A diversified rice planting method in a composite environment based on big data analysis

Abstract

This invention discloses a diversified rice cultivation method under complex environments based on big data analysis, specifically relating to the field of agricultural information processing technology. It involves collecting multidimensional monitoring data within the rice cultivation area, performing nonlinear correlation analysis to extract the interaction characteristics between environmental variables, conducting multi-scale reconstruction analysis based on spatial scale differences to identify the main areas of influence of environmental variables, performing mapping analysis based on historical rice growth status data and the interaction characteristics of environmental variables to assess the comprehensive impact on rice growth, analyzing the temporal sequence of the effects of different environmental variables within the rice growth cycle to extract the changing patterns of the influence weights of environmental variables at each growth stage, and integrating the interaction characteristics and influence weight patterns of environmental variables to assess the growth potential of different rice varieties and optimize rice planting varieties and density, thereby achieving precise cultivation of multiple rice varieties under complex ecological conditions.

Description

Technical Field

[0001] This invention relates to the field of agricultural information processing technology, and more specifically, to a diversified rice cultivation method based on big data analysis in a complex environment. Background Technology

[0002] In the existing agricultural planting management system, environmental monitoring and regulation of rice planting areas are mostly based on typical climatic factors, and static factor thresholds, linear weighted models or empirical grading rules are used for variety selection and planting configuration.

[0003] However, in a complex ecological environment, rice growth is influenced by the coupled effects of various meteorological, soil, and biological factors. These factors are highly heterogeneous in time and space, and their interactions exhibit nonlinear, feedback, and stage-specific characteristics. Existing analytical methods lack the ability to dynamically analyze the interactions and evolutionary patterns among multiple variables, making it difficult to accurately identify key environmental response mechanisms, leading to uneven planting density and mismatched varieties.

[0004] To address the aforementioned problems, a technical solution is provided. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a diversified rice planting method and system based on big data analysis in a complex environment to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A diversified rice cultivation method based on big data analysis in a complex environment includes the following steps:

[0008] S1: Obtain multidimensional monitoring data within the rice planting area and perform nonlinear correlation analysis to extract the interaction characteristics between different environmental variables;

[0009] S2: Multi-scale reconstruction analysis of the interaction characteristics between different environmental variables based on spatial scale differences to identify the main influence areas of different environmental variables;

[0010] S3: Based on the main areas of influence of different environmental variables, perform mapping analysis on historical rice growth data to assess the impact of the interaction characteristics between different environmental variables on rice growth;

[0011] S4: Analyze the timing of the effects of different environmental variables on the rice growth cycle and extract the changing patterns of the influence weights of different environmental variables at different growth stages;

[0012] S5: Based on the evaluation results of the impact of the interaction characteristics between different environmental variables on rice growth and the changing pattern of the impact weight of different environmental variables at different growth stages, assess the growth potential of different rice varieties in rice planting areas.

[0013] S6: Based on the growth potential assessment results, adjust the rice varieties and planting density in the rice planting area.

[0014] In a preferred embodiment, S1 specifically refers to:

[0015] Collect multidimensional monitoring data within the rice-growing area; the multidimensional monitoring data includes meteorological environment monitoring data, soil environment monitoring data, and rice growth status monitoring data;

[0016] The multidimensional monitoring data is processed by outlier removal, missing value imputation, and standardization.

[0017] Based on standardized multidimensional monitoring data, a nonlinear correlation analysis was performed using mutual information analysis to calculate the nonlinear correlation strength between different environmental variables.

[0018] Based on the nonlinear correlation strength between different environmental variables, the interaction features between different environmental variables are extracted.

[0019] In a preferred embodiment, S2 specifically refers to:

[0020] Rice planting areas are divided into multiple spatial scale levels according to differences in spatial scale;

[0021] For each spatial scale level, wavelet multi-scale analysis is used to perform scale reconstruction analysis on the interaction characteristics between environmental variables, and the reconstructed data of the interaction characteristics of environmental variables at each spatial scale level are obtained.

[0022] Based on the interaction characteristics of environmental variables, the data is reconstructed, and the spatial hotspot analysis method is used to identify and mark the main influence areas of different environmental variables at each spatial scale level.

[0023] In a preferred embodiment, S3 specifically refers to:

[0024] Based on the main areas of influence of different environmental variables at each spatial scale level, historical rice growth status data are obtained within the rice planting area.

[0025] For the main affected areas at each spatial scale level, the spatial mapping correlation coefficients between historical rice growth status data and different environmental variables were calculated.

