CN121186000A - A Method and System for Diagnosing Crop Water Stress Based on Sunlight-Induced Chlorophyll Fluorescence - Google Patents
A Method and System for Diagnosing Crop Water Stress Based on Sunlight-Induced Chlorophyll FluorescenceInfo
- Publication number
- CN121186000A CN121186000A CN202511745465.4A CN202511745465A CN121186000A CN 121186000 A CN121186000 A CN 121186000A CN 202511745465 A CN202511745465 A CN 202511745465A CN 121186000 A CN121186000 A CN 121186000A
- Authority
- CN
- China
- Prior art keywords
- crop
- sif
- sifwdi
- water stress
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
本发明涉及农业干旱监测和精准灌溉技术领域，尤其涉及基于日光诱导叶绿素荧光的作物水分胁迫诊断方法及系统，通过高光谱传感器采集作物冠层氧吸收波段光谱数据，采用荧光提取算法解算日光诱导叶绿素荧光强度SIF值。以无水分胁迫作物冠层的SIF值作为参照冠层SIF值，确定待测作物冠层SIF值与参照冠层SIF值之间的差异，然后结合预设公式生成相对SIF水分亏缺指数SIFWDI，利用回归分析模型建立SIFWDI与土壤水分亏缺指数的映射关系输出诊断报告，根据胁迫等级触发变量灌溉决策及预警，并通过反馈机制实现模型参数自适应优化。系统实现无损、实时、高精度的水分胁迫监测与灌溉管理。
This invention relates to the fields of agricultural drought monitoring and precision irrigation technology, and particularly to a method and system for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence (SIF). The system collects spectral data of crop canopy oxygen absorption bands using a hyperspectral sensor, and calculates the SIF value of sunlight-induced chlorophyll fluorescence using a fluorescence extraction algorithm. Using the SIF value of a crop canopy without water stress as a reference, the difference between the SIF value of the crop under test and the reference canopy is determined. Then, a relative SIF water deficit index (SIFWDI) is generated using a preset formula. A regression analysis model is used to establish a mapping relationship between SIFWDI and the soil water deficit index, and a diagnostic report is output. Irrigation decisions and early warnings are triggered based on stress levels, and a feedback mechanism enables adaptive optimization of model parameters. The system achieves non-destructive, real-time, and high-precision water stress monitoring and irrigation management.
Description
Technical Field
The invention relates to the technical field of agricultural drought monitoring and precise irrigation, in particular to a crop water stress diagnosis method and system based on sunlight-induced chlorophyll fluorescence.
Background
Sunlight-induced chlorophyll fluorescence (SIF) is a weak electromagnetic radiation signal emitted by chlorophyll when a plant performs photosynthesis under sunlight conditions, the intensity of the signal is closely related to photochemical efficiency of a light system, when the plant is in an environment stress or physiological regulation state, partial light energy absorbed by a photosynthetic mechanism can be re-emitted in a fluorescence form, and the actual photosynthetic capacity of vegetation and a response mechanism to environment change can be inverted by capturing the signal through a remote sensing technology, so that the SIF can be used for directly diagnosing physiological drought of crops and diagnosing potential water stress conditions of the crops.
In the practical application process, the existing crop drought diagnosis technology based on the soil water deficiency index has the technical pain points that the soil probe arranged in the field is relied on to measure the water, the root system layer of the crop is damaged in the installation process, the integral condition can be accurately reflected only by densely distributing points, accurate monitoring is difficult to realize on the area, meanwhile, the drought condition of the crop cannot be monitored from the physiological level by the soil water condition, and the physiological signal of early drought of the plant cannot be captured. It follows that existing soil moisture based crop water deficit diagnostics are subject to high cost, limited monitoring range and monitoring lag when applied to intelligent irrigation decisions.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a crop water stress diagnosis method and a crop water stress diagnosis system based on sunlight-induced chlorophyll fluorescence, and solves the technical problems that the existing crop drought grade diagnosis technology based on the Soil Water Deficiency Index (SWDI) is high in diagnosis process cost, high in destructiveness, insufficient in representativeness and delayed in early warning response, and is difficult to meet the requirements of modern agriculture on low-cost, nondestructive, large-area and high-precision drought monitoring due to the fact that early signals of photosynthesis inhibition cannot be directly captured from a plant physiological level due to the fact that the existing crop drought grade diagnosis technology depends on field physical probe installation.
In order to solve the technical problems, the technical contents of the invention are as follows:
In a first aspect, the present invention provides a crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, comprising:
Step S1, acquiring original spectrum data of a crop canopy which is free of water stress and to be detected in the same environment through a hyperspectral sensor carried on a remote sensing platform, wherein the original spectrum data comprises a downlink irradiance spectrum and an uplink radiance spectrum in an oxygen molecule absorption band;
S2, calculating apparent reflectivity of an oxygen molecule A in an absorption band wave band based on downlink irradiance spectrum data, uplink irradiance spectrum data and a fluorescence extraction algorithm based on a spectrum filling principle, and calculating a sunlight-induced chlorophyll fluorescence intensity SIF value of the wave band of 760nm serving as a canopy;
Step S3, taking the calculated SIF value of the crop canopy without water stress as a reference canopy SIF value, and simultaneously substituting the calculated SIF value of the crop canopy to be detected into a preset formula to generate a relative SIF water deficiency index SIFWDI;
S4, constructing a regression analysis model by using the relative SIF water deficit index SIFWDI and the soil water deficit index SWDI generated based on the measured soil water data, and outputting a diagnosis report by establishing a mapping relation between the relative SIF water deficit index SIFWDI and the soil water deficit index SWDI, wherein the diagnosis report comprises crop water stress grades;
And S5, based on the diagnosis report output by the step S4, if the crop water stress level exceeds the preset threshold, generating a variable irrigation decision instruction and triggering early warning, taking the relative SIF water deficiency index, the soil water deficiency index SWDI and the crop water stress level corresponding to the judgment as new data samples, and automatically feeding back the new data samples to a regression analysis model for realizing the self-adaptive optimization of the regression analysis model parameters.
