Water-saving, yield-increasing, efficiency-improving and emission-reducing irrigation and nitrogen application optimization method and device

Abstract

This invention relates to the field of agricultural production technology and discloses a method and apparatus for optimizing irrigation nitrogen application to save water, increase yield, improve efficiency, and reduce emissions. The invention uses planting control parameter values ​​and planting effect evaluation data for each grid in a study area during each period to determine the optimal control interval. Multiple control parameter values ​​to be evaluated are extracted from the optimal control interval, and the planting effect prediction data for the target grid is obtained when planting the target crop using each of the evaluated control parameter values. Based on each planting effect prediction data, the optimal control parameter value for the target grid is determined from the multiple evaluated control parameter values. This invention combines the planting control parameter values ​​for each grid in the study area during each period to determine the optimal irrigation ratio or optimal nitrogen application ratio for each grid, achieving optimization of irrigation nitrogen application for crop planting in each grid, and comprehensively improving the water-saving, yield-increasing, efficiency-improving, and emission-reducing benefits of crop planting.

Description

Technical Field

[0001] This invention relates to the field of agricultural production technology, and in particular to an optimized method and apparatus for irrigation nitrogen application that saves water, increases yield, improves efficiency, and reduces emissions. Background Technology

[0002] Under the multiple pressures of population growth and climate change, the global food crisis is becoming increasingly severe. Agricultural irrigation and nitrogen fertilizer application are considered important means to increase food yields and enhance agriculture's ability to adapt to climate change. However, excessive irrigation and nitrogen fertilizer input have led to reduced water use efficiency and nitrogen fertilizer use efficiency in many key agricultural areas around the world, causing groundwater depletion and resulting in [various consequences]. The increasing environmental emissions of substances such as ammonia and nitrates have had a profound impact on ecosystems, human health, and climate change.

[0003] Compared to traditional irrigation, water-saving irrigation can effectively reduce greenhouse gas emissions while simultaneously increasing food production. However, there are complex interrelationships between water-saving irrigation, increased production, and emission reduction. For example, while water-saving irrigation increases production, it may also lead to… Increased emissions. While nitrogen reduction management can reduce greenhouse gas emissions and improve nitrogen use efficiency, it may lead to reduced crop yields. Slight reduction in nitrogen fertilizer application can reduce greenhouse gas emissions slightly without seriously affecting yields, but as the proportion of fertilizer application further decreases, greenhouse gas emissions are significantly suppressed, but yield losses are severe.

[0004] Therefore, finding a balance between reducing agricultural water use, increasing grain production, improving resource utilization efficiency, and reducing greenhouse gas emissions has become an important issue that urgently needs to be addressed. Summary of the Invention

[0005] This invention provides an irrigation nitrogen application optimization method and device for water saving, yield increase, efficiency improvement and emission reduction, which solves the defects in related technologies that cannot find a balance point between reducing agricultural water use, increasing grain production, improving resource utilization efficiency and reducing greenhouse gas emissions. It realizes the optimization of irrigation nitrogen application for grid crop planting, and comprehensively improves the water saving, yield increase, efficiency improvement and emission reduction benefits of crop planting.

[0006] In a first aspect, the present invention provides an optimized irrigation nitrogen application method for water conservation, increased yield, improved efficiency, and reduced emissions, comprising: The optimal control interval is determined based on the planting control parameter values ​​and corresponding planting effect evaluation data for each grid in the study area during each period. The planting control parameter values ​​are the irrigation ratio or nitrogen application ratio for the target crop, and the planting effect evaluation data is used to evaluate the water-saving, yield-increasing, efficiency-improving, and emission-reducing effects. Multiple control parameter values ​​to be evaluated are extracted from the optimal control range; Using a trained planting effect prediction model, the planting effect prediction data of the target grid is predicted when the target crop is planted with each of the aforementioned control parameters to be evaluated; wherein, the target grid is any of the aforementioned grids; Based on each of the predicted planting effect data, the optimal control parameter value for the target grid is determined from among the plurality of control parameter values ​​to be evaluated.

[0007] Optionally, determining the optimal control interval based on the planting control parameter values ​​and corresponding planting effect evaluation data of each grid cell in the study area during each period includes: In the specified data source, the planting control parameter values ​​and planting effect evaluation data of each grid in each period are obtained respectively; Cluster the planting control parameter values ​​of each grid within each periodic time to determine multiple planting control intervals; Meta-analysis was used to determine the overall improvement benefit of each planting control interval on the planting effect evaluation data, and the maximum overall improvement benefit was determined. The planting control interval corresponding to the maximum overall improvement benefit is determined as the optimal control interval.

[0008] Optionally, the planting effect evaluation data includes the index values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators, and emission-reduction evaluation indicators; The method of using a trained planting effect prediction model to predict the planting effect of the target grid when the target crop is planted with each of the evaluated control parameters includes: For any of the aforementioned control parameter values ​​to be evaluated, the target period for planting the target crop using the aforementioned control parameter value is found in the specified data source. Other planting impact data corresponding to the target crop within the target period for the target grid are obtained. The control parameter value to be evaluated and the other planting impact data are input into the planting effect prediction model to predict the planting effect, thereby obtaining the predicted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index. These values ​​are then used as the overall planting effect prediction data for the target grid when the target crop is planted using the control parameter value to be evaluated.

[0009] Optionally, determining the optimal control parameter value for the target grid from the plurality of control parameter values ​​to be evaluated based on each of the planting effect prediction data includes: For any of the aforementioned control parameter values ​​to be evaluated, the predicted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index of the target grid under the condition of planting the target crop with the aforementioned control parameter value to be evaluated are standardized to obtain the corresponding standardized predicted value. Based on each standardized predicted value, the comprehensive evaluation value of the planting effect of the target grid under the condition of planting the target crop with the aforementioned control parameter value to be evaluated is determined. The maximum comprehensive evaluation value of planting effect is determined among each of the comprehensive evaluation values ​​of planting effect, and the value of the control parameter to be evaluated corresponding to the maximum comprehensive evaluation value of planting effect is determined as the optimal control parameter value of the target grid.

[0010] Optionally, the standardization of the predicted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index for the target grid when the target crop is planted using the evaluation control parameter values ​​includes: For any evaluation index, obtain the index prediction value of the evaluation index of the target grid when the target crop is planted with each of the evaluation control parameter values ​​respectively. Determine the maximum prediction value and the minimum prediction value of each obtained index prediction value. Use the maximum prediction value and the minimum prediction value to standardize the index prediction value of the evaluation index of the target grid when the target crop is planted with the evaluation control parameter value to obtain the corresponding standardized prediction value. The evaluation indicators are the water-saving evaluation indicators, the production-increasing evaluation indicators, the efficiency-improving evaluation indicators, or the emission-reduction evaluation indicators.

