Organic carbon source data optimization method and system based on crop growth feedback

Abstract

The invention provides an organic carbon source data optimization method and system based on crop growth feedback, and the method comprises the steps: carrying out the data collection and data preprocessing of crops, obtaining a crop growth data set and a crop environment data set, and obtaining a crop growth index and an environment pressure index based on the crop growth data set and the crop environment data set respectively; mining a causal association chain between the crop growth index and the environmental stress index, constructing a growth environment association rule base according to the causal association chain, and constructing an organic carbon source regulation and control model based on the crop growth index, the environmental stress index and the growth environment association rule base, and generating an organic carbon source regulation decision according to the organic carbon source regulation model, obtaining an implementation effect of the organic carbon source regulation decision, and performing iterative optimization on the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect of the organic carbon source regulation decision, thereby improving the accuracy of the organic carbon source regulation scheme.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to an organic carbon source data optimization method and system based on crop growth feedback. Background Art

[0002] In current agricultural production, the application of organic carbon sources mainly relies on empirical formulas, fixed-cycle management or static models based on basic soil nutrients for decision-making. Due to the lack of a direct response mechanism to crop growth, traditional methods often find it difficult to establish a dynamic relationship between organic carbon source input and plant growth efficiency, resulting in mismatch of farmland resources and increased environmental risks.

[0003] On the one hand, the optimization decisions for regulating organic carbon sources in traditional methods often rely on static indicators such as soil organic carbon and pH, and ignore the real-time monitoring of key parameters of crop growth, making it difficult to reflect the actual impact of carbon source input on the physiological processes of crop growth, thereby causing the problem of mismatch of farmland resources; on the other hand, traditional methods mostly use fixed thresholds or linear rules to analyze the relationship between crops and carbon sources, and have certain limitations in analyzing the complex nonlinear coupling relationship between the environment, crops and carbon sources. When faced with variety differences, soil heterogeneity and climate fluctuations, the accuracy of the organic carbon source regulation plan is difficult to guarantee. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides an organic carbon source data optimization method and system based on crop growth feedback to solve the technical problems in the existing technology that the actual impact of carbon source input on the physiological process of crop growth is difficult to reflect and the accuracy of the organic carbon source control plan is difficult to ensure when facing variety differences, soil heterogeneity and climate fluctuation scenarios.

[0005] The purpose and efficacy of the organic carbon source data optimization method and system based on crop growth feedback of the present invention are achieved by the following specific technical means: Organic carbon source data optimization method based on crop growth feedback, including: S1: Collect and preprocess crop data to obtain crop growth data sets and crop environment data sets; S2: Based on the crop growth data set and the crop environment data set, crop growth indicators and environmental pressure indicators are obtained respectively; S3: mining the causal association chain between crop growth indicators and environmental pressure indicators, and building a growth environment association rule base based on the causal association chain; S4: Construct an organic carbon source regulation model based on crop growth indicators, environmental pressure indicators and growth environment association rule base, and generate organic carbon source regulation decisions based on the organic carbon source regulation model; S5: Obtain the implementation effect of the organic carbon source regulation decision, and iteratively optimize the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect of the organic carbon source regulation decision.

[0006] As a further solution of the present invention, the crop growth index and the environmental pressure index are obtained based on the crop growth data set and the crop environment data set, respectively, including: Perform feature extraction on the crop growth dataset to obtain stem image data, root projection area data, soil moisture data, canopy LAI, leaf chlorophyll content data, and leaf texture density data; By analyzing the displacement changes of three consecutive frames of stem image data at a fixed time interval, the internal strain energy distribution of the stem tissue is obtained, and the vascular strain energy density is generated based on the internal strain energy distribution of the tissue; By analyzing the time series acceleration of root projection area data and combining it with the fluctuation characteristics of soil moisture data, the root anchorage attenuation rate is generated. By analyzing the root projected area data and canopy LAI, the transmission efficiency of crop root and canopy growth signals is obtained, and the root-canopy response entropy is generated based on the transmission efficiency. The photosynthetic phase space is constructed based on the leaf chlorophyll content data and the leaf texture density data. The compression degree of the photosynthetic phase space is generated by analyzing the movement trajectory of the leaf chlorophyll content data and the leaf texture density data in the photosynthetic phase space. A crop structural index is constructed based on vascular strain energy density and root anchorage attenuation rate, and a functional synergy index is constructed based on root-cap response entropy and photosynthetic phase spatial compression. The crop growth index includes a crop structural index and a functional synergy index. Feature extraction is performed on the crop environmental dataset to obtain environmental characteristic data, and environmental pressure indicators are constructed based on the environmental characteristic data.

[0007] As a further solution of the present invention, feature extraction is performed on the crop environmental data set to obtain environmental feature data, and an environmental pressure index is constructed based on the environmental feature data, including: Environmental characteristic data include photosynthetically active radiation data, canopy spectrum data, air temperature and humidity data, stem surface strain rate, soil redox potential data, and light intensity data; By analyzing the response relationship between photosynthetically active radiation data and canopy spectrum data, light-carbon disorder data is generated; By analyzing the response relationship between air temperature and humidity data and stem surface strain rate, water damage coupling data is generated; By analyzing soil redox potential data, light intensity data and corresponding spatial position coordinates, marginal load data is generated; By analyzing soil redox potential data over a continuous period of time, environmental disturbance memory data are generated; A metabolic abnormality environment coupling index is constructed based on the photo-carbon disorder data and the water damage coupling data, and a spatial heterogeneity index is constructed based on the marginal load data and the environmental disturbance memory data. The environmental pressure index includes the metabolic abnormality environment coupling index and the spatial heterogeneity index.

[0008] As a further solution of the present invention, the causal association chain between crop growth indicators and environmental pressure indicators is mined, and a growth environment association rule base is constructed based on the causal association chain, including: Obtaining causal entropy between crop growth indicators and environmental pressure indicators within a preset time window length, and quantifying the temporal coupling relationship between the crop growth indicators and environmental pressure indicators corresponding to different crop growth stages based on the causal entropy; Calculate the hierarchical transition causal gain value from the organ level to the system level, and filter the macro-hysteresis interference based on the hierarchical transition causal gain value; The organ level represents the structural and functional performance of each organ of the crop, the system level represents the comprehensive growth status of the crop, and the macro-hysteresis interference represents the delayed phenomenon of organs and systems responding to environmental changes. While keeping the environmental pressure indicators unchanged, the crop varieties are virtually switched and the change difference rate of the crop growth indicators is observed. The universality of the temporal coupling relationship is tested based on the change difference rate. If the change difference rate reaches the preset difference rate threshold range, it is determined that the temporal coupling relationship has variety universality. Generate adversarial networks to synthesize virtual data with different soil conditions on the same plot, and separate the interference of soil properties on temporal coupling relationships. Based on the temporal coupling relationship, a causal association chain between crop growth indicators and environmental pressure indicators is generated, and a growth environment association rule base is constructed based on the causal association chain.

[0009] As a further solution of the present invention, a growth environment association rule base is constructed based on the causal association chain, including: Rules are extracted from the causal association chain to obtain three types of growth environment association rules: atomic rules, combination rules, and spatiotemporal constraint rules. The support, confidence, and lift corresponding to the growth environment association rules are obtained, and the growth environment association rules that do not meet the preset support threshold, confidence threshold, and lift threshold are eliminated to build a growth environment association rule library.