Further, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, provided by the invention, comprises the following steps of:
Step S101, installing spectrum sensing equipment at a fixed height above a crop canopy, and adjusting a probe to vertically point to a canopy central area;
step S102, synchronously acquiring downlink irradiance and uplink radiance data in a specified period of sunny weather by using a pre-installed spectrum sensing device;
step S103, the collected downlink irradiance and uplink irradiance data are recorded and stored in a local storage unit, and the data format is a continuous spectrum curve covering an oxygen absorption wave band.
Further, the method for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence, which is disclosed by the invention, comprises the following steps of:
Step S201, filtering and baseline correction are carried out on the downlink irradiance spectrum data and the uplink irradiance spectrum data, and corrected spectrum data are obtained;
Step S202, adopting a fluorescence extraction algorithm based on the Fraunhofer line depth principle to process the corrected spectrum data obtained in the step 201, and calculating apparent fluorescence emission intensities of characteristic points inside and outside an oxygen absorption wave band dark line;
step S203, based on a preset parameter adjustment rule, taking apparent fluorescence emission intensity as input, dynamically adjusting the width of a wave band window and weight parameters in the adopted fluorescence extraction algorithm, and extracting a final sunlight-induced chlorophyll fluorescence value.
Further, the method for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence, which is disclosed by the invention, comprises the following steps of:
Step S301, acquiring a canopy SIF value of the crop without water stress based on the step 2 as a reference canopy SIF value;
step S302, acquiring a SIF value of a canopy to be measured based on the step 2, and substituting the result into a preset formula for calculation, wherein the preset formula is as follows:
SIF well-watered is the SIF value of the canopy of the crop without water stress (mu W cm -2·mm-1·sr-1）;SIFtarget is the SIF value of the canopy of the crop to be tested (mu W cm -2·mm-1·sr-1), SIFWDI is the relative SIF water deficiency index;
In step S304, the calculated value is outputted as the relative SIF water deficiency index SIFWDI.
Further, the method for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence, which is disclosed by the invention, comprises the following steps of:
Step 401, constructing a regression analysis model by calculating a soil water deficit index SWDI relative to the SIF water deficit index SIFWDI and measured soil water data;
Step 402, a regression analysis model outputs a diagnosis report by establishing a mapping relation between a relative SIF water deficiency index SIFWDI and a soil water deficiency index SWDI, wherein the diagnosis report comprises a crop water stress grade, the crop water stress grade is used for representing a crop drought degree caused by water deficiency, the grade division of the crop drought degree is determined according to SIFWDI numerical values, SIFWDI <0 is no drought, 0 < SIFWDI <1 is light drought, 1 < SIFWDI <2 is medium drought, 2 < SIFWDI <4 is heavy drought, and SIFWDI is extreme drought;
step 403, determining the grade of the drought degree of the final crop of the crop according to the water stress grade of the crop in the diagnosis report.
Further, the method for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence, which is disclosed by the invention, comprises the following steps of:
step S501, monitoring time sequence change of the crop water stress level based on the crop water stress level in the diagnosis report output in the step S4, and activating an early warning mechanism and generating early warning information when the crop water stress level exceeds a preset threshold value in a plurality of continuous monitoring periods;
Step S502, packaging the early warning information generated in the step S501, the geographic position and the time stamp into a data packet, and transmitting the data packet to a cloud platform through an encryption communication protocol;
Step S503, after the cloud platform receives the data packet, highlighting the stressed area on the visual interface, and pushing an early warning notice to the binding terminal;
step S504, generating differentiated irrigation instructions based on the crop water stress level in the diagnosis report output in step S4, wherein the differentiated irrigation instructions comprise maintenance plans, water-saving irrigation or emergency irrigation schemes.
Further, the method for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence, which is disclosed by the invention, comprises the following steps of:
Step S505, after the irrigation instruction is executed, the original spectrum data of the crop canopy are collected again, and a new sunlight-induced chlorophyll fluorescence intensity value is calculated based on the collected data;
Step S506, combining the new sunlight-induced chlorophyll fluorescence intensity value with the soil moisture content record, and updating the parameters of the regression analysis model by adopting a sliding window algorithm;
Step S507, after verifying the accuracy of the regression analysis model, storing the updated data into a database.
Further, the method for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence, which is disclosed by the invention, comprises the following steps of:
Step 508, inputting the time sequence data of the relative SIF water deficiency index generated in the step 3 into a time sequence analysis model, and outputting an early abnormal signal;
Step 509, inputting the early abnormal signal into a mutation detection algorithm for time sequence mutation point analysis to obtain a mutation point positioning result;
Step 510, based on the mutation point positioning result, outputting early drought risk probability by calculating abnormal continuous intensity and trend change in a preset time window.
In a second aspect, the crop water stress diagnosis system based on sunlight-induced chlorophyll fluorescence provided by the invention is applied to the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, and comprises the following steps:
The data acquisition module is mounted on the remote sensing platform and is provided with a hyperspectral sensor for acquiring original spectrum data of crop canopy, wherein the original spectrum data comprises a downlink irradiance spectrum and an uplink radiance spectrum in an oxygen molecule A absorption band;
The fluorescence inversion module is in communication connection with the data acquisition module and is configured to calculate apparent reflectivity of an oxygen molecule A in an absorption band wave band based on downlink irradiance spectrum and uplink irradiance spectrum data and a fluorescence extraction algorithm based on a spectrum filling principle, and calculate a sunlight-induced chlorophyll fluorescence intensity SIF value of the wave band of 760nm serving as a canopy of the object;
The index generation module is in communication connection with the fluorescence inversion module and is configured to acquire the SIF value of the crop canopy without water stress in the current environment, acquire the SIF value of the crop canopy to be detected, and substitute the result into a preset formula to generate a relative SIF water deficiency index SIFWDI;
The regression diagnosis module is in communication connection with the index generation module and is configured to construct a regression analysis model relative to the SIF water deficit index SIFWDI and the soil water deficit index SWDI calculated based on measured soil water data, and output a diagnosis report by establishing a mapping relation between the relative SIF water deficit index SIFWDI and the soil water deficit index SWDI, wherein the diagnosis report comprises crop water stress grades, the crop water stress grades are used for representing the drought degree of crops caused by water deficit, the grade division of the drought degree of the crops is determined according to SIFWDI numerical values, SIFWDI <0 is no drought, 0 is less than or equal to SIFWDI <1 is light drought, 1 is less than or equal to SIFWDI <2 is medium drought, 2 is less than or equal to SIFWDI <4 is heavy drought, and SIFWDI is more than or equal to 4 is extreme drought;
The decision optimization module is in communication connection with the regression diagnosis module and is configured to generate a variable irrigation decision instruction and trigger early warning if judging that the crop water stress level exceeds a preset threshold based on the diagnosis report, and automatically feed back the relative SIF water deficiency index SIFWDI, the soil water deficiency index SWDI and the crop water stress level corresponding to the judgment as new data samples to the regression analysis model for realizing the self-adaptive optimization of the regression analysis model parameters.
