A Big Data-Based Agricultural Environmental Monitoring Method and System

Abstract

This application discloses a big data-based agricultural environmental monitoring method and system for wheat growth monitoring, relating to the field of agricultural environmental monitoring, including: dividing the monitoring area into time zones of equal size according to size and time; collecting leaf area index time series {LAI} ij} and wheat ear number time series {EPN ij The Mann-Kendall trend test was used to perform significance tests, and the test results were denoted as Trend. LAI and Trend EPN Perform rank transformation to obtain the rank value sequence {RLAI}. ij} and {REPN ij The correlation coefficient ρ is calculated using the Spearman rank correlation coefficient algorithm. s Nonlinear fitting was performed using the Gompertz function to obtain the growth rate parameter b and the maximum number of wheat ears K; Trend LAI Trend EPN , ρ s Using b and K as inputs, a weighted average algorithm is used to calculate wheat growth, yielding an evaluation index reflecting crop growth. Addressing the low accuracy of existing wheat growth monitoring technologies, this application combines the weights of various indicators to calculate a comprehensive evaluation index reflecting wheat growth, thus improving monitoring accuracy.

Description

Technical Field

[0001] This application relates to the field of agricultural environmental monitoring, and in particular to an agricultural environmental monitoring method and system based on big data. Background Technology

[0002] Wheat growth is easily affected by environmental factors such as light, temperature, and water, and is also subject to threats such as pests, diseases, and natural disasters, resulting in significant instability in wheat yield and quality. Therefore, timely and accurate monitoring of wheat growth and development is of great importance for agricultural production management and agricultural product trade decisions.

[0003] In recent years, with the rapid development of modern information technologies such as 3S (RS, GIS, GPS), the Internet of Things, and artificial intelligence, precision agriculture has ushered in new development opportunities. By deploying various sensors in the fields, environmental parameters and growth indicators during crop growth can be collected in real time. Big data analysis, deep learning, and other technologies can then be used to build agricultural monitoring and early warning models, providing intelligent decision support for agricultural production. Particularly in wheat growth monitoring, scholars both domestically and internationally have conducted extensive and fruitful research, providing scientific and technological support for increasing wheat yield and improving its quality.

[0004] However, several problems remain to be addressed in wheat growth monitoring. First, limited by monitoring methods and coverage, most studies focus on critical growth stages of wheat, lacking continuous monitoring data throughout the entire growth period, making it difficult to accurately grasp the dynamic changes in wheat growth and development. Second, most studies emphasize the analysis of a single growth indicator, such as leaf area index or vegetation index, neglecting the intrinsic relationships between multiple indicators, leading to biased monitoring results. Third, due to differences in wheat varieties, planting systems, and site conditions, wheat growth and development exhibit significant spatiotemporal variability in different regions. Using a uniform monitoring model and threshold standards often fails to meet the needs of refined management at the regional scale. Summary of the Invention

[0005] To address the problem of low accuracy in wheat growth monitoring in existing technologies, this application provides a big data-based agricultural environment monitoring method. By dividing the monitoring area into multiple sub-regions, data such as leaf area index and wheat ear number are collected in each sub-region. Statistical methods such as Mann-Kendall trend test, Spearman rank correlation analysis, and Gompertz growth model fitting are used to analyze and model the data. Finally, by combining the weights of each indicator, a comprehensive evaluation index reflecting wheat growth is calculated, thereby improving monitoring accuracy.

[0006] The purpose of this application is achieved through the following technical solution.

[0007] One aspect of this application provides a big data-based agricultural environment monitoring method for wheat growth monitoring, comprising: determining a target agricultural environment monitoring area as the target monitoring area; dividing the target monitoring area into n equally sized monitoring sub-areas using a pre-set grid size; determining the monitoring time of each monitoring sub-area as the target time area; dividing the target time area into m sub-time areas using equal time intervals; and for each monitoring sub-area, collecting leaf area index and number of wheat ears per unit area within the corresponding sub-time area to obtain a leaf area index time series {LAI}. ij} and wheat ear number time series {EPN ij}; For the leaf area index time series {LAI ij} and wheat ear number time series {EPN ij The Mann-Kendall trend test was used to determine the significance of leaf area and ear number data. At a given significance level α, the absolute value of the Mann-Kendall statistic Z, |Z|, is greater than the critical value Z. (1-α / 2) When a significant monotonic trend is observed in the corresponding indicator, the test results are recorded as Trend. LAI and Trend EPN ; respectively for the leaf area index time series {LAI ij} and wheat ear number time series {EPN ij}, perform rank transformation to obtain the rank value sequence {RLAI} ij} and {REPN ij The Spearman rank correlation coefficient algorithm is used to calculate the rank value sequence {RLAI}. ij} and {REPN ij The correlation coefficient ρ between} s ; the time series data of wheat ear count {EPN ij Using the data as input, a nonlinear fitting was performed using the Gompertz function to obtain the wheat ear number growth curve model. This model includes the growth rate parameter b and the maximum number of wheat ears K. The leaf area index trend test results were then used. LAI Trend test results for the number of wheat ears EPN Correlation coefficient ρ s The growth rate parameter b and the maximum number of wheat ears K are used as inputs. The weighted average algorithm is used to calculate the wheat growth status and obtain the evaluation index reflecting the crop growth status.

[0008] Furthermore, the correlation coefficient ρ is calculated. s The formula is as follows:

[0009] in, The standard score represents the rank value of the leaf area index at the j-th time point in the i-th monitoring sub-region; mean(R LAI* std(R) represents the overall mean of the leaf area index rank values ​​at all time points across all monitored sub-regions; LAI* ) represents the overall standard deviation of the leaf area index rank values ​​at all time points across all monitored sub-regions;

[0010] The standard score representing the rank of the number of wheat ears at the j-th time point in the i-th monitoring sub-region; mean(R EPN* ) and std(R EPN* ) represent the population mean and population standard deviation of the rank values ​​of wheat ear count at all time points in all monitored sub-regions, respectively; Represents the time weight at time point j, satisfying Represents the anomaly weight of the i-th monitoring sub-region, satisfying

[0011] ΔLAI i =mean(LAI i* )-mean(LAI ** ), representing the deviation of the mean leaf area index (LAI) of the i-th monitoring sub-region from the overall mean; mean(LAI) i* () represents the mean of the raw leaf area index values ​​within the i-th monitoring sub-region; mean(LAI) ** ) represents the overall mean of the raw leaf area index values ​​at all time points across all monitored sub-regions; ΔEPN i =mean(EPN) i* )-mean(EPN ** ), representing the deviation of the mean number of wheat ears in the i-th monitoring sub-region from the overall mean; mean(EPN) i* () represents the mean of the original number of wheat ears in the i-th monitoring sub-region; mean(EPN) ** ) represents the overall mean of the original values ​​of the number of wheat ears at all time points in all monitored sub-regions.