[0010] As a further solution of the present invention, an organic carbon source regulation model is constructed based on a crop growth index, an environmental pressure index, and a growth environment association rule library, and an organic carbon source regulation decision is generated according to the organic carbon source regulation model, including: The physiological status of crops can be diagnosed in real time according to crop growth indicators, and the environmental impacts on crops during growth can be quantified through environmental pressure indicators. The growth environment association rules corresponding to crop growth indicators and environmental pressure indicators in the growth environment association rule library can be matched and called. Based on the matched growth environment association rules, organic carbon source regulation decisions can be generated to regulate the organic carbon source of crops.

[0011] As a further solution of the present invention, obtaining the implementation effect of the organic carbon source regulation decision, and iteratively optimizing the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect of the organic carbon source regulation decision, including: The organic carbon source regulation decision that fails to improve the growth index of the target crop within the predetermined time is judged as a failed decision. At the same time, the growth environment association rule corresponding to the failed decision is marked as a gradually invalid rule, and the confidence of the gradually invalid rule is reduced. The growth environment association rules that have been marked as gradually invalid rules for three consecutive times are determined to be invalid rules, and the invalid rules are frozen; The organic carbon source regulation decision that improves the growth indicators of target crops within the predetermined time is judged as a successful decision. At the same time, the growth environment association rule corresponding to the successful decision is marked as a valid rule, and the confidence of the valid rule is improved.

[0012] As a further solution of the present invention, data collection and data preprocessing are performed on crops to obtain crop growth data sets and crop environment data sets, including: Performing data preprocessing on the collected crop data, including at least outlier filtering, time-space alignment, data standardization, and data normalization, to obtain crop growth data sets and crop environment data sets; The crop growth data set is used to describe the multi-dimensional dynamic growth characteristics of crops, and at least includes crop canopy dimension data, stem dimension data, underground root dimension data, and physiological dimension data; The crop environment dataset is used to describe the growing environment of crops and at least includes surface environment data, soil layer environment data, and microenvironment data.

[0013] As a further embodiment of the present invention, the collected crop data is subjected to data preprocessing including at least outlier filtering, time-space alignment, data standardization and data normalization, including: The outlier filtering is performed on the crop data to filter outliers and fill in missing values; The time-space alignment is to unify the crop data into the same geographic coordinate reference and time reference; The data standardization is performed on the crop growth data included in the crop data; The data normalization is performed on the crop environment data included in the crop data.

[0014] Organic carbon source data optimization system based on crop growth feedback, including: A data processing module, which is used to collect data on crops, perform data preprocessing on the collected data, and generate a crop growth data set and a crop environment data set; An indicator generation module, the indicator generation module is used to generate corresponding crop growth indicators and environmental pressure indicators according to the crop growth data set and the crop environment data set; A rule extraction module, which is used to extract the causal relationship chain between crop growth indicators and environmental pressure indicators, and generate corresponding rules based on the causal relationship chain; A model building module, wherein the model building module is used to build an organic carbon source regulation model based on crop growth indicators, environmental pressure indicators and a growth environment association rule library, and generate an organic carbon source regulation decision; The feedback optimization module is used to obtain the implementation effect of the organic carbon source regulation decision and optimize and adjust the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect.

[0015] Based on the above aspects, the embodiments of the present application implement data collection and data preprocessing for crops, obtain crop growth data sets and crop environment data sets, and eliminate interference noise and data offset generated during the collection process by preprocessing the collected data. At the same time, the preprocessed data provides accurate data input for the subsequent generation of quantitative indicators. Based on the crop growth data set and the crop environment data set, crop growth indicators and environmental pressure indicators are respectively obtained, the causal association chain between the crop growth indicators and the environmental pressure indicators is mined, and a growth environment association rule library is constructed based on the causal association chain. By constructing the crop growth indicators and the environmental pressure indicators, the discrete environmental data and crop physiological data are accurately quantified, which provides comprehensive and accurate data input for the subsequent model to generate organic carbon source regulation decisions. By mining the causal association chain between the indicators, the causal coupling relationship between the environmental data and the crop physiological data is analyzed, and the corresponding quantitative rules are obtained, which provides a reference benchmark for the subsequent model to generate organic carbon source regulation decisions; An organic carbon source regulation model is constructed based on the crop growth indicators, environmental pressure indicators and growth environment association rule library, and organic carbon source regulation decisions are generated according to the organic carbon source regulation model to obtain the implementation effect of the organic carbon source regulation decision. The organic carbon source regulation rule library and the organic carbon source regulation model are iteratively optimized according to the implementation effect of the organic carbon source regulation decision. By monitoring the implementation effect of the organic carbon source regulation decision, the confidence of the efficient rules in the organic carbon source regulation rule library is strengthened, and the confidence of the inefficient rules is weakened, thereby improving the accuracy of the organic carbon source regulation plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 1 is a schematic diagram of the execution flow of the organic carbon source data optimization method based on crop growth feedback provided by an embodiment of the present invention; Figure 2 1 is a schematic diagram of the execution flow of step S2 in the organic carbon source data optimization method based on crop growth feedback provided in an embodiment of the present invention; Figure 3 3 is a schematic diagram of the execution flow of step S3 in the organic carbon source data optimization method based on crop growth feedback provided in an embodiment of the present invention; Figure 4 Schematic diagram of grid division of a marginal two-dimensional plane coordinate system provided by an embodiment of the present invention; Figure 5 Schematic diagram of an organic carbon source data optimization system based on crop growth feedback provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the technical solutions of the present invention, but are not intended to limit the scope of protection of the present invention.

[0018] Example 1:

[0019] As attached Figure 1 、 Figure 2 、 Figure 3 、 Figure 4 、 Figure 5 As shown: The embodiment of the present invention provides an organic carbon source data optimization method based on crop growth feedback, which is applicable to the field of agricultural technology and includes the following steps: Step S1: Data collection and data preprocessing of crops are performed to obtain a crop growth data set and a crop environment data set.

[0020] Specifically, the collected crop data are subjected to data preprocessing including at least outlier filtering, time-space alignment, data standardization and data normalization to obtain a crop growth data set and a crop environment data set.

[0021] It can be understood that the outlier filtering is represented by filtering outliers and filling missing values ​​in crop data; the spatiotemporal alignment is represented by unifying the crop data into the same geographic coordinate base and time base; the data standardization is represented by performing data standardization operations on the crop growth data contained in the crop data; and the data normalization is represented by performing data normalization operations on the crop environment data contained in the crop data.

[0022] It can be understood that the crop growth data set is used to describe the multi-dimensional dynamic growth characteristics of crops, and at least includes crop canopy dimension data, stem dimension data, underground root dimension data and physiological dimension data.

[0023] Specifically, crop canopy data is collected using drones equipped with multispectral cameras to obtain canopy LAI. Canopy LAI measures key parameters of vegetation canopy structure and is used to quantify ecological processes such as photosynthesis and respiration. The obtained canopy LAI is then topographically corrected. For example, 1-meter DEM data is input, and for areas with a terrain slope greater than 5 degrees, the canopy LAI is topographically compensated according to "original LAI*(1+0.018*terrain slope value)". The terrain slope value is obtained based on the terrain slope angle and the relative sun position. For example, if the terrain slope corresponding to the canopy LAI is 15 degrees and the canopy faces the sun at this time, the corresponding terrain slope value is +15. The canopy LAI corresponding to the effective time period is filtered, such as excluding data corresponding to solar altitude angles below 40 degrees. The spectral bands of the corresponding multispectral camera are transformed during the effective time period of rainy weather to ensure the accuracy of the collected canopy LAI. (This is just an example of terrain correction and effective time period screening; the actual situation needs to be determined according to the specific situation).