The invention has the beneficial effects that:
The method has the advantages that the remote sensing monitoring method based on sunlight-induced chlorophyll fluorescence is used for nondestructively collecting crop canopy spectral data, a fluorescence extraction algorithm based on a spectrum filling principle is used for calculating a sunlight-induced chlorophyll fluorescence intensity SIF value to generate a relative SIF water deficiency index SIFWDI, traditional soil probe measurement is replaced, damage to crop roots in the installation process is avoided, high cost caused by intensive distribution is overcome, a diagnosis report is output by establishing a mapping relation between SIFWDI and the soil water deficiency index SWDI, early signals of photosynthesis inhibition are directly captured from a plant physiological level, the problem that soil water change is delayed from physiological response is solved, regression analysis models and self-adaptive optimization mechanisms are used for improving diagnosis precision and instantaneity, and finally accurate irrigation management is supported through variable irrigation decision and early warning triggering, so that the water utilization efficiency is improved, and the requirements of modern agriculture on low-cost, nondestructively, large-area and high-precision drought monitoring are met.
Drawings
For a clearer description of the invention, the drawings that are required to be used in the examples will be briefly described, it being obvious to a person skilled in the art that other drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flow chart of a crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence according to an embodiment of the present invention.
Fig. 2 is a graph showing the correlation between the Soil Water Deficit Index (SWDI) and the relative SIF water stress index (SIFWDI) according to an embodiment of the present invention.
Detailed Description
For the purposes of promoting an understanding of the principles of the invention, reference will now be made to the embodiments of the invention and the accompanying drawings, in which the invention will be described more fully hereinafter. It should be apparent that the described embodiments are merely module embodiments of the present invention and not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. The present invention provided by the embodiments of the present invention is described in detail below with reference to the accompanying drawings. For a better understanding of the present invention, the present invention is described in further detail below.
In a first aspect, the present invention provides a method for diagnosing crop water stress based on sunlight-induced chlorophyll fluorescence, comprising;
step S1, acquiring original spectrum data of a crop canopy without water stress and to be detected in the same environment through a hyperspectral sensor carried on a remote sensing platform, wherein the original spectrum data comprises a downlink irradiance spectrum and an uplink radiance spectrum in an oxygen molecule absorption band (760 nm);
S2, calculating apparent reflectivity of an oxygen molecule A in an absorption band wave band based on downlink irradiance spectrum data, uplink irradiance spectrum data and a fluorescence extraction algorithm based on a spectrum filling principle, and calculating a sunlight-induced chlorophyll fluorescence intensity SIF value of the wave band of 760nm serving as a canopy;
Step S3, taking the calculated SIF value of the crop canopy without water stress as a reference canopy SIF value, and simultaneously substituting the calculated SIF value of the crop canopy to be detected into a preset formula to generate a relative SIF water deficiency index SIFWDI;
S4, constructing a regression analysis model by using the relative SIF water deficit index SIFWDI and the soil water deficit index SWDI generated based on the measured soil water data, and outputting a diagnosis report by establishing a mapping relation between the relative SIF water deficit index SIFWDI and the soil water deficit index SWDI, wherein the diagnosis report comprises crop water stress grades;
And S5, based on the diagnosis report output by the step S4, if the crop water stress level exceeds the preset threshold, generating a variable irrigation decision instruction and triggering early warning, taking the relative SIF water deficiency index corresponding to the judgment and the crop water stress level judged at the time as new data samples, and automatically feeding back the new data samples to a regression analysis model for realizing the self-adaptive optimization of the regression analysis model parameters.
The crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence firstly realizes data acquisition through a step S1. Specifically, a hyperspectral sensor mounted on a remote sensing platform is used for collecting original spectrum data of crop canopy, and the data cover a downlink irradiance spectrum and an uplink radiance spectrum of an oxygen molecule A absorption band. The hyperspectral sensor is arranged at a fixed height above a crop canopy, the probe vertically points to the central area of the canopy, downlink irradiance and uplink radiance data are synchronously collected in a specified period of sunny weather, and the data are recorded and stored as continuous spectrum curves covering an oxygen absorption wave band. This step ensures that high quality spectral data is acquired, providing a basis for subsequent processing.
Step S2, processing the collected spectrum data to extract the SIF value of fluorescence intensity of sunlight-induced chlorophyll. The downlink irradiance spectrum and the uplink irradiance spectrum data are filtered and baseline corrected to eliminate noise and environmental interference. The corrected spectrum data is processed by adopting a fluorescence extraction algorithm based on the Fraunhofer line depth principle, the apparent fluorescence emission intensity of the characteristic points inside and outside the oxygen absorption wave band dark line is calculated, and finally the fluorescence intensity SIF value of sunlight-induced chlorophyll of the crop canopy-760 nm wave band is calculated. The method ensures the accurate extraction of fluorescent signals through a spectrum filling principle, and provides key input for water stress diagnosis.
Step S3 generates a relative SIF water deficit index SIFWDI for quantifying the degree of water stress. Taking the SIF value of the crop canopy without water stress as a reference, and simultaneously obtaining the SIF value of the crop canopy to be detected. Substituting the reference SIF value and the SIF value to be measured into a preset formula for calculation, and outputting a relative SIF water deficiency index SIFWDI based on the fluorescence intensity difference between the water stress free state and the state to be measured. The index directly reflects the water deficiency degree of crops and replaces the traditional soil probe measurement.