[0012] Furthermore, nonlinear fitting is performed using the Gompertz function, which is expressed as follows: EPN(t)=K×exp{-exp[α-(b T ×∑GDD(t)+b P ×∑Prec(t))]};where, EPN(t) represents the predicted number of wheat ears at time t; K represents the theoretical maximum number of wheat ears, determined by genetic factors; a is a constant related to the initial number of wheat ears EPN(0), satisfying b T and b PThese are the sensitivity parameters of growth rate to temperature and precipitation, respectively; ∑GDD(t) represents the accumulated active temperature from sowing to time t, Growing Degree Days, which is calculated using the following formula: Among them, T max (t k ) and T min (t k T represents the daily maximum and minimum temperatures on day k, respectively. base The baseline temperature for wheat growth and development is usually taken as 10℃. ∑Prec(t) represents the cumulative precipitation from sowing to time t, and its calculation formula is: Where Prec(t) k ) represents the daily precipitation on day k.

[0013] Wherein, K represents the theoretical maximum value of the number of wheat ears, and K represents the maximum possible value of the number of ears per unit area of ​​wheat under ideal conditions. This parameter is mainly determined by the genetic characteristics of wheat varieties and is not significantly related to environmental factors. The K values ​​of different varieties vary greatly, reflecting the ear number potential of the variety. K is one of the main parameters to be fitted when fitting the model. EPN(0) represents the number of ears per unit area of ​​wheat in the early stage of growth (t=0). This value is usually very small and can be regarded as a constant. The value of EPN(0) is related to factors such as sowing density and emergence rate. Given EPN(0), the value of parameter a can be estimated, and vice versa. ∑GDD(t) represents the cumulative active temperature (Growing Degree Days) from sowing (t=0) to time t. Active temperature is an important indicator for describing the growth and development process of crops and is closely related to the phenological development rate of wheat. In the Gompertz model, the parameter b_T characterizes the degree of response of the number of ears to ∑GDD(t). The larger the b_T value, the more sensitive the number of ears is to temperature, and an increase in accumulated temperature will significantly promote an increase in the number of ears; conversely, the smaller the b_T value, the less sensitive the number of ears is to temperature.

[0014] Furthermore, the rank value sequence {RLAI} is obtained. ij} and {REPN ij}, including: for the i-th monitoring sub-region i = 1, 2, ..., n, the corresponding leaf area index time series {LAI} ij}j=1,2,....,m are arranged in ascending order to obtain the sorted sequence {SLAI} ij}, among which, SLAI ij LAI ij In {LAI ij The index in} ranges from 1 to m; based on the sorted sequence {SLAI ij} Calculate the rank value RLAI of the leaf area index at the j-th time point for the i-th monitoring sub-region. ij : Repeat this process for the i-th monitoring sub-region (i = 1, 2, ..., n), and record the corresponding wheat ear count time series {EPN}. ij}j=1,2,....,m are arranged in ascending order to obtain the sorted sequence {SEPN ij}, where SEPN ij Indicates EPN ij In {EPN ij The index in} ranges from 1 to m; based on the sorted sequence {SEPN ij} Calculate the rank value REPN of the number of wheat ears at the j-th time point in the i-th monitoring sub-region. ij : For all monitoring sub-regions i = 1, 2, ..., n and all time points j = 1, 2, ..., m, the leaf area index rank value sequence {RLAI} is repeatedly obtained. ij} and the sequence of rank values ​​of wheat ears {REPN ij}

[0015] Furthermore, the test results are denoted as Trend. LAI and Trend EPN This includes: denoting time series data of length n as {x1, x2, ..., x...} n}, where x i Let represent the observation value of the i-th monitoring sub-region, i = 1, 2, ..., n; define the sign function for the difference between the observation values ​​after the i-th monitoring sub-region and the previous observation values: Among them, i=1,2,...,n-1; j=i+1,i+2,...,n;x j Let represent the observation value at time point j; calculate the Mann-Kendall statistic S; count the number q consecutive data sets with equal values ​​in the time series data, and record the length t of each set. p p = 1, 2, ..., q, satisfying Calculate the mean E(S) and variance Var(S) of the Mann-Kendall statistic S; calculate the standardized Mann-Kendall statistic Z based on the sign and whether S is zero; select a significance level α and find the 1-α / 2 quantile Z of the standard normal distribution. (1-α / 2) As a critical value for judging the significance of the trend; the leaf area index time series {LAI} were respectively used as the critical value for judging the significance of the trend. ij} and wheat ear number time series {EPN ijSubstituting the values, we obtain the corresponding standardized Mann-Kendall statistic Z. LAI and Z EPN And based on its absolute value |Z| and critical value Z (1-α / 2) To determine the significance of the monotonic trend of two indicators, we need to consider their relative magnitudes. Among them, Trend LAI and Trend EPN A value of 1 indicates a significant monotonic trend at the significance level α, while a value of 0 indicates no significant monotonic trend.

[0016] Furthermore, the Mann-Kendall statistic S is calculated, expressed as:

[0017] Furthermore, the mean E(S) and variance Var(S) of the Mann-Kendall statistic S are calculated using the following expressions: E(S) = 0.

[0018] Furthermore, based on the sign of S and whether it is 0, the standardized Mann-Kendall statistic Z is calculated, with the expression:

[0019] Furthermore, the weighted average algorithm is used to calculate wheat growth, resulting in an evaluation index reflecting crop growth. The weighted average algorithm expression is as follows: Where W1, W2, W3, W4, and W5 are the weighting coefficients for the leaf area index trend contribution, the wheat ear number trend test result, the rank correlation coefficient, the wheat ear number growth rate contribution, and the maximum wheat ear number, respectively, satisfying the following conditions:

[0020] W1+W2+W3+W4+W5=1; Calculate the trend contribution C of leaf area index. LAI :C LAI =Trend LAI ×|cor(R LAI* ,R EPN* )|;where, cor(R) LAI* ,R EPN* ) represents the sequence of leaf area index rank values ​​at all time points in all monitored sub-regions {RLAI} ij} and the sequence of rank values ​​of wheat ears {REPN ij The Pearson correlation coefficient between the numbers was used to calculate the contribution of the wheat ear growth rate C. b : Where b0 is the growth rate threshold, determined based on the wheat variety and planting conditions. When b is greater than or equal to b0, C b Choose 1; otherwise, C b It equals the ratio of b to b0.

[0021] Another aspect of this application provides a big data-based agricultural environment monitoring system for implementing the big data-based agricultural environment monitoring method of this application.

[0022] Compared to existing technologies, the advantages of this application are:

[0023] By dividing the monitoring area into multiple spatiotemporal two-dimensional grids and collecting multi-dimensional data such as leaf area index and number of wheat ears within each monitoring sub-region and sub-time region, the spatiotemporal distribution characteristics of wheat growth can be comprehensively depicted. On the one hand, spatial division of the monitoring area can reveal the differences in wheat growth between different regions; on the other hand, equally spaced division of the monitoring period can reveal the dynamic changes in the wheat growth process. Combining these two approaches forms a wheat growth monitoring network within a spatiotemporal three-dimensional framework, laying a solid data foundation for subsequent data analysis and model building.