[0024] Furthermore, the chlorophyll content of crop leaves and the corresponding leaf temperature are collected, and the collected leaf chlorophyll content data are compensated for temperature drift, such as correcting the data according to "SPAD correction value = measured value + 0.28×(25-leaf temperature); the leaf chlorophyll content data are corrected and compensated according to the crop variety. For example, for indica rice in the tillering stage, the SPAD is increased by 5%, that is, the measured SPAD value is 42, and the SPAD value after compensation is 42*1.05=44.1 (this is just an example to illustrate temperature drift compensation and crop variety compensation, and the actual compensation needs to be determined according to the specific situation).

[0025] Furthermore, data is collected from the back of crop leaves to obtain leaf texture density data, and noise is eliminated from the collected leaf texture density data, such as using HSV color gamut segmentation and near-infrared absorption detection to remove data noise in the leaf diseased area; light intensity calibration and data normalization are performed according to the canopy irradiance map to obtain leaf texture stretch, such as correcting the leaf texture density data according to "leaf texture stretch = measured value of leaf texture density data * (1000 / actual light intensity)" (this is just an example to illustrate noise elimination and light intensity calibration, the actual situation needs to be determined).

[0026] In this embodiment, the pre-processed canopy LAI, leaf chlorophyll content data and leaf texture density data are temporally and spatially aligned to generate crop canopy dimensional data.

[0027] Specifically, monitoring points are marked on the stems of crops, and the stems of crops are photographed and monitored at fixed intervals to obtain stem image data. At the same time, the temperature corresponding to the stems of crops during the shooting time period is recorded. The phase correlation algorithm is used to measure the displacement of the marked monitoring points in the stem image data to obtain the stem displacement, and the obtained stem displacement is subjected to noise removal. The stem surface strain rate is obtained based on the stem displacement, and the preprocessed stem image data is aligned in time and space to generate stem dimensional data.

[0028] Furthermore, the original image of the root projection area and the soil moisture data at 20 cm and 40 cm underground are obtained, and the soil moisture content is obtained by performing feature fusion based on the soil moisture data at 20 cm and 40 cm underground and the characteristics of the crops. For example, cotton uses a weighted fusion structure of 0.3*soil moisture data at 20 cm underground + 0.7×soil moisture data at 40 cm underground to obtain the soil moisture content, and lettuce uses a weighted fusion structure of 0.8*soil moisture data at 20 cm underground + 0.2×soil moisture data at 40 cm underground to obtain the soil moisture content. The data update is frozen 2 hours after the crops are irrigated to shield the water infiltration disturbance. The characteristic areas corresponding to the new roots in the original image of the root projection area are screened based on the convolutional neural network, such as areas with a daily increase greater than 5%, an aspect ratio greater than 3, a milky white color, and reaching a preset RGB threshold, and combined with Geometric verification that the angle between the root tip extension direction and the gravity direction is less than 30 degrees eliminates interference from soil crack artifacts. The original root projection area image is visibility corrected based on soil moisture content to obtain root projection area data. For example, for clay plots with a clay content greater than 45%, visibility correction is performed by dividing the scanned area of ​​the original root projection area image by 0.89 multiplied by e raised to the power of -0.028 times the moisture content. For sandy plots with a sand content greater than 70%, visibility correction is performed by multiplying the scanned area by the inverse of the coefficient obtained by subtracting 1.8 from 0.016 times the moisture content. The preprocessed root projection area data are spatiotemporally aligned with the soil moisture data to generate underground root dimension data. (This is just an example of soil moisture content, new root area screening, and visibility correction of the original root projection area image; the actual correction needs to be determined according to specific circumstances.)

[0029] Furthermore, the canopy spectral data of the crops are obtained, the canopy spectral red edge of the canopy spectral data is analyzed, and the canopy spectral red edge displacement is obtained. For example, the canopy spectral red edge is located based on the first-order derivative peak in the [680, 750] nanometer range, and the canopy spectral red edge displacement is obtained by analyzing the difference in the canopy spectral red edge within a fixed time period; the pre-processed leaf chlorophyll content data and leaf texture density data are aligned with the canopy spectral red edge displacement in time and space, and the initial physiological dimension data of the crops is obtained based on the leaf texture density data, and the initial physiological dimension data is corrected and compensated according to the canopy spectral red edge displacement. At the same time, the initial physiological dimension data is corrected for a second time by the leaf chlorophyll content data to generate physiological dimension data, for example, by Obtaining physiological dimension data of crops, including It is physiological dimension data used to characterize the photosynthetic efficiency of crops. is the leaf texture density data, is the red edge displacement of the canopy spectrum. At the same time, it is set that when the leaf chlorophyll content is lower than 45, the maximum η value shall not exceed 0.6 (this is just an example of one possibility of physiological dimension data, and the actual content needs to be determined by specific circumstances).

[0030] It can be understood that the crop environment dataset is used to describe the growth environment of crops, and at least includes surface environment data, soil layer environment data, and microenvironment data.

[0031] Specifically, a sensor module group is deployed 1 meter above the canopy. The sensor group includes at least sensors such as temperature and humidity sensors and light sensors. Data is collected normally, including raw photosynthetic active radiation data, air temperature and humidity data, and light intensity data. The data are synchronously bound to the Beidou positioning space coordinates. For sudden changes in photosynthetic active radiation data caused by cloud flashing, a sliding window median filter with a sliding window length of 5 minutes is used to remove noise. For photosynthetic active radiation data collection during the dew condensation period of crops, water droplet shielding correction is started. When the crop leaf temperature is lower than the dew point temperature and the corresponding humidity is greater than 80%, the raw photosynthetic active radiation data is corrected according to "photosynthetic active radiation data correction value = photosynthetic active radiation data measured value * (1-0.4*dew coverage rate)" (this is just an example of one possibility of water droplet shielding correction, and the actual content needs to be determined by the specific situation).

[0032] Furthermore, for the air temperature and humidity data, a preset physical threshold is used to eliminate abnormal data noise, and the air temperature and humidity data are mutated to perform mutation rationality verification. For example, when the temperature difference within 10 minutes is greater than 3°C or the humidity difference is greater than 15%, wind speed auxiliary verification is performed. Under the condition that the wind speed is lower than 1m / s, the mutation is regarded as a fault, the mutation data is eliminated and the backup sensor is switched to re-collect data to fill the data gap; for the direct exposure points without sunshades, the temperature is compensated according to the solar radiation intensity, such as 0.4°C for every 1kW / m² of radiation. In the case of heavy rainfall with a rainfall of more than 5mm / h, the temperature is compensated by reducing the solar radiation intensity. The weight of the corresponding air humidity data during the rainfall period is used to suppress falsely high humidity. For example, the confidence level of the air humidity data within 30 minutes after the rain is reduced to 80%. During the crop condensation period, the theoretical dew point temperature is obtained based on the air temperature and humidity data. If the deviation between the air temperature data and the theoretical dew point temperature data exceeds the preset temperature deviation threshold, and the air humidity data exceeds the preset humidity threshold, it is determined to be a condensation failure. The air temperature and humidity data of the corresponding period are replaced with data from an adjacent time period. For example, the average of the air temperature and humidity data 5 minutes before the condensation failure period is used to replace the corresponding data in the condensation failure period.

[0033] Furthermore, for light intensity data, valid data is dynamically screened according to the solar altitude angle. For example, only light intensity data within the corresponding period when the solar altitude angle is greater than 40 degrees is retained, and low signal-to-noise ratio interference data at dawn and dusk is eliminated. For light intensity data on cloudy days, the weight of light intensity data is increased by 20%. The weight of light intensity data is reduced during periods of heavy rainfall to avoid inflated light intensity caused by water droplet scattering. During periods of condensation on crops, the droplet coverage area is located with the help of an infrared thermal imager, and the contaminated sensor data corresponding to the droplet coverage area is marked, and the corresponding confidence level is reduced to 60%.