And S4, outputting a diagnosis report by using the regression analysis model. And constructing a regression analysis model by the relative SIF water deficit index SIFWDI and the soil water deficit index SWDI calculated by actually measured soil water data, and generating a diagnosis report by establishing a mapping relation between SIFWDI and the soil water deficit index SWDI. The diagnostic report includes crop water stress levels, which are classified into drought-free, light drought, medium drought, heavy drought and extreme drought according to SIFWDI values, for characterizing the degree of drought in crops caused by water deficit.
Step S5 performs decision and feedback optimization based on the diagnostic report. If the crop water stress level exceeds a preset threshold and the dominant factor is soil water deficiency, generating a variable irrigation decision instruction and triggering early warning, wherein the instruction comprises a maintenance plan, water-saving irrigation or emergency irrigation scheme. Meanwhile, the relative SIF water deficiency index SIFWDI and the crop water stress level corresponding to the judgment are used as new data samples and automatically fed back to the regression analysis model, so that the model parameter self-adaptive optimization is realized. The closed-loop feedback mechanism continuously improves the system precision by re-collecting data, calculating a new fluorescence value and combining with the soil moisture content record and adopting a sliding window algorithm, thereby ensuring the real-time performance and the accuracy of diagnosis. The whole method realizes nondestructive and efficient crop water stress monitoring and irrigation decision support through optical sensing and data processing fusion.
Specifically, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence comprises the following steps:
Step S101, installing spectrum sensing equipment at a fixed height above a crop canopy, and adjusting a probe to vertically point to a canopy central area;
step S102, synchronously acquiring downlink irradiance and uplink radiance data in a specified period of sunny weather by using a pre-installed spectrum sensing device;
step S103, the collected downlink irradiance and uplink irradiance data are recorded and stored in a local storage unit, and the data format is a continuous spectrum curve covering an oxygen absorption wave band.
The crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence comprises the following steps that step 1 relates to a data acquisition process. In step S101, the spectrum sensing device is installed at a fixed height above the canopy of the crop, the installation height is determined according to the crop growth characteristics and the remote sensing platform requirements, and is usually kept within a range of 1.5 to 2.5 meters above the canopy to minimize environmental interference, the probe is adjusted to be vertically directed to the central area of the canopy, and the optical path is ensured to be vertical to the surface of the canopy, so that the downlink irradiance and the uplink radiance data are accurately captured, and spectral distortion caused by angle deviation is avoided. In step S102, the pre-installed spectrum sensing equipment is used for synchronously collecting downlink irradiance and uplink radiance data in a period of 10:00 to 14:00 a day under a clear weather condition, wherein the period is selected to be maximized based on a solar altitude angle so as to reduce the influence of atmospheric scattering and shadow, improve the data quality, and the equipment is kept stable, avoids movement or vibration and ensures the spectrum continuity in the collecting process. In step S103, the collected downlink irradiance and uplink irradiance data are recorded in real time and stored in a local storage unit, the storage unit adopts a solid state disk or an embedded memory, the data format is a continuous spectrum curve covering an oxygen absorption band, the continuous spectrum curve comprises a band near 760nm of an oxygen molecule A absorption band, the spectral resolution is better than 1nm so as to ensure the accuracy of subsequent fluorescence extraction, and the stored data are provided with a time stamp and geographical position information, so that the tracing and the integrated processing are facilitated. The steps are logically connected, wherein a hardware foundation is established in S101, acquisition conditions are optimized in S102 to acquire original data, and S103 ensures complete storage of the data and provides reliable input for subsequent spectrum processing and fluorescence inversion. The whole data acquisition process aims at minimizing external interference, ensuring that spectrum data represent the true state of crop canopy and supporting the accuracy of water stress diagnosis.
Specifically, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence of the present invention, step 2 includes:
Step S201, filtering and baseline correction are carried out on the downlink irradiance spectrum data and the uplink irradiance spectrum data, and corrected spectrum data are obtained;
Step S202, adopting a fluorescence extraction algorithm based on the Fraunhofer line depth principle to process the corrected spectrum data obtained in the step 201, and calculating apparent fluorescence emission intensities of characteristic points inside and outside an oxygen absorption wave band dark line;
step S203, based on a preset parameter adjustment rule, taking apparent fluorescence emission intensity as input, dynamically adjusting the width of a wave band window and weight parameters in the adopted fluorescence extraction algorithm, and extracting a final sunlight-induced chlorophyll fluorescence value.
In the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, the step 2 involves the processing of spectrum data and fluorescence extraction, and specifically comprises three sub-steps. Step S201, filtering and baseline correction are carried out on the downlink irradiance spectrum data and the uplink irradiance spectrum data to eliminate environmental noise and instrument errors, a digital filtering algorithm such as moving average or Gaussian filtering is adopted for filtering, random fluctuation is smoothed, baseline correction is carried out by fitting a spectrum baseline and subtracting an offset, real spectrum characteristics are restored, and corrected spectrum data are output to provide clean input for subsequent analysis. Step S202 adopts a fluorescence extraction algorithm based on the Fraunhofer line depth principle to process corrected spectrum data, the algorithm focuses on the oxygen absorption wave band such as around 760nm, the difference of the radiance of characteristic points inside and outside a dark line is calculated, the dark line corresponds to absorption valley points, the dark line corresponds to continuous spectrum points, and the apparent fluorescence emission intensity of the points is compared to initially estimate a sunlight-induced chlorophyll fluorescence signal. Step S203 is based on a preset parameter adjustment rule, apparent fluorescence emission intensity is used as input, the width of a wave band window and weight parameters in a fluorescence extraction algorithm are dynamically adjusted, the width of the wave band window defines a spectrum calculation range, the weight parameters optimize different wave band contribution ratios, a final sunlight-induced chlorophyll fluorescence value is extracted through an iterative optimization process and is used for subsequent water stress index calculation, the logic of the whole step 2 is consistent, from data preprocessing to fluorescence extraction, gradual refinement processing is carried out, the accuracy and the reliability of a fluorescence signal are ensured, and the accuracy of water stress diagnosis is supported.