[0024] The Mann-Kendall trend test was used to determine the significance of monotonic trends in leaf area index and ear number within each monitoring sub-region, and the trend test results were incorporated into the comprehensive wheat growth assessment indicators. Analyzing the historical trends of each monitoring indicator can identify potential abnormal fluctuations during wheat growth, providing a basis for early warning of agricultural risks. When the trend of a certain indicator is inconsistent with other indicators, it often indicates that wheat growth may be affected by certain stress factors, requiring attention from monitoring personnel. Using trend test results to guide wheat growth assessment can improve the reliability of the assessment results.

[0025] An improved Spearman rank correlation coefficient algorithm was used to quantitatively assess the correlation between leaf area index (LAI) and wheat ear number. Traditional Spearman rank correlation coefficients only consider the rank values ​​of the two variables, while this invention introduces two correction factors: anomaly weight and time weight. The anomaly weight reflects the relative importance of each monitored sub-region; regions with larger anomalies are often more critical in wheat production and should be assigned higher weights. The time weight reflects the emphasis at different wheat growth stages; growth stages closer to maturity contribute more to yield formation and should be assigned higher weights. This dual-weighted correlation analysis method can objectively assess the intrinsic relationship between LAI and wheat ear number, revealing the patterns of their coupled changes and providing an important reference for comprehensive wheat growth assessment.

[0026] The Gompertz growth model was used to perform nonlinear fitting on the time series data of wheat ear number to obtain key parameters reflecting the growth pattern of wheat ear number. The growth rate parameter and the maximum number of wheat ears were incorporated into the comprehensive evaluation index of wheat growth vigor. The Gompertz model can effectively describe the characteristics of the four stages of crop growth: slow growth, rapid growth, steady growth, and slow growth. By fitting the wheat ear number growth curve, the growth rate and theoretical maximum value of wheat ear number can be quantitatively evaluated. The growth rate reflects the activity level of wheat population growth; the higher the growth rate, the better the wheat growth. The maximum number of wheat ears reflects the upper limit of wheat yield and is the result of the interaction between variety and environment; the more maximum number of wheat ears, the better the wheat growth. Incorporating these two parameters into the comprehensive evaluation of growth vigor allows for a description of the overall status of wheat growth and development from both dynamic and static perspectives. Attached Figure Description

[0027] This application will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0028] Figure 1 This is an exemplary flowchart illustrating a big data-based agricultural environment monitoring method according to some embodiments of this application. Detailed Implementation

[0029] The methods and systems provided in the embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0030] Figure 1 This is an exemplary flowchart of an agricultural environment monitoring method based on big data, according to some embodiments of this application. As shown in the figure, the target agricultural environment monitoring area is determined as the target monitoring area, and the target monitoring area is divided into n monitoring sub-areas of equal size using a preset grid size; the monitoring time of each monitoring sub-area is determined as the target time area, and the target time area is divided into m sub-time areas using equal time intervals; for each monitoring sub-area, within the corresponding sub-time area, leaf area index and number of wheat ears per unit area are collected to obtain the leaf area index time series {LAI}. ij} and wheat ear number time series {EPN ij}; For the leaf area index time series {LAI ij} and wheat ear number time series {EPN ij The Mann-Kendall trend test was used to determine the significance of leaf area and ear number data. At a given significance level α, the absolute value of the Mann-Kendall statistic Z, |Z|, is greater than the critical value Z. (1-α / 2)When a significant monotonic trend is observed in the corresponding indicator, the test results are recorded as Trend. LAI and Trend EPN ; respectively for the leaf area index time series {LAI ij} and wheat ear number time series {EPN ij}, perform rank transformation to obtain the rank value sequence {RLAI} ij} and {REPN ij The Spearman rank correlation coefficient algorithm is used to calculate the rank value sequence {RLAI}. ij} and {REPN ij The correlation coefficient ρ between} s ; the time series data of wheat ear count {EPN ij Using the data as input, a nonlinear fitting was performed using the Gompertz function to obtain the wheat ear number growth curve model. This model includes the growth rate parameter b and the maximum number of wheat ears K. The leaf area index trend test results were then used. LAI Trend test results for the number of wheat ears EPN Correlation coefficient ρ s The growth rate parameter b and the maximum number of wheat ears K are used as inputs. The weighted average algorithm is used to calculate the wheat growth status and obtain the evaluation index reflecting the crop growth status.

[0031] Based on the research objectives and data availability, the target agricultural environmental monitoring area is identified as the research object and denoted as the target monitoring area. This area can be the administrative boundary of a province, city, or county, or the natural boundary of a farm, irrigation area, or meteorological zone. Using a preset grid size, the target monitoring area is divided into n equally sized monitoring sub-regions. The selection of the grid size needs to comprehensively consider factors such as data spatial resolution, computational efficiency, and terrain features. Common grid sizes include 1km×1km, 5km×5km, and 10km×10km. Grid division can be implemented using GIS software like Fishnet or programming languages ​​such as Python. Each sub-region is assigned a unique number, such as 1, 2, ..., n. Based on the characteristics of wheat's growth period and the time span of the data, the monitoring time for each sub-region is determined as the target time zone. Typically, the wheat greening-up stage to maturity stage is chosen as the target time zone to cover the key stages of wheat growth and development. Using equal time intervals, the target time zone is divided into m sub-time zones. The selection of the time intervals needs to comprehensively consider factors such as data temporal resolution, observation frequency, and growth process. Common time intervals include 5 days, 10 days, and half a month. Each sub-time region is assigned a unique number, such as 1, 2, ..., m. The monitoring sub-regions and sub-time regions are combined to generate an n×m two-dimensional spatiotemporal matrix. Rows in the matrix represent monitoring sub-regions, columns represent sub-time regions, and each element represents the corresponding spatiotemporal combination. This matrix provides a framework for subsequent data organization, statistical analysis, and mapping. Through gridding and time discretization, this invention divides the continuous spatiotemporal domain into discrete spatiotemporal units. The wheat growth within each unit is relatively uniform, while the differences in wheat growth between units are highlighted. This division method fully considers the spatiotemporal heterogeneity of wheat growth, ensuring the representativeness of data within units while facilitating comparative analysis between units. Simultaneously, gridding and equal time interval division lay the foundation for standardized data organization and batch processing. In this embodiment, a 10-day time interval is selected to divide the entire wheat growth period into 24 sub-time regions (m=24), which are numbered T1 to T24, representing different periods such as sowing period, three-leaf stage, jointing stage, heading stage, grain filling stage and maturity stage.