[0011] Optionally, determining the comprehensive evaluation value of the planting effect of the target grid when the target crop is planted using the evaluation control parameter value, based on each of the standardized predicted values, includes: Obtain the set weights for the water-saving evaluation index, the production increase evaluation index, the efficiency improvement evaluation index, and the emission reduction evaluation index; Based on the weighted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index, a weighted sum is calculated for each standardized predicted value corresponding to the value of the control parameter to be evaluated, and this sum is used as the comprehensive evaluation value of the planting effect of the target grid when the target crop is planted using the control parameter value to be evaluated.

[0012] Optionally, the extraction of multiple control parameter values ​​to be evaluated within the optimal control range includes: According to the set interval step size, the multiple control parameter values ​​to be evaluated are extracted in the optimal control range.

[0013] Optionally, when the interval step size is positive, the step of extracting the multiple control parameter values ​​to be evaluated within the optimal control range according to the set interval step size includes: The minimum value in the optimal control range is determined as the first control parameter value to be evaluated. The first control parameter value to be evaluated is added to the interval step size to obtain the corresponding sum value, which is then used as the second control parameter value to be evaluated. The second control parameter value to be evaluated is added to the interval step size to obtain the corresponding sum value, which is then used as the third control parameter value to be evaluated, until all control parameter values ​​to be evaluated are obtained.

[0014] Optionally, before using the trained planting effect prediction model to predict the planting effect prediction data of the target grid when the target crop is planted with each of the evaluated control parameter values, the method further includes: For any of the grids, if the value of the planting control parameter of the target crop for the grid is within the optimal control range during the periodic time, the grid is determined as a training grid. For any of the training grids, other planting impact data corresponding to the target crop within the specified period are obtained from the specified data source. The planting control parameter values ​​and other planting impact data of the training grid within the specified period are used as training data as a whole, and the planting effect evaluation data of the training grid within the specified period are used as the label of the training data. The pre-trained model is trained using each of the training data and the corresponding label to obtain a trained planting effect prediction model.

[0015] Secondly, the present invention provides an irrigation nitrogen application optimization device for water saving, yield increase, efficiency improvement, and emission reduction, comprising: The interval determination unit is used to determine the optimal control interval based on the planting control parameter values ​​and corresponding planting effect evaluation data of each grid in the study area during each period; wherein, the planting control parameter values ​​are the irrigation ratio or nitrogen application ratio of the target crop, and the planting effect evaluation data is used to evaluate the water-saving, yield-increasing, efficiency-improving and emission-reducing effects. The proportional extraction unit is used to extract multiple control parameter values ​​to be evaluated within the optimal control range. The effect prediction unit is used to predict the planting effect prediction data of the target grid when the target crop is planted with each of the evaluation control parameter values ​​using a trained planting effect prediction model; wherein, the target grid is any of the grids. The proportion determination unit is used to determine the optimal control parameter value of the target grid from among the plurality of control parameter values ​​to be evaluated, based on each of the planting effect prediction data.

[0016] The present invention provides an irrigation nitrogen application optimization method and apparatus for water conservation, yield increase, efficiency improvement, and emission reduction. It utilizes planting control parameter values ​​and planting effect evaluation data for each grid cell in a study area during each period to determine the optimal control interval. The planting control parameter values ​​are the irrigation or nitrogen application ratios for the target crop, and the planting effect evaluation data is used to evaluate water conservation, yield increase, efficiency improvement, and emission reduction effects. Multiple control parameter values ​​to be evaluated are extracted from the optimal control interval. A trained planting effect prediction model is used to predict the planting effect of the target grid cell when planting the target crop with each of the evaluated control parameter values. Here, the target grid cell can be any grid cell. Based on each planting effect prediction data, the optimal control parameter value for the target grid cell is determined from the multiple evaluated control parameter values. This invention can combine the planting control parameter values ​​of each grid in the research area during each cycle period, and determine the optimal irrigation ratio or optimal nitrogen application ratio for each grid while comprehensively considering the effects of water saving, yield increase, efficiency improvement and emission reduction. This achieves optimization of irrigation and nitrogen application for crop planting in each grid, and finds a balance point between reducing agricultural water use, increasing grain production, improving resource utilization efficiency and reducing greenhouse gas emissions, thereby comprehensively improving the water-saving, yield increase, efficiency improvement and emission reduction benefits of crop planting. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating an optimized irrigation nitrogen application method for water conservation, yield increase, efficiency improvement, and emission reduction, provided by an embodiment of the present invention; Figure 2 This invention provides a record table of predicted values ​​for various evaluation indicators for grid A when using different nitrogen application ratios to be evaluated. Figure 3 This invention provides an extreme value recording table of predicted values ​​of various evaluation indicators for grid A when using different nitrogen application ratios to be evaluated; Figure 4 A standardized predicted value recording table of various evaluation indicators for grid A when using different nitrogen application ratios to be evaluated is provided for an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an irrigation nitrogen application optimization device for water saving, yield increase, efficiency improvement and emission reduction provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] The following is combined Figures 1-4 This invention describes an optimized irrigation nitrogen application method for water conservation, increased yield, improved efficiency, and reduced emissions.

[0021] like Figure 1 As shown in the figure, this embodiment proposes a first method for optimizing irrigation nitrogen application to save water, increase yield, improve efficiency, and reduce emissions. This method may include the following steps: S101. Based on the planting control parameter values ​​and corresponding planting effect evaluation data of each grid in the study area during each period, determine the optimal control interval; wherein, the planting control parameter values ​​are the irrigation ratio or nitrogen application ratio of the target crop, and the planting effect evaluation data are used to evaluate the water-saving, yield-increasing, efficiency-improving and emission-reducing effects.

[0022] The research area can be a large geographical region, such as a province or city, a domestic region, or a global region.

[0023] Specifically, a raster is one of several regions obtained by rasterizing the study area.

[0024] A cycle period is an artificially defined time period with a specific market, used to collect data related to crop cultivation during the planting process. Adjacent cycle periods are consecutive. Cycle periods can be set by technicians based on actual conditions and needs, and can be relatively long; for example, a cycle period can be a whole year, multiple consecutive whole years, or even half a year.

[0025] It should be noted that there can be multiple periodic periods. When the periodic period is a whole year, multiple periodic periods can include the first year, the second year, the third year, and so on up to the Nth year of planting crops.