[0034] Next, the pre-processed photosynthetically active radiation data, air temperature and humidity data, and light intensity data are aligned in time and space to generate surface environment data.

[0035] The soil redox potential data of the corresponding depth is obtained by burying redox potential sensors at a depth of 20 cm and 40 cm in the soil, and the collected soil redox potential data is temperature compensated, such as applying a temperature compensation factor of "-0.7*(T-25)" to the soil redox potential data, where T is the current soil temperature; the collected soil redox potential data is compensated for salinity, such as applying a +0.1mV compensation for every 0.1mS / cm excess of conductivity over the preset benchmark; data updates are frozen for 2 hours after fertilization to avoid data disturbances caused by fertilization; weighted fusion is performed according to the root distribution characteristics of crops to generate fused soil redox potential data, such as using "0.3*20 cm depth corresponding to" for deep-rooted plants. The weighted fusion is performed using the weight ratio of "soil redox potential data corresponding to a depth of 0.7*40 cm + soil redox potential data corresponding to a depth of 0.7*40 cm". For shallow-rooted plants, the weighted fusion is performed using the weight ratio of "soil redox potential data corresponding to a depth of 0.8*20 cm + soil redox potential data corresponding to a depth of 0.2*40 cm". The fused soil redox potential data is normalized. For example, the soil redox potential data corresponding to rice fields ranges from [-200, 200] mV. The data within this range is mapped to the range of [0, 1]. Taking -120 mV as an example, the value of the fused soil redox potential data after normalization is [-120-(-200)] / [200-(-200)]=0.2.

[0036] Furthermore, the preprocessed soil redox potential data were spatially and temporally aligned with the soil moisture data to generate soil layer environmental data, and the canopy spectral data were spatially and temporally aligned with the stem surface strain rate to generate microenvironmental data.

[0037] Step S2: obtaining a crop growth index and an environmental pressure index based on the crop growth data set and the crop environment data set respectively.

[0038] In this embodiment, step S2 includes: Step S21 , extracting features from the crop growth data set to obtain stem image data, root projection area data, soil moisture data, canopy LAI, leaf chlorophyll content data, and leaf texture density data.

[0039] Step S22 , obtaining the internal strain energy distribution of the stem tissue by analyzing the displacement changes of three consecutive frames of stem image data at a fixed time interval, and generating the vascular strain energy density based on the internal strain energy distribution of the tissue.

[0040] In some possible embodiments, assuming that in a force 7 gale environment, the maximum stalk displacement of a corn stalk at a marked monitoring point within 3 hours is 0.35 mm, the maximum stalk displacement is divided by the stalk internode distance of 300 mm, and the vascular strain rate is obtained as 0.35 / 300≈0.12%. The corresponding elastic modulus of the corn is obtained as 1.8 GPa, and the vascular strain energy density is obtained according to "0.5*elastic modulus*vascular strain rate squared" as 1.296 kJ / m³ (this is just an example to illustrate the calculation process of the vascular strain energy density, and the actual calculation data needs to be determined by the specific situation).

[0041] Step S23: Analyze the time series acceleration of the root projection area data and combine it with the fluctuation characteristics of the soil moisture data to generate the root anchorage attenuation rate.

[0042] In some possible embodiments, assume that the root projection area data for three consecutive days during the jointing period of winter wheat are 650 cm², 590 cm², and 540 cm², respectively, and the corresponding time series change acceleration is -10 cm² / day². The soil moisture content is obtained based on soil moisture data. The soil moisture content sequences corresponding to the root projection area data sequence are 35%, 28%, and 41%. The mean, variance, and standard deviation of the soil moisture content sequence are 34.67%, 28.22%, and 5.31%. The time series change acceleration is corrected based on the standard deviation of the soil moisture content sequence. For example, in the above example, the time series change acceleration is -10 cm² / day² and the standard deviation of the soil moisture content sequence is 5. 31%, and an acceleration compensation of "1+0.3*standard deviation" is assigned to the time-series acceleration, obtaining a corrected time-series acceleration of -10*(1+0.3*0.0531)≈-10.16cm² / day²; the corrected time-series acceleration is mapped to the root anchorage attenuation rate according to the preset attenuation rate mapping function. For example, using the preset attenuation rate mapping function of 1% root anchorage attenuation rate per -10cm² / day², the corrected time-series acceleration obtained in the above example is mapped to the root anchorage attenuation rate, that is, -10.16 / 10=-1.016% (this is just an example to illustrate the calculation process of the root anchorage attenuation rate; the actual calculation data needs to be determined according to the specific situation).

[0043] Step S24 , by analyzing the root projected area data and the canopy LAI, the transmission efficiency of the crop root and canopy growth signals is obtained, and the root-canopy response entropy is generated based on the transmission efficiency.

[0044] In some possible embodiments, assuming that the root projected area data of a certain indica rice for 5 consecutive days are 550 cm², 610 cm², 690 cm², 780 cm², and 760 cm², respectively, and the canopy LAI in the corresponding time periods are 3.8, 4.2, 4.5, 4.7, and 4.6, respectively. Based on this root projected area data sequence, 4 groups of effective root projected area data daily increment data can be extracted, which are 60 cm², 80 cm², 90 cm², and -20 cm², respectively. Based on this canopy LAI sequence, 4 groups of effective canopy LAI daily increment data can be extracted, which are 0.4, 0.3, 0.2, and -0.1, respectively. Based on the above 4 groups of effective root projected area data daily increment data and the effective canopy LAI daily increment data, the corresponding root-crown efficiency ratio sequences are 150 cm² / LAI, 267 cm² / LAI, 450 cm² / LAI, and 200 cm² / LAI; The mean and standard deviation of the root-cap efficiency ratio series are calculated, and the quotient of the standard deviation and the mean is taken as the dispersion coefficient of the root-cap efficiency ratio series, that is, the dispersion coefficient corresponding to the above root-cap efficiency ratio series is 118.6 / 266.75*100%≈44.5%; the obtained dispersion coefficient is compared with the preset dispersion threshold. If the dispersion coefficient is lower than the preset dispersion threshold, the root-cap response entropy value mapping is performed according to the root-cap response entropy value mapping function in the form of "0.5*(dispersion coefficient / 20%)". If the dispersion coefficient is higher than the preset dispersion threshold, the root-cap response entropy value mapping is performed according to the root-cap response entropy value mapping function in the form of "0.8+0.5*[(dispersion coefficient-40%) / 30%]". That is, after the above dispersion coefficient is mapped to the root-cap response entropy value, the obtained root-cap response entropy value is 0.875 (this is just an example to illustrate the calculation process of the root-cap response entropy value, and the actual calculation data needs to be determined according to the specific situation).

[0045] Step S25 , constructing a photosynthetic phase space based on the leaf chlorophyll content data and the leaf texture density data, and generating a photosynthetic phase space compression degree by analyzing the movement trajectories of the leaf chlorophyll content data and the leaf texture density data in the photosynthetic phase space.

[0046] In some possible embodiments, a two-dimensional plane coordinate system can be constructed with the leaf chlorophyll content as the horizontal axis and the leaf stretch obtained based on the leaf texture density data as the vertical axis. The leaf chlorophyll content data and leaf texture density data corresponding to the same crop plant are collected every 2 hours from 6:00 to 18:00 every day. The collected data are mapped to the constructed two-dimensional plane coordinate system to form dynamic trajectory points, and a continuous motion trajectory path is generated through cubic spline interpolation. The phase space area enclosed by the motion trajectory is calculated, and the ratio of the daily minimum phase space area to the maximum phase space area is used as the photosynthetic phase space compression degree (this is just an example to illustrate one possibility of the photosynthetic phase space compression degree, and the actual situation needs to be determined according to the specific situation).