[0032] Leaf area index (LAI) and number of wheat ears per unit area were collected in each monitoring sub-region within their respective sub-time periods to obtain time-series data reflecting the dynamic changes in wheat growth. LAI reflects the canopy's ability to intercept light energy and is an important indicator for assessing canopy photosynthetic intensity; the number of wheat ears reflects the canopy's sink capacity and is a key factor determining wheat yield. The combination of these two indicators provides a more comprehensive picture of wheat growth. Leaf area index (LAI) collection: For the i-th monitoring sub-region (i = 1, 2, ..., n), within the j-th sub-time region (i = 1, 2, ..., m), the leaf area index of the wheat canopy was collected and denoted as LAI. ij LAI (Leaf Area Index) represents the ratio of total leaf area per unit area of ​​ground surface, and is an important indicator describing the photosynthetic capacity and yield potential of the canopy. LAI can be collected in three ways: Direct ground measurement: A quadrat is set up within the monitoring sub-area, and parameters such as the length and width of wheat leaves are directly measured. The leaf area is calculated, multiplied by the number of wheat plants to obtain the total leaf area within the quadrat, and then divided by the quadrat area to obtain the LAI. This method has high accuracy but is time-consuming and labor-intensive. Indirect measurement using optical instruments: Optical instruments such as plant canopy analyzers (e.g., LAI-2200) and digital imaging analysis systems (e.g., WinSEEDLE) are used to indirectly estimate LAI by measuring parameters such as canopy radiation transmittance and leaf angle distribution. This method is simple to operate and suitable for large-scale implementation. Remote sensing inversion: Using satellite remote sensing imagery, based on the spectral characteristics of the wheat canopy, statistical or physical models are used to invert and obtain the LAI. This method has the advantages of large-area, rapid, and dynamic monitoring, but its accuracy is relatively low.

[0033] Ears per unit area (EPN) data collection. For the i-th monitoring sub-region (i = 1, 2, ..., n), within the j-th sub-time region (i = 1, 2, ..., m), the number of wheat ears per unit area is collected, denoted as EPN_ij. EPN represents the number of wheat ears per unit area and is one of the core factors determining wheat yield. EPN can be collected in two ways: Direct ground measurement method. Sample plots are set up within the monitoring sub-region, and the total number of wheat ears in the sample plots is directly counted during the wheat heading stage. Dividing this by the sample plot area gives the EPN. This method is accurate but labor-intensive. Remote sensing estimation method. High-resolution satellite remote sensing imagery is used to extract the number of pixels per wheat ear through visual interpretation or image segmentation. Then, the EPN is estimated based on the pixel area and ground resolution. This method allows for rapid measurement at the regional scale, but its accuracy is lower than direct ground measurement. Generation of LAI and EPN time series. For the i-th monitoring sub-region, the LAI collected within the m sub-time regions is arranged in chronological order to obtain an LAI time series of length m.

[0034] {LAI ij}j=1,2,....,m. Similarly, by arranging the EPNs collected in the m sub-time regions in chronological order, we obtain an EPN time series {EPN} of length m. ij}j=1,2,.....,m. The LAI and EPN time series characterize the dynamic changes in wheat growth and ear number in the i-th monitoring sub-region.

[0035] By collecting LAI and EPN data from each monitoring sub-region within their respective sub-time regions, this invention obtained time-series data reflecting the dynamic changes in wheat growth and ear number. LAI time series {LAI} ij The EPN time series reflects the growth and development of the wheat canopy at different growth stages. ij The data reflects the formation process of wheat spike number at different growth stages. The two time series complement each other, comprehensively depicting the growth dynamics of wheat and laying a data foundation for subsequent applications such as growth model construction, yield estimation, and growth status diagnosis. Furthermore, because the spatiotemporal scale matches step S1, the LAI and EPN time series take into account both temporal dynamics and spatial representativeness, reflecting a full consideration of the spatiotemporal heterogeneity of wheat growth and contributing to improved monitoring and prediction accuracy.

[0036] In this embodiment, the leaf area index (LAI-2200C) was used to measure the leaf area index. Five representative points were selected within each quadrat, and each point was measured three times. The average value was taken as the leaf area index for that quadrat. The number of wheat ears was measured by taking vertical photographs of the wheat canopy with a digital camera, then using image processing software to identify the wheat ears in the photographs, and finally calculating the number of wheat ears.

[0037] The Mann-Kendall trend test was used to analyze the leaf area index time series {LAI}. ij} and wheat ear number time series {EPN ij A significance test is performed to determine whether there is a significant monotonic trend between the two indicators. The Mann-Kendall test is a non-parametric statistical method that does not require the samples to follow a specific distribution, is insensitive to missing values, and is suitable for detecting trends in time series data. Let the time series data of length n be denoted as {x1, x2, ..., x...} n}, where x i Let x represent the observed value of the i-th monitoring sub-region, where i = 1, 2, ..., n. For the leaf area index, x i Let LAI_ij represent the number of wheat ears, x i Indicates EPN ij .

[0038] In this implementation, the leaf area index time series of a selected monitoring sub-region is as follows:

[0039] Sample plot number j Leaf area index time series LAIij 1 0.5 2 0.8 3 1.2 ... ... 22 4.1 23 3.8 24 3.5

[0040] The sign function is defined in the Mann-Kendall trend test to compare the magnitudes of any two observations in time series data. For the observation x in the i-th monitoring sub-region... i Compare it with each subsequent observation x j Compare (j>i), and quantify their magnitude relationship using the sign function sgn(x_j-x_i): when x j >x i At that time, sgn(x) j -x i ) = 1, indicating that the later observation is greater than the previous observation; when x j =x i At that time, sgn(x) j -x i ) = 0, indicating that the later observation is equal to the earlier observation; when x j <x i At that time, sgn(x) j -x i The sign function () = -1 indicates that the later observation is less than the earlier observation. Here, i ranges from 1 to n-1, and j ranges from i+1 to n, ensuring that each pair of observations is compared only once. The sign function transforms the magnitude relationship of the original data into three values: 1, 0, and -1, simplifying subsequent calculations and analysis.

[0041] The Mann-Kendall statistic S is a core indicator for determining whether time series data exhibits a monotonic trend. The calculation steps for S are as follows: For the i-th monitoring sub-region (i = 1, 2, ..., n-1), calculate its observed values ​​x... i With each subsequent observation x j Compare (j = i+1, i+2, ..., ...), and calculate sgn(x). j -x i This yields a set of 1, 0, and -1 values. Summing these results gives a result in terms of x. i The reference statistic S i : For all S i Summing these values ​​yields the Mann-Kendall statistic S for the entire time series: The sign of S reflects the monotonic trend of the time series: when S is positive, it indicates that the data is generally trending upward; when S is negative, it indicates that the data is generally trending downward; the larger the absolute value of S, the more obvious the trend. S = 0 indicates that there is no obvious monotonic trend.

[0042] Preferably, the presence of consecutive data points with equal values ​​in time series data will affect the variance of the Mann-Kendall statistic S, therefore it needs to be statistically analyzed. The statistical process is as follows: Traverse the time series data, find consecutive data segments with equal values, and record them. For example, in the sequence {1, 2, 2, 2, 3}, there is a segment with a length of 3. Record the number of segments q and the length t of each segment. p Let p = 1, 2, ..., q. For the above sequence, q = 1, t1 = 3. Verify. That is, the total length does not exceed the length of the time series. The statistical results will be used for subsequent variance correction of the Mann-Kendall statistic S.