[0026] The target crop is a specific type of crop, such as corn, wheat and cotton. This embodiment does not limit the type of crop.

[0027] Specifically, the planting control parameter value is the irrigation ratio or nitrogen application ratio used by the grid to plant the target crop within a periodic time. Taking the nitrogen application ratio as an example, it is the ratio of the actual nitrogen application amount to the conventional nitrogen application amount, reflecting the reduction in the actual nitrogen application amount compared to the conventional nitrogen application amount. For example, when the nitrogen application ratio is 0.8, it means that the actual nitrogen application amount is reduced by 20% compared to the conventional nitrogen application amount. The irrigation ratio is the ratio of the actual irrigation amount to the conventional irrigation amount.

[0028] Among them, the planting effect evaluation data is used to evaluate the effects of the grid on water conservation, yield increase, efficiency improvement and emission reduction when the target crop is planted with planting control parameter values ​​within a period of time.

[0029] The optimal control range is the range of planting control parameter values ​​that achieves the best comprehensive effect in terms of water saving, yield increase, efficiency improvement and emission reduction among the planting control parameter values ​​used in each grid in each period.

[0030] Specifically, in this embodiment, the planting control parameter values ​​and planting effect evaluation data of each grid in the research area for each period can be searched and collected from a specified data source (such as a specified database or industry association website). Then, the optimal control interval can be determined based on the collected planting control parameter values ​​and planting effect evaluation data.

[0031] To better illustrate the execution process of step S101, this embodiment uses the planting control parameter value as the nitrogen application ratio as an example, and the following Example 1 is presented for illustration.

[0032] Example 1: If there are two time periods, namely the first time period and the second time period, this embodiment can obtain the nitrogen application ratio and planting effect evaluation data of any grid in the study area during the first time period, and obtain the nitrogen application ratio and planting effect evaluation data of the grid during the second time period. Then, based on the nitrogen application ratio and planting effect evaluation data of each grid during the first time period and the second time period, the optimal nitrogen application ratio range is determined.

[0033] Optionally, step S101 includes: In the specified data source, obtain the planting control parameter values ​​and planting effect evaluation data for each grid cell in each period. Cluster the planting control parameter values ​​of each grid within each period to determine multiple planting control intervals; Meta-analysis was used to determine the overall improvement benefit of each planting control interval on the planting effect evaluation data, and the maximum overall improvement benefit was determined. The planting control range corresponding to the maximum overall improvement benefit is determined as the optimal control range.

[0034] To better illustrate the clustering process described above, this embodiment uses Example 1 as an example. If there are two time periods, namely the first time period and the second time period, this embodiment can obtain the nitrogen application ratio and planting effect evaluation data for each grid in the first time period and the second time period, respectively, and cluster all the obtained nitrogen application ratios to obtain multiple nitrogen application ratio intervals.

[0035] Optionally, in this embodiment, technicians can directly set multiple nitrogen application ratio ranges without determining them by clustering the nitrogen application ratio of each grid cell in each period. For example, in this embodiment, technicians can set four nitrogen application ratio ranges, namely (0, 0.4), [0.4, 0.6), [0.6, 0.8), and [0.8, 1).

[0036] Optionally, an example is provided using the nitrogen application ratio as a planting control parameter. The planting effect evaluation data includes the values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators, and emission-reduction evaluation indicators. Among them, the water-saving evaluation indicator includes evapotranspiration (ET), the yield-increasing evaluation indicator includes crop yield, the efficiency-improving evaluation indicators include water use efficiency (WUE) and nitrogen fertilizer use efficiency (NUE), and the emission-reduction evaluation indicators include... Emissions and Emissions.

[0037] Specifically, this example uses nitrogen application ratio as the planting control parameter, with the planting control interval being the nitrogen application ratio interval. This embodiment uses meta-analysis to analyze the overall improvement benefits of different nitrogen application ratio intervals on various evaluation indicators in the planting effect evaluation data. For example, for the first nitrogen application ratio interval, this embodiment uses meta-analysis to determine the improvement value of each evaluation indicator when using the first nitrogen application ratio interval. The improvement values ​​of each evaluation indicator are then added together to obtain the overall improvement benefit of the first nitrogen application ratio interval on the planting effect evaluation data. It should be noted that the improvement value of the first nitrogen application ratio interval on a certain evaluation indicator can be positive, 0, or negative. This embodiment can determine the maximum overall improvement benefit among the overall improvement benefits of various nitrogen application ratio intervals on the planting effect evaluation data, and determine the nitrogen application ratio interval corresponding to the maximum overall improvement benefit as the optimal nitrogen application ratio interval, i.e., the optimal control interval. For example, this embodiment analyzes the overall improvement benefits of nitrogen application ratios [0.8, 1) and [0.6, 0.8) on planting effect evaluation data. Among the improvements in benefits for various evaluation indicators in the nitrogen application ratio range [0.6, 0.8), Yield is reduced only slightly, and WUE and ET are almost unaffected, but Yield is significantly reduced. and While the nitrogen application ratio range [0.8, 1) offers slightly better benefits for some evaluation indicators, its greenhouse gas emission reduction effect is insufficient. Considering all evaluation indicators, the overall improvement benefit of [0.6, 0.8) is the highest. In this embodiment, [0.6, 0.8) can be determined as the optimal nitrogen application ratio range.

[0038] Optionally, in this embodiment, when determining the optimal nitrogen application ratio range among each nitrogen application ratio range, ranges that clearly do not conform to realistic logic can be excluded first, and then the optimal nitrogen application ratio range can be determined from the remaining ranges. For example, when four nitrogen application ratio ranges (0, 0.4), [0.4, 0.6), [0.6, 0.8), and [0.8, 1) are determined by clustering, the nitrogen application ratio range (0, 0.4) indicates that the actual fertilizer application of the grid during the period is reduced by more than 60% compared to the conventional fertilizer application amount, which clearly does not conform to realistic logic. Therefore, the nitrogen application ratio range (0, 0.4) can be excluded, and the optimal nitrogen application ratio range can be determined from the remaining nitrogen application ratio ranges [0.4, 0.6), [0.6, 0.8), and [0.8, 1).

[0039] Understandably, the nitrogen application ratio reflects the percentage reduction in actual nitrogen application compared to the conventional nitrogen application rate. Therefore, the nitrogen application ratio range reflects the range of this reduction. For example, a nitrogen application ratio range of [0.6, 0.8) indicates that the actual nitrogen application rate is reduced by 20% to 40% compared to the conventional rate. Another example is a nitrogen application ratio range of (0, 0.4), indicating that the actual nitrogen application rate is reduced by more than 60% compared to the conventional rate. Yet another example is a nitrogen application ratio range of [0.8, 1), indicating that the actual nitrogen application rate is reduced by less than 20% compared to the conventional rate.