Specifically, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence of the present invention, step 3 includes:
Step S301, acquiring a canopy SIF value of the crop without water stress based on the step 2 as a reference canopy SIF value;
step S302, acquiring a SIF value of a canopy to be measured based on the step 2, and substituting the result into a preset formula for calculation, wherein the preset formula is as follows:
SIF well-watered SIF value of canopy of crop without water stress (μW cm -2·mm-1·sr-1）;SIFtarget: SIF value of canopy of crop to be measured (μW cm -2·mm-1·sr-1). SIFWDI: relative SIF water deficiency index;
In step S304, the calculated value is outputted as the relative SIF water deficiency index SIFWDI.
In the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, the step 3 involves generating a relative SIF water deficiency index SIFWDI, and specifically comprises three sub-steps. Step S301 is to obtain a water stress free crop canopy SIF value as a reference canopy SIF value, wherein the reference SIF value represents typical sunlight-induced chlorophyll fluorescence intensity of a healthy crop canopy, and provides a benchmark for subsequent calculation. Step S302, based on the SIF value of the canopy to be measured obtained in the step 2, substituting the reference SIF value and the SIF value to be measured into a preset formula for calculation, wherein the preset formula is used for quantifying the water deficiency degree by comparing the fluorescence intensity difference between the water-free stress state and the state to be measured, the calculation process focuses on the relative change of the fluorescence signal, avoids absolute value dependence, and outputs a preliminary index result. Step S304 is to output the calculated value as a relative SIF water deficit index SIFWDI which directly reflects the crop water stress level for the generation of a subsequent diagnosis report, and the logic of the whole step 3 is coherent, and index calculation is retrieved from data, so that the index is ensured to be based on an actual physiological signal, and accurate assessment of water stress is supported.
Specifically, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence of the present invention, step 4 includes:
Step 401, constructing a regression analysis model by calculating a soil water deficit index SWDI relative to the SIF water deficit index SIFWDI and measured soil water data;
Step 402, a regression analysis model outputs a diagnosis report by establishing a mapping relation between a relative SIF water deficiency index SIFWDI and a soil water deficiency index SWDI, wherein the diagnosis report comprises a crop water stress grade, the crop water stress grade is used for representing a crop drought degree caused by water deficiency, the grade division of the crop drought degree is determined according to SIFWDI numerical values, SIFWDI <0 is no drought, 0 < SIFWDI <1 is light drought, 1 < SIFWDI <2 is medium drought, 2 < SIFWDI <4 is heavy drought, and SIFWDI is extreme drought;
step 403, determining the grade of the drought degree of the final crop of the crop according to the water stress grade of the crop in the diagnosis report.
In the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, the step 4 relates to the generation of a diagnosis report and the determination of drought grade, and specifically comprises three sub-steps. In step 401, a regression analysis model is constructed by using the SIF water deficit index SIFWDI and the soil water deficit index SWDI calculated by actually measured soil water data, the regression analysis model adopts a linear or nonlinear regression algorithm, a mapping function is obtained by training a historical data set, the historical data comprises SIFWDI values of different crop varieties in a plurality of growing seasons and corresponding soil water deficit index SWDI values, a model input layer receives SIFWDI and soil water data, and an output layer predicts SWDI values to realize conversion from an optical signal to a soil water state. In step 402, the regression analysis model outputs a diagnosis report by establishing a mapping relation between a relative SIF water deficiency index SIFWDI and a soil water deficiency index SWDI, wherein the diagnosis report comprises crop water stress grades, the mapping relation is based on a least square method or machine learning optimization parameter, so that SIFWDI values and SWDI values are in negative correlation, that is, SIFWDI value increase represents water stress aggravation, the crop water stress grades are used for representing the drought degree of crops caused by water deficiency, the grading is determined according to SIFWDI numerical values, SIFWDI <0 is no drought, 0 is less than SIFWDI <1 is light drought, 1 is less than SIFWDI <2 is medium drought, 2 is less than SIFWDI <4 is heavy drought, SIFWDI is more than 4 is special drought, and the grading is obtained based on field test data statistics and reflects the quantitative relation of crop physiological response and water deficiency. Step 403, determining the grade of the drought degree of the final crop of the crop according to the water stress grade of the crop in the diagnosis report, outputting the diagnosis report in a digital or class form, automatically matching the grade description by a system, for example, when SIFWDI is 1.5, triggering corresponding early warning and irrigation decisions corresponding to the drought grade, and ensuring that the diagnosis is based on multi-source data fusion from data input and model processing to result output according to the logic continuity of the whole step 4, thereby improving the accuracy and reliability of water stress assessment and supporting agricultural management decisions.
Specifically, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence of the present invention, step 5 includes:
step S501, monitoring time sequence change of the crop water stress level based on the crop water stress level in the diagnosis report output in the step S4, and activating an early warning mechanism and generating early warning information when the crop water stress level exceeds a preset threshold value in a plurality of continuous monitoring periods;
Step S502, packaging the early warning information generated in the step S501, the geographic position and the time stamp into a data packet, and transmitting the data packet to a cloud platform through an encryption communication protocol;
Step S503, after the cloud platform receives the data packet, highlighting the stressed area on the visual interface, and pushing an early warning notice to the binding terminal;
step S504, generating differentiated irrigation instructions based on the crop water stress level in the diagnosis report output in step S4, wherein the differentiated irrigation instructions comprise maintenance plans, water-saving irrigation or emergency irrigation schemes.