[0043] The mean and variance of the Mann-Kendall statistic S are calculated as follows: Under the null hypothesis (i.e., the data has no trend), the mean E(S) of the Mann-Kendall statistic S is 0. This is because, under random permutations, the probability of a relationship between any two observations is equal, and sgn(x) = 0. j -x i Since the probability of S being 1 and -1 is the same, the expected value of S is 0. The variance of S, Var(S), needs to take into account the influence of the variance, and its calculation formula is:

[0044] Where n is the length of the time series, q is the number of groups, and t p Let p = 1, 2, ..., q be the length of the p-th group. When the data does not contain the group, i.e., q = 0, the formula simplifies to: By calculating the mean and variance, the distribution characteristics of the Mann-Kendall statistic S under the null hypothesis can be determined, providing a basis for subsequent significance tests.

[0045] To facilitate significance testing, the standardized statistic Z needs to be converted from the Mann-Kendall statistic S to its standardized form. The calculation method for Z differs depending on the sign of S and whether it is zero: The standardized statistic Z follows a standard normal distribution, with a mean of 0 and a variance of 1. The larger the value of |Z|, the more significant the monotonic trend of the time series.

[0046] The significance test is used to determine whether the monotonic trend of a time series is significant. First, a significance level α is selected (usually 0.05), and then the (1-α / 2) quantile Z of the standard normal distribution is found. (1-α / 2) The quantile Z serves as a critical value for judging the significance of a trend. (1-α / 2) Let Z represent the Z-value corresponding to a cumulative probability of (1-α / 2) under a standard normal distribution. The rule for determining the significance of a trend is as follows: when |Z| > Z...(1-α / 2) At a significance level of α, the time series exhibits a significant monotonic trend; when |Z|≤Z (1-α / 2) At a significance level of α, the time series does not exhibit a significant monotonic trend. Significance testing allows for an objective assessment of whether the monotonic trend of a time series is statistically significant, avoiding the overinterpretation of spurious trends caused by random fluctuations.

[0047] The trend significance test of leaf area index and wheat ear number was performed by comparing the time series of leaf area index {LAI_ij} and the time series of wheat ear number {EPN}. ij Substituting these values ​​into the Mann-Kendall trend test, the corresponding standardized statistics Z_LAI and Z_EPN are calculated. Based on the relationship between |Z_LAI| and |Z_EPN| and the critical value Z... (1-α / 2) To determine the significance of the monotonic trend of two indicators, consider their relative magnitudes: when |Z LAI |>Z (1-α / 2) At that time, Trend LAI =1 indicates that the leaf area index has a significant monotonic trend at the significance level α; otherwise, Trend LAI =0 indicates that there is no significant monotonic trend. When |Z EPN |>Z (1-α / 2) At that time, Trend EPN =1 indicates that the number of wheat ears shows a significant monotonic trend at the significance level α; otherwise, Trend EPN =0 indicates that there is no significant monotonic trend. Trend LAI and Trend EPN The value of is either 1 or 0, intuitively representing the trend significance test results of leaf area index and wheat ear number, facilitating subsequent analysis and application. Through subsequent steps of the Mann-Kendall trend test, including the calculation of mean and variance, the calculation of standardized statistics, and significance testing, the monotonic trend of the time series and its statistical significance can be quantitatively assessed. These steps fully utilize the distribution characteristics of the Mann-Kendall statistic S, objectively reflecting the significance level of the trend through standardization and hypothesis testing. Applying this method to trend analysis of leaf area index and wheat ear number can reveal the dynamic changes of key parameters during wheat growth, providing an objective basis for assessing wheat growth vigor.

[0048] In this implementation, the monitoring results for sub-region k are as follows:

[0049]

[0050] Leaf area index time series {LAI ij} and wheat ear number time series {EPN ij}, perform rank transformation to obtain the rank value sequence {RLAI} ij} and {REPN ij The Spearman rank correlation coefficient algorithm is used to calculate the rank value sequence {RLAI}. ij} and {REPN ij The correlation coefficient ρ between} s By using rank transformation and Spearman's rank correlation coefficient calculation, the correlation between leaf area index and wheat ear number was revealed, overcoming problems such as inconsistent dimensions of agronomic indicators and irregular data distribution, and improving the comparability between indicators and the reliability of results.

[0051] For the i-th monitoring sub-region (i = 1, 2, ..., n): the leaf area index time series {LAI} will be used. ij}j=1,2,....,m are arranged in ascending order to obtain the sorted sequence {SLAI} ij}, where SLAI ij LAI ij In {LAI ij The index in} ranges from 1 to m. Based on the sorted sequence {SLAI} ij}, calculate the rank value RLAI of the leaf area index at the j-th time point. ij : Similarly, the wheat ear number time series {EPN ij}j=1,2,....,m are arranged in ascending order to obtain the sorted sequence {SEPN ij}, where SEPN ij Indicates EPN ij In {EPN ij The sequence number {SEPN_ij} ranges from 1 to m. Based on the sorted sequence {SEPN_ij}, calculate the rank value REPN of the number of wheat ears at the j-th time point. ij : Repeat the above steps for all monitored sub-regions i = 1, 2, ..., n and all time points j = 1, 2, ..., m to obtain the leaf area index rank value sequence {RLAI}. ij} and the sequence of rank values ​​of wheat ears {REPN ij The rank value ranges from (0, 1), reflecting the relative size and position of the original data within its time series.

[0052] The Spearman rank correlation coefficient is a nonparametric correlation measure used to assess the monotonic correlation between two variables. In this study, the leaf area index rank value sequence {RLAI} was calculated. ij} and the sequence of rank values ​​of wheat ears {REPN ijThe Spearman rank correlation coefficient ρ between} s This study revealed the correlation between leaf area index and the number of wheat ears.

[0053] ρ s The calculation formula is as follows: in: and Let represent the standard scores of the leaf area index rank value and the wheat ear number rank value at the j-th time point in the i-th monitoring sub-region, respectively, obtained by subtracting the population mean and dividing by the population standard deviation. LAI* ) and std(R LAI* ) represent the population mean and population standard deviation of the leaf area index rank values ​​at all time points across all monitored sub-regions; mean(R EPN* ) and std(R EPN* ) represent the overall mean and overall standard deviation of the rank values ​​of wheat ear count at all time points in all monitored sub-regions. Let represent the time weight at time point j, taking into account the influence of time order on correlation, and satisfying that the sum of weights is 1.