[0040] S102. Extract multiple control parameter values ​​to be evaluated from the optimal control range.

[0041] Specifically, taking the planting control parameter value as the nitrogen application ratio as an example, this embodiment can randomly extract multiple nitrogen application ratios as nitrogen application ratios to be evaluated from the optimal nitrogen application ratio range, or it can extract multiple nitrogen application ratios to be evaluated from the optimal nitrogen application ratio range in a specific way.

[0042] Optionally, step S102 may include: According to the set interval step size, multiple control parameter values ​​to be evaluated are extracted in the optimal control range.

[0043] The interval step size can be set by technicians according to actual conditions and needs, and this embodiment does not limit it. For example, when the optimal nitrogen application ratio range is [0.6, 0.8), the interval step size can be 0.01.

[0044] Optionally, when the interval step size is positive, the above-mentioned extraction of multiple control parameter values ​​to be evaluated within the optimal control range according to the set interval step size includes: The minimum value in the optimal control range is determined as the first control parameter value to be evaluated. Add the first control parameter value to the interval step size to obtain the corresponding sum value, which is then used as the second control parameter value to be evaluated. The second control parameter value to be evaluated is added to the interval step size to obtain the corresponding sum value, which is then used as the third control parameter value to be evaluated, until all control parameter values ​​to be evaluated are obtained.

[0045] It is understandable that the first nitrogen application ratio to be evaluated, the second nitrogen application ratio to be evaluated, and so on up to the Nth nitrogen application ratio to be evaluated are all nitrogen application ratios to be evaluated. For example, when the optimal nitrogen application ratio range is [0.6, 0.8), and the interval step size is 0.01, 0.6, 0.61, 0.62...0.79 can all be determined as nitrogen application ratios to be evaluated.

[0046] Understandably, the interval step size can also be negative.

[0047] S103. Using the trained planting effect prediction model, predict the planting effect prediction data of the target grid when the target crop is planted with each value of the control parameter to be evaluated; wherein, the target grid is any grid.

[0048] The example uses the planting control parameter value as the nitrogen application ratio. The planting effect prediction data is the prediction result data obtained by using the planting effect prediction model to predict the planting effect that can be obtained by applying nitrogen to the target crop at a certain nitrogen application ratio during the period of the target grid.

[0049] It should be noted that in this embodiment, when a certain nitrogen application ratio to be evaluated is used to apply nitrogen to the target crop, it means that this embodiment will use that nitrogen application ratio to be evaluated to apply nitrogen to the target crop within a certain period. This embodiment uses a planting effect prediction model to predict the planting effect prediction data of the target grid when a certain nitrogen application ratio to be evaluated is applied. That is to say, for the case where the target grid is used to apply nitrogen to the target crop with the nitrogen application ratio to be evaluated within a certain period, this embodiment uses a planting effect prediction model to predict the planting effect prediction data under this case.

[0050] Optionally, in other water-saving, yield-increasing, efficiency-enhancing, and emission-reducing irrigation nitrogen application optimization methods proposed in this embodiment, before step S103, the method further includes: For any given grid cell, if the value of the planting control parameter for the target crop is within the optimal control range during the periodic time, the grid cell will be designated as the training grid cell. For any training grid, obtain other planting impact data corresponding to the target crop in the specified data source. Use the planting control parameter value and other planting impact data of the training grid in the period as training data. Use the planting effect evaluation data of the training grid in the period as the label of the training data. The pre-trained model is trained using each training data point and its corresponding label to obtain a well-trained model for predicting planting effects.

[0051] The example uses the nitrogen application ratio as a planting control parameter. Other planting impact data refers to the planting impact data of the target crop corresponding to the grid during the period, excluding the nitrogen application ratio. Specifically, other planting impact data may include at least one of the following: soil texture, soil pH, soil organic carbon content, annual rainfall, and average annual temperature during the grid period.

[0052] Specifically, the pre-trained model is a neural network model or other type of model with preliminary predictive capabilities. For example, the pre-trained model can be a random forest model.

[0053] Specifically, in this embodiment, a certain training data can be input into a pre-trained model to predict the planting effect, obtaining the planting effect prediction data output by the pre-trained model. A loss function value is calculated based on the difference between this planting effect prediction data and the corresponding label. The pre-trained model is then updated based on the loss function value to obtain the updated model. Next, another training data is input into the updated model to predict the planting effect, obtaining the planting effect prediction data output by the updated model. A loss function value is calculated based on the difference between this planting effect prediction data and the corresponding label. The updated model continues to be updated based on the loss function value until the required number of training iterations is met or the loss function value is less than a set value. The latest model is then determined as the trained planting effect prediction model.

[0054] Optionally, the planting effect evaluation data includes the values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators, and emission-reduction evaluation indicators. Step S103 may include: For any value of the control parameter to be evaluated, the target period for planting the target crop using the control parameter value is found in the specified data source. Other planting impact data corresponding to the target crop within the target period are obtained. The control parameter value to be evaluated and other planting impact data are input into the planting effect prediction model to predict the planting effect. The predicted values ​​of water-saving evaluation index, yield-increasing evaluation index, efficiency-improving evaluation index and emission-reduction evaluation index are obtained. The whole data is used as the planting effect prediction data of the target grid when the target crop is planted using the control parameter value to be evaluated.

[0055] Specifically, taking the nitrogen application ratio as an example, this embodiment can determine the predicted planting effect data of the target grid under the nitrogen application ratio to be evaluated for any nitrogen application ratio to be evaluated, including the predicted values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators and emission-reduction evaluation indicators.

[0056] S104. Based on each planting effect prediction data, determine the optimal control parameter value of the target grid from multiple control parameter values ​​to be evaluated.

[0057] Specifically, taking the planting control parameter value as the nitrogen application ratio as an example, this embodiment can determine the optimal planting effect prediction data in each planting effect prediction data, and determine the nitrogen application ratio to be evaluated corresponding to the optimal planting effect prediction data as the optimal nitrogen application ratio of the target grid.

[0058] Specifically, when the planting effect prediction data includes predicted values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators, and emission-reduction evaluation indicators, this embodiment can sum the predicted values ​​of these indicators for any planting effect prediction data to obtain a corresponding sum. Then, the maximum value is determined from the sums corresponding to each planting effect prediction data, and the planting effect prediction data corresponding to this maximum value is determined as the optimal planting effect prediction data.