[0047] Step S26, constructing a crop structural index based on vascular strain energy density and root anchorage attenuation rate, and constructing a functional synergy index based on root-cap response entropy and photosynthetic phase space compression, wherein the crop growth index includes the crop structural index and the functional synergy index.

[0048] In some possible embodiments, the quantitative value of the crop structural index can be obtained in the form of "√(strain energy² + attenuation rate²)". When the quantitative value of the crop structural index exceeds a preset structural imbalance threshold, it is determined that the crop has structural imbalance, and the physical strength and stability of the crop organ are monitored based on the crop structural index.

[0049] In some possible embodiments, the quantitative value of the functional synergy index can be obtained in the form of "root-cap response entropy * photosynthetic phase space compression degree", the quantitative value of the functional synergy index can be used to diagnose the photosynthetic efficiency of crops, and drive the optimization of the organic carbon source delivery strategy, and quantify the photosynthetic material transfer and energy conversion efficiency between crop organs according to the functional synergy index.

[0050] Step S27 , extracting features from the crop environmental data set to obtain environmental feature data, and constructing an environmental pressure index based on the environmental feature data.

[0051] Specifically, environmental characteristic data include photosynthetically active radiation data, canopy spectrum data, air temperature and humidity data, stem surface strain rate, soil redox potential data, and light intensity data.

[0052] In this embodiment, step S27 further specifically includes the following steps: Step S271 : generating photo-carbon disorder data by analyzing the response relationship between photosynthetically active radiation data and canopy spectrum data.

[0053] In some possible embodiments, a sudden change event of photosynthetically active radiation data is identified, such as a sudden increase of photosynthetically active radiation data by more than 200 μmol / m⁻² / s⁻¹ within 1 minute due to cloud movement, and the response delay time of the red edge displacement of the canopy spectrum data is captured. For example, after a sudden increase in photosynthetically active radiation data, the red edge displacement of the canopy spectrum data is obtained to be 15 nm. According to historical data analysis, the average normal response delay time is 5 minutes; when the actual response delay time continues to exceed the preset response delay threshold, the ratio of the total cumulative duration of the full-day response delay time to the total duration of the effective light period is obtained, for example, the total duration of the full-day effective light period is 15 nm. The duration is 6 hours, and the total cumulative response delay time for the whole day is 36 minutes, then the corresponding ratio is 0.1; the optical carbon disorder data is obtained in the form of "final disorder = delay ratio * red edge displacement anomaly amplitude coefficient", for example, the red edge displacement anomaly amplitude coefficient of 0.2 is increased for every 1nm deviation of the optical carbon disorder data from the theoretical value. In the above example, the delay ratio is 0.1, and the corresponding red edge displacement offset is 8nm, then the corresponding optical carbon disorder data is 0.1*(1+0.2×8)=0.26 (here is just an example to illustrate the calculation process of the optical carbon disorder data, the actual calculation data needs to be determined by the specific situation).

[0054] Step S272: Generate water damage coupling data by analyzing the response relationship between the air temperature and humidity data and the stem surface strain rate.

[0055] In some possible embodiments, the saturated vapor pressure difference (VPD) is obtained based on air temperature and humidity data, and the stem surface strain rate is compensated for temperature drift in real time to obtain a stem surface strain rate correction value. For example, a value of "-0.0000125*temperature change" is applied to the stem surface strain rate, that is, a 0.01% thermal expansion pseudo-strain is automatically deducted when the temperature suddenly rises by 8°C. When the VPD and the stem surface strain rate simultaneously exceed corresponding preset thresholds, the moisture damage coupling data is calculated. For example, a set of data has a VPD of 2.8 kPa and a strain rate of 0. 13% / min. Since the VPD=2.8kPa corresponding to this group of data is greater than the preset VPD threshold of 2.5kPa, and the stem surface strain rate of 0.13% / min is greater than the preset stem surface strain rate threshold of 0.1% / min, the water damage coupling data is calculated in the form of "(VPD-2.0)*stem surface strain rate*10", and the water damage coupling data is obtained as (2.8-2.0)*0.13*10=1.04 (this is just an example to illustrate the calculation process of water damage coupling data, and the actual calculation data needs to be determined by specific circumstances).

[0056] Step S273 , generating marginal load data by analyzing soil redox potential data, light intensity data and corresponding spatial position coordinates.

[0057] Furthermore, a marginal two-dimensional plane coordinate system is constructed and meshing is performed.

[0058] Specifically, as attached Figure 4 As shown in the figure, the intersection of multiple ridges is used as the coordinate origin, the inner boundary line of the ridge is used as the X axis, and the direction perpendicular to the ridge is used as the Y axis. The field is divided into square grid units with a side length of 0.5 meters, and the grid is divided according to the grid unit. Figure 3 The core area and the edge area are divided in the form shown in the figure; the center point of each grid is used as the data collection point, and the soil redox potential data, light intensity data and distance data from the field ridge in the grid are collected synchronously, and the collected data are preprocessed; the collected light intensity data is divided by the mean value of the light intensity data in the core area for data normalization to obtain the relative light intensity data. When the mean value of the light intensity data in the core area is greater than the light saturation point of the corresponding crop, the relative light intensity data is nonlinearly corrected. For example, in a field where rice is planted, the light intensity in the core area is less than 0. The average light intensity data is 1850 μmol, and the light intensity data collected in a unit block is 1295. The relative light intensity data is calculated to be 1295 / 1850=0.7. Assuming that the light saturation point of rice is 1800 μmol, since the average light intensity data in the core area is greater than the light saturation point of the corresponding crop, a correction coefficient of "1-0.2*(1850-1800) / 1000=0.99" is applied to the obtained relative light intensity. The corrected relative light intensity data is 0.7*0.9 9=0.693; obtain the distance attenuation coefficient based on the spatial position coordinates. For example, the corresponding spatial coordinates in the above example are (0,2). From the coordinates, it can be seen that the current data collection point is 1 meter away from the ridge. According to "0.7+0.15*distance from the ridge", the corresponding distance attenuation coefficient is 0.7+0.15*1=0.85; obtain the marginal load data based on the soil redox potential data, relative light intensity data and distance attenuation coefficient. For example, the corresponding soil redox potential data and relative light intensity data in the above example are and distance attenuation coefficients are -120mV, 0.693, and 0.85, respectively. The soil redox potential data is normalized and converted to 0.2. The marginal load data is calculated in the form of "0.4*soil redox potential data + 0.3*relative light intensity data + 0.3*distance attenuation coefficient", and the marginal load data is 0.4*0.2+0.3*0.693+0.3*0.85=0.5429 (this is just an example to illustrate the calculation process of the marginal load data, the actual calculation data needs to be determined by the specific situation).

[0059] Step S274: Generate environmental disturbance memory data by analyzing soil redox potential data over a continuous period of time.

[0060] In some possible embodiments, it is assumed that the arithmetic mean of the soil redox potential data for 6 consecutive hours is taken as the initial historical memory value, and after collecting the new fused Eh value every hour, a new memory value is generated according to the weight ratio of "historical memory value: current soil redox potential data = 8:2"; the standard deviation of the deviation between the current soil redox potential data and the new memory value is calculated, and the standard deviation of the deviation is used as the environmental disturbance memory data.

[0061] Step S275: constructing a metabolic abnormality environment coupling index based on the photo-carbon disorder data and the water damage coupling data, and constructing a spatial heterogeneity index based on the marginal load data and the environmental disturbance memory data. The environmental pressure index includes the metabolic abnormality environment coupling index and the spatial heterogeneity index.

[0062] In some possible embodiments, the quantitative value of the metabolic abnormality environment coupling index can be obtained in the form of "√light-carbon disorder data*water damage coupling data", and the metabolic status of crops can be diagnosed based on the quantitative value of the metabolic abnormality environment coupling index.

[0063] In some possible embodiments, the quantitative value of the spatial heterogeneity index can be obtained in the form of "marginal load data / 10+0.2*environmental disturbance memory data", and the generation of organic carbon source regulation decisions can be optimized based on the quantitative value of the spatial heterogeneity index.

[0064] Step S3: mining the causal association chain between the crop growth indicators and the environmental pressure indicators, and constructing a growth environment association rule base based on the causal association chain.

[0065] In this embodiment, step S3 includes: Step S31, obtaining the causal entropy between the crop growth index and the environmental pressure index within a preset time window length, and quantifying the temporal coupling relationship between the crop growth index and the environmental pressure index corresponding to the crops at different growth stages based on the causal entropy.

[0066] In some possible embodiments, a probability analysis is performed on the transmission efficiency of the functional synergy index based on changes in the metabolic abnormality-environment coupling index. For example, when the calculated metabolic abnormality-environment coupling index exceeds 0.6, the probability of deterioration of the root-shoot response entropy in the functional synergy index increases to 73%. This means that for every 0.1 unit increase in the intensity of environmental stress to which the crop is subjected, the risk of its functional synergy capacity decline will increase by 18.7% accordingly. Assume that during the tillering stage of crops, the mean causal entropy between crop structural indicators and environmental stress indicators is 0.28, and the crop structural indicators and environmental stress indicators corresponding to this growth stage show weak coupling characteristics. At this time, environmental pressure can only explain part of the structural changes of crops. Therefore, for crops in this stage, the corresponding decisions generated are mainly based on root repair carbon sources; after entering the heading stage, the causal entropy between the functional synergy index and the metabolic abnormality environment coupling index jumps to 0.79. At this time, the functional synergy index and the metabolic abnormality environment coupling index show a strong decoupling state. Therefore, for crops in this stage, the corresponding decisions generated are mainly based on optimizing the carbon assimilation of crop leaves.

[0067] Step S32: Calculate the hierarchical transition causal gain value from the organ level to the system level, and filter the macro-hysteresis interference based on the hierarchical transition causal gain value.

[0068] Specifically, the organ level represents the structural and functional performance of each organ of the crop, the system level represents the comprehensive growth status of the crop, and the macro-hysteresis interference represents the delay phenomenon of organs and systems responding to environmental changes.

[0069] In some possible embodiments, when an organ-level indicator triggers a system-level response, such as a sudden drop in leaf stomatal conductance leading to a decrease in photosynthetic rate, the response time difference of the organ-level indicator triggering the system-level response, the probability of the organ-level indicator triggering the system-level response, and the probability of the system-level response occurring under natural conditions without any change in the organ-level indicator are obtained. A causal gain value for the changes in the response time difference and the probability of the occurrence is generated based on the response time difference and the probability of the occurrence. For example, if the probability of photosynthetic attenuation due to stem damage is 80% and the probability of photosynthetic attenuation under natural conditions is 35%, then the corresponding causal gain value is 0.8-0.35=0.45. If the causal gain value is greater than a preset effective correlation strength threshold, it is determined to be effective correlation conduction. If the response time difference is greater than the crop response time threshold or the causal gain value is lower than the preset effective correlation strength threshold, it is considered to be delayed interference, such as instantaneous stomatal closure caused by short-term cloud cover. By dynamically tracking the causal gain value mutation nodes, interference signals caused by environmental noise or physiological buffering are actively shielded, such as shielding the environmental noise of short-term stem vibration caused by gusts and the physiological buffering interference signal caused by short-term root water shortage.

[0070] Step S33: Under the premise of keeping the environmental pressure index unchanged, virtually switch the crop varieties, observe the change difference rate of the crop growth indicators, and detect the universality of the time series coupling relationship based on the change difference rate. If the change difference rate reaches the preset difference rate threshold range, it is determined that the time series coupling relationship has variety universality.

[0071] In some possible embodiments, under the premise of maintaining the environmental pressure index unchanged for 48 consecutive hours, assuming that a certain temporal coupling relationship is an atomic rule involving the root anchorage attenuation rate, and the recorded root anchorage attenuation rate of stress-resistant crop varieties is -4.8%, while the root anchorage attenuation rate of sensitive crop varieties reaches -12.3%, the calculated change difference rate is |-4.8%--12.3%)| / |-4.8%|=156%. This change difference rate falls within the preset change difference rate threshold range of [80%, 200%], so it is determined that the current temporal coupling relationship has variety universality.

[0072] In step S34, virtual data of different soil conditions on the same plot are synthesized by generating an adversarial network to separate the interference of soil properties on the temporal coupling relationship.

[0073] A dual-channel adversarial model was constructed to generate virtual data from the same plot with different soil conditions based on the time series data corresponding to the crop environment dataset of the real plot. The distribution differences between the real and virtual data were compared, and through iterative adversarial training, the statistical characteristic error between the generated virtual data and the real data was reduced to below a preset error threshold, ensuring that the virtual data was physiologically reasonable. Virtual data is imported into the temporal coupling relationship for verification. If a temporal coupling relationship still maintains a strong correlation after the virtual data is injected for verification, it is determined that the temporal coupling relationship is weakly interfered by soil conditions. On the contrary, if the correlation collapses, the relationship is marked as having soil-specific interference. The soil property interference item is analyzed by the difference between the virtual data and the real data, and the interference item of the corresponding temporal coupling relationship is eliminated based on the soil property interference item, thereby improving the universality of the temporal coupling relationship.

[0074] Step S35 , generating a causal association chain between the crop growth indicators and the environmental pressure indicators based on the temporal coupling relationship, and constructing a growth environment association rule base based on the causal association chain.

[0075] Specifically, rules are extracted from the causal association chain to obtain three types of growth environment association rules, namely atomic rules, combination rules and spatiotemporal constraint rules. The support, confidence and lift corresponding to the growth environment association rules are obtained, and the growth environment association rules that do not meet the preset support threshold, confidence threshold and lift threshold are eliminated to construct a growth environment association rule library.

[0076] It can be understood that atomic rules are represented by growth environment association rules driven directly by a single indicator, combination rules are represented by growth environment association rules coordinated by multiple indicators, spatiotemporal constraint rules are represented by growth environment association rules that associate crop growth stages with geographical locations, support is represented by the frequency of occurrence of growth environment association rules in historical data, confidence is represented by the probability that the growth environment association rules will successfully take effect when the corresponding conditions for triggering the growth environment association rules are met, and improvement is represented by the efficiency gain multiplier of the rule prediction ability of the growth environment association rules relative to random guessing.

[0077] Step S4: constructing an organic carbon source regulation model based on crop growth indicators, environmental pressure indicators and a growth environment association rule library, and generating an organic carbon source regulation decision according to the organic carbon source regulation model.

[0078] Specifically, the physiological state of crops is diagnosed in real time based on crop growth indicators, the environmental impacts on crops during growth are quantified through environmental pressure indicators, the growth environment association rules corresponding to the crop growth indicators and environmental pressure indicators in the growth environment association rule library are matched and called, and organic carbon source regulation decisions are generated based on the matched growth environment association rules to regulate the organic carbon source of crops.

[0079] In some possible embodiments, assuming that the vascular strain energy density of rice collected in a certain period is 0.22 kJ / m³ and the root anchorage attenuation rate is -7%, the corresponding quantitative value of the crop structural index is √(0.22² +(-0.07)²) ≈ 0.23; the root-shoot response entropy is 0.75 and the photosynthetic space compression is 0.32, then the corresponding quantitative value of the functional synergy index is 0.75*0.32=0.24; the light-carbon disorder data is 0.29 and the water damage coupling data is 1.3, then the corresponding quantitative value of the metabolic abnormality environment coupling index is √(0.29*1.3) ≈0.61; the marginal load data is 0.43 and the environmental disturbance memory data is 9.1, then the corresponding quantitative value of the spatial heterogeneity index is (0.43 / 10)+0.2*9.1=1.863; the quantitative value corresponding to each indicator is compared with the corresponding preset threshold, and the priority is divided according to the proportion exceeding the preset threshold, and a weight is assigned to the indicator of each priority. In this example, the priority is set from high to low as functional synergy index, crop structure index, metabolic abnormality environment coupling index, and spatial heterogeneity index. The organic carbon source regulation model matches the corresponding rules from the growth environment association rule library, generates corresponding regulation decisions for each indicator, and performs decision fusion according to the obtained weights of each indicator. When the corresponding decisions of each indicator conflict, the corresponding decisions of the indicators with higher weights are retained first (this is just an example to illustrate the process of the organic carbon source regulation model generating organic carbon source regulation decisions based on crop growth indicators and environmental pressure indicators. The actual situation needs to be determined according to the specific situation).

[0080] Step S5: obtaining the implementation effect of the organic carbon source regulation decision, and iteratively optimizing the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect of the organic carbon source regulation decision.

[0081] Specifically, the organic carbon source regulation decision that fails to improve the growth indicators of the target crop within the scheduled time will be judged as a failed decision. At the same time, the growth environment association rule corresponding to the failed decision will be marked as a gradually invalid rule, and the confidence of the gradually invalid rule will be reduced. The growth environment association rule that is marked as a gradually invalid rule for three consecutive times will be judged as an invalid rule, and the invalid rule will be frozen. The organic carbon source regulation decision that improves the growth indicators of the target crop within the scheduled time will be judged as a successful decision. At the same time, the growth environment association rule corresponding to the successful decision will be marked as a valid rule, and the confidence of the valid rule will be improved.

[0082] In some possible embodiments, the weights of indicators corresponding to the gradually invalidating rules are increased according to the contribution rates of the crop growth stages. If the failed decision is not converted into a successful decision within 3 days after the adjustment, the indicator weights are automatically rolled back and iterative adjustments are made again until the failed decision is converted into a successful decision or the gradually invalidating rule is determined to be an invalid rule. For scenarios where the decision misjudgment rate exceeds 20%, the preset thresholds corresponding to each indicator are adjusted based on the climate characteristics corresponding to the region where the crops are located. The adjusted thresholds of each indicator need to reduce the misjudgment rate to below 8% within 7 days. Otherwise, the thresholds are restored to the original indicator thresholds and iterative adjustments are made again until the misjudgment rate is reduced to below 8%.

[0083] The embodiment of the present invention also provides an organic carbon source data optimization system based on crop growth feedback, which is applicable to the field of agricultural technology and includes: A data processing module, which is used to collect data on crops, perform data preprocessing on the collected data, and generate a crop growth data set and a crop environment data set; An indicator generation module, the indicator generation module is used to generate corresponding crop growth indicators and environmental pressure indicators according to the crop growth data set and the crop environment data set; A rule extraction module, which is used to extract the causal relationship chain between crop growth indicators and environmental pressure indicators, and generate corresponding rules based on the causal relationship chain; A model building module, wherein the model building module is used to build an organic carbon source regulation model based on crop growth indicators, environmental pressure indicators and a growth environment association rule library, and generate an organic carbon source regulation decision; The feedback optimization module is used to obtain the implementation effect of the organic carbon source regulation decision and optimize and adjust the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect.

[0084] The specific usage and function of this embodiment are as follows: First, we collect and preprocess crop data to obtain crop growth and environmental datasets. By preprocessing the collected data, we eliminate interference noise and data offsets generated during the collection process, improving data accuracy. The preprocessed data also provides highly accurate data support for the subsequent generation of quantitative indicators. Then, based on the crop growth data set and the crop environment data set, crop growth indicators and environmental pressure indicators are obtained respectively, and the causal association chain between the crop growth indicators and the environmental pressure indicators is mined. A growth environment association rule library is constructed based on the causal association chain. By constructing crop growth indicators and environmental pressure indicators, accurate quantification of discrete environmental data and crop physiological data is achieved. By mining the causal association chain between indicators, the causal coupling relationship between environmental data and crop physiological data is analyzed, and corresponding quantitative rules are obtained, which provides data support and decision-making reference benchmarks for subsequent model generation of organic carbon source regulation decisions; Finally, an organic carbon source regulation model is constructed based on the crop growth indicators, environmental pressure indicators and growth environment association rule library, and organic carbon source regulation decisions are generated according to the organic carbon source regulation model to obtain the implementation effect of the organic carbon source regulation decision. According to the implementation effect of the organic carbon source regulation decision, the organic carbon source regulation rule library and the organic carbon source regulation model are iteratively optimized. By monitoring the implementation effect of the organic carbon source regulation decision, the confidence of the efficient rules in the organic carbon source regulation rule library is improved, and the confidence of the inefficient rules is reduced, thereby improving the accuracy of the organic carbon source regulation plan.

[0085] In addition, an embodiment of the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method in the above-mentioned embodiment one.

[0086] The following is a detailed introduction to the various components of electronic equipment: The term "processor" is the control center of an electronic device and can be a single processor or a collective term for multiple processing elements. For example, the processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the first embodiment of the present invention, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0087] The processor can execute various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0088] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0089] The memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and be coupled to the processor via an interface circuit of the electronic device, and this is not specifically limited in the embodiments of the present invention.

[0090] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wireless communication (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer, or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0091] It should be understood that the term "and / or" as used herein simply describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent the existence of A alone, the existence of both A and B, or the existence of B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the related objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0092] It should be understood that in the embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0093] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. An organic carbon source data optimization method based on crop growth feedback, characterized in that: The method comprises: S1: Collect and preprocess crop data to obtain crop growth data sets and crop environment data sets; S2: Based on the crop growth data set and the crop environment data set, crop growth indicators and environmental pressure indicators are obtained respectively; S3: mining the causal association chain between crop growth indicators and environmental pressure indicators, and building a growth environment association rule base based on the causal association chain; S4: Construct an organic carbon source regulation model based on crop growth indicators, environmental pressure indicators and growth environment association rule base, and generate organic carbon source regulation decisions based on the organic carbon source regulation model; S5: Obtain the implementation effect of the organic carbon source regulation decision, and iteratively optimize the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect of the organic carbon source regulation decision.