[0026] Based on spatial mapping correlation coefficients, a nonlinear regression method was used to assess the comprehensive impact of the interaction characteristics between different environmental variables on rice growth, and the assessment results of the impact of the interaction characteristics between different environmental variables on rice growth were obtained.

[0027] In a preferred embodiment, S4 specifically refers to:

[0028] Rice growth stages are divided based on the complete growth cycle of rice. The growth stages of rice include the jointing and booting stage, the heading and flowering stage, and the grain filling and ripening stage.

[0029] At each growth stage, the values ​​of each environmental variable in the standardized multidimensional monitoring data were extracted, and time-series modeling was performed on the changes in environmental variable values ​​at different growth stages.

[0030] Based on time series modeling, the influence weight values ​​of each environmental variable at different growth stages are calculated to obtain the variation law of the influence weight of each environmental variable at different growth stages of rice.

[0031] In a preferred embodiment, S5 specifically refers to:

[0032] The assessment results of the impact of the interaction characteristics between different environmental variables on rice growth are integrated with the changing patterns of the influence weights of each environmental variable at different growth stages of rice.

[0033] Based on the fusion results, a matching matrix between rice varieties and environmental responses is constructed;

[0034] Based on the matching matrix between rice varieties and environmental responses, the growth potential of multiple rice varieties in the rice-growing area is assessed, and the adaptability score of each rice variety in the current complex environment is output.

[0035] In a preferred embodiment, S6 specifically refers to:

[0036] A preset adaptation score threshold is set, and the adaptation score is compared with the adaptation score threshold to select rice varieties with an adaptation score higher than the adaptation score threshold.

[0037] Within the rice-growing area, the planting range of each selected rice variety was determined, and the planting density of each rice variety within the planting range was determined by combining standardized multidimensional monitoring data.

[0038] The technical effects and advantages of this invention, which proposes a diversified rice cultivation method based on big data analysis in a complex environment, are as follows:

[0039] By conducting nonlinear correlation analysis on multidimensional monitoring data, we can deeply explore the interaction characteristics among environmental factors such as meteorology, soil, and crop status, significantly improving the ability to identify complex coupled disturbances. Multi-scale reconstruction analysis identifies the main impact areas of different environmental variables, providing spatial support for differentiated regional management. Mapping these main impact areas to historical rice growth status data enables a quantitative assessment of the impact of environmental interactions on rice growth, laying a data foundation for precise adjustments in target areas. Combined with time-series analysis of the growth cycle, we clarify the weight changes of different environmental variables during the rice growth cycle, providing a basis for precise regulation. Integrating spatial and temporal assessment results, we evaluate the growth potential of various rice varieties under the current complex environment, providing a reliable basis for multi-variety collaborative planting. Based on the growth potential assessment results, we dynamically optimize variety configuration and planting density, achieving efficient resource utilization and steady yield increases, significantly improving the accuracy and responsiveness of planting decisions, and meeting the planting needs under complex ecological conditions. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of a diversified rice cultivation method based on big data analysis in a complex environment according to the present invention. Detailed Implementation

[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0042] Example

[0043] Figure 1 This invention presents a diversified rice cultivation method based on big data analysis in a complex environment, comprising the following steps:

[0044] S1: Obtain multidimensional monitoring data within the rice planting area and perform nonlinear correlation analysis to extract the interaction characteristics between different environmental variables;

[0045] S2: Multi-scale reconstruction analysis of the interaction characteristics between different environmental variables based on spatial scale differences to identify the main influence areas of different environmental variables;

[0046] S3: Based on the main areas of influence of different environmental variables, perform mapping analysis on historical rice growth data to assess the impact of the interaction characteristics between different environmental variables on rice growth;

[0047] S4: Analyze the timing of the effects of different environmental variables on the rice growth cycle and extract the changing patterns of the influence weights of different environmental variables at different growth stages;

[0048] S5: Based on the evaluation results of the impact of the interaction characteristics between different environmental variables on rice growth and the changing pattern of the impact weight of different environmental variables at different growth stages, assess the growth potential of different rice varieties in rice planting areas.

[0049] S6: Based on the growth potential assessment results, adjust the rice varieties and planting density in the rice planting area.