[0059] The irrigation nitrogen application optimization method proposed in this embodiment, which focuses on water conservation, yield increase, efficiency improvement, and emission reduction, can determine the optimal control interval using the planting control parameter values ​​and corresponding planting effect evaluation data for each grid in the study area during each period. The planting control parameter values ​​represent the irrigation or nitrogen application ratio for the target crop, while the planting effect evaluation data is used to evaluate water conservation, yield increase, efficiency improvement, and emission reduction effects. Multiple control parameter values ​​to be evaluated are extracted from the optimal control interval. A trained planting effect prediction model is used to predict the planting effect of the target grid when planting the target crop with each of the evaluated control parameter values; the target grid can be any grid. Based on each planting effect prediction data, the optimal control parameter value for the target grid is determined from among the multiple evaluated control parameter values. This embodiment combines the planting control parameter values ​​and corresponding planting effect evaluation data of each grid in the study area during each period. Taking into account the effects of water saving, yield increase, efficiency improvement and emission reduction, it determines the optimal control parameter value for each grid, realizes the optimization of irrigation nitrogen application for crop planting in each grid, finds the balance point of irrigation nitrogen application between reducing agricultural water use, increasing grain production, improving resource utilization efficiency and reducing greenhouse gas emissions, and comprehensively improves the water saving, yield increase, efficiency improvement and emission reduction benefits of crop planting.

[0060] based on Figure 1 This embodiment proposes a second method for optimizing irrigation nitrogen application to save water, increase yield, improve efficiency, and reduce emissions. In this method, step S104 includes: For any value of the control parameter to be evaluated, the predicted values ​​of the water-saving evaluation index, yield-increasing evaluation index, efficiency-improving evaluation index, and emission-reduction evaluation index of the target grid under the condition of planting the target crop with the value of the control parameter to be evaluated are standardized to obtain the corresponding standardized predicted value. Based on each standardized predicted value, the comprehensive evaluation value of the planting effect of the target grid under the condition of planting the target crop with the value of the control parameter to be evaluated is determined. The maximum comprehensive evaluation value of planting effect is determined in each comprehensive evaluation value of planting effect, and the control parameter value to be evaluated corresponding to the maximum comprehensive evaluation value of planting effect is determined as the optimal control parameter value of the target grid.

[0061] The example uses the planting control parameter value as the nitrogen application ratio. The comprehensive evaluation value of planting effect is used to evaluate the comprehensive planting effect that the target grid can achieve when a certain nitrogen application ratio is applied to the target crop during the period.

[0062] Optionally, the above-mentioned predicted values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators, and emission-reduction evaluation indicators for the target grid when planting the target crop using the evaluation control parameter values ​​are respectively standardized, including: For any evaluation index, obtain the index prediction value of the evaluation index of the target grid when the target crop is planted with each value of the control parameter to be evaluated. Determine the maximum and minimum prediction values ​​among the obtained index prediction values. Use the maximum and minimum prediction values ​​to standardize the index prediction values ​​of the evaluation index of the target grid when the target crop is planted with the control parameter to be evaluated, and obtain the corresponding standardized prediction values. The evaluation indicators include water-saving evaluation indicators, production-increasing evaluation indicators, efficiency-improving evaluation indicators, or emission-reduction evaluation indicators.

[0063] Specifically, among the node evaluation indicators, production increase evaluation indicators, efficiency improvement evaluation indicators, and emission reduction evaluation indicators, if the value of an indicator is higher, it indicates better performance and is considered a positive indicator, such as water use efficiency in the efficiency improvement evaluation indicators. Conversely, if the value of an indicator is lower, it indicates better performance and is considered a negative indicator, such as emission reduction indicators. Emissions and Emissions.

[0064] Specifically, in this embodiment, when standardizing a value X of a positive indicator, the maximum and minimum predicted values ​​of the positive indicator can be used to normalize X, resulting in a normalized indicator value. This normalized indicator value is then directly used as the standardized predicted value for X. Similarly, when standardizing a value Y of a negative indicator, the maximum and minimum predicted values ​​of the negative indicator can be used to normalize Y, resulting in a normalized indicator value. This normalized indicator value is then subtracted from 1 to obtain the difference, which is then used as the standardized predicted value for Y.

[0065] like Figure 2 and Figure 3 As shown, the example uses the planting control parameter value as the nitrogen application ratio. When the extracted nitrogen application ratios to be evaluated are 0.61, 0.62, 0.63...0.79, the water-saving evaluation index includes ET, the yield increase evaluation index includes Yield, the efficiency improvement evaluation index includes WUE and NUE, and the emission reduction evaluation index includes... Emissions and When calculating emissions, this embodiment calculates the predicted values ​​of various evaluation indicators for grid A under different nitrogen application ratios applied to the target crop, as well as the maximum and minimum predicted values ​​of each evaluation indicator. Among these, Figure 3 In this context, Min and Max represent the minimum and maximum values, respectively.

[0066] like Figure 4 As shown, this embodiment presents the standardized predicted values ​​obtained by standardizing the predicted values ​​of various evaluation indicators of grid A under different nitrogen application ratios for the target crop, as well as the comprehensive evaluation value of the planting effect of grid A under different nitrogen application ratios for the target crop. Figure 4 It can be seen that grid A has the highest comprehensive evaluation value of 4.55 when applying nitrogen to the target crop at a ratio of 0.61. Therefore, this embodiment can determine that a crop nitrogen application ratio of 0.61 is the optimal nitrogen application ratio for grid A.

[0067] It should be noted that in this embodiment, when a certain nitrogen application ratio to be evaluated is used to apply nitrogen to the target crop, it means that this embodiment will use that nitrogen application ratio to be evaluated to apply nitrogen to the target crop within a certain period.

[0068] It is understood that, for any nitrogen application ratio to be evaluated, this embodiment can determine the comprehensive evaluation value of the planting effect of the target grid when the target crop is irrigated with nitrogen using the nitrogen application ratio to be evaluated within a periodic time.

[0069] Specifically, in this embodiment, when determining the comprehensive evaluation value of the planting effect of the target grid on the target crop under the nitrogen application ratio of the target crop within a periodic time based on each standardized prediction value corresponding to a certain nitrogen application ratio to be evaluated, the standardized prediction values ​​corresponding to the nitrogen application ratio to be evaluated are directly added together, and the sum is determined as the comprehensive evaluation value of the planting effect of the target grid on the target crop under the nitrogen application ratio of the target crop within a periodic time.