In the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, the step 5 involves early warning generation and irrigation decision-making, and specifically comprises four sub-steps. Step S501 is based on the crop water stress level in the diagnosis report output in step S4, the time sequence change of the crop water stress level is monitored, the level fluctuation is tracked by adopting a time sequence analysis algorithm, and when the crop water stress level exceeds a preset threshold value in a plurality of continuous monitoring periods, an early warning mechanism is activated and early warning information is generated, wherein the early warning information comprises stress level values, change trend and duration time and is used for indicating the severity of water deficiency. Step S502 encapsulates the early warning information generated in step S501, the geographic position coordinates and the time stamp into a structured data packet, the data packet is organized in a JSON or XML format, and the data packet is transmitted to a cloud platform through an encrypted communication protocol such as TLS or SSL, so that the safety and the integrity of data transmission are ensured. In step S503, after the cloud platform receives the data packet, the early warning information is parsed and the stressed area is highlighted on the visual interface, the visual interface integrates the geographic information system map, the stress intensity is rendered by the color gradient, and meanwhile, the early warning notification is pushed to the binding terminal such as the mobile phone APP or the monitoring center, and the notification content contains the stress position, the grade and the recommended measures. Step S504 generates a differentiated irrigation instruction based on the crop water stress grade in the diagnosis report output in step S4, the instruction generation module selects a corresponding strategy according to the grade range, namely, outputting a maintenance plan instruction when no drought or light drought exists, outputting a water-saving irrigation instruction when the drought exists, such as reducing irrigation amount, outputting an emergency irrigation instruction when the drought exists or the drought exists, such as increasing irrigation frequency, and issuing the instruction to an irrigation execution device through the cloud platform. The logic of the whole step 5 is coherent, and automatic response is realized from monitoring and early warning to instruction generation, so that timely intervention of water stress is ensured, and healthy growth of crops is supported.
Specifically, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence of the present invention, step 5 further comprises:
Step S505, after the irrigation instruction is executed, the original spectrum data of the crop canopy are collected again, and a new sunlight-induced chlorophyll fluorescence intensity value is calculated based on the collected data;
Step S506, combining the new sunlight-induced chlorophyll fluorescence intensity value with the soil moisture content record, and updating the parameters of the regression analysis model by adopting a sliding window algorithm;
Step S507, after verifying the accuracy of the regression analysis model, storing the updated data into a database.
Detailed description of the technical solution
In the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, the step 5 further comprises three sub-steps for performing data updating and model optimization after irrigation. Step S505, after an irrigation instruction is executed, collecting original spectrum data of a crop canopy again, specifically collecting a downlink irradiance spectrum and an uplink radiance spectrum of an oxygen molecule A absorption band under the same condition through a hyperspectral sensor carried on a remote sensing platform, calculating apparent reflectivity of an oxygen absorption band by adopting a fluorescence extraction algorithm based on a spectrum filling principle based on the collected spectrum data, and calculating a fluorescence intensity SIF value of sunlight-induced chlorophyll of the crop canopy-760 nm band, wherein the process ensures that a latest fluorescence signal after irrigation is obtained and changes of the moisture state of the crop are reflected.
Step S506, combining the new fluorescence intensity value of sunlight-induced chlorophyll with the soil moisture content record, adopting a sliding window algorithm to process time sequence data, setting the size of the sliding window according to the data acquisition frequency and the crop growth period, extracting the correlation characteristic of the fluorescence intensity and the soil moisture content data in the window by the algorithm, and dynamically updating the coefficient and the mapping relation of a regression analysis model to adapt the model to new data distribution, thereby improving the diagnosis accuracy.
Step S507, verifying the accuracy of the regression analysis model, wherein the verification method comprises the steps of calculating a prediction error, a correlation coefficient or a cross verification index, storing updated reference data and model parameters into a database after the accuracy reaches the standard, and supporting quick inquiry and subsequent analysis by adopting a relational or time sequence database structure to complete closed-loop management of the data. The additional process logic of the whole step 5 is coherent, namely, new data are acquired in S505, a model is processed and updated in S506, and verification and storage in S507 are carried out, so that continuous optimization of the system is ensured, and the reliability and instantaneity of water stress diagnosis are enhanced.
Specifically, the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence of the present invention, step 5 further comprises:
Step 508, inputting the time sequence data of the relative SIF water deficiency index generated in the step 3 into a time sequence analysis model, and outputting an early abnormal signal;
Step 509, inputting the early abnormal signal into a mutation detection algorithm for time sequence mutation point analysis to obtain a mutation point positioning result;
Step 510, based on the mutation point positioning result, outputting early drought risk probability by calculating abnormal continuous intensity and trend change in a preset time window.
In the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, the step 5 also comprises three sub-steps for early abnormal signal detection and drought risk probability assessment. Step 508, based on the time sequence data of the relative SIF water deficiency index generated in step S3, inputting the time sequence data into a time sequence analysis model, and outputting an early abnormal signal, wherein the time sequence analysis model adopts a time sequence decomposition algorithm to separate a trend component, a season component and a residual component, and identifies an abnormal point deviating from a normal mode by monitoring the fluctuation amplitude and the frequency of the residual component, and the early abnormal signal is expressed as sudden rise or fall of a plant physiological water stress index at a continuous time point and indicates the potential occurrence of water stress.
Step 509 inputs the early abnormal signal into a mutation detection algorithm to perform time sequence mutation point analysis to obtain a mutation point positioning result, the mutation detection algorithm calculates the statistical characteristic change of time sequence data based on an accumulation and control chart or a Bayesian change point detection method, when the data distribution parameters such as mean value or variance change significantly, the data distribution parameters are marked as mutation points, and the mutation point positioning result provides a specific time position of occurrence of the abnormal signal and is used for accurately positioning the starting moment of water stress.
Step 510, based on the mutation point positioning result, outputting early drought risk probability by calculating abnormal continuous intensity and trend change in a preset time window, wherein the preset time window is set according to a crop growth period and a monitoring frequency, the abnormal continuous intensity is obtained by integrating an abnormal signal amplitude over time window, the trend change is quantified by adopting a linear regression analysis slope, a probability value is calculated by combining the continuous intensity and the trend direction, the early drought risk probability is expressed as a numerical value between 0 and 1, and the higher the probability is, the greater the drought occurrence probability is. The additional process logic of the whole step 5 is coherent, namely S508 detects abnormal signals, S509 locates mutation points, S510 evaluates risk probability, realizes closed loop from data monitoring to risk quantification, and supports early warning and intervention decision.