[0050] S1: Acquire multidimensional monitoring data within the rice-growing area and perform nonlinear correlation analysis to extract the interaction characteristics between different environmental variables, including:

[0051] Collect multidimensional monitoring data within the rice-growing area; the multidimensional monitoring data includes meteorological environment monitoring data, soil environment monitoring data, and rice growth status monitoring data;

[0052] Specifically, multiple environmental monitoring and data acquisition devices are set up within the rice-growing area, including meteorological environmental monitoring devices, soil environmental monitoring devices, and rice growth status monitoring devices. The meteorological environmental monitoring devices include air temperature sensors, air humidity sensors, light intensity sensors, and wind speed sensors; the soil environmental monitoring devices include soil moisture sensors, soil organic matter content analyzers, and soil pH sensors; and the rice growth status monitoring devices include rice plant height measuring instruments, leaf area index measuring instruments, and chlorophyll content measuring instruments. Each type of device has multiple monitoring nodes to ensure that the collected data covers the entire rice-growing area.

[0053] Meteorological environmental monitoring devices continuously record data on air temperature, air humidity, light intensity, and wind speed on a minute-by-minute basis; soil environmental monitoring devices record data on soil moisture content, soil organic matter content, and soil pH once per hour; and rice growth status monitoring devices record data on rice plant height, leaf area index, and chlorophyll content once per day. The collection of all the above-mentioned data is referred to as multidimensional monitoring data.

[0054] The multidimensional monitoring data is processed by outlier removal, missing value imputation, and standardization.

[0055] Specifically, outlier removal employs box plotting, where the upper and lower boundaries of each environmental and crop growth variable's data are calculated using box plot statistics. Data points outside these boundaries are considered outliers and removed. Missing value imputation uses an average interpolation method based on adjacent spatial data. When monitoring data is missing, the average of data from the same type of variable at multiple monitoring stations spatially closest to the location of the missing data is used for imputation, ensuring the continuity and accuracy of the monitoring data. Standardization employs extreme value normalization, normalizing the data of each variable to between zero and one by using the difference between its maximum and minimum values ​​to eliminate the influence of dimensionality.

[0056] Based on standardized multidimensional monitoring data, a nonlinear correlation analysis was performed using mutual information analysis to calculate the nonlinear correlation strength between different environmental variables.

[0057] Specifically, mutual information analysis is used to calculate the strength of the nonlinear association between any two distinct environmental variables. The calculation process is as follows: Calculate the data entropy of each environmental variable, which is the sum of the product of the probability distribution of the environmental variable and the logarithm of its probability; calculate the joint entropy of each pair of data variables, which is the sum of the product of the probability of both environmental variables occurring simultaneously and the logarithm of their probabilities; the mutual information value is obtained by adding the data entropies of the two environmental variables separately and then subtracting the joint entropy of the data pair. A larger mutual information value indicates a stronger nonlinear association between the two environmental variables.

[0058] Based on the nonlinear correlation strength between different environmental variables, the interaction features between different environmental variables are extracted;

[0059] Specifically, based on a preset mutual information threshold, pairs of environmental variables with significant correlations are selected. Significantly correlated pairs of environmental variables are defined as combinations of environmental variables whose mutual information values ​​are higher than the mutual information threshold.

[0060] Interaction features are extracted from significantly correlated pairs of environmental variables. These interaction features are characterized by the nonlinear correlation strength of the combinations of significantly correlated environmental variables, the coupling patterns between them, and the coupling trends over time.

[0061] The coupling pattern between environmental variables is defined as follows: when both environmental variables in a pair show an increasing trend or a decreasing trend simultaneously, the pair is defined as a positive coupling pattern; when one environmental variable shows an increasing trend while the other shows a decreasing trend, the pair is defined as a negative coupling pattern; otherwise, the pair is defined as a non-monotonic coupling pattern. For example, if air humidity and leaf area index both increase or decrease simultaneously, then air humidity and leaf area index are determined to have a positive coupling pattern.

[0062] The coupling trend over time refers to the dynamic changes in the coupling relationship over time. For example, if the slope of the regression curve between air temperature and soil moisture content is small during the jointing and booting stage, but significantly increases during the heading and flowering stage, it can be determined that the coupling relationship between air temperature and soil moisture content becomes more significant from the jointing and booting stage to the heading and flowering stage, exhibiting a dynamic trend characteristic as it changes with the growth stage.

[0063] S2: Multi-scale reconstruction analysis of the interaction characteristics between different environmental variables based on spatial scale differences, identifying the main influence areas of different environmental variables, including:

[0064] Rice planting areas are divided into multiple spatial scale levels according to differences in spatial scale;

[0065] Specifically, rice-growing areas are divided into three spatial scales: microscale, mesoscale, and macroscale. The microscale spatial scale is defined as a local area ranging from a few meters to tens of meters, the mesoscale spatial scale is defined as a plot-level area ranging from hundreds of meters, and the macroscale spatial scale is defined as an area ranging from kilometers.