[0070] Specifically, in this embodiment, for the comprehensive evaluation value of the planting effect of the target grid when applying nitrogen to the target crop using various nitrogen application ratios to be evaluated, the maximum comprehensive evaluation value of planting effect can be determined among each comprehensive evaluation value. Then, this embodiment can determine the nitrogen application ratio to be evaluated corresponding to the maximum comprehensive evaluation value of planting effect, and determine this nitrogen application ratio to be evaluated as the optimal nitrogen application ratio for the target grid, that is, determine this nitrogen application ratio to be evaluated as the optimal nitrogen application ratio used by the target grid for planting the target crop within the period.

[0071] Optionally, based on each standardized predicted value, the comprehensive evaluation value of the planting effect of the target grid when the target crop is planted using the control parameter value to be evaluated is determined, including: Obtain the set weights for water-saving evaluation indicators, production increase evaluation indicators, efficiency improvement evaluation indicators, and emission reduction evaluation indicators; Based on the weighted evaluation indicators of water conservation, yield increase, efficiency improvement and emission reduction, the standardized predicted values ​​corresponding to the control parameter values ​​to be evaluated are weighted and summed to obtain the corresponding sum value, which is used as the comprehensive evaluation value of the planting effect of the target grid when the target crop is planted with the control parameter values ​​to be evaluated.

[0072] Specifically, the weights can be set by technical personnel according to the actual situation and needs, and this embodiment does not limit them.

[0073] It is understandable that the weights assigned to different evaluation indicators can be the same or different.

[0074] The irrigation nitrogen application optimization method proposed in this embodiment can effectively standardize the predicted values ​​of various evaluation indicators of the grid when planting target crops with different evaluation control parameter values. Furthermore, by assigning corresponding weights to different evaluation indicators, the comprehensive evaluation value of the planting effect of the grid when planting target crops with the evaluation control parameter values ​​can be quantified.

[0075] It should be noted that different irrigation nitrogen application strategies in related technologies have varying trends in their positive and negative effects on water conservation and yield increase, making it difficult to intuitively define the optimal management scheme. Therefore, there is an urgent need to develop a method that can quantitatively analyze and determine the optimal balance point for water conservation, yield increase, efficiency improvement, and emission reduction. This would effectively address the complex trade-offs between reduced agricultural water use, increased grain production, improved resource utilization efficiency, and greenhouse gas emission reduction, thereby analyzing the optimal irrigation nitrogen application strategy.

[0076] It is understood that this embodiment can be used to optimize irrigation and nitrogen application management strategies for water conservation, yield increase, efficiency improvement, and emission reduction in various global grids, aiming to solve the complex trade-off between water resource consumption, food yield increase, and greenhouse gas emissions in agricultural production. This embodiment can first construct an analysis database by collecting experimental data; then, based on data analysis, it can analyze indicators (including yield, water consumption, water use efficiency, nitrogen fertilizer use efficiency, and...) under different irrigation and nitrogen application strategies. , This method involves zoning and analyzing data from various regions (e.g., emissions) to identify suitable intervals that offer the best overall benefits for water conservation, increased production, improved efficiency, and emission reduction. Next, a predictive model is trained using data from these suitable intervals based on machine learning algorithms (such as random forests). Subsequently, the study area data and the established management strategies are input into the trained model for indicator prediction. Finally, by setting weights for each indicator, a comprehensive weighted index for water conservation, increased production, improved efficiency, and emission reduction is constructed and calculated. This quantitatively evaluates the overall benefits under different irrigation and nitrogen application management strategies and determines the optimal irrigation and nitrogen application strategies for each geographic data point. This embodiment enables the quantitative, comprehensive evaluation, and spatial heterogeneity optimization of agricultural management measures (irrigation and nitrogen fertilizer management), providing a scientific basis and decision support for achieving synergistic effects of water conservation, increased production, improved efficiency, and emission reduction in agricultural production.

[0077] This embodiment executes... Figure 1 The irrigation nitrogen application optimization method shown can optimize agricultural management based on data-driven approaches. It comprehensively and quantitatively analyzes the impact of management measures or levels on the overall benefits of water conservation, yield increase, efficiency improvement, and emission reduction. A computational framework is constructed to quantitatively evaluate the overall benefits of agricultural production under different irrigation and fertilization management strategies, further defining and identifying the optimal management strategy. This embodiment can achieve the following technical effects: 1. Comprehensive assessment to avoid the limitations of single indicators. Agricultural management in related technologies generally focuses on a single indicator (such as maximizing yield), while this embodiment incorporates multiple key physiological and environmental factors such as crop yield, water use, and carbon emissions into a unified assessment system through water-saving, yield-increasing, efficiency-improving, and emission-reducing indicators. Through weighted calculation, it achieves a balance and optimization among multiple objectives.

[0078] 2. A computational approach supporting spatially heterogeneous management is proposed, allowing model prediction and determination of optimal management schemes to be performed for each data point in the study area. This means that this embodiment can identify locally optimal management schemes under different geographical locations, soil types, or climatic conditions, rather than simply providing a uniform scheme for an average region. This provides strong technical support for achieving precision agriculture, thereby comprehensively promoting the development of agriculture towards a more sustainable, efficient, and environmentally friendly direction.

[0079] like Figure 5 As shown, this embodiment proposes an irrigation nitrogen application optimization device for water saving, yield increase, efficiency improvement, and emission reduction. The device includes: The interval determination unit 501 is used to determine the optimal control interval based on the planting control parameter values ​​and corresponding planting effect evaluation data of each grid in the study area during each period. The planting control parameter values ​​are the irrigation ratio or nitrogen application ratio of the target crop, and the planting effect evaluation data are used to evaluate the water-saving, yield-increasing, efficiency-improving and emission-reducing effects. The proportional extraction unit 502 is used to extract multiple control parameter values ​​to be evaluated within the optimal control range; The effect prediction unit 503 is used to predict the planting effect prediction data of the target grid when the target crop is planted with each value of the control parameter to be evaluated, using a trained planting effect prediction model; wherein, the target grid is any grid. The proportion determination unit 504 is used to determine the optimal control parameter value of the target grid from multiple control parameter values ​​to be evaluated based on each planting effect prediction data.

[0080] It should be noted that the processing procedures and beneficial effects of the interval determination unit 501, the proportion extraction unit 502, the effect prediction unit 503, and the proportion determination unit 504 can be referred to respectively. Figure 1 Steps S101 to S104 in the process will not be described again.

[0081] Optionally, the interval determination unit 501 is also used for: In the specified data source, obtain the planting control parameter values ​​and planting effect evaluation data for each grid cell in each period. Cluster the planting control parameter values ​​of each grid within each period to determine multiple planting control intervals; Meta-analysis was used to determine the overall improvement benefit of each planting control interval on the planting effect evaluation data, and the maximum overall improvement benefit was determined. The planting control range corresponding to the maximum overall improvement benefit is determined as the optimal control range.

