light intensity of 55,000 lux, providing a reliable basis for subsequent management.

[0134] In another embodiment, parameter verification was conducted on wheat seedlings at different growth stages. It was found that seedlings in the tillering stage were more sensitive to temperature changes and required more frequent triggering of adjustment signals, while seedlings in the jointing stage showed stronger adaptability and lower adjustment frequency. Comparative analysis reveals the impact of growth stage on parameter adjustment requirements, necessitating the development of differentiated strategies based on stage characteristics in subsequent management to improve efficiency.

[0135] Step S7: Generate a continuous monitoring instruction sequence based on the fine management parameter group to dynamically optimize environmental control.

[0136] This step is the final stage of the entire method, aiming to construct a sequence of instructions for continuous monitoring and dynamic adjustment based on the aforementioned fine-grained management parameter set, ensuring the long-term stability of the wheat seedling growth environment. Dynamic optimization of environmental control requires comprehensive consideration of the seedling growth needs and the real-time nature of environmental changes, achieving automated management through the instruction sequence. The specific execution process of this step is as follows: Step S71: Based on the fine management parameter group, construct the environmental control basic data group and generate the initial management instruction sequence.

[0137] In practice, the light intensity and temperature values ​​from the refined management parameter set are first used as basic data, such as a light intensity of 55,000 lux and an ambient temperature of 23 degrees Celsius, to construct a basic data set for environmental control. Next, based on this basic data, an initial sequence of management instructions is generated. For example, instructions are given to shading devices to adjust their coverage area to 40% daily from 10:00 AM to 2:00 PM, and instructions are given to cooling devices to activate their cooling function when the ambient temperature exceeds 24 degrees Celsius. These instruction sequences cover the environmental control needs at different times of the day, ensuring that the light and heat conditions continuously meet the growth requirements of wheat seedlings.

[0138] Step S72: Analyze the real-time environmental regulation requirements based on the wheat seedling growth stages, and obtain data on the changes in environmental variables at different stages. Specifically, wheat seedlings have different requirements for light and heat conditions at different growth stages; for example, they are more sensitive to temperature during the tillering stage and require more light during the jointing stage.

[0139] In this step, the real-time environmental control needs of the seedlings are analyzed based on their current growth stage. For example, temperature fluctuations need to be closely monitored during the tillering stage, while stable light intensity needs to be ensured during the jointing stage. Next, data on changes in environmental variables at different stages are collected using a sensor array, such as the daily range of light intensity changes and the amplitude of ambient temperature fluctuations. This data reflects whether environmental conditions meet the needs of the current growth stage, providing a basis for subsequent adjustments.

[0140] Step S73: Based on the periodic environmental variable change data, generate real-time monitoring instructions and transmit them to the environmental control equipment. This step, after obtaining the periodic environmental variable change data, requires generating real-time monitoring instructions to guide the operation of the environmental control equipment.

[0141] Specifically, based on environmental variable change data, the monitoring frequency and key monitoring parameters are determined. The monitoring frequency is dynamically adjusted according to the rate of change of environmental variables, and an environmental change rate coefficient is introduced. The monitoring interval is determined using a piecewise function. (Unit: minutes), the formula is as follows:

[0142] Among them, the environmental change rate coefficient The calculation formula is: , For a unit of time ( Change in light intensity (lx) within minutes. It represents the change in ambient temperature (°C) per unit time. The value range is [0,1]. The larger the value, the more drastic the environmental change, and the more frequent the monitoring needs to be.

[0143] For example, during periods of high temperature and high light intensity, the monitoring frequency of light intensity and temperature is increased, with data collected every 10 minutes. These real-time monitoring commands are then transmitted to environmental control equipment, such as the sensor and control systems within the greenhouse, ensuring that the equipment can collect and report environmental data in real time according to the commands. In this way, dynamic monitoring of environmental conditions is achieved, providing real-time data support for subsequent adjustments.

[0144] Step S74 involves analyzing the environmental adaptation of wheat seedlings through real-time monitoring commands to determine the deviation range. The deviation range is calculated using both absolute and relative deviation indicators, while also incorporating a deviation duration coefficient. A comprehensive assessment of environmental adaptation is performed using the following formula: Absolute deviation (the direct difference between photothermal parameters and the target value):

[0145] Relative deviation (reflecting the proportion of deviation to the target value, and is more meaningful for reference):

[0146] Deviation duration coefficient (characterizing the degree of influence of the deviation):

[0147] in, , Real-time light intensity (lx) and ambient temperature (°C); , To refine the target values ​​for light and temperature in the parameter group; The duration of the deviation (in minutes); The allowable duration threshold for deviation (in this embodiment) minute); This indicates that the duration of the deviation exceeds the allowable range and requires close monitoring.