[0054] ρ represents the anomaly weight for the i-th monitoring sub-region, calculated based on the distances of the mean leaf area index and mean number of wheat ears within this sub-region relative to the overall mean, ensuring that the sum of the weights is 1. The introduction of the anomaly weight allows outlier regions to contribute more significantly to the correlation estimation. s The value range is [-1, 1]. A larger absolute value indicates a stronger monotonic correlation between the two variables, and the sign indicates the positive or negative nature of the correlation. By using rank transformation and calculating the Spearman rank correlation coefficient, the correlation between leaf area index and wheat ear number can be objectively assessed after eliminating the influence of dimensions and differences in data distribution. Information from multiple monitoring sub-regions and multiple time points is fully utilized, and the robustness and reliability of the correlation estimation are enhanced by introducing time weights and anomaly weights.

[0055] The Gompertz function is a commonly used growth curve model that can effectively describe the dynamic changes of certain indicators during crop growth. By using the Gompertz function to perform nonlinear fitting on the wheat ear number time series data {EPN_ij}, key parameters reflecting the growth characteristics of wheat ear number can be estimated, including the growth rate parameter b and the maximum number of wheat ears K.

[0056] Determine the expression for the Gompertz function: EPN(t) = K × exp{-exp[α-(b T ×∑GDD(t)+b P×∑Prec(t))]};where, EPN(t) represents the predicted number of wheat ears at time t; K represents the theoretical maximum number of wheat ears; a is a constant related to the initial number of wheat ears EPN(0); b T and b P ∑GDD(t) and ∑Prec(t) represent the sensitivity parameters of growth rate to temperature and precipitation, respectively; ∑GDD(t) and ∑Prec(t) represent the accumulated active temperature and accumulated precipitation from sowing to time t, respectively. Calculating the accumulated active temperature ∑GDD(t): For each time point t, calculate the accumulated active temperature GDD(t) for that day. k ): Among them, T max (t k ) and T min (t k T represents the daily maximum and minimum temperatures on day k, respectively. base Let be the baseline temperature for wheat growth and development (usually taken as 10℃). The accumulated active temperature is obtained by summing the daily active temperature, resulting in the cumulative active temperature ∑GDD(t) from sowing to time t: Calculate the cumulative precipitation ∑Prec(t): For each time point t, calculate the daily precipitation Prec(t) from sowing to time t. k The cumulative precipitation ∑Prec(t) is obtained by summing the amounts of each t.

[0057] Preferably, in order to utilize wheat ear number time series data {EPN ij Estimating the parameters of the Gompertz function requires constructing a nonlinear least squares problem and solving it using an optimization algorithm. The objective function is defined as the sum of squared residuals between the actual number of wheat ears and the predicted values ​​from the Gompertz function.

[0058] Among them, EPN ij Let K, a, and b represent the actual number of wheat ears at the j-th time point in the i-th monitoring sub-region. T and b P Let ∑GDD(t) be the parameters of the Gompertz function to be estimated. j ) and ∑Prec(t j ) represent the accumulated activity temperature and accumulated precipitation at the j-th time point, respectively.

[0059] Calculate the Jacobian matrix: The Jacobian matrix J represents the partial derivatives of the objective function with respect to each parameter, and has a size of (n×m)×4, where n is the number of monitored sub-regions and m is the number of time points. The elements of the Jacobian matrix J... (i-1)×m+j,k This represents the relationship between the i-th monitoring sub-region and the j-th time point and the k-th parameter (K, α, b). T ,b P The partial derivative of ).

[0060] Partial derivative with respect to K: ;

[0061] right Partial derivatives: ;

[0062] right Partial derivatives: ;

[0063] right Partial derivatives: .

[0064] Initialize parameter values: to the parameters K, a, and b of the Gompertz function. T and b P Provide initial values, denoted as K0, α0, and b. T0 and b P0 Initial values ​​can be set based on prior knowledge, experience, or data characteristics. Iteration process: Set the iteration count t = 0, and the maximum iteration count t... max The convergence threshold ε. When t < t max And ||g||>ε: Calculate the residual vector Calculate the Jacobian matrix J t Calculate the increment δ: Where λ is the damping factor, and its initial value is set to 0.01. express A diagonal matrix composed of diagonal elements.

[0065] Update parameter value: K t+1 =K t +δ1;α t+1 =α t +δ2;b T(t+1) =b T(t) +δ3;b P(t+1) =b P(t) +δ4. Calculate the new residual vector r. t+1 , If ||r t+1 ||<||r t If ||, then accept the new parameter value and let λ = λ / 10; otherwise, let λ = 10λ, and repeat until ||r t+1 ||<||r t || Or the upper limit of the inner loop iterations is reached. Let t = t + 1. Output the estimated results: After the iteration, the parameter estimates of the Gompertz function are obtained.

[0066] This application presents a detailed technical scheme for solving nonlinear least squares problems using the Levenberg-Marquardt algorithm and estimating the parameters of the Gompertz function. The algorithm introduces a damping factor λ to adaptively adjust between the gradient descent method and the Gauss-Newton method, ensuring both convergence speed and stability. Estimating the Gompertz function parameters using the nonlinear least squares method yields optimal parameter estimates under given wheat ear number time-series data and environmental factors (temperature and precipitation), minimizing the error between model predictions and actual observations. The fitted wheat ear number growth curve model can be used to describe and predict the dynamic changes in wheat ear number, providing a basis for wheat growth monitoring and yield estimation.

[0067] In a specific embodiment of this application, K = 682.5, a = 2.37, b T =0.0048, b P =0.0015; Substituting the estimated parameters into the Gompertz function, the wheat ear number growth curve model for the first monitoring sub-region is obtained: EPN(t)=K×exp{-exp[α-(b T ×∑GDD(t)+b P The model shows that the number of wheat ears increases from 425 to 682.5 throughout the entire growth period, exhibiting a "slow-fast-slow" S-shaped curve. Temperature and precipitation regulate the growth process of the number of wheat ears by affecting the growth rate parameter b; the larger the value of b, the steeper the curve and the faster the growth rate. b = b T ×∑GDD(t)+b P ×∑Prec(t). Specifically, when the accumulated temperature ∑GDD(t) increases by 100℃·d, the growth rate parameter increases by 0.48; when the cumulative precipitation ∑Prec(t) increases by 100mm, the growth rate parameter increases by 0.15. This indicates that the number of wheat ears is more sensitive to temperature.

[0068] The trend test results of leaf area index were used to analyze the trend. LAI Trend test results for the number of wheat ears EPN Correlation coefficient ρ s Using the growth rate parameter b and the maximum number of wheat ears K as inputs, a weighted average algorithm is used to calculate wheat growth vigor, yielding an evaluation index reflecting crop growth vigor. The leaf area index trend contribution C is also calculated. LAI : Obtain leaf area index data for all monitored sub-regions and time points, denoted as LAI ij Where i represents the monitoring sub-region and j represents the time point. The wheat ear count data for all monitoring sub-regions and time points are obtained and denoted as EPN. ij, where i represents the monitoring sub-region and j represents the time point. For each monitoring sub-region i, the leaf area index (LAI) data for all its time points are calculated. ij Sort the leaf area index rank values ​​of the subregion in ascending order to obtain the sequence RLAI. ij For each monitoring sub-region i, the wheat ear count data EPN at all time points is calculated. ij Sort the wheat ears in ascending order to obtain the rank sequence REPN of the sub-region. ij RLAI sequence of leaf area index rank values ​​for all monitored sub-regions. ij Combined into a vector RLAI ** The sequence is of length n×m, where n is the number of monitored sub-regions and m is the number of time points. The rank sequence of the number of wheat ears in all monitored sub-regions is REPN. ij Combined into a vector REPN ** The length is n×m, where n is the number of monitored sub-regions and m is the number of time points. Calculate the vector RLAI. ** The mean, denoted as RLAI mean .