[0082] Optionally, the planting effect evaluation data includes the values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators, and emission-reduction evaluation indicators; The effect prediction unit 503 is also used for: For any value of the control parameter to be evaluated, the target period for planting the target crop using the control parameter value is found in the specified data source. Other planting impact data corresponding to the target crop within the target period are obtained. The control parameter value to be evaluated and other planting impact data are input into the planting effect prediction model to predict the planting effect. The predicted values ​​of water-saving evaluation index, yield-increasing evaluation index, efficiency-improving evaluation index and emission-reduction evaluation index are obtained. The whole data is used as the planting effect prediction data of the target grid when the target crop is planted using the control parameter value to be evaluated.

[0083] Optionally, the effect prediction unit 503 is also used for: For any value of the control parameter to be evaluated, the predicted values ​​of the water-saving evaluation index, yield-increasing evaluation index, efficiency-improving evaluation index, and emission-reduction evaluation index of the target grid under the condition of planting the target crop with the value of the control parameter to be evaluated are standardized to obtain the corresponding standardized predicted value. Based on each standardized predicted value, the comprehensive evaluation value of the planting effect of the target grid under the condition of planting the target crop with the value of the control parameter to be evaluated is determined. The maximum comprehensive evaluation value of planting effect is determined in each comprehensive evaluation value of planting effect, and the control parameter value to be evaluated corresponding to the maximum comprehensive evaluation value of planting effect is determined as the optimal control parameter value of the target grid.

[0084] Optionally, the effect prediction unit 503 is also used for: For any evaluation index, obtain the index prediction value of the evaluation index of the target grid when the target crop is planted with each value of the control parameter to be evaluated. Determine the maximum and minimum prediction values ​​among the obtained index prediction values. Use the maximum and minimum prediction values ​​to standardize the index prediction values ​​of the evaluation index of the target grid when the target crop is planted with the control parameter to be evaluated, and obtain the corresponding standardized prediction values. The evaluation indicators include water-saving evaluation indicators, production-increasing evaluation indicators, efficiency-improving evaluation indicators, or emission-reduction evaluation indicators.

[0085] Optionally, the effect prediction unit 503 is also used for: Obtain the set weights for water-saving evaluation indicators, production increase evaluation indicators, efficiency improvement evaluation indicators, and emission reduction evaluation indicators; Based on the weighted evaluation indicators of water conservation, yield increase, and emission reduction, the standardized predicted values ​​corresponding to the control parameters to be evaluated are weighted and summed to obtain the corresponding sum value, which is used as the comprehensive evaluation value of the planting effect of the target grid when the target crop is planted with the control parameters to be evaluated.

[0086] Optionally, the proportional extraction unit 502 is also used for: According to the set interval step size, multiple control parameter values ​​to be evaluated are extracted in the optimal control range.

[0087] Optionally, when the interval step size is positive, the proportional extraction unit 502 is also used for: The minimum value in the optimal control range is determined as the first control parameter value to be evaluated. Add the first control parameter value to the interval step size to obtain the corresponding sum value, which is then used as the second control parameter value to be evaluated. The second control parameter value to be evaluated is added to the interval step size to obtain the corresponding sum value, which is then used as the third control parameter value to be evaluated, until all control parameter values ​​to be evaluated are obtained.

[0088] Optionally, the above-mentioned device may also include a training unit; Training units are used for: Before using the trained planting effect prediction model to predict the planting effect prediction data of the target grid when planting the target crop with each value of the control parameter to be evaluated, for any grid, if the value of the planting control parameter of the target crop is within the optimal control range during the period, the grid is determined as the training grid. For any training grid, obtain other planting impact data corresponding to the target crop in the specified data source. Use the planting control parameter value and other planting impact data of the training grid in the period as training data. Use the planting effect evaluation data of the training grid in the period as the label of the training data. The pre-trained model is trained using each training data point and its corresponding label to obtain a well-trained model for predicting planting effects.

[0089] The irrigation nitrogen application optimization device proposed in this embodiment, which focuses on water conservation, yield increase, efficiency improvement, and emission reduction, can determine the optimal control interval using the planting control parameter values ​​and planting effect evaluation data for each grid in the study area during each cycle period. The planting control parameters are the irrigation or nitrogen application ratios for the target crop, and the planting effect evaluation data is used to evaluate the water-saving, yield-increasing, efficiency-improving, and emission-reducing effects. Multiple control parameter values ​​to be evaluated are extracted from the optimal control interval. A trained planting effect prediction model is used to predict the planting effect of the target grid when planting the target crop with each of the evaluated control parameter values. Here, the target grid can be any grid. Based on each planting effect prediction data, the optimal control parameter value for the target grid is determined from among the multiple evaluated control parameter values. This invention can combine the planting control parameter values ​​of each grid in the research area during each cycle period, and determine the optimal irrigation ratio or optimal nitrogen application ratio for each grid while comprehensively considering the effects of water saving, yield increase, efficiency improvement and emission reduction. This achieves optimization of irrigation and nitrogen application for crop planting in each grid, and finds a balance point between reducing agricultural water use, increasing grain production, improving resource utilization efficiency and reducing greenhouse gas emissions, thereby comprehensively improving the water-saving, yield increase, efficiency improvement and emission reduction benefits of crop planting.

[0090] The water-saving, yield-increasing, efficiency-enhancing, and emission-reducing irrigation nitrogen application optimization device in this embodiment is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0091] This invention also provides a computer device having the above-described features. Figure 5 The irrigation nitrogen application optimization device shown is designed to save water, increase production, improve efficiency, and reduce emissions.

[0092] Please see Figure 6 The present invention provides a schematic diagram of the structure of a computer device according to an optional embodiment. The computer device includes one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0093] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0094] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0095] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function. The data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0096] Memory 20 may include volatile memory, such as random access memory. Memory may also include non-volatile memory, such as flash memory, hard disk, or solid-state drive. Memory 20 may also include combinations of the above types of memory.

[0097] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0098] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing irrigation nitrogen application to save water, increase yield, improve efficiency, and reduce emissions, characterized in that: include: The optimal control interval is determined based on the planting control parameter values ​​and corresponding planting effect evaluation data for each grid in the study area during each period. The planting control parameter values ​​are the irrigation ratio or nitrogen application ratio for the target crop, and the planting effect evaluation data is used to evaluate the water-saving, yield-increasing, efficiency-improving, and emission-reducing effects. Multiple control parameter values ​​to be evaluated are extracted from the optimal control range; Using a trained planting effect prediction model, the planting effect prediction data of the target grid is predicted when the target crop is planted with each of the aforementioned control parameters to be evaluated; wherein, the target grid is any of the aforementioned grids; Based on each of the predicted planting effect data, the optimal control parameter value of the target grid is determined from the plurality of control parameter values ​​to be evaluated; The step of determining the optimal control interval based on the planting control parameter values ​​and corresponding planting effect evaluation data of each grid in the study area during each period includes: In the specified data source, the planting control parameter values ​​and planting effect evaluation data of each grid in each period are obtained respectively; Cluster the planting control parameter values ​​of each grid within each periodic time to determine multiple planting control intervals; Meta-analysis was used to determine the overall improvement benefit of each planting control interval on the planting effect evaluation data, and the maximum overall improvement benefit was determined. The planting control interval corresponding to the maximum overall improvement benefit is determined as the optimal control interval; The planting effect evaluation data includes the values ​​of water-saving evaluation indicators, yield-increasing evaluation indicators, efficiency-improving evaluation indicators, and emission-reduction evaluation indicators. The method of using a trained planting effect prediction model to predict the planting effect of the target grid when the target crop is planted with each of the evaluated control parameters includes: For any of the aforementioned control parameter values ​​to be evaluated, the target period for planting the target crop using the aforementioned control parameter value is located in the specified data source. Other planting impact data corresponding to the target crop within the target period for the target grid are obtained. The control parameter value to be evaluated and the other planting impact data are input into the planting effect prediction model to predict the planting effect, thereby obtaining the predicted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index. These values ​​are then used as the overall planting effect prediction data for the target grid when the target crop is planted using the control parameter value to be evaluated.

2. The method according to claim 1, characterized in that, The step of determining the optimal control parameter value for the target grid from among the plurality of control parameter values ​​to be evaluated based on each of the predicted planting effect data includes: For any of the aforementioned control parameter values ​​to be evaluated, the predicted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index of the target grid under the condition of planting the target crop with the aforementioned control parameter value to be evaluated are standardized to obtain the corresponding standardized predicted value. Based on each standardized predicted value, the comprehensive evaluation value of the planting effect of the target grid under the condition of planting the target crop with the aforementioned control parameter value to be evaluated is determined. The maximum comprehensive evaluation value of planting effect is determined among each of the comprehensive evaluation values ​​of planting effect, and the value of the control parameter to be evaluated corresponding to the maximum comprehensive evaluation value of planting effect is determined as the optimal control parameter value of the target grid.

3. The method according to claim 2, characterized in that, The standardization of the predicted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index for the target grid when the target crop is planted using the evaluation control parameter values ​​includes: For any evaluation index, obtain the index prediction value of the evaluation index of the target grid when the target crop is planted with each of the evaluation control parameter values ​​respectively. Determine the maximum prediction value and the minimum prediction value of each obtained index prediction value. Use the maximum prediction value and the minimum prediction value to standardize the index prediction value of the evaluation index of the target grid when the target crop is planted with the evaluation control parameter value to obtain the corresponding standardized prediction value. The evaluation indicators are the water-saving evaluation indicators, the production-increasing evaluation indicators, the efficiency-improving evaluation indicators, or the emission-reduction evaluation indicators.

4. The method according to claim 2, characterized in that, The step of determining a comprehensive evaluation value of the planting effect of the target grid when the target crop is planted using the evaluation control parameter value, based on each of the standardized predicted values, includes: Obtain the set weights for the water-saving evaluation index, the production increase evaluation index, the efficiency improvement evaluation index, and the emission reduction evaluation index; Based on the weighted values ​​of the water-saving evaluation index, the yield-increasing evaluation index, the efficiency-improving evaluation index, and the emission-reduction evaluation index, a weighted sum is calculated for each standardized predicted value corresponding to the value of the control parameter to be evaluated, and this sum is used as the comprehensive evaluation value of the planting effect of the target grid when the target crop is planted using the control parameter value to be evaluated.

5. The method according to claim 1, characterized in that, The process involves extracting multiple control parameter values ​​to be evaluated within the optimal control range, including: According to the set interval step size, the multiple control parameter values ​​to be evaluated are extracted in the optimal control range.

6. The method according to claim 5, characterized in that, When the interval step size is positive, the extraction of the multiple control parameter values ​​to be evaluated within the optimal control range according to the set interval step size includes: The minimum value in the optimal control range is determined as the first control parameter value to be evaluated. The first control parameter value to be evaluated is added to the interval step size to obtain the corresponding sum value, which is then used as the second control parameter value to be evaluated. The second control parameter value to be evaluated is added to the interval step size to obtain the corresponding sum value, which is then used as the third control parameter value to be evaluated, until all control parameter values ​​to be evaluated are obtained.

7. The method according to claim 1, characterized in that, Before using the trained planting effect prediction model to predict the planting effect prediction data of the target grid when planting the target crop with each of the evaluated control parameter values, the method further includes: For any of the grids, if the value of the planting control parameter of the target crop for the grid is within the optimal control range during the periodic time, the grid is determined as a training grid. For any of the training grids, other planting impact data corresponding to the target crop within the specified period are obtained from the specified data source. The planting control parameter values ​​and other planting impact data of the training grid within the specified period are used as training data as a whole, and the planting effect evaluation data of the training grid within the specified period are used as the label of the training data. The pre-trained model is trained using each of the training data and the corresponding label to obtain a trained planting effect prediction model.

8. An irrigation nitrogen application optimization device for water conservation, yield increase, efficiency improvement, and emission reduction, characterized in that, The irrigation nitrogen application optimization method for water-saving, yield-increasing, efficiency-improving, and emission-reducing irrigation as described in any one of claims 1 to 7, wherein the apparatus comprises: The interval determination unit is used to determine the optimal control interval based on the planting control parameter values ​​and corresponding planting effect evaluation data of each grid in the study area during each period; wherein, the planting control parameter values ​​are the irrigation ratio or nitrogen application ratio of the target crop, and the planting effect evaluation data is used to evaluate the water-saving, yield-increasing, efficiency-improving and emission-reducing effects. The proportional extraction unit is used to extract multiple control parameter values ​​to be evaluated within the optimal control range. The effect prediction unit is used to predict the planting effect prediction data of the target grid when the target crop is planted with each of the evaluation control parameter values ​​using a trained planting effect prediction model; wherein, the target grid is any of the grids. The proportion determination unit is used to determine the optimal control parameter value of the target grid from among the plurality of control parameter values ​​to be evaluated, based on each of the planting effect prediction data.

Images