In a second aspect, the crop water stress diagnosis system based on sunlight-induced chlorophyll fluorescence provided by the invention is applied to the crop water stress diagnosis method based on sunlight-induced chlorophyll fluorescence, and comprises the following steps:
The data acquisition module is mounted on the remote sensing platform and is provided with a hyperspectral sensor for acquiring original spectrum data of crop canopy, wherein the original spectrum data comprises a downlink irradiance spectrum and an uplink radiance spectrum in an oxygen molecule A absorption band;
The fluorescence inversion module is in communication connection with the data acquisition module and is configured to calculate apparent reflectivity of an oxygen molecule A in an absorption band wave band based on downlink irradiance spectrum and uplink irradiance spectrum data and a fluorescence extraction algorithm based on a spectrum filling principle, and calculate a sunlight-induced chlorophyll fluorescence intensity SIF value of the wave band of 760nm serving as a canopy of the object;
The index generation module is in communication connection with the fluorescence inversion module and is configured to acquire the SIF value of the crop canopy without water stress in the current environment, acquire the SIF value of the crop canopy to be detected, and substitute the result into a preset formula to generate a relative SIF water deficiency index SIFWDI: ;
The regression diagnosis module is in communication connection with the index generation module and is configured to input the relative SIF water deficiency index SIFWDI and the actually measured soil water data into a regression analysis model constructed based on historical data together, and output a diagnosis report by establishing a mapping relation between the relative SIF water deficiency index SIFWDI and the soil water deficiency index SWDI, wherein the diagnosis report comprises a crop water stress grade, the crop water stress grade is used for representing the drought degree of crops caused by water deficiency, the grade division of the drought degree of the crops is determined according to SIFWDI numerical values, wherein SIFWDI <0 is no drought, SIFWDI <1 is light drought, SIFWDI <2 is medium drought, SIFWDI <4 is heavy drought, and SIFWDI is special drought;
The decision optimization module is in communication connection with the regression diagnosis module and is configured to generate a variable irrigation decision instruction and trigger early warning if the crop water stress level exceeds a preset threshold and the dominant factor is soil water deficiency based on the diagnosis report, automatically feed back the relative SIF water deficiency index SIFWDI corresponding to the judgment and the crop water stress level judged by the judgment into the regression analysis model as new data samples and realize the self-adaptive optimization of the regression analysis model parameters.
The embodiment of the invention is as follows:
In order to verify the applicability of the present invention, winter wheat in a certain area was selected as the test crop for the test. Three water treatments are set for full irrigation, namely 75% of field water holding capacity is used as the lower limit of irrigation, 95% of field water holding capacity is used as the upper limit of irrigation, 60-70% of full irrigation water holding capacity is used as the slight deficient irrigation, and 50-60% of full irrigation water holding capacity is used as the moderate deficient irrigation. And (5) respectively irrigating 40mm water after the winter wheat is sown and enters a green-returning period to serve as seedling emergence water and green-returning water. Drought treatment begins with the heading stage of the node.
And (3) observing the downlink irradiance and the uplink irradiance of the canopy of the vegetation in real time based on a sunlight-induced chlorophyll fluorescence Spectrometer (SIF), and calculating the sunlight-induced chlorophyll fluorescence index of the vegetation through a 3FLD algorithm. And selecting a sunny and cloudless weather after drought treatment for 10 days, and calculating SIF index average values of different irrigation treatment cells from 10:00 am to 14:00 pm.
And synchronously calculating the average soil moisture content of the period according to the soil moisture probe.
The calculated Soil Water Deficit Index (SWDI) and the calculated SIF water stress index (SIFWDI) of the sunlight-induced chlorophyll fluorescence index have a strong linear relationship (SIFWDI = -0.4045swdi, r2= 0.7427) (fig. 2). Further, according to the drought grades classified by SWDI values, the SIFWDI values may also be classified into corresponding drought grades (table 1), i.e., SIFWDI values corresponding to extreme drought, heavy drought, medium drought, light drought and no drought are >4, 2 to 4, 1 to 2, 0 to 1 and <0, respectively. Drought early warning can be performed according to the monitored SIF index in the future.
Drought rating of SIFWDI value scale for the SWDI values of Table 1
According to the technical scheme, the remote sensing monitoring method based on sunlight-induced chlorophyll fluorescence solves the problems that existing crop drought diagnosis technology based on soil water deficiency index relies on field physical probe installation, is severely interfered by soil space heterogeneity and cannot directly capture photosynthesis inhibition early signals from a plant physiological layer. Firstly, original spectrum data of crop canopy is collected through a hyperspectral sensor carried on a remote sensing platform, wherein the original spectrum data comprises a downlink irradiance spectrum and an uplink irradiance spectrum of an oxygen molecule A absorption band, damage to the crop root system layer caused by physical probe arrangement in the field is avoided, and lossless data collection is realized. And secondly, calculating a fluorescence intensity SIF value of sunlight-induced chlorophyll based on a fluorescence extraction algorithm of a spectrum filling principle, wherein the SIF value directly reflects photochemical efficiency of a crop photosynthetic mechanism, so that early photosynthesis inhibition signals caused by water stress are captured from a plant physiological level, and the limitation that soil water change lags behind physiological response is overcome. Then, a relative SIF water deficit index SIFWDI is generated, the water stress degree is quantified by comparing the fluorescence intensity difference between the water stress free state and the state to be measured, the traditional soil probe measurement is replaced, and the high cost of densely distributed points is reduced. Furthermore, SIFWDI and measured soil moisture data are input into a regression analysis model together, a diagnosis report is output by establishing a mapping relation, the diagnosis report comprises crop water stress grades, and the diagnosis precision is improved by combining multi-source data. Finally, triggering early warning and generating irrigation decisions based on the diagnosis report, updating reference data and model parameters through a feedback mechanism, realizing self-adaptive optimization, supporting real-time early warning and accurate irrigation, and meeting the requirements of modern agriculture on nondestructive, real-time and high-precision drought monitoring. The whole scheme realizes the closed loop from the direct monitoring of plant physiological signals to the water stress diagnosis through the fusion of optical remote sensing and data processing, and effectively solves the problems of high cost, limited monitoring range, monitoring lag and the like in the prior art.