[0069] Calculate vector REPN ** The mean, denoted as REPN mean .

[0070] Compute vector RLAI ** and REPN ** The covariance is denoted as cov(RLAI). ** REPN ** ).

[0071] Compute vector RLAI ** The standard deviation is denoted as std(RLAI). ** ).

[0072] Calculate vector REPN ** The standard deviation is denoted as std(REPN). ** ). Compute vector RLAI ** and REPN ** The Pearson correlation coefficient between them. The trend test results of leaf area index (Typical) are used to determine the trend. LAI Correlation coefficient with Pearson (RLAI) ** REPN ** Multiplying the absolute values ​​of the leaf area index by the absolute values ​​yields the trend contribution C of the leaf area index. LAI C LAI =TrendLAI ×|cor(RLAI ** REPN ** )|.

[0073] Calculate the contribution of wheat ear number growth rate C b Based on the wheat variety and planting conditions, a growth rate threshold b0 is set. This threshold represents the minimum growth rate of the number of wheat ears; a value below this threshold is considered too low and detrimental to wheat growth. The growth rate parameter b is compared with the growth rate threshold b0. If b is greater than or equal to b0, the contribution of the wheat ear growth rate C is... b A value of 1 indicates that the growth rate has reached or exceeded the threshold, which is beneficial to wheat growth. If b is less than b0, then the contribution of the wheat ear number growth rate C... b The ratio of b to b0 indicates that the growth rate is below the threshold and contributes little to wheat growth. C b =min(1,b / b0).

[0074] Weighting coefficients are set as follows: Based on expert knowledge and experience, the following weights are set: leaf area index trend contribution weight W1, wheat ear number trend test result weight W2, rank correlation coefficient weight W3, wheat ear number growth rate contribution weight W4, and maximum wheat ear number weight W5. The weighting coefficients satisfy the constraint: W1 + W2 + W3 + W4 + W5 = 1.

[0075] Preferably, historical data is collected, including indicators such as the trend contribution of leaf area index, the trend test results of wheat ear number, rank correlation coefficient, the contribution of wheat ear number growth rate, and the maximum number of wheat ears, as well as the corresponding wheat growth assessment results. Data preprocessing is performed, such as handling missing values ​​and outliers, to ensure data completeness and quality. Each indicator is standardized to have a mean of 0 and a variance of 1. Standardization formula: Among them, Z ij X is the standardized index value. ij These are the original index values. Let be the mean of the j-th indicator. Let be the standard deviation of the j-th indicator. Perform principal component analysis on the standardized indicator data. Calculate the covariance matrix or correlation coefficient matrix of the indicator data. Calculate the eigenvalues ​​and eigenvectors of the covariance matrix or correlation coefficient matrix, and then calculate the covariance matrix: Choose principal components with eigenvalues ​​greater than 1, or select a sufficient number of principal components based on the cumulative variance contribution rate to explain most of the variance in the original data.

[0076] Principal component score calculation: Using the eigenvectors of the selected principal components, calculate the score for each sample on the principal components. Principal component score formula: Among them, PC ikLet α be the score of the i-th sample on the k-th principal component. kj Z is the j-th element of the eigenvector of the k-th principal component. ij Let be the j-th standardized index value of the i-th sample. Calculate the principal component weights: Calculate the weight of each principal component based on its variance contribution rate. Variance contribution rate formula: Where, r k Let λ be the variance contribution rate of the k-th principal component. k Let be the eigenvalue of the k-th principal component, and m be the number of principal components selected. Weight calculation formula: Among them, w k This represents the weight of the k-th principal component. Calculating index weights: Using the weights of the principal components and their eigenvectors, calculate the weights of the original indexes. Index weight calculation formula: Among them, W j w is the weight of the j-th indicator. k Let α be the weight of the k-th principal component. kj This is the absolute value of the j-th element of the eigenvector of the k-th principal component. Weight normalization: The calculated index weights are normalized to satisfy the constraint that the sum of the weights is 1. Normalization formula: Among them, W j_normalized Let be the weight of the j-th indicator after normalization, and p be the number of indicators.

[0077] Calculate wheat growth assessment index G: Use a weighted average algorithm to calculate the contribution of leaf area index trend C. LAI Trend test results for the number of wheat ears EPN Correlation coefficient ρ s Contribution of wheat ear number growth rate C b The weighted sum is calculated by taking the sum of the maximum number of wheat ears, K. The weighted average algorithm expression is as follows:

[0078] The evaluation index G reflecting wheat growth is obtained. The value of G ranges from [0, 1], and the larger the value, the better the wheat growth.

Claims

1. A big data-based agricultural environmental monitoring method for wheat growth monitoring, characterized in that, include: The target agricultural environment monitoring area is defined as the target monitoring area. Using a grid with a preset grid size, the target monitoring area is divided into n monitoring sub-areas of equal size. The monitoring time of each monitoring sub-area is defined as the target time area. Using equal time intervals, the target time area is divided into m sub-time areas. For each monitoring sub-region, leaf area index and number of wheat ears per unit area were collected within the corresponding sub-time regions to obtain the leaf area index time series {LAI}. ij } and wheat ear number time series {EPN ij }; Leaf area index time series {LAI ij } and wheat ear number time series {EPN ij The Mann-Kendall trend test was used to determine the significance of leaf area and ear number data. At a given significance level α, the absolute value of the Mann-Kendall statistic Z| is greater than the critical value Z|. (1-α2) When a significant monotonic trend is observed in the corresponding indicator, the test results are recorded as Trend. LAI and Trend EPN ; Leaf area index time series {LAI ij } and wheat ear number time series {EPN ij }, perform rank transformation to obtain the rank value sequence {RLAI} ij } and {REPN ij The Spearman rank correlation coefficient algorithm is used to calculate the rank value sequence {RLAI}. ij } and {REPN ij The correlation coefficient ρ between} s ; Time series data of wheat ear count {EPN ij As input, the Gompertz function is used for nonlinear fitting to obtain the wheat ear number growth curve model, which includes the growth rate parameter b and the maximum number of wheat ears K. Trend test results of leaf area index LAI Trend test results for the number of wheat ears EPN Correlation coefficient ρ s The growth rate parameter b and the maximum number of wheat ears K are used as inputs. The weighted average algorithm is used to calculate the wheat growth status and obtain the evaluation index reflecting the crop growth status.

2. The agricultural environmental monitoring method based on big data according to claim 1, characterized in that: Calculate the correlation coefficient ρ s The formula is as follows: in, The standard score represents the rank value of the leaf area index at the j-th time point in the i-th monitoring sub-region; mean(R LAI* std(R) represents the overall mean of the leaf area index rank values ​​at all time points across all monitored sub-regions; LAI* ) represents the overall standard deviation of the leaf area index rank values ​​at all time points across all monitored sub-regions; The standard score representing the rank of the number of wheat ears at the j-th time point in the i-th monitoring sub-region; mean(R EPN* ) and std(R EPN* ) represent the population mean and population standard deviation of the rank values ​​of wheat ear count at all time points in all monitored sub-regions, respectively; Represents the time weight at time point j, satisfying Represents the anomaly weight of the i-th monitoring sub-region, satisfying ΔLAI i =mean(LAI i* )-mean(LAI ** ), representing the deviation of the mean leaf area index (LAI) of the i-th monitoring sub-region from the overall mean; mean(LAI) i* () represents the mean of the raw leaf area index values ​​within the i-th monitoring sub-region; mean(LAI) ** () represents the overall mean of the raw leaf area index values ​​at all time points across all monitored sub-regions; ΔEPN i =mean(EPN) i* )-mean(EPN ** ), representing the deviation of the mean number of wheat ears in the i-th monitoring sub-region from the overall mean; mean(EPN) i* () represents the mean of the original number of wheat ears in the i-th monitoring sub-region; mean(EPN) ** ) represents the overall mean of the original values ​​of the number of wheat ears at all time points in all monitored sub-regions.

3. The agricultural environmental monitoring method based on big data according to claim 2, characterized in that: Nonlinear fitting is performed using the Gompertz function, whose expression is as follows: EPN(t)=K×exp{-exp[α-(b T ×∑GDD(t)+b P ×∑Prec(t))]} Where EPN(t) represents the predicted number of wheat ears at time t; K represents the theoretical maximum number of wheat ears; a is a constant related to the initial number of wheat ears EPN(0); b T and b P ∑GDD(t) represents the sensitivity parameters of growth rate to temperature and precipitation, respectively; ∑GDD(t) represents the accumulated active temperature from sowing to time t; ∑Prec(t) represents the accumulated precipitation from sowing to time t.

4. The agricultural environmental monitoring method based on big data according to claim 3, characterized in that: Obtain the rank value sequence {RLAI ij } and {REPN ij },include: For the i-th monitoring sub-region i = 1, 2, ..., n, the corresponding leaf area index time series {LAI} will be used. ij }j=1,2,....,m are arranged in ascending order to obtain the sorted sequence {SLAI} ij }, among which, SLAI ij LAI ij In {LAI ij The index in} ranges from 1 to m; Based on the sorted sequence {SLAI ij } Calculate the rank value RLAI of the leaf area index at the j-th time point for the i-th monitoring sub-region. ij : For the i-th monitoring sub-region (i = 1, 2, ..., n), the corresponding wheat ear number time series will be... {EPN ij }j=1,2,....,m are arranged in ascending order to obtain the sorted sequence {SEPN ij }, where SEPN ij Indicates EPN ij In {EPN ij The index in} ranges from 1 to m; Based on the sorted sequence {SEPN ij } Calculate the rank value REPN of the number of wheat ears at the j-th time point in the i-th monitoring sub-region. ij : For all monitoring sub-regions i = 1, 2, ..., n and all time points j = 1, 2, ..., m, repeat the above steps to obtain the leaf area index rank value sequence {RLAI}. ij } and the sequence of rank values ​​of wheat ears {REPN ij } 5. The agricultural environmental monitoring method based on big data according to claim 4, characterized in that: The test results were obtained. LAI and Trend EPN ,include: Let the time series data of length n be denoted as {x1, x2, ..., xn}. n }, where x i This represents the observation value of the i-th monitoring sub-region, where i = 1, 2, ..., n; Define a sign function for the difference between the observations after the i-th monitoring sub-region and the previous observations: Among them, i=1,2,...,n-1; j=i+1,i+2,...,n;x j This represents the observation value at the j-th time point; Calculate the Mann-Kendall statistic S; Count the number q consecutive data sets with equal values ​​in a time series data set, and record the length t of each set. p p = 1, 2, ..., q, satisfying Calculate the mean E(S) and variance Var(S) of the Mann-Kendall statistic S; Calculate the standardized Mann-Kendall statistic Z based on the sign of S and whether it is 0; Choose a significance level α and find the 1-α / 2 quantile Z of the standard normal distribution. (1-α2) This serves as a critical value for judging the significance of a trend; Based on the leaf area index time series {LAI ij } and wheat ear number time series {EPN ij }, thus obtaining the corresponding standardized Mann-Kendall statistic Z. LAI and Z EPN And based on its absolute value |Z| and critical value Z (1-α2) To determine the significance of the monotonic trend of two indicators, we need to consider their relative magnitudes. Among them, Trend LAI and Trend EPN A value of 1 indicates a significant monotonic trend at the significance level α, while a value of 0 indicates no significant monotonic trend.

6. The agricultural environment monitoring method based on big data according to claim 5, characterized in that: The Mann-Kendall statistic S is calculated as follows:

7. The agricultural environmental monitoring method based on big data according to claim 6, characterized in that: The mean E(S) and variance Var(S) of the Mann-Kendall statistic S are calculated using the following expressions: E(S) = 0.

8. The agricultural environmental monitoring method based on big data according to claim 7, characterized in that: Based on the sign of S and whether it is 0, calculate the standardized Mann-Kendall statistic Z, expressed as:

9. The agricultural environment monitoring method based on big data according to any one of claims 1 to 8, characterized in that: The weighted average algorithm is used to calculate wheat growth, resulting in an evaluation index reflecting crop growth. The expression for the weighted average algorithm is as follows: Among them, W1, W2, W3, W4, and W5 are the weighting coefficients of the leaf area index trend contribution, the wheat ear number trend test result, the rank correlation coefficient, the wheat ear number growth rate contribution, and the maximum wheat ear number, respectively. Calculate the trend contribution of leaf area index C LAI : C LAI =Trend LAI ×|cor(R LAI* ,R EPN* ) Among them, cor(R) LAI* ,R EPN* ) represents the sequence of leaf area index rank values ​​at all time points in all monitored sub-regions {RLAI} ij } and the sequence of rank values ​​of wheat ears {REPN ij The Pearson correlation coefficient between them; Calculate the contribution of wheat ear number growth rate C b : Where b0 is the growth rate threshold, determined based on the wheat variety and planting conditions; when b is greater than or equal to b0, C b Choose 1; otherwise, C b It equals the ratio of b to b0.

10. An agricultural environmental monitoring system based on big data, characterized in that, include: At least one processing unit; for executing instructions to implement the big data-based agricultural environment monitoring method according to any one of claims 1 to 9.

Images