An optimization method, system and storage medium for agricultural land use

Abstract

The present invention discloses an optimization method, system and storage medium for agricultural land use patterns. The method includes: collecting agricultural land characteristic data of a target area; identifying crop production areas corresponding to different crop categories in the target area based on the agricultural land characteristic data; calculating production resource parameters, greenhouse gas emission data and land resource parameters of each crop production area to obtain spatio-temporal dynamic evolution data of each crop production area; identifying key evolution nodes and evolution factors of each crop production area; constructing an agricultural land use pattern model including multiple objective functions and constraint conditions according to the crop categories, key evolution nodes and evolution factors; and outputting an optimized agricultural land use pattern through the agricultural land use pattern model according to the selected objective functions and constraint conditions. The present invention can improve the pertinence of optimizing agricultural land use patterns to ensure that the implementation of the optimization pattern can truly meet the agricultural land requirements of the target area.

Description

Technical Field

[0001] The present invention relates to the technical field of optimizing land use patterns, and particularly to a method, a system and a storage medium for optimizing agricultural land use patterns. Background Art

[0002] In the process of agricultural development, the rational use of land resources has always been a crucial issue. The lack of agricultural land use patterns has become a bottleneck restricting the sustainable development of agriculture. To better solve this problem, a series of agricultural land use strategies have been proposed in the prior art.

[0003] However, the prior art lacks a way to specifically carry out agricultural land use, so it is difficult to ensure that the optimized pattern can meet the agricultural land requirements of the target area, and instead it will cause waste of agricultural land resources. Therefore, a solution that can improve the specificity of agricultural land use patterns is needed to ensure the rational use of agricultural land resources. Summary of the Invention

[0004] Embodiments of the present invention provide a method, a system and a storage medium for optimizing agricultural land use patterns, which can improve the specificity of optimizing agricultural land use patterns to ensure that the implementation of the optimized pattern can truly meet the agricultural land requirements of the target area.

[0005] An embodiment of the present invention provides a method for optimizing agricultural land use patterns, including:

[0006] Collecting agricultural land characteristic data of the target area;

[0007] Based on the agricultural land characteristic data, identifying crop production areas corresponding to different crop categories in the target area;

[0008] Measuring production resource parameters, greenhouse gas emission data and land resource parameters of each of the crop production areas, and obtaining spatio-temporal dynamic evolution data of each of the crop production areas according to the production resource parameters, the greenhouse gas emission data and the land resource parameters;

[0009] Identifying key evolution nodes of each of the crop production areas from the spatio-temporal dynamic evolution data, and obtaining evolution factors corresponding to the key evolution nodes;

[0010] Constructing an agricultural land use pattern model including a plurality of objective functions and constraint conditions according to the crop categories, the key evolution nodes and the evolution factors;

[0011] Outputting an optimized agricultural land use pattern through the agricultural land use pattern model according to the selected objective functions and the constraint conditions.

[0012] As an improvement to the above solution, the objective function of the agricultural land use pattern model includes: maximizing the agricultural production benefit function, maximizing the land use efficiency function, and minimizing the carbon emission function;

[0013] The constraint conditions of the agricultural land use pattern model include: land resource constraints, production resource constraints, and social and economic constraints.

[0014] As an improvement to the above solution, the maximizing agricultural production benefit function includes:

[0015]

[0016] where i is the type of crop, I is the total number of crop types, YZi is the yield of the i-th crop, and PRi is the unit price of the i-th crop;

[0017] The maximizing land use efficiency function includes:

[0018]

[0019] where DA is the expected execution period of the optimized agricultural land use pattern, LF is the labor cost per unit time, TOi is the number of seeds of the i-th crop, PCi is the unit price of the seeds of the i-th crop, FE is the amount of chemical fertilizer applied per unit area, ARE is the agricultural land area of the target area, and WA is the amount of water irrigation per unit area;

[0020] The minimizing carbon emission function includes:

[0021] minf3 = FE × E fe × ARE + WA × E wa × ARE - C soil

[0022] where E fe is the carbon emission rate generated by chemical fertilizer application, E wa is the carbon emission rate generated by water irrigation, and C soil is the carbon absorption of the soil.

[0023] As an improvement to the above solution, the land resource constraints include:

[0024] AR min ≤ ARE ≤ AR max ;

[0025] AR min ≤ YZi / PERYi ≤ AR max ;

[0026] where ARE is the agricultural land area of the target area, AR minis the minimum value of the agricultural land area available for the target area, AR max is the maximum value of the agricultural land area available for the target area, YZi is the yield of the i-th crop, and PERYi is the yield per unit area of the i-th crop;

[0027] The production resource constraints include:

[0028] DA ≥ 0;

[0029] LF ≥ LF am ;

[0030] TOi ≥ YZi / rai;

[0031] PC min ≤ PCi ≤ PC max ;

[0032] FE min ≤ FE ≤ FE max ;

[0033] Among them, DA is the period expected to implement the optimized agricultural land use method, LF is the labor cost per unit time, and LF am is the minimum value of the labor cost per unit time in the target area, TOi is the number of seeds of the i-th crop, rai is the seed-crop conversion rate of the i-th crop, PCi is the unit price of the seeds of the i-th crop, and PC min is the minimum value of the market price of the seeds of the i-th crop, PC max is the maximum value of the market price of the seeds of the i-th crop, FE is the amount of chemical fertilizer applied per unit area, and FE min is the minimum value of the amount of chemical fertilizer applied per unit area, FE max is the maximum value of the amount of chemical fertilizer applied per unit area, WA is the amount of water irrigation per unit area, and WA min is the minimum value of the amount of water irrigation per unit area, WA max is the maximum value of the amount of water irrigation per unit area;

[0034] The social and economic constraints include:

[0035] PR min ≤ PRi ≤ PR max ;

[0036] Among them, PRi is the unit price of the i-th crop, and PR min is the minimum value of the market price of the i-th crop, and PR max is the maximum value of the market price of the i-th crop.

[0037] As an improvement to the above solution, identifying crop production areas corresponding to different crop categories in the target area based on the agricultural land feature data includes:

[0038] Obtain a dataset containing the agricultural land features; wherein, the dataset includes land use type, soil type, topography, and climate conditions;

[0039] Perform data analysis on the dataset, and use a geographic information system to obtain the correlation between the agricultural land features and different crop categories;

[0040] Use a clustering algorithm to identify the planting areas of different crops under different land features.

[0041] As an improvement to the above solution, identifying key evolution nodes of each of the crop production areas from the spatio-temporal dynamic evolution data and obtaining the evolution factors corresponding to the key evolution nodes includes:

[0042] Based on the spatio-temporal dynamic evolution data, generate evolution curves corresponding to the production resource parameters, the greenhouse gas emission data, and the land resource parameters;

[0043] Standardize the evolution curves to the same data points and data range by interpolation or resampling method and align them in time;

[0044] Perform weighted summation on the three evolution curves according to preset weights to obtain an integrated curve;

[0045] Perform derivative calculation on the integrated curve, and use the data points with derivatives greater than the preset derivative value as the key evolution nodes;

[0046] Obtain the time data corresponding to the key evolution nodes, and obtain the change events of land resources, production resources, or social economy corresponding to the time data.

[0047] As an improvement to the above solution, outputting an optimized agricultural land use method through the agricultural land use method model according to the selected objective function and constraint conditions includes:

[0048] Select the objective function based on the characteristics of the target area;

[0049] The agricultural land use method model calls the constraint conditions corresponding to the selected objective function;

[0050] Output agricultural land data that satisfies the constraint conditions corresponding to the selected objective function to form the agricultural land use method.

[0051] Another embodiment of the present invention correspondingly provides an agricultural land use optimization system, including: a feature data acquisition module, configured to acquire agricultural land feature data of a target area;

[0052] a crop production area identification module, configured to identify crop production areas corresponding to different crop categories in the target area based on the agricultural land feature data;

[0053] an evolution data acquisition module, configured to calculate production resource parameters, greenhouse gas emission data, and land resource parameters of each of the crop production areas, and obtain spatio-temporal dynamic evolution data of each of the crop production areas according to the production resource parameters, the greenhouse gas emission data, and the land resource parameters;

[0054] an evolution factor acquisition module, configured to identify key evolution nodes of each of the crop production areas from the spatio-temporal dynamic evolution data, and obtain evolution factors corresponding to the key evolution nodes;

[0055] a target model construction module, configured to construct an agricultural land use model including a plurality of objective functions and constraint conditions according to the crop categories, the key evolution nodes, and the evolution factors;

[0056] an agricultural land optimization module, configured to output an optimized agricultural land use mode through the agricultural land use model according to the selected objective functions and the constraint conditions.