[0066] For each spatial scale level, wavelet multi-scale analysis is used to perform scale reconstruction analysis on the interaction characteristics between environmental variables, and the reconstructed data of the interaction characteristics of environmental variables at each spatial scale level are obtained.

[0067] Specifically, wavelet multi-scale analysis decomposes the interaction features between different environmental variables into different scales using wavelet functions, obtaining reconstructed data of variable interaction features at different spatial scales. Specifically: spatial location data corresponding to different spatial scale levels are extracted from the interaction features between different environmental variables and used as input data; Morleet wavelets of continuous wavelet transform are selected as wavelet basis functions; continuous wavelet transforms are performed on the interaction features between different environmental variables at each spatial scale level using Morleet wavelets to obtain the scale components of the interaction features at different scales; and the scale components at the same spatial scale level are recombined using the scale component reconstruction method to form reconstructed data of environmental variable interaction features at the corresponding spatial scale level.

[0068] The reconstructed data of environmental variable interaction characteristics show the distribution characteristics of the interaction characteristics between different environmental variables as they change with spatial location. For example, at the micro-scale spatial level, the interaction characteristics of environmental variables may be dominated by the interaction between local soil moisture and air humidity in a field, while at the macro-scale spatial level, they may be represented by the overall spatial distribution pattern between soil organic matter content and regional climate variables.

[0069] Based on the interaction characteristics of environmental variables, the data is reconstructed, and the spatial hotspot analysis method is used to identify and mark the main influence areas of different environmental variables at each spatial scale level.

[0070] Specifically, the implementation process of the spatial hotspot analysis method is as follows: Spatial autocorrelation calculation is performed on the reconstructed data of environmental variable interaction characteristics. The spatial autocorrelation calculation method is the calculation of the local spatial autocorrelation coefficient. Specifically, taking the spatial grid at each spatial scale level as the unit, the spatial neighborhood structure of each grid cell is defined, and eight neighboring grids are selected as the analysis neighborhood. The reconstructed data of environmental variable interaction characteristics of each grid cell is standardized, the product of the standardized values ​​between the current cell and neighboring cells is calculated, and normalized with the total variance of all cells to obtain the local spatial autocorrelation coefficient, which is used to identify spatial hotspot areas. Based on the results of the local spatial autocorrelation calculation, it is determined whether the local spatial autocorrelation coefficient exceeds the significance threshold, which is specifically determined based on Monte Carlo simulation calculations. Spatial locations exceeding the significance threshold are defined as spatial hotspot areas, and spatial locations not exceeding the significance threshold are defined as non-hotspot areas.

[0071] Within the spatial hotspot regions at each spatial scale level, the main areas of influence for each environmental variable are identified and marked. For example, at the micro-scale spatial level, the interaction characteristics of soil moisture content and air humidity are identified as hotspot regions; while at the macro-scale spatial level, the interaction characteristics of light intensity and wind speed are identified as hotspot regions.

[0072] S3: Based on the main influence areas of different environmental variables, perform mapping analysis on historical rice growth data to assess the impact of the interaction characteristics between different environmental variables on rice growth, including:

[0073] Based on the main areas of influence of different environmental variables at each spatial scale level, historical rice growth status data are obtained within the rice planting area.

[0074] Specifically, based on the main influence areas of different environmental variables identified and labeled at the micro-scale, meso-scale, and macro-scale spatial levels, corresponding historical rice growth status data were collected, including plant height, leaf area index, and chlorophyll content. The rice growth status data consisted of observational data from corresponding spatial regions over several complete rice growing cycles. Observations were conducted regularly within each rice growth cycle, for example, weekly, to ensure the continuity and completeness of the time series data.

[0075] For the main affected areas at each spatial scale level, the spatial mapping correlation coefficients between historical rice growth status data and different environmental variables were calculated.

[0076] Specifically, based on the main influence areas at each spatial scale level, the spatial mapping correlation coefficient between historical rice growth status data and each environmental variable is calculated to quantify the spatial influence of environmental variables on rice growth. The calculation method for the spatial mapping correlation coefficient is as follows: for the main influence areas of each environmental variable at each spatial scale level, the data reconstructed using the interaction characteristics of environmental variables are used as spatial variables, and historical rice growth status data is used as the target variable. The correlation between these two variables at spatial locations is calculated separately. A spatial bivariate correlation analysis method is employed. This method involves calculating the degree of co-change between environmental variable values ​​and rice growth status values ​​corresponding to the same spatial location to obtain the spatial mapping correlation coefficient. The calculation first calculates the standardized values ​​of the environmental variable and the rice growth status variable in space, then averages the products of the two sets of standardized values. The final average value is the spatial mapping correlation coefficient. A spatial mapping correlation coefficient close to one indicates a high spatial correlation between the environmental variable and the rice growth status data.

[0077] For example, at the micro-scale spatial level, the spatial mapping correlation coefficient between soil moisture content and rice leaf area index is calculated; at the meso-scale spatial level, the spatial mapping correlation coefficient between air humidity and rice plant height is calculated; and at the macro-scale spatial level, the spatial mapping correlation coefficient between light intensity and rice chlorophyll content is calculated. The spatial mapping correlation coefficient calculation for each spatial scale is performed separately to avoid interference between scales.

[0078] Based on the spatial mapping correlation coefficient, a nonlinear regression method was used to assess the comprehensive impact of the interaction characteristics between different environmental variables on rice growth, and the assessment results of the impact of the interaction characteristics between different environmental variables on rice growth were obtained.

[0079] Specifically, spatial mapping correlation coefficients and interaction characteristics between different environmental variables were used as independent variables, and rice growth status monitoring data were used as dependent variables. A nonlinear regression model was selected for fitting. First, a set of candidate nonlinear regression models was determined, including exponential, logarithmic, and power-law nonlinear models. Cross-validation was used to optimize the parameters of the candidate models. The cross-validation method involved dividing historical observation data into multiple subsets, one for model fitting and another for model accuracy testing, alternating between fitting and validation to evaluate the goodness of fit. The parameter configuration scheme was determined from the model with the highest goodness of fit. The model parameters were determined using the least squares method, i.e., by adjusting the parameters to minimize the sum of squared residuals between the predicted values ​​output by the nonlinear regression model and the actual historical rice growth status data.

[0080] After fitting the nonlinear regression model, the evaluation results of the influence of the interaction between various environmental variables on the growth status of rice are obtained through the model parameters and the nonlinear regression function. The evaluation results are reflected in the proportion or trend of changes in rice plant height, leaf area index and chlorophyll content caused by changes in the value of the interaction of environmental variables.

[0081] For example, nonlinear regression analysis may find that a 10 percent increase in the interaction between soil moisture content and air humidity will cause an average increase of 5 percent in rice leaf area index; while at another spatial scale level, a 10 percent increase in the interaction between light intensity and soil organic matter content will lead to a 3 percent increase in rice chlorophyll content; these constitute the assessment results of the impact of the interaction between different environmental variables on rice growth.

[0082] S4: Analyze the temporal sequence of the effects of different environmental variables during the rice growth cycle, and extract the changing patterns of the influence weights of different environmental variables at different growth stages, including:

[0083] Rice growth stages are divided based on the complete growth cycle of rice. The growth stages of rice include the jointing and booting stage, the heading and flowering stage, and the grain filling and ripening stage.

[0084] Specifically, based on the growth patterns of rice crops in actual production and practical experience in agricultural planting and management, the complete growth cycle of rice is rationally divided into three typical growth stages: the jointing and booting stage, the heading and flowering stage, and the grain-filling stage. The jointing and booting stage begins when the rice stem elongates and ends before the formation of the panicle; the heading and flowering stage begins when the panicle emerges from the leaf sheath and begins to emerge, and ends when the panicle is fully flowering; the grain-filling stage begins after flowering at the panicle and continues until grain filling is completed before maturity.

[0085] At each growth stage, the values ​​of each environmental variable in the standardized multidimensional monitoring data were extracted, and time-series modeling was performed on the changes in environmental variable values ​​at different growth stages.

[0086] Specifically, for the jointing and booting stage, heading and flowering stage, and grain-filling stage, the values ​​of all environmental variables for each stage were independently extracted from multidimensional monitoring data that had undergone outlier removal, missing value imputation, and standardization. These included meteorological environmental monitoring data, soil environmental monitoring data, and rice growth status monitoring data. The meteorological environmental monitoring data included values ​​for air temperature, air humidity, light intensity, and wind speed; the soil environmental monitoring data included values ​​for soil moisture content, soil organic matter content, and soil pH; and the rice growth status monitoring data included values ​​for rice plant height, leaf area index, and chlorophyll content. The extraction method involved extracting the standardized data daily according to the start and end dates of each stage, forming a continuous numerical sequence of environmental variables for each stage, thus constituting the dataset for each stage.

[0087] Time-series modeling was performed on datasets from the jointing and booting stage, heading and flowering stage, and grain-filling stage. The autoregressive moving average (ARMA) model was chosen for time-series modeling analysis. The ARMA modeling method involves: treating environmental variables at each growth stage as time series; calculating the autocorrelation relationship between the current variable value and values ​​from previous time points, as well as the moving average relationship between the variable value and random disturbance terms from previous time points, based on the variable values' positions on the time axis; subsequently, determining the optimal parameters for the order of the autoregressive and moving average terms using the autocorrelation and partial autocorrelation functions; determining the optimal values ​​of the model parameters using maximum likelihood estimation; and finally, evaluating the model's accuracy through residual analysis and goodness-of-fit tests to ensure the model reflects the actual growth conditions of rice.

[0088] For example, for the environmental variable of air temperature during the jointing and booting stage, the modeling process of the autoregressive moving average model is as follows: calculate the numerical sequence of daily air temperature during the jointing and booting stage, analyze the correlation between the current air temperature value and the air temperature values ​​of several consecutive days in the past, and determine the most suitable order and model parameters through maximum likelihood estimation, thereby obtaining a dynamic model of the change of air temperature variable with the time of the jointing and booting stage.

[0089] Based on time series modeling, the influence weight values ​​of each environmental variable at different growth stages are calculated to obtain the variation law of the influence weight of each environmental variable at different growth stages of rice.

[0090] Specifically, after time-series modeling is completed, the influence weights of each environmental variable during the jointing and booting stage, the heading and flowering stage, and the grain-filling stage are calculated. The calculation method for these influence weights is as follows: First, using the time-series model for each environmental variable, the covariance between the amplitude of the environmental variable's numerical fluctuation and the amplitude of the rice growth status variable's numerical fluctuation is calculated; then, the covariance is divided by the sum of the covariances of all environmental variables to obtain the standardized influence weight of each environmental variable at the corresponding growth stage. The influence weight of each environmental variable represents its contribution to changes in the rice's growth status.

[0091] The influence weight values ​​of each environmental variable obtained at the jointing and booting stage, heading and flowering stage, and grain filling stage are arranged in chronological order to form a sequence of weight changes of each environmental variable at different growth stages, demonstrating the dynamic evolution of the influence pattern of environmental variables on rice growth stages.

[0092] For example, based on the above analysis, the environmental variable of air temperature may have a higher weight in its influence on rice growth during the jointing and booting stage, while its weight gradually decreases during the heading and flowering stage and the grain filling stage; while the environmental variable of light intensity has a lower weight in its influence during the jointing and booting stage, and gradually increases during the grain filling stage.

[0093] The changing patterns of influence weights can clearly express the varying degrees of importance of different environmental variables at different growth stages of rice, providing a basis for decision-making in assessing the growth potential of rice varieties and formulating planting management plans.

[0094] S5: Based on the assessment results of the impact of the interaction characteristics between different environmental variables on rice growth and the changing patterns of the influence weights of different environmental variables at different growth stages, assess the growth potential of different rice varieties in the rice-growing area, including:

[0095] The assessment results of the impact of the interaction characteristics between different environmental variables on rice growth are integrated with the changing patterns of the influence weights of each environmental variable at different growth stages of rice.

[0096] Specifically, based on the assessment results of the impact of the interaction characteristics between different environmental variables on rice growth and the changing patterns of the influence weights of each environmental variable during the jointing and booting stages, heading and flowering stages, and grain-filling stages, data fusion was performed. The fusion method was a weighted data fusion method. The implementation process of the weighted data fusion method was as follows: for each environmental variable, its influence weight value at each growth stage was used as a weight coefficient, which was then multiplied by the assessment value of the interaction between the environmental variable and other variables on rice growth to obtain the weighted environmental variable interaction influence value; then, the weighted environmental variable interaction influence values ​​of all environmental variables were summed, and the summed value was the fusion result. The weighted data fusion method can reasonably take into account both the spatial characteristics of the interaction between environmental variables and the dynamic changes of each environmental variable at different stages, thus accurately reflecting the comprehensive influence pattern of environmental variables on rice growth.

[0097] For example, taking air temperature and air humidity as two environmental variables, during the jointing and booting stage, the weighted values ​​of the influence of air temperature on rice growth are first multiplied by the impact assessment values ​​of the interaction between air temperature and air humidity; then, the weighted values ​​of the influence of air humidity on rice growth are multiplied by the impact assessment values ​​of the interaction between air humidity and air temperature; finally, all the weighted values ​​obtained above are summed to form the fusion result of the interaction between air temperature and air humidity environmental variables during the jointing and booting stage. The data fusion process for the heading and flowering stage and the grain-filling stage is the same as the above method, and fusion calculations are performed separately.