[0148] Specifically, real-time light intensity and temperature data are compared with target values ​​in the fine-grained management parameter set. For example, is the light intensity maintained at around 55,000 lux, and is the ambient temperature stable at around 23 degrees Celsius? If deviations exist, the range of deviation is calculated, for example, a deviation of 5,000 lux in light intensity and 1.5 degrees Celsius in temperature. Furthermore, the duration and impact of the deviations are analyzed, such as whether the deviations lead to abnormal increases in leaf temperature, to determine if further adjustments are needed. Through this analysis, a comprehensive understanding of the environmental adaptation of wheat seedlings is obtained.

[0149] Step S75: If the deviation range exceeds the preset threshold, an adjustment signal is generated, the instruction sequence is updated, the details of the dynamic adjustment operation are recorded, and a structured control log is generated.

[0150] To ensure the stability of environmental conditions, this step first sets preset thresholds for photothermal parameters and allowable thresholds for light intensity deviation. lx, temperature deviation allowable threshold ℃; when or At that time, an adjustment signal is generated, and the adjustment parameter is calculated using the following formula: Shade net coverage area adjustment (%) (when light intensity is high): ; Power adjustment of supplemental lighting equipment (W) (When light intensity is low): ; Temperature control equipment power adjustment amount (W) (when there is a temperature deviation): ; in, W (maximum power of the supplemental lighting equipment) W (maximum power of the temperature control device), adjust the value to an integer to ensure stable operation of the device.

[0151] If the deviation range in the real-time monitoring data exceeds the threshold, an adjustment signal is generated, triggering the update process of the instruction sequence.

[0152] Specifically, new adjustment parameters are calculated based on the deviation value. For example, if the light intensity is 5000 lux higher, the shading equipment is instructed to increase its coverage area by 10%. Next, the initial management command sequence is updated, incorporating the new adjustment parameters to ensure the environmental control equipment operates according to the updated instructions. Furthermore, details of the dynamic adjustment operations are recorded, such as adjustment time, adjustment parameter values, and environmental data before and after the adjustment, forming a structured control log for subsequent analysis and optimization.

[0153] In one possible implementation, dynamic optimization is performed on seedling data for a specific wheat-growing area to identify temperature deviations in seedlings during the tillering stage during high-temperature periods. ℃, exceeding the preset threshold ℃. Calculated according to the temperature adjustment parameter formula: W generates an adjustment signal, updates the command sequence, and instructs the cooling equipment to increase its cooling power by 435W, lowering the ambient temperature to 23℃. After adjustment, the temperature deviation... The temperature was reduced to within 0.5 degrees Celsius, and the seedling leaf temperature returned to a suitable range. Recorded control logs show that the adjustment effectively mitigated the effects of heat stress during the high-temperature period, providing valuable experience for subsequent management.

[0154] In another embodiment, dynamic optimization was performed on wheat-growing areas in different geographical locations. It was found that in high-altitude areas, due to large diurnal temperature variations, environmental temperature deviations frequently exceeded preset thresholds, requiring multiple updates to the instruction sequence and increased insulation measures. In contrast, in low-altitude areas, due to prolonged periods of high temperatures, the focus was on adjusting light intensity. Comparative analysis reveals the impact of geographical location on environmental control needs, necessitating the development of differentiated instruction sequences tailored to regional characteristics in subsequent management to improve control effectiveness.

[0155] It should be noted that the above dynamic optimization process, through continuous monitoring and command updates, enables real-time management of the wheat seedling growth environment. Combining growth stage and environmental variable change data ensures the targeted nature and effectiveness of control commands, providing long-term protection for the healthy growth of seedlings.

[0156] In one embodiment, an analysis of the environmental adaptability of wheat seedlings under different planting densities revealed that high-density planting areas, due to poor ventilation, were more prone to temperature deviations exceeding preset thresholds, requiring more frequent updates to the instruction sequence and increased cooling measures. Low-density planting areas, on the other hand, exhibited better environmental adaptability, with lower instruction update frequencies. By generating control logs for different planting densities, planting layout can be optimized in subsequent management, reducing the probability of environmental deviations.

[0157] For example, in a wheat planting experimental field, the ambient temperature deviation in high-density planting areas during the high-temperature period in summer was observed. The temperature exceeds the preset threshold. The adjustment amount is calculated based on the formula: W, simultaneously calculate the adjustment amount of the shade net coverage area. The system updated its instruction sequence, increased the operating time of cooling equipment, and adjusted the coverage area of ​​the shade net, reducing the temperature deviation to within 0.8 degrees Celsius. The control log showed that the adjustments effectively reduced the risk of heat stress, and the seedling photosynthetic rate recovered to over 85% of normal levels. This case demonstrates that dynamic optimization combined with planting density can significantly improve the accuracy of environmental control.

[0158] In another possible approach, an analysis of wheat seedlings' environmental adaptation under different soil moisture conditions revealed that seedlings were highly sensitive to temperature deviations when soil moisture was low, with even small deviations causing a rapid increase in leaf temperature. By updating the instruction sequence, adjusting soil moisture in conjunction with irrigation measures, and simultaneously lowering the ambient temperature, the impact of these deviations could be effectively mitigated. The study showed a negative correlation between soil moisture and wheat seedling temperature sensitivity; a 10% decrease in soil moisture increased temperature deviation sensitivity by more than 25%. Control logs showed that after soil moisture returned to an appropriate level, the temperature deviation decreased to within the preset threshold, and the physiological state of the seedlings significantly improved. These analytical results help to comprehensively consider soil conditions and formulate more comprehensive control strategies in subsequent management.

[0159] It should be noted that the above steps, through multi-dimensional data analysis and dynamic adjustments, comprehensively optimize the management of the wheat seedling growth environment. Continuous monitoring of the generation and updating of instruction sequences ensures the real-time nature and adaptability of environmental control, providing strong support for the healthy growth of seedlings under different growth stages and environmental conditions.

[0160] In one embodiment, the environmental regulation needs of wheat seedlings under different light shading conditions were analyzed. It was found that some areas experienced significant deviations in light intensity due to shading from surrounding crops, requiring frequent updates to the instruction sequence and the addition of artificial lighting. By recording the adjustment details in the regulation log, it was shown that the supplemental lighting measures effectively increased light intensity, and the seedling photosynthetic rate returned to normal levels. This result indicates that dynamic optimization combined with light shading conditions can significantly improve environmental adaptation and provides an important reference for subsequent management.

[0161] For example, in a wheat planting base, some seedling areas experienced inadequate sunlight intensity due to shading from surrounding tall crops. lx exceeds the preset threshold. Calculated according to the supplementary light power adjustment formula: The command sequence was updated to increase the operating time of the supplemental lighting equipment and raise the light intensity to 50,000 lux. After the adjustment, the photosynthetic rate recovered from the normal level of 60% to over 85%. The control log showed that the supplemental lighting measures effectively alleviated the low-temperature suppression response during periods of insufficient light. This case fully demonstrates the important role of dynamic optimization in solving illumination deviation problems.

[0162] In another embodiment, the environmental control effects on wheat seedlings under different weather conditions were analyzed. It was found that light intensity deviations were significant under cloudy and rainy weather, requiring adjustments through supplemental lighting. Conversely, under sunny and hot weather, temperature deviations needed to be closely monitored, necessitating additional cooling measures. By generating instruction sequences and control logs for different weather conditions, pre-adjustment strategies can be developed in conjunction with weather forecasts during subsequent management, mitigating the impact of environmental deviations in advance. This analysis helps improve the predictability and proactivity of environmental control.

[0163] The above description is only a preferred embodiment of the present invention. It should be noted that those skilled in the art can make several modifications and improvements without departing from the inventive concept of the present invention, and these all fall within the protection scope of the present invention.

Claims

1. A method for precise control of light and heat in wheat seedling cultivation, characterized in that, The method includes: The light intensity and temperature data in the photothermal environment are collected by a sensor array, and the leaf temperature changes and photosynthetic rate indicators of wheat seedlings are recorded simultaneously to obtain the initial response dataset. Based on the initial response dataset, the correlation between photothermal environment and physiological signals was analyzed, a mapping model was constructed, and the response characteristics of wheat seedlings under different environments were determined. The response features are processed using a classification algorithm to generate health status categories and abnormal pattern classification results. Real-time features are extracted from the classification results to predict dynamic adaptation trends and generate adaptation curve data. Based on the adaptation curve data, determine the deviation status of photothermal conditions, adjust the light intensity and temperature parameters, and obtain the optimized parameter set; The optimized parameter set is verified through a feedback loop mechanism to determine the final fine management parameter set. Based on the fine management parameter set, a continuous monitoring instruction sequence is generated to dynamically optimize environmental control.

2. The method for precise control of light and heat in wheat seedling cultivation according to claim 1, characterized in that, The process involves collecting light intensity and temperature data from a photothermal environment using a sensor array, simultaneously recording changes in leaf temperature and photosynthetic rate indices of wheat seedlings, and obtaining an initial response dataset, including: The sensor array acquires light intensity and ambient temperature data in real time, and records the dynamic changes in wheat seedling leaf temperature and the index value of photosynthetic rate to form a preliminary physiological signal dataset. For the preliminary physiological signal dataset, time series analysis is used to determine the dynamic pattern of leaf temperature change. If the leaf temperature change in the dynamic pattern exceeds the preset threshold range, outliers are removed by data filtering technology to generate a corrected temperature change dataset. Based on the corrected temperature change dataset and the photosynthetic rate index, the correlation between the two is analyzed to determine the degree of influence of the photothermal environment on photosynthetic efficiency.