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511745465.4A CN121186000B (en) | 2025-11-26 | 2025-11-26 | A Method and System for Diagnosing Crop Water Stress Based on Sunlight-Induced Chlorophyll Fluorescence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511745465.4A CN121186000B (en) | 2025-11-26 | 2025-11-26 | A Method and System for Diagnosing Crop Water Stress Based on Sunlight-Induced Chlorophyll Fluorescence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN121186000A true CN121186000A (en) | 2025-12-23 |
| CN121186000B CN121186000B (en) | 2026-02-03 |
Family
ID=98216294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511745465.4A Active CN121186000B (en) | 2025-11-26 | 2025-11-26 | A Method and System for Diagnosing Crop Water Stress Based on Sunlight-Induced Chlorophyll Fluorescence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN121186000B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278503A (en) * | 2013-04-25 | 2013-09-04 | 浙江大学 | Multi-sensor technology-based grape water stress diagnosis method and system therefor |
| US20190003972A1 (en) * | 2017-06-30 | 2019-01-03 | Ut-Battelle, Llc | System and method for measuring sun-induced chlorophyll fluorescence |
| CN111398227A (en) * | 2020-03-18 | 2020-07-10 | 浙江大学 | Sunlight-induced Chlorophyll Fluorescence Measurement System Applicable to Observation of Crop Whole Growth Period |
| CN111638195A (en) * | 2020-05-12 | 2020-09-08 | 中国科学院空天信息创新研究院 | Drought monitoring method and device |
| CN115830458A (en) * | 2023-02-09 | 2023-03-21 | 中关村睿宸卫星创新应用研究院 | Method and device for determining farmland irrigation frequency based on sunlight-induced chlorophyll fluorescence |
| CN117408530A (en) * | 2023-10-26 | 2024-01-16 | 扬州大学 | A rice drought monitoring method considering the nonlinear relationship between chlorophyll fluorescence and total primary productivity |
-
2025
- 2025-11-26 CN CN202511745465.4A patent/CN121186000B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278503A (en) * | 2013-04-25 | 2013-09-04 | 浙江大学 | Multi-sensor technology-based grape water stress diagnosis method and system therefor |
| US20190003972A1 (en) * | 2017-06-30 | 2019-01-03 | Ut-Battelle, Llc | System and method for measuring sun-induced chlorophyll fluorescence |
| CN111398227A (en) * | 2020-03-18 | 2020-07-10 | 浙江大学 | Sunlight-induced Chlorophyll Fluorescence Measurement System Applicable to Observation of Crop Whole Growth Period |
| CN111638195A (en) * | 2020-05-12 | 2020-09-08 | 中国科学院空天信息创新研究院 | Drought monitoring method and device |
| CN115830458A (en) * | 2023-02-09 | 2023-03-21 | 中关村睿宸卫星创新应用研究院 | Method and device for determining farmland irrigation frequency based on sunlight-induced chlorophyll fluorescence |
| CN117408530A (en) * | 2023-10-26 | 2024-01-16 | 扬州大学 | A rice drought monitoring method considering the nonlinear relationship between chlorophyll fluorescence and total primary productivity |
Non-Patent Citations (1)
| Title |
|---|
| 吴泽棉 等: "基于土壤水分的农业干旱监测研究进展", 《地理科学进展》, vol. 39, no. 10, 31 October 2020 (2020-10-31), pages 1758 - 1769 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN121186000B (en) | 2026-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117455062A (en) | A crop yield prediction algorithm based on multi-source heterogeneous agricultural data | |
| CN110956381A (en) | Remote agricultural information intelligent analysis system and agricultural environment regulation and control method | |
| CN103278503B (en) | Multi-sensor technology-based grape water stress diagnosis method and system therefor | |
| CN118411601B (en) | A vegetation index prediction method for crops | |
| CN118058178A (en) | Intelligent irrigation control method and system for rice fields based on cloud service platform | |
| CN120373776B (en) | A carbon emission monitoring method and system based on agricultural carbon neutrality | |
| CN118592313A (en) | An irrigation system that automatically adjusts the amount of rainwater collected from corn for irrigation | |
| CN112819227A (en) | County scale winter wheat yield per unit prediction method and system | |
| CN119247517A (en) | A spatiotemporal prediction method for rainfall kinetic energy based on dual-polarization weather radar observation parameters | |
| CN119444477A (en) | A smart agriculture method and system based on Internet of Things and artificial intelligence | |
| CN120450393B (en) | A Precision Management Method for Agricultural Planting Based on Multi-Source Data Fusion | |
| CN121186000B (en) | A Method and System for Diagnosing Crop Water Stress Based on Sunlight-Induced Chlorophyll Fluorescence | |
| CN120494761B (en) | Remote monitoring and managing rice seedling raising irrigation plant protection system, computer equipment and medium | |
| CN121094423A (en) | Multi-source sensing data-driven method for irrigation district water demand prediction and precision water allocation | |
| CN120780070A (en) | Intelligent detection and regulation method based on planting environment of traditional Chinese medicinal materials | |
| CN119942445A (en) | A high-yield and high-efficiency rapeseed cultivation integrated processing method and system | |
| Xu et al. | Considering different water supplies can improve the accuracyof the WOFOST crop model and remote sensing assimilation in predicting wheat yield | |
| CN118940961A (en) | Vineyard soil microbial control analysis method and system based on digital twin | |
| CN119310143A (en) | Automatic management method of soil moisture monitoring sensor combined with Internet of Things technology | |
| CN117849040A (en) | A non-destructive monitoring method for tea tree biomass integrating multiple types of hyperspectral indices | |
| CN109141371B (en) | Winter wheat disaster identification method, device and equipment | |
| CN119580129B (en) | A sugarcane growth monitoring and evaluation device based on multispectral imaging | |
| CN120597225B (en) | Method and system for constructing rice growth model based on salinity stress | |
| CN120873371B (en) | A comprehensive monitoring system and method for forest-based health and wellness environments | |
| Wang et al. | Machine learning-based inversion and sensitivity analysis of soil moisture in Hemerocallis cultivation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |