A method, system and storage medium for formulating a strategy for improving agricultural land productivity

Abstract

The present invention discloses a method, system and storage medium for formulating a strategy for improving agricultural land productivity, the method comprising: obtaining agricultural data of a target area; constructing an agricultural system model based on the agricultural data, and predicting crop yields and carbon emission data under different land use modes based on the agricultural system model; obtaining crop supply and demand data of the target area, and obtaining the resource carrying range of agricultural land in the target area according to the crop supply and demand data and the crop yield; obtaining a plurality of preset initial productivity strategies, and assigning weights to the initial productivity strategies respectively according to the agricultural data, the crop yield, the carbon emission data and the resource carrying range, and obtaining the implementable weights corresponding to each initial productivity strategy; using the initial productivity strategy with an implementable weight greater than an implementable threshold as the productivity improvement strategy for agricultural land in the target area. The present invention can improve the integrity and systematicness of the formulation of agricultural land productivity improvement strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of land productivity optimization, and in particular to a method, system and storage medium for formulating a strategy for improving agricultural land productivity. Background Art

[0002] There is currently a large amount of agricultural data, including land use, crop yields, climate conditions, etc., but these data are often scattered and lack effective integration and analysis methods, lack integrity and systematicity, resulting in a lack of scientific basis for the management of agricultural land use systems, making it difficult to effectively respond to the challenges and problems facing agricultural development.

[0003] To sum up, the technical method system for agricultural land use system management lacks integration, advancement and scientificity. It is necessary to strengthen data integration and analysis, promote advanced technologies, and improve the management system to achieve scientific, efficient and sustainable development of agricultural land use. Summary of the invention

[0004] The embodiments of the present invention provide a method, system and storage medium for formulating a strategy for improving agricultural land productivity, which can improve the integrity and systematicness of the formulation of a strategy for improving agricultural land productivity.

[0005] An embodiment of the present invention provides a method for formulating a strategy for improving agricultural land productivity, comprising:

[0006] Acquiring agricultural data of a target area, wherein the agricultural data includes land information, water resources information, and climate information;

[0007] Building an agricultural system model based on the agricultural data, and predicting crop yield and carbon emission data under different land use patterns based on the agricultural system model;

[0008] Acquire crop supply and demand data of the target area, and obtain the resource carrying range of the agricultural land in the target area according to the crop supply and demand data and the crop yield;

[0009] Obtaining a plurality of preset initial capacity strategies, assigning weights to the initial capacity strategies respectively according to the land information, water resources information and climate information, crop yield, carbon emission data and resource carrying range, and obtaining implementable weights corresponding to the initial capacity strategies;

[0010] The initial production capacity strategy with the implementable weight greater than the implementable threshold is used as the production capacity improvement strategy for the agricultural land in the target area.

[0011] As an improvement of the above solution, the step of obtaining agricultural data of the target area includes:

[0012] Collecting land information and water resource information of the target area through GIS;

[0013] Collecting historical meteorological data of the target area, wherein the historical meteorological data includes rainfall, temperature and humidity, and corresponding timestamps;

[0014] Fill missing values ​​and process outliers on the historical meteorological data, and select a time series prediction model;

[0015] Using the historical meteorological data to train a selected time series prediction model and perform parameter tuning;

[0016] Using a preset evaluation index to evaluate the verification result of the time series prediction model on the verification set, and adjusting the model parameters according to the verification result until the verification result of the time series prediction model meets the accuracy standard;

[0017] The trained time series prediction model is used to perform prediction to obtain climate information of the target area.

[0018] As an improvement of the above scheme, the agricultural system model is constructed based on the agricultural data, and the crop yield and carbon emission data under different land use modes are predicted based on the agricultural system model, including:

[0019] Randomly extracting multiple sample subsets from the agricultural data with replacement, each of the sample subsets serving as a training set for a decision tree;

[0020] Randomly select some features from each of the sample subsets to train the corresponding decision tree;

[0021] The decision trees are integrated to form a random forest model, and the agricultural data and a preset land use pattern set are input into the random forest model to obtain a prediction result of the crop yield.

[0022] As an improvement of the above scheme, the agricultural system model is constructed based on the agricultural data, and the crop yield and carbon emission data under different land use modes are predicted based on the agricultural system model, including:

[0023] Predicting the biological area, biomass and chlorophyll content of different vegetation in the target area according to the preset land use mode and the crop yield;

[0024] Obtaining a lighting function of the target area according to the climate information;

[0025] The total primary productivity of the target area was calculated by the following formula:

[0026]

[0027] Wherein, G is the total primary productivity of the target area, lum(t) is the light function, [a, b] is the light interval, Biomn is the biomass of the nth vegetation, arean is the biological area of ​​the nth vegetation, and Choln is the chlorophyll content of the nth vegetation;

[0028] Calculate the amount of carbon released by ecosystem respiration in the target area based on the CENTURY model;

[0029] The carbon emission data is calculated by the following formula:

[0030] N=GR

[0031] Wherein, N is the carbon emission data, G is the total primary productivity of the target area, and R is the amount of carbon released by ecosystem respiration in the target area.

[0032] As an improvement of the above solution, obtaining the crop supply and demand data of the target area, and obtaining the resource carrying range of the agricultural land in the target area according to the crop supply and demand data and the crop yield, includes:

[0033] Calculate the corresponding crop demand according to the population data of the target area;

[0034] Obtaining crop input and crop output in the target area;

[0035] The resource carrying range is obtained by the following formula:

[0036] Dm≥(OUTm+Qm)-INm

[0037] Where Dm is the resource carrying range of the m-th crop, OUTm is the crop output of the m-th crop, Qm is the crop demand of the m-th crop, and INm is the crop input of the m-th crop.

[0038] As an improvement of the above scheme, the preset several initial production capacity strategies are obtained, and weights are assigned to the initial production capacity strategies respectively according to the land information, water resources information, climate information, crop yield, carbon emission data and resource carrying range, so as to obtain the implementable weights corresponding to the initial production capacity strategies, including:

[0039] After obtaining the several initial production capacity strategies, marking the initial production capacity strategies with demand tags corresponding to the land information, water resource information, climate information, crop yield, carbon emission data and resource carrying range;

[0040] When the demand tag of the initial capacity strategy matches the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, assigning a corresponding first weight value to the initial capacity strategy;

[0041] When the demand tag of the initial capacity strategy does not match the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, assigning a corresponding second weight value to the initial capacity strategy;

[0042] The implementable weights corresponding to the respective initial capacity strategies are obtained according to the first weight value and the second weight value.

[0043] As an improvement of the above solution, the initial production capacity strategy with the implementable weight greater than the implementable threshold is used as the production capacity improvement strategy for the agricultural land in the target area, including:

[0044] The implementable threshold is obtained by calculating the implementable weight corresponding to each of the initial capacity strategies;

[0045] The initial production capacity strategy with the implementable weight greater than the implementable threshold is used as the production capacity improvement strategy for the agricultural land in the target area.

[0046] Another embodiment of the present invention provides a system for formulating a strategy for improving agricultural land productivity, including:

[0047] An agricultural data acquisition module, used to acquire agricultural data of a target area, wherein the agricultural data includes land information, water resource information and climate information;

[0048] A land data prediction module, used to construct an agricultural system model based on the agricultural data, and predict crop yield and carbon emission data under different land use modes based on the agricultural system model;

[0049] A land resource calculation module, used to obtain the crop supply and demand data of the target area, and obtain the resource carrying range of the agricultural land in the target area according to the crop supply and demand data and the crop yield;

[0050] A strategy weight assignment module is used to obtain a plurality of preset initial capacity strategies, and assign weights to the initial capacity strategies according to the land information, water resource information, climate information, crop yield, carbon emission data and resource carrying range, so as to obtain the implementable weight corresponding to each of the initial capacity strategies;

[0051] The capacity strategy selection module is used to use the initial capacity strategy with the implementable weight greater than the implementable threshold as the capacity improvement strategy for the agricultural land in the target area.

[0052] Another embodiment of the present invention provides a system for formulating a strategy for improving agricultural land productivity, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for formulating a strategy for improving agricultural land productivity as described in the above-mentioned embodiment of the invention when executing the computer program.

[0053] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for formulating an agricultural land productivity improvement strategy as described in the above-mentioned embodiment of the invention.

[0054] Compared with the prior art, in the embodiment of the present invention, land information, water resource information and climate information provide a solid foundation for building an agricultural system model. By obtaining agricultural data of the target area, an in-depth understanding and accurate analysis of the agricultural system can be ensured, thereby making the prediction based on the model more accurate and reliable; based on the agricultural system model, it is possible to predict crop yields and carbon emission data under different land use modes. This comprehensive prediction method not only considers the economic benefits of agricultural production, but also takes into account the impact of the ecological environment, and provides a scientific basis for formulating sustainable production capacity improvement strategies; combined with crop supply and demand data and crop yields, the resource carrying range of agricultural land in the target area can be clarified, thereby avoiding over-exploitation or under-utilization and ensuring the sustainability of agricultural production; by assigning weights to the initial production capacity strategy, multiple factors such as land, water resources, climate, yield, carbon emissions and resource carrying range are comprehensively considered, overcoming the limitations of single factor consideration in traditional decision-making methods, making the formulation of production capacity improvement strategies more scientific and systematic; by screening out the initial production capacity strategy with an implementable weight greater than the implementable threshold as the production capacity improvement strategy for agricultural land in the target area, it can be ensured that these strategies have higher feasibility and effectiveness in actual operation. This helps to improve the productivity of agricultural land while reducing unnecessary waste of resources and environmental pollution; in summary, this embodiment achieves accurate formulation of agricultural land productivity improvement strategies through data-driven, comprehensive prediction, resource carrying range definition and scientific and systematic strategy formulation, which helps promote the sustainable development of agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a method for formulating a strategy for improving agricultural land productivity provided by an embodiment of the present invention;

[0056] Figure 2 It is a structural schematic diagram of a system for formulating a strategy for improving agricultural land productivity provided by an embodiment of the present invention;

[0057] Figure 3It is a structural schematic diagram of a system for formulating a strategy for improving agricultural land productivity provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] See also Figure 1 , is a flow chart of a method for formulating a strategy for improving agricultural land productivity provided by an embodiment of the present invention, including steps S101 to S105:

[0060] S101, obtaining agricultural data of a target area, wherein the agricultural data includes land information, water resources information and climate information;

[0061] Specifically, in the process of data collection and processing, comprehensive collection of relevant data such as land quality, water resources, and climate conditions in the target area can be carried out, including historical meteorological data such as rainfall, temperature, humidity, etc. These data can help understand the local climate characteristics and changing trends; at the same time, it is also necessary to collect land use conditions, such as the area of ​​agricultural land, the type of agricultural land, forest coverage, etc. These data are helpful in analyzing the sustainable use and development potential of the land; in addition, it also includes topographic data of the target area, so as to obtain the height of the terrain, the direction of water flow, the water quality, the soil type, etc.

[0062] S102. Construct an agricultural system model based on agricultural data, and predict crop yield and carbon emission data under different land use patterns based on the agricultural system model;

[0063] Specifically, the agricultural system model can be a DSSAT model, a CENTURY model, or the like.

[0064] S103, obtaining crop supply and demand data of the target area, and obtaining the resource carrying range of the agricultural land in the target area according to the crop supply and demand data and the crop yield;

[0065] Specifically, the balance of crop supply and demand is a crucial link in agricultural production, which is directly related to the stability of agricultural production and food security in the target area. Therefore, in order to better understand the supply and demand of crops in the target area, it is necessary to obtain real-time crop yield data, market demand and supply of crops, so as to obtain the minimum resource carrying range of agricultural land under the premise of ensuring the normal supply of food in the target area, thereby providing a bottom line for crop supply when formulating strategies.

[0066] S104, obtaining a plurality of preset initial production capacity strategies, assigning weights to the initial production capacity strategies respectively according to land information, water resources information and climate information, crop yield, carbon emission data and resource carrying range, and obtaining implementable weights corresponding to each initial production capacity strategy;

[0067] Specifically, in order to formulate a capacity strategy that conforms to the actual situation, a series of preset initial capacity strategies can be obtained first. These strategies can cover a variety of possible capacity planning directions. The strategy source can be an expert team, survey statistical results, related databases, etc., which are not limited in this embodiment.

[0068] Exemplarily, the initial production capacity strategy may include: improving soil management, improving irrigation management, optimizing crop varieties, crop rotation to increase soil carbon storage, adopting low-carbon agricultural technology, etc. The strategy can be reasonable and is not limited in this embodiment.

[0069] S105. Using the initial production capacity strategy with an implementable weight greater than the implementable threshold as the production capacity improvement strategy for agricultural land in the target area.

[0070] Specifically, the implementability weight refers to the possibility of a strategy being successfully implemented in actual operation or the comprehensive evaluation value of the benefits it brings. The implementability threshold is a standard line. Only when the implementability weight of a strategy exceeds this standard, it is considered a strategy with practical promotion and application value.

[0071] In this embodiment, preferably, the obtaining of agricultural data of the target area includes:

[0072] Collect land and water resource information of the target area through GIS;

[0073] Collect historical meteorological data of the target area, where the historical meteorological data includes rainfall, temperature and humidity, as well as corresponding timestamps;

[0074] Fill missing values ​​and handle outliers in historical meteorological data, and select a time series prediction model;

[0075] Use historical meteorological data to train the selected time series forecasting model and perform parameter tuning;

[0076] Use the preset evaluation indicators to evaluate the verification results of the time series prediction model on the verification set, and adjust the model parameters according to the verification results until the verification results of the time series prediction model meet the accuracy standards;

[0077] Use the trained time series prediction model to make predictions and obtain the climate information of the target area.

[0078] Specifically, the land information and water resource information of the target area are collected through the Geographic Information System (GIS). The land information includes land type, topography, and soil texture; the water resource information includes water resource distribution, water flow direction, water quality, etc., which will provide basic data for subsequent predictions.

[0079] Specifically, the historical meteorological data of the target area will be used to train the time series prediction model. Before training, the historical meteorological data can be used to fill missing values ​​and process outliers through interpolation, averaging, etc. The outlier processing can be carried out using the maximum and minimum method, the triple standard deviation method, etc.

[0080] Specifically, time series prediction models include ARIMA, LSTM, Prophet and other models. In a specific implementation method, a suitable model can be selected for training according to the characteristics of the target area and data properties.

[0081] Specifically, the above evaluation indicators include mean square error (MSE), root mean square error (RMSE), determination coefficient (R 2 )wait.

[0082] In addition, historical meteorological data can be updated regularly and the time series prediction model can be retrained so that the model can be further improved as data continues to accumulate.

[0083] In this embodiment, preferably, an agricultural system model is constructed based on agricultural data, and crop yield and carbon emission data under different land use modes are predicted based on the agricultural system model, including:

[0084] Multiple sample subsets are randomly selected from agricultural data with replacement, and each sample subset is used as a training set for a decision tree;

[0085] Randomly select some features from each sample subset to train the corresponding decision tree;

[0086] The decision trees are integrated to form a random forest model, and agricultural data and a preset land use pattern set are input into the random forest model to obtain the prediction results of crop yields.

[0087] Specifically, for each sample subset, a portion of features is randomly selected to train the decision tree, which helps to reduce overfitting and improve the generalization ability of the model.

[0088] In this embodiment, preferably, an agricultural system model is constructed based on agricultural data, and crop yield and carbon emission data under different land use modes are predicted based on the agricultural system model, including:

[0089] Predict the biological area, biomass and chlorophyll content of different vegetation in the target area based on the preset land use pattern and crop yield;

[0090] Obtain the illumination function of the target area based on climate information;

[0091] The total primary productivity of the target area was calculated by the following formula:

[0092]

[0093] Where G is the total primary productivity of the target area, lum(t) is the light function, [a,b] is the light interval, Biomn is the biomass of the nth vegetation, arean is the biological area of ​​the nth vegetation, and Choln is the chlorophyll content of the nth vegetation;

[0094] Calculate the amount of carbon released by ecosystem respiration in the target area based on the CENTURY model;

[0095] Carbon emissions data is calculated using the following formula:

[0096] N=GR

[0097] Where N is the carbon emission data, G is the total primary productivity of the target area, and R is the amount of carbon released by ecosystem respiration in the target area.

[0098] Specifically, in [a, b], a may be the sunrise time, b may be the sunset time, and lum(t) is the light intensity variation curve during the sunshine period.

[0099] Furthermore, when considering soil carbon dynamics, carbon emission data can also be calculated as follows:

[0100] N=(G+C)-R

[0101] Where N is the carbon emission data, G is the total primary productivity of the target area, R is the amount of carbon released by ecosystem respiration in the target area, and C is the organic carbon stock in the soil.

[0102] The soil organic carbon stock C in the above formula can be obtained by the following steps:

[0103] According to the types and distribution characteristics of soil collected under different land use patterns, soil samples under different land use patterns are obtained in advance;

[0104] The organic carbon stock per unit volume in soil samples is measured by pyrolysis or wet chemical oxidation;

[0105] Calculate the organic carbon stock in soil samples;

[0106] C=OCS1*A1*Dep1+OCS2*A2*Dep2+…+OCS i *A i *Dep i

[0107] Where C is the organic carbon stock in the soil, A i is the area occupied by the i-th soil, Dep i is the depth of the i-th soil, OCS i is the organic carbon stock per unit volume of the ith soil.

[0108] Regarding the above-mentioned soil depth, since the terrain has a significant impact on soil development, for example, mountainous terrain usually leads to shallower soil depth, while plain areas may have deeper soil, and forest soil may be deeper than farmland soil, etc., the soil depth can be predicted based on terrain data (such as a digital elevation model) in this embodiment.

[0109] In addition, a large amount of geographic data and soil depth measurement data can be used to build prediction models such as decision trees, random forests, and neural networks to automatically predict the depth Dep in areas with different soil types. i .

[0110] The above-mentioned carbon emission data calculation method can help us better understand the sources and patterns of agricultural carbon emissions, provide a scientific basis for the management and control of agricultural carbon emissions, and further contribute to the sustainable development of agriculture, reduce carbon emissions, and protect the ecological environment.

[0111] In this embodiment, preferably, the crop supply and demand data of the target area is obtained, and the resource carrying range of the agricultural land in the target area is obtained according to the crop supply and demand data and the crop yield, including:

[0112] Calculate the corresponding crop demand based on the population data of the target area;

[0113] Obtain crop input and crop output in the target area;

[0114] The resource carrying range is obtained by the following formula:

[0115] Dm≥(OUTm+Qm)-INm

[0116] Where Dm is the resource carrying range of the m-th crop, OUTm is the crop output of the m-th crop, Qm is the crop demand of the m-th crop, and INm is the crop input of the m-th crop.

[0117] Specifically, in order to determine the resource carrying capacity of crops, it is necessary to obtain the crop input and output of the target area. The crop input mainly includes the amount of input from outside the target area, such as the import of grain, vegetables, and fruits, while the crop output refers to the amount of foreign trade of agricultural production results, including the export of grain, vegetables, and fruits.

[0118] The above calculation method can be used to understand the minimum carrying threshold of crop resources in the target area. If the crop yield in the target area is lower than the minimum carrying threshold, the crop balance in the target area will be disrupted. For example, the import quantity needs to be increased to meet the normal diet of the population in the target area. Therefore, the minimum carrying threshold can provide a basis for the rational allocation of agricultural resources.

[0119] In addition, the maximum carrying threshold of crop resources in the target area can also be set. Specifically, when the land utilization rate exceeds a certain threshold (for example, 80%), the land use is considered to be overloaded, which may lead to land degradation and ecological environment deterioration. Therefore, the maximum carrying threshold of crop resources in the target area can be set to 80% of the saturated load of agricultural land in the target area.

[0120] In this embodiment, preferably, several preset initial capacity strategies are obtained, and weights are assigned to the initial capacity strategies according to land information, water resource information, climate information, crop yield, carbon emission data, and resource carrying range, to obtain the implementable weights corresponding to each initial capacity strategy, including:

[0121] After obtaining several initial capacity strategies, label the initial capacity strategies with land information, water resources information, climate information, crop yields, carbon emission data, and demand labels corresponding to resource carrying ranges;

[0122] When the demand tag of the initial capacity strategy matches the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, the initial capacity strategy is assigned a corresponding first weight value;

[0123] When the demand label of the initial capacity strategy does not match the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, the initial capacity strategy is assigned a corresponding second weight value;

[0124] The feasible weights corresponding to the various initial capacity strategies are obtained according to the first weight value and the second weight value.

[0125] Specifically, this embodiment describes the steps of assigning weights to the initial capacity strategy in an exemplary manner:

[0126] Assume that the initial capacity strategy includes:

[0127] Strategy a: Increase the planting area of ​​crop A by 10%;

[0128] Strategy b: Reduce the area of ​​crop B by 15%;

[0129] Strategy c: Plant additional C crops and plant them in the vacant space after the reduction of B crops;

[0130] Strategy d: adopt water-saving irrigation technology;

[0131] Strategy e: Regularly add organic matter (such as straw, compost, etc.);

[0132] Strategy f: Utilize a rainwater centralized irrigation system to collect, store and use rainwater for irrigation.

[0133] The method of labeling the corresponding demand labels for the initial capacity strategy is as follows:

[0134] If the carbon emission data exceeds the preset threshold after the planting area of ​​crop A is increased by 10%, the label corresponding to the carbon emission data will be marked as mismatched;

[0135] If the crop yield and the corresponding crop supply and demand data still meet the resource carrying range after reducing the planting area of ​​crop B by 15%, the labels corresponding to the crop yield and resource carrying range are marked as matching;

[0136] If crop C is newly planted and planted in the vacant space after crop B is reduced, and it is found that crop C is difficult to survive in the land suitable for crop B according to the topographic information in the land information, the label corresponding to the land information is marked as mismatched;

[0137] If water-saving irrigation technology and rainwater centralized irrigation system are adopted, which meets the water resource distribution and climate characteristics of the target area, then the water resource information and climate information corresponding to strategies d and f are both matched;

[0138] If the regular addition of organic matter (such as straw, compost, etc.) meets the requirements of the carbon emission data, but it is difficult to achieve due to rugged terrain, the land information corresponding to the e-strategy is mismatched and the carbon emission data label is matched.

[0139] Based on the above example, let the initial values ​​of the six labels of land information, water resources information, climate information, crop yield, carbon emission data or resource carrying range be 1, the first weight value be 1.5, and the second weight value be 0.8. Then the implementable weight value k of the above strategy is as follows:

[0140] Strategy a: ka=1*1*1*1*1*0.8=0.8

[0141] Strategy b: kb = 1*1*1*1*1.5*1.5 = 2.25

[0142] Strategy c: kc = 1*1*1*1*1*0.8 = 0.8

[0143] Strategy d: kd = 1*1*1*1*1.5*1.5 = 2.25

[0144] Strategy e: ke=1*1*1*1*1.5*0.8=1.2

[0145] Strategy f: kf = 1*1*1*1*1.5*1.5 = 2.25

[0146] In summary, the above weight assignment method can be used to obtain the implementable weight of each strategy, where labels irrelevant to the strategy can keep their original values, and related labels can be multiplied to obtain the final implementable weight value, thereby reflecting the abstract implementability through specific numerical values.

[0147] In this embodiment, preferably, the initial production capacity strategy with an implementable weight greater than the implementable threshold is used as the production capacity improvement strategy for agricultural land in the target area, including:

[0148] The feasible threshold is calculated according to the feasible weight corresponding to each initial capacity strategy;

[0149] The initial capacity strategy with an implementable weight greater than the implementable threshold is used as the capacity improvement strategy for agricultural land in the target area.

[0150] Based on the above example, the feasible threshold K may be the weighted average of the feasible weights of each initial capacity strategy, that is:

[0151] K=(0.8+2.25+0.8+2.25+1.2+2.25) / 6≈1.6

[0152] Therefore, strategies b, d, and f that are greater than the implementable threshold K can be used as productivity improvement strategies for agricultural land in the target area.

[0153] In addition, the implementable weights may also be specifically set according to actual needs, for example, set to a fixed value, which will not be described in detail in this embodiment.

[0154] In summary, in the embodiment of the present invention, land information, water resources information and climate information provide a solid foundation for building an agricultural system model. By obtaining agricultural data of the target area, an in-depth understanding and accurate analysis of the agricultural system can be ensured, thereby making the model-based prediction more accurate and reliable; based on the agricultural system model, it is possible to predict crop yields and carbon emission data under different land use patterns. This comprehensive prediction method not only takes into account the economic benefits of agricultural production, but also takes into account the impact of the ecological environment, and provides a scientific basis for formulating sustainable production capacity improvement strategies; combined with crop supply and demand data and crop yields, the resource carrying range of agricultural land in the target area can be clarified, thereby avoiding over-exploitation or under-utilization and ensuring the sustainability of agricultural production; by assigning weights to the initial production capacity strategy, multiple factors such as land, water resources, climate, yield, carbon emissions and resource carrying range are comprehensively considered, overcoming the limitations of single factor considerations in traditional decision-making methods, making the formulation of production capacity improvement strategies more scientific and systematic; by screening out the initial production capacity strategy with an implementable weight greater than the implementable threshold as the production capacity improvement strategy for agricultural land in the target area, it can be ensured that these strategies have higher feasibility and effectiveness in actual operations. This helps to improve the productivity of agricultural land while reducing unnecessary waste of resources and environmental pollution; in summary, this embodiment achieves accurate formulation of agricultural land productivity improvement strategies through data-driven, comprehensive prediction, resource carrying range definition and scientific and systematic strategy formulation, which helps promote the sustainable development of agricultural production.

[0155] See also Figure 2 , is a structural diagram of a system for formulating a strategy for improving agricultural land productivity provided by an embodiment of the present invention, including:

[0156] The agricultural data acquisition module 201 is used to acquire agricultural data of a target area, wherein the agricultural data includes land information, water resource information and climate information;

[0157] The land data prediction module 202 is used to construct an agricultural system model based on agricultural data, and predict crop yields and carbon emission data under different land use modes based on the agricultural system model;

[0158] The land resource calculation module 203 is used to obtain the crop supply and demand data of the target area, and obtain the resource carrying range of the agricultural land in the target area according to the crop supply and demand data and the crop yield;

[0159] The strategy weight assignment module 204 is used to obtain a plurality of preset initial production capacity strategies, and assign weights to the initial production capacity strategies according to land information, water resource information, climate information, crop yield, carbon emission data and resource carrying range, so as to obtain the implementable weight corresponding to each initial production capacity strategy;

[0160] The capacity strategy selection module 205 is used to use the initial capacity strategy with an implementable weight greater than the implementable threshold as the capacity improvement strategy for the agricultural land in the target area.

[0161] Furthermore, agricultural data of the target area is obtained, including:

[0162] Collect land and water resource information of the target area through GIS;

[0163] Collect historical meteorological data of the target area, where the historical meteorological data includes rainfall, temperature and humidity, as well as corresponding timestamps;

[0164] Fill missing values ​​and handle outliers in historical meteorological data, and select a time series prediction model;

[0165] Use historical meteorological data to train the selected time series forecasting model and perform parameter tuning;

[0166] Use the preset evaluation indicators to evaluate the verification results of the time series prediction model on the verification set, and adjust the model parameters according to the verification results until the verification results of the time series prediction model meet the accuracy standards;

[0167] Use the trained time series prediction model to make predictions and obtain the climate information of the target area.

[0168] Furthermore, an agricultural system model is constructed based on agricultural data, and crop yield and carbon emission data under different land use patterns are predicted based on the agricultural system model, including:

[0169] Multiple sample subsets are randomly selected from agricultural data with replacement, and each sample subset is used as a training set for a decision tree;

[0170] Randomly select some features from each sample subset to train the corresponding decision tree;

[0171] The decision trees are integrated to form a random forest model, and agricultural data and a preset land use pattern set are input into the random forest model to obtain the prediction results of crop yields.

[0172] Furthermore, an agricultural system model is constructed based on agricultural data, and crop yield and carbon emission data under different land use patterns are predicted based on the agricultural system model, including:

[0173] Predict the biological area, biomass and chlorophyll content of different vegetation in the target area based on the preset land use pattern and crop yield;

[0174] Obtain the illumination function of the target area based on climate information;

[0175] The total primary productivity of the target area was calculated by the following formula:

[0176]

[0177] Where G is the total primary productivity of the target area, lum(t) is the light function, [a,b] is the light interval, Biomn is the biomass of the nth vegetation, arean is the biological area of ​​the nth vegetation, and Choln is the chlorophyll content of the nth vegetation;

[0178] Calculate the amount of carbon released by ecosystem respiration in the target area based on the CENTURY model;

[0179] Carbon emissions data is calculated using the following formula:

[0180] N=GR

[0181] Where N is the carbon emission data, G is the total primary productivity of the target area, and R is the amount of carbon released by ecosystem respiration in the target area.

[0182] Furthermore, the crop supply and demand data of the target area is obtained, and the resource carrying range of the agricultural land in the target area is obtained according to the crop supply and demand data and the crop yield, including:

[0183] Calculate the corresponding crop demand based on the population data of the target area;

[0184] Obtain crop input and crop output in the target area;

[0185] The resource carrying range is obtained by the following formula:

[0186] Dm≥(OUTm+Qm)-INm

[0187] Where Dm is the resource carrying range of the m-th crop, OUTm is the crop output of the m-th crop, Qm is the crop demand of the m-th crop, and INm is the crop input of the m-th crop.

[0188] Furthermore, several preset initial capacity strategies are obtained, and weights are assigned to the initial capacity strategies according to land information, water resources information, climate information, crop yields, carbon emission data, and resource carrying capacity, and the implementable weights corresponding to each initial capacity strategy are obtained, including:

[0189] After obtaining several initial capacity strategies, label the initial capacity strategies with land information, water resources information, climate information, crop yields, carbon emission data, and demand labels corresponding to resource carrying ranges;

[0190] When the demand tag of the initial capacity strategy matches the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, the initial capacity strategy is assigned a corresponding first weight value;

[0191] When the demand label of the initial capacity strategy does not match the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, the initial capacity strategy is assigned a corresponding second weight value;

[0192] The feasible weights corresponding to the various initial capacity strategies are obtained according to the first weight value and the second weight value.

[0193] Furthermore, the initial capacity strategies with implementable weights greater than the implementable threshold are used as the capacity improvement strategies for agricultural land in the target area, including:

[0194] The feasible threshold is calculated according to the feasible weight corresponding to each initial capacity strategy;

[0195] The initial capacity strategy with an implementable weight greater than the implementable threshold is used as the capacity improvement strategy for agricultural land in the target area.

[0196] In summary, in the embodiment of the present invention, land information, water resources information and climate information provide a solid foundation for building an agricultural system model. By obtaining agricultural data of the target area, an in-depth understanding and accurate analysis of the agricultural system can be ensured, thereby making the model-based prediction more accurate and reliable; based on the agricultural system model, it is possible to predict crop yields and carbon emission data under different land use patterns. This comprehensive prediction method not only takes into account the economic benefits of agricultural production, but also takes into account the impact of the ecological environment, and provides a scientific basis for formulating sustainable production capacity improvement strategies; combined with crop supply and demand data and crop yields, the resource carrying range of agricultural land in the target area can be clarified, thereby avoiding over-exploitation or under-utilization and ensuring the sustainability of agricultural production; by assigning weights to the initial production capacity strategy, multiple factors such as land, water resources, climate, yield, carbon emissions and resource carrying range are comprehensively considered, overcoming the limitations of single factor considerations in traditional decision-making methods, making the formulation of production capacity improvement strategies more scientific and systematic; by screening out the initial production capacity strategy with an implementable weight greater than the implementable threshold as the production capacity improvement strategy for agricultural land in the target area, it can be ensured that these strategies have higher feasibility and effectiveness in actual operations. This helps to improve the productivity of agricultural land while reducing unnecessary waste of resources and environmental pollution; in summary, this embodiment achieves accurate formulation of agricultural land productivity improvement strategies through data-driven, comprehensive prediction, resource carrying range definition and scientific and systematic strategy formulation, which helps promote the sustainable development of agricultural production.

[0197] See also Figure 3, is a schematic diagram of a system for formulating a strategy for improving agricultural land productivity provided by an embodiment of the present invention. The system for formulating a strategy for improving agricultural land productivity of this embodiment includes: a processor 1, a memory 2, and a computer program stored in the memory 2 and executable on the processor, such as a program for formulating a strategy for improving agricultural land productivity. When the processor 1 executes the computer program, the steps in each of the above-mentioned embodiments of the method for formulating a strategy for improving agricultural land productivity are implemented. Alternatively, when the processor 1 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0198] Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the agricultural land productivity improvement strategy formulation system.

[0199] The agricultural land productivity improvement strategy formulation system may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is only an example of the agricultural land productivity improvement strategy formulation system and does not constitute a limitation on the agricultural land productivity improvement strategy formulation system. The system may include more or fewer components than shown in the diagram, or a combination of certain components, or different components. For example, the agricultural land productivity improvement strategy formulation system may also include input and output devices, network access devices, CAN buses, etc.

[0200] An embodiment of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for formulating a strategy for improving agricultural land productivity such as the first embodiment of the present invention.

[0201] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the agricultural land productivity improvement strategy formulation system, and uses various interfaces and lines to connect the various parts of the entire agricultural land productivity improvement strategy formulation system.

[0202] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the agricultural land productivity improvement strategy formulation system by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0203] Among them, if the module / unit integrated in the agricultural land productivity improvement strategy formulation system is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0204] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0205] The above are preferred embodiments of the present invention. It should be noted that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for formulating a strategy to improve agricultural land productivity, characterized in that: include: Acquiring agricultural data of a target area, wherein the agricultural data includes land information, water resources information, and climate information; Building an agricultural system model based on the agricultural data, and predicting crop yield and carbon emission data under different land use patterns based on the agricultural system model; Acquire crop supply and demand data of the target area, and obtain the resource carrying range of the agricultural land in the target area according to the crop supply and demand data and the crop yield; Obtaining a plurality of preset initial capacity strategies, assigning weights to the initial capacity strategies respectively according to the land information, water resources information and climate information, crop yield, carbon emission data and resource carrying range, and obtaining implementable weights corresponding to the initial capacity strategies; Using the initial production capacity strategy with the implementable weight greater than the implementable threshold as the production capacity improvement strategy for the agricultural land in the target area; The step of constructing an agricultural system model based on the agricultural data and predicting crop yield and carbon emission data under different land use patterns based on the agricultural system model includes: Randomly extracting multiple sample subsets from the agricultural data with replacement, each of the sample subsets serving as a training set for a decision tree; Randomly select some features from each of the sample subsets to train the corresponding decision tree; The decision trees are integrated to form a random forest model, and the agricultural data and a preset land use pattern set are input into the random forest model to obtain a prediction result of the crop yield; Predicting the biological area, biomass and chlorophyll content of different vegetation in the target area according to the preset land use mode and the crop yield; Obtaining a lighting function of the target area according to the climate information; The total primary productivity of the target area was calculated by the following formula: Wherein, G is the total primary productivity of the target area, lum(t) is the light function, [a, b] is the light interval, Biomn is the biomass of the nth vegetation, arean is the biological area of ​​the nth vegetation, and Choln is the chlorophyll content of the nth vegetation; Calculate the amount of carbon released by ecosystem respiration in the target area based on the CENTURY model; The carbon emission data is calculated by the following formula: N=GR Wherein, N is the carbon emission data, G is the total primary productivity of the target area, and R is the amount of carbon released by ecosystem respiration in the target area.

2. The method for formulating a strategy for improving agricultural land productivity according to claim 1, characterized in that: The step of obtaining agricultural data of the target area includes: Collecting land information and water resource information of the target area through GIS; Collecting historical meteorological data of the target area, wherein the historical meteorological data includes rainfall, temperature and humidity, and corresponding timestamps; Fill missing values ​​and process outliers on the historical meteorological data, and select a time series prediction model; Using the historical meteorological data to train a selected time series prediction model and perform parameter tuning; Using a preset evaluation index to evaluate the verification result of the time series prediction model on the verification set, and adjusting the model parameters according to the verification result until the verification result of the time series prediction model meets the accuracy standard; The trained time series prediction model is used to perform prediction to obtain climate information of the target area.

3. The method for formulating a strategy for improving agricultural land productivity according to claim 1, characterized in that: The obtaining of the crop supply and demand data of the target area, and obtaining the resource carrying range of the agricultural land of the target area according to the crop supply and demand data and the crop yield, includes: Calculate the corresponding crop demand according to the population data of the target area; Obtaining crop input and crop output in the target area; The resource carrying range is obtained by the following formula: Dm≥(OUTm+Qm)-INm Where Dm is the resource carrying range of the m-th crop, OUTm is the crop output of the m-th crop, Qm is the crop demand of the m-th crop, and INm is the crop input of the m-th crop.

4. The method for formulating a strategy for improving agricultural land productivity according to claim 1, characterized in that: The obtaining of a plurality of preset initial production capacity strategies, assigning weights to the initial production capacity strategies respectively according to the land information, water resource information, climate information, crop yield, carbon emission data and resource carrying range, and obtaining implementable weights corresponding to the initial production capacity strategies, includes: After obtaining the several initial production capacity strategies, marking the initial production capacity strategies with demand tags corresponding to the land information, water resource information, climate information, crop yield, carbon emission data and resource carrying range; When the demand tag of the initial capacity strategy matches the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, assigning a corresponding first weight value to the initial capacity strategy; When the demand tag of the initial capacity strategy does not match the land information, water resource information, climate information, crop yield, carbon emission data or resource carrying range, assigning a corresponding second weight value to the initial capacity strategy; The implementable weights corresponding to the respective initial capacity strategies are obtained according to the first weight value and the second weight value.

5. The method for formulating a strategy for improving agricultural land productivity according to claim 1, characterized in that: The initial production capacity strategy with the implementable weight greater than the implementable threshold is used as the production capacity improvement strategy for the agricultural land in the target area, including: The implementable threshold is obtained by calculating the implementable weight corresponding to each of the initial capacity strategies; The initial production capacity strategy with the implementable weight greater than the implementable threshold is used as the production capacity improvement strategy for the agricultural land in the target area.

6. A system for formulating a strategy to improve agricultural land productivity, characterized in that: include: An agricultural data acquisition module, used to acquire agricultural data of a target area, wherein the agricultural data includes land information, water resource information and climate information; A land data prediction module, used to construct an agricultural system model based on the agricultural data, and predict crop yield and carbon emission data under different land use modes based on the agricultural system model; A land resource calculation module, used to obtain the crop supply and demand data of the target area, and obtain the resource carrying range of the agricultural land in the target area according to the crop supply and demand data and the crop yield; A strategy weight assignment module is used to obtain a plurality of preset initial capacity strategies, and assign weights to the initial capacity strategies according to the land information, water resource information, climate information, crop yield, carbon emission data and resource carrying range, so as to obtain the implementable weight corresponding to each of the initial capacity strategies; A capacity strategy selection module, used to use the initial capacity strategy with the implementable weight greater than the implementable threshold as the capacity improvement strategy for the agricultural land in the target area; The step of constructing an agricultural system model based on the agricultural data and predicting crop yield and carbon emission data under different land use patterns based on the agricultural system model includes: Randomly extracting multiple sample subsets from the agricultural data with replacement, each of the sample subsets serving as a training set for a decision tree; Randomly select some features from each of the sample subsets to train the corresponding decision tree; The decision trees are integrated to form a random forest model, and the agricultural data and a preset land use pattern set are input into the random forest model to obtain a prediction result of the crop yield; Predicting the biological area, biomass and chlorophyll content of different vegetation in the target area according to the preset land use mode and the crop yield; Obtaining a lighting function of the target area according to the climate information; The total primary productivity of the target area was calculated by the following formula: Wherein, G is the total primary productivity of the target area, lum(t) is the light function, [a, b] is the light interval, Biomn is the biomass of the nth vegetation, arean is the biological area of ​​the nth vegetation, and Choln is the chlorophyll content of the nth vegetation; Calculate the amount of carbon released by ecosystem respiration in the target area based on the CENTURY model; The carbon emission data is calculated by the following formula: N=GR Wherein, N is the carbon emission data, G is the total primary productivity of the target area, and R is the amount of carbon released by ecosystem respiration in the target area.

7. A system for formulating agricultural land productivity improvement strategies, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a method for formulating an agricultural land productivity improvement strategy as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the agricultural land productivity improvement strategy formulation method as described in any one of claims 1 to 5.

Images