3. The method for precise control of light and heat in wheat seedling cultivation according to claim 1, characterized in that, The process involves analyzing the correlation between photothermal environment and physiological signals based on the initial response dataset, constructing a mapping model, and determining the response characteristics of wheat seedlings under different environments, including: Based on the initial response dataset, fluctuation data of light intensity and ambient temperature were extracted. Combined with leaf temperature changes and photosynthetic rate indicators, the influence pattern of photothermal conditions on physiological signals was analyzed. Based on the influence pattern, a mapping model between photothermal environment and physiological signals was constructed for different combinations of light intensity and temperature. Based on the mapping model, response characteristic data of wheat seedlings under various environmental conditions are obtained. Through the response characteristic data, the adaptability of wheat seedlings to light and heat conditions is analyzed, and an environmental response characteristic set is generated.

4. The method for precise control of light and heat in wheat seedling cultivation according to claim 1, characterized in that, The process of using a classification algorithm to process the response features and generate health status categories and abnormal pattern classification results includes: Based on the response characteristics, the physiological signals of wheat seedlings are classified using the support vector machine algorithm to determine the health status categories under different light and heat conditions. If the amount of data in a certain health status category is lower than the preset proportion, the sample is expanded through data augmentation technology to generate a balanced classification dataset. For balanced classification datasets, the random forest algorithm is used to extract abnormal pattern features and classify the abnormal types of physiological signals. If the photosynthetic rate index is lower than a preset threshold, it is determined to be a photoinhibition response, and a specific response type label is generated.

5. The method for precise control of light and heat in wheat seedling cultivation according to claim 1, characterized in that, The process of extracting real-time features from classification results, predicting dynamic adaptation trends, and generating adaptation curve data includes: The light suppression response data were filtered from the classification results, real-time perception-related features were extracted, and the real-time perception-related features were standardized to generate a normalized feature set. For the normalized feature set, the support vector machine algorithm is applied to predict the dynamic adaptation trend and generate the adaptation trend prediction result. Based on the adaptive trend prediction results, key node data are extracted and an adaptive trend curve representation is constructed. If there are missing data in the adaptive trend curve representation, the missing parts are supplemented by interpolation to generate complete adaptive curve data.

6. The method for precise control of light and heat in wheat seedling cultivation according to claim 1, characterized in that, The process of determining the deviation state of photothermal conditions based on adaptation curve data, adjusting light intensity and temperature parameters, and obtaining an optimized parameter set includes: Based on the adaptation curve data, analyze the current deviation status of the photothermal conditions. If the deviation status exceeds the preset threshold, trigger the light intensity parameter adjustment process and generate a preliminary adjustment plan. For the initial adjustment plan, the optimized light intensity value is determined through iterative calculation. Based on the optimized light intensity value, parameter adjustment instructions are generated. Combined with target interval calibration, a calibrated parameter set is generated. By analyzing the real-time state of photothermal conditions using the calibrated parameter set, it can be determined whether the target interval constraints are met.

7. The method for precise control of light and heat in wheat seedling cultivation according to claim 1, characterized in that, The optimized parameter set is validated through a feedback loop mechanism to determine the final fine-grained management parameter set, including: Based on the optimized parameter set, combined with temperature data, environmental control commands are generated and sent to environmental equipment to collect real-time blade temperature change data. By continuously monitoring the blade temperature change data using a feedback loop mechanism, if the temperature change exceeds the preset threshold range, an adjustment signal is triggered, a new temperature adjustment value is calculated, and an update control command is generated. According to the updated control command, the blade temperature change is monitored synchronously to obtain the adjusted temperature data. If the adjusted temperature data tends to be stable, the final set of temperature adjustment parameters is determined.

8. The method for precise control of light and heat in wheat seedling cultivation according to claim 1, characterized in that, The step of generating a continuous monitoring instruction sequence based on a set of refined management parameters and dynamically optimizing environmental control includes: Based on the refined management parameter set, an environmental control basic data set is constructed, an initial management instruction sequence is generated, and combined with the wheat seedling growth stage, the real-time demand for environmental control is analyzed to obtain data on the changes in environmental variables in stages. Based on the phased changes in environmental variables, real-time monitoring instructions are generated and transmitted to environmental control equipment. Through these instructions, the environmental adaptation of wheat seedlings is analyzed, and the deviation range is determined. If the deviation range exceeds a preset threshold, an adjustment signal is generated, the instruction sequence is updated, the details of the dynamic adjustment operation are recorded, and a structured control log is generated.

Images