2. The organic carbon source data optimization method based on crop growth feedback according to claim 1, characterized in that: Based on the crop growth dataset and the crop environment dataset, crop growth indicators and environmental pressure indicators are obtained respectively, including: Perform feature extraction on the crop growth dataset to obtain stem image data, root projection area data, soil moisture data, canopy LAI, leaf chlorophyll content data, and leaf texture density data; By analyzing the displacement changes of three consecutive frames of stem image data at a fixed time interval, the internal strain energy distribution of the stem tissue is obtained, and the vascular strain energy density is generated based on the internal strain energy distribution of the tissue; By analyzing the time series acceleration of root projection area data and combining it with the fluctuation characteristics of soil moisture data, the root anchorage attenuation rate is generated. By analyzing the root projected area data and canopy LAI, the transmission efficiency of crop root and canopy growth signals is obtained, and the root-canopy response entropy is generated based on the transmission efficiency. The photosynthetic phase space is constructed based on the leaf chlorophyll content data and the leaf texture density data. The compression degree of the photosynthetic phase space is generated by analyzing the movement trajectory of the leaf chlorophyll content data and the leaf texture density data in the photosynthetic phase space. A crop structural index is constructed based on vascular strain energy density and root anchorage attenuation rate, and a functional synergy index is constructed based on root-cap response entropy and photosynthetic phase spatial compression. The crop growth index includes a crop structural index and a functional synergy index. Feature extraction is performed on the crop environmental dataset to obtain environmental characteristic data, and environmental pressure indicators are constructed based on the environmental characteristic data.

3. The organic carbon source data optimization method based on crop growth feedback according to claim 2, characterized in that: Extract features from crop environmental datasets, obtain environmental characteristic data, and construct environmental pressure indicators based on the environmental characteristic data, including: Environmental characteristic data include photosynthetically active radiation data, canopy spectrum data, air temperature and humidity data, stem surface strain rate, soil redox potential data, and light intensity data; By analyzing the response relationship between photosynthetically active radiation data and canopy spectrum data, light-carbon disorder data is generated; By analyzing the response relationship between air temperature and humidity data and stem surface strain rate, water damage coupling data is generated; By analyzing soil redox potential data, light intensity data and corresponding spatial position coordinates, marginal load data is generated; By analyzing soil redox potential data over a continuous period of time, environmental disturbance memory data are generated; A metabolic abnormality environment coupling index is constructed based on the photo-carbon disorder data and the water damage coupling data, and a spatial heterogeneity index is constructed based on the marginal load data and the environmental disturbance memory data. The environmental pressure index includes the metabolic abnormality environment coupling index and the spatial heterogeneity index.

4. The method for optimizing organic carbon source data based on crop growth feedback according to claim 1, characterized in that: Mining the causal association chain between crop growth indicators and environmental pressure indicators, and building a growth environment association rule base based on the causal association chain, including: Obtaining causal entropy between crop growth indicators and environmental pressure indicators within a preset time window length, and quantifying the temporal coupling relationship between the crop growth indicators and environmental pressure indicators corresponding to different crop growth stages based on the causal entropy; Calculate the hierarchical transition causal gain value from the organ level to the system level, and filter the macro-hysteresis interference based on the hierarchical transition causal gain value; The organ level represents the structural and functional performance of each organ of the crop, the system level represents the comprehensive growth status of the crop, and the macro-hysteresis interference represents the delayed phenomenon of organs and systems responding to environmental changes. While keeping the environmental pressure indicators unchanged, the crop varieties are virtually switched and the change difference rate of the crop growth indicators is observed. The universality of the temporal coupling relationship is tested based on the change difference rate. If the change difference rate reaches the preset difference rate threshold range, it is determined that the temporal coupling relationship has variety universality. Generate adversarial networks to synthesize virtual data with different soil conditions on the same plot, and separate the interference of soil properties on temporal coupling relationships. Based on the temporal coupling relationship, a causal association chain between crop growth indicators and environmental pressure indicators is generated, and a growth environment association rule base is constructed based on the causal association chain.

5. The method for optimizing organic carbon source data based on crop growth feedback according to claim 4, characterized in that: Build a growth environment association rule base based on the causal association chain, including: Rules are extracted from the causal association chain to obtain three types of growth environment association rules: atomic rules, combination rules, and spatiotemporal constraint rules. The support, confidence, and lift corresponding to the growth environment association rules are obtained, and the growth environment association rules that do not meet the preset support threshold, confidence threshold, and lift threshold are eliminated to build a growth environment association rule library.

6. The method for optimizing organic carbon source data based on crop growth feedback according to claim 1, characterized in that: An organic carbon source regulation model is constructed based on the crop growth indicators, environmental pressure indicators and growth environment association rule base, and an organic carbon source regulation decision is generated based on the organic carbon source regulation model, including: The physiological status of crops can be diagnosed in real time according to crop growth indicators, and the environmental impacts on crops during growth can be quantified through environmental pressure indicators. The growth environment association rules corresponding to crop growth indicators and environmental pressure indicators in the growth environment association rule library can be matched and called. Based on the matched growth environment association rules, organic carbon source regulation decisions can be generated to regulate the organic carbon source of crops.

7. The method for optimizing organic carbon source data based on crop growth feedback according to claim 1, characterized in that: Obtain the implementation effect of the organic carbon source regulation decision, and iteratively optimize the organic carbon source regulation rule base and the organic carbon source regulation model based on the implementation effect of the organic carbon source regulation decision, including: The organic carbon source regulation decision that fails to improve the growth index of the target crop within the predetermined time is judged as a failed decision. At the same time, the growth environment association rule corresponding to the failed decision is marked as a gradually invalid rule, and the confidence of the gradually invalid rule is reduced. The growth environment association rules that have been marked as gradually invalid rules for three consecutive times are determined to be invalid rules, and the invalid rules are frozen; The organic carbon source regulation decision that improves the growth indicators of target crops within the predetermined time is judged as a successful decision. At the same time, the growth environment association rule corresponding to the successful decision is marked as a valid rule, and the confidence of the valid rule is improved.

8. The method for optimizing organic carbon source data based on crop growth feedback according to claim 1, characterized in that: Collect and preprocess crop data to obtain crop growth data sets and crop environment data sets, including: Performing data preprocessing on the collected crop data, including at least outlier filtering, time-space alignment, data standardization, and data normalization, to obtain crop growth data sets and crop environment data sets; The crop growth data set is used to describe the multi-dimensional dynamic growth characteristics of crops, and at least includes crop canopy dimension data, stem dimension data, underground root dimension data, and physiological dimension data; The crop environment dataset is used to describe the growing environment of crops and at least includes surface environment data, soil layer environment data, and microenvironment data.

9. The method for optimizing organic carbon source data based on crop growth feedback according to claim 8, characterized in that: The collected crop data is preprocessed by at least outlier filtering, time-space alignment, data standardization and data normalization, including: The outlier filtering is performed on the crop data to filter outliers and fill in missing values; The time-space alignment is to unify the crop data into the same geographic coordinate reference and time reference; The data standardization is performed on the crop growth data included in the crop data; The data normalization is performed on the crop environment data included in the crop data.

10. An organic carbon source data optimization system based on crop growth feedback, characterized in that: include: A data processing module, which is used to collect data on crops, perform data preprocessing on the collected data, and generate a crop growth data set and a crop environment data set; An indicator generation module, the indicator generation module is used to generate corresponding crop growth indicators and environmental pressure indicators according to the crop growth data set and the crop environment data set; A rule extraction module, which is used to extract the causal relationship chain between crop growth indicators and environmental pressure indicators, and generate corresponding rules based on the causal relationship chain; A model building module, wherein the model building module is used to build an organic carbon source regulation model based on crop growth indicators, environmental pressure indicators and a growth environment association rule library, and generate an organic carbon source regulation decision; The feedback optimization module is used to obtain the implementation effect of the organic carbon source regulation decision and optimize and adjust the organic carbon source regulation rule base and the organic carbon source regulation model according to the implementation effect.

Images