[0098] Based on the fusion results, a matching matrix between rice varieties and environmental responses is constructed;

[0099] Specifically, the different rice varieties to be evaluated within the rice-growing area are used as rows in the matching matrix; the combined environmental scenarios formed by the jointing and booting stages, heading and flowering stages, and grain-filling stages with each environmental variable are used as columns in the matching matrix; the adaptability of each rice variety in each combined environmental scenario is scored individually. The adaptability score is determined by the similarity between the historical planting performance data of the rice variety and the fusion result, that is, by calculating the cosine similarity between the historical growth state performance vector of each rice variety and the fusion result vector using a cosine similarity algorithm. The larger the cosine value, the higher the adaptability of the rice variety to the corresponding environmental scenario. Finally, all the adaptability scores formed by the above methods constitute a complete matching matrix of rice varieties and environmental responses.

[0100] The cosine similarity algorithm is calculated as follows: First, the growth performance data of each rice variety under historical environmental conditions, including plant height, leaf area index, and chlorophyll content, are used as historical growth performance vectors. Then, the current environmental variables are fused to form the current environmental feature vector. The inner product of the historical performance vector and the current environmental feature vector, as well as the lengths of the historical performance vector and the current environmental feature vector, are calculated separately. Finally, the cosine value is determined by dividing the inner product by the product of the two vector lengths. The calculated cosine value ranges from -1 to +1; the closer the value is to +1, the higher the degree of matching between the rice variety and the environmental conditions, and the higher the adaptability score.

[0101] Based on the matching matrix between rice varieties and environmental responses, the growth potential of multiple rice varieties in the rice planting area is assessed, and the adaptability score of each rice variety in the current complex environment is output.

[0102] Specifically, the growth potential of multiple rice varieties within the rice-growing area is assessed based on the adaptability scores in the matching matrix. The growth potential assessment method is as follows: for each rice variety, the adaptability scores at the jointing and booting stage, heading and flowering stage, and grain-filling stage are arithmetically averaged. This involves adding the adaptability scores for the three stages and then dividing by the number of scores to obtain the adaptability score for each rice variety under the current complex environment. A higher adaptability score indicates stronger growth potential of the rice variety under the complex environment.

[0103] The current complex environment refers to a multifunctional agricultural ecosystem dominated by paddy fields, whose spatial structure, resource utilization, and ecological elements exhibit highly intertwined and complex characteristics. It is usually distributed in semi-mountainous or hilly areas with large topographic relief and diverse types of arable land. It realizes three-dimensional planting of rice and dryland crops such as sorghum in the same farming unit, and carries out aquaculture activities such as fish, shrimp, and soft-shelled turtles in combination with the water layer conditions of paddy fields.

[0104] S6: Based on the growth potential assessment results, adjustments are made to the rice planting varieties and planting density within the rice-growing area, including:

[0105] A preset adaptation score threshold is set, and the adaptation score is compared with the adaptation score threshold to select rice varieties with an adaptation score higher than the adaptation score threshold.

[0106] Specifically, an adaptation score threshold is set for variety selection. The adaptation score threshold is set using a dynamic method based on statistical quantiles: first, the comprehensive adaptation scores of all rice varieties are sorted from high to low; then, based on the set target retention ratio (e.g., 30%), the value of the adaptation score at that quantile is determined as the adaptation score threshold.

[0107] After setting the adaptability score threshold, the comprehensive adaptability scores of all rice varieties are screened, and rice varieties with comprehensive adaptability scores higher than the adaptability score threshold are retained as the target variety set for planting in the current complex environment.

[0108] Within the rice-growing area, the planting range of each selected rice variety was determined, and the planting density of each rice variety within the planting range was determined by combining the standardized multidimensional monitoring data.

[0109] Specifically, based on the target set of rice varieties, spatial positioning and planting range delineation are performed within the rice planting area: standardized multidimensional monitoring data are used as spatial input into the matching matrix of each rice variety and its environmental response to determine the matching degree between each spatial grid and each target rice variety under the current environment. Each spatial grid retains only the target rice variety with the highest matching degree, and the spatial grid is delineated as the recommended planting range for the corresponding rice variety.

[0110] For example, in a complex ecological planting area, the air humidity is high, the soil moisture content is stable, and the light intensity is relatively weak. By inputting multidimensional monitoring data and comparing it with the matching matrix of multiple screened rice varieties, it is found that the matching degree of a certain rice variety in the complex ecological planting area is higher than that of other rice varieties. Then, the complex ecological planting area is designated as the recommended planting range for the corresponding rice variety.

[0111] After determining the planting area for each rice variety, specific planting density and management methods are established within that area. The planting density is determined based on a combination of the rice variety's growth characteristics and the local resource and environmental carrying capacity: the combination of air temperature, air humidity, light intensity, and soil moisture content within the planting area is used as input characteristics; the optimal density range is consulted using a database of the variety's growth habits, and the recommended planting density for the target plot is determined through a range mapping method. For example, the suitable density for a certain variety under low light and high humidity conditions is 30 plants per square meter, while the suitable density under high light and low humidity conditions is adjusted to 25 plants per square meter.

[0112] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0113] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0114] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0115] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0117] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0118] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0119] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0121] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A diversified rice planting method in a composite environment based on big data analysis, characterized in that, Includes the following steps: S1: Obtain multidimensional monitoring data within the rice-growing area and perform nonlinear correlation analysis to extract the interaction characteristics between different environmental variables, specifically: Collect multidimensional monitoring data within the rice-growing area; the multidimensional monitoring data includes meteorological environment monitoring data, soil environment monitoring data, and rice growth status monitoring data; The multidimensional monitoring data is processed by outlier removal, missing value imputation, and standardization. Based on standardized multidimensional monitoring data, a nonlinear correlation analysis was performed using mutual information analysis to calculate the nonlinear correlation strength between different environmental variables. Based on the nonlinear correlation strength between different environmental variables, the interaction features between different environmental variables are extracted; S2: Based on spatial scale differences, multi-scale reconstruction analysis is performed on the interaction characteristics between different environmental variables to identify the main influence areas of different environmental variables, specifically: Rice planting areas are divided into multiple spatial scale levels according to differences in spatial scale; For each spatial scale level, wavelet multi-scale analysis is used to perform scale reconstruction analysis on the interaction characteristics between environmental variables, and the reconstructed data of the interaction characteristics of environmental variables at each spatial scale level are obtained. Based on the interaction characteristics of environmental variables, the data is reconstructed, and the spatial hotspot analysis method is used to identify and mark the main influence areas of different environmental variables at each spatial scale level. S3: Based on the main influence areas of different environmental variables, perform mapping analysis on historical rice growth data to assess the impact of the interaction characteristics between different environmental variables on rice growth. Specifically: Based on the main areas of influence of different environmental variables at each spatial scale level, historical rice growth status data are obtained within the rice planting area. For the main affected areas at each spatial scale level, the spatial mapping correlation coefficients between historical rice growth status data and different environmental variables were calculated. Based on spatial mapping correlation coefficient, nonlinear regression method is used to evaluate the comprehensive impact of the interaction characteristics between different environmental variables on rice growth, and the evaluation results of the impact of the interaction characteristics between different environmental variables on rice growth are obtained. S4: Analyze the temporal sequence of the effects of different environmental variables during the rice growth cycle, and extract the changing patterns of the influence weights of different environmental variables at different growth stages. Specifically: Rice growth stages are divided based on the complete growth cycle of rice. The growth stages of rice include the jointing and booting stage, the heading and flowering stage, and the grain filling and ripening stage. At each growth stage, the values ​​of each environmental variable in the standardized multidimensional monitoring data were extracted, and time-series modeling was performed on the changes in environmental variable values ​​at different growth stages. Based on time series modeling, the influence weight values ​​of each environmental variable at different growth stages are calculated to obtain the variation law of the influence weight of each environmental variable at different growth stages of rice. S5: Based on the assessment results of the impact of the interaction characteristics between different environmental variables on rice growth and the changing patterns of the influence weights of different environmental variables at different growth stages, the growth potential of different rice varieties in the rice-growing area is assessed, specifically: The assessment results of the impact of the interaction characteristics between different environmental variables on rice growth are integrated with the changing patterns of the influence weights of each environmental variable at different growth stages of rice. Based on the fusion results, a matching matrix between rice varieties and environmental responses is constructed; Based on the matching matrix between rice varieties and environmental responses, the growth potential of multiple rice varieties in the rice planting area is assessed, and the adaptability score of each rice variety in the current complex environment is output. S6: Based on the growth potential assessment results, adjustments will be made to the rice varieties and planting density within the rice-growing area, specifically as follows: A preset adaptation score threshold is set, and the adaptation score is compared with the adaptation score threshold to select rice varieties with an adaptation score higher than the adaptation score threshold. Within the rice-growing area, the planting range of each selected rice variety was determined, and the planting density of each rice variety within the planting range was determined by combining standardized multidimensional monitoring data.

Images