[0057] Another embodiment of the present invention provides an agricultural land use optimization system, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the agricultural land use optimization method described in the above-mentioned embodiment of the present invention is implemented.

[0058] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, the device where the computer-readable storage medium is located is controlled to execute the agricultural land use optimization method described in the above-mentioned embodiment of the present invention.

[0059] Compared with the prior art, in the embodiments of the present invention, the agricultural land characteristic data, the production resource parameters of each of the crop production areas, the greenhouse gas emission data, and the land resource parameters can help identify the key evolution nodes and evolution factors of the crop production areas, and construct an agricultural land use mode model, so as to optimize the agricultural land use mode, improve the resource utilization rate, reduce the greenhouse gas emissions, and improve the land resource parameters; by constructing a variety of different objective functions and constraint conditions, the decision maker can selectively obtain the agricultural land optimization direction according to the actual demand of the target area, so as to improve the pertinence of the optimization of the agricultural land use mode, and ensure that the implementation of the optimization mode can truly meet the agricultural land demand of the target area. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a schematic flow chart of a method for optimizing an agricultural land use mode provided by an embodiment of the present invention;

[0061] Figure 2 is a schematic structural diagram of a system for optimizing an agricultural land use mode provided by an embodiment of the present invention;

[0062] Figure 3 is a schematic structural diagram of a system for optimizing an agricultural land use mode provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0064] See Figure 1 , which is a schematic flow chart of a method for optimizing an agricultural land use mode provided by an embodiment of the present invention, including steps S101 to S105:

[0065] S101. Collect the agricultural land characteristic data of the target area;

[0066] Specifically, the agricultural land characteristic data may include data related to agricultural land such as the land use type, soil type, topography and landform, and climate conditions of the target area.

[0067] S102. Based on the agricultural land characteristic data, identify the crop production areas corresponding to different crop categories in the target area;

[0068] Specifically, based on the agricultural land characteristic data, the crop production areas corresponding to different crop categories are identified, so as to accurately obtain the spatio-temporal dynamic evolution data corresponding to each category of crops.

[0069] Exemplarily, the crop categories may include food crops (such as wheat, rice, corn, rice, sorghum, etc.), cash crops (such as cotton, rapeseed, soybean, peanut, sugarcane, sweet potato, tobacco, etc.), vegetable crops (such as tomato, cucumber, carrot, Chinese cabbage, spinach, eggplant, pepper, etc.), fruit crops (such as apple, banana, orange, lemon, grape, strawberry, peach, plum, etc.), herbaceous crops (such as forage grass, feed crops, etc.). In addition, it may also include specialty crops, ornamental crops, medicinal crops, etc. in the target area. Specifically, tools such as Geographic Information System (GIS) can be used for spatial analysis to perform correlation analysis on crop planting data and agricultural land characteristic data.

[0070] S103. Measure the production resource parameters, greenhouse gas emission data, and land resource parameters of each crop production area, and obtain the spatio-temporal dynamic evolution data of each crop production area based on the production resource parameters, greenhouse gas emission data, and land resource parameters;

[0071] Specifically, the production resource parameters may include labor costs over the years, seed-crop conversion rates, seed prices, fertilizer use, and water irrigation amounts, etc.

[0072] Specifically, the emission factor method recommended by the IPCC is used to calculate agricultural greenhouse gas emissions, including obtaining the emission factors and corresponding activity data of straw field burning, agricultural land, paddy field methane emissions, and soil carbon sinks, etc., and then summing the products of the emission factors and the corresponding activity data to obtain the greenhouse gas emission data.

[0073] Specifically, the land resource parameters include collecting land resource parameters such as soil type, land use type, and land quality.

[0074] Specifically, using the data collected above, analyze the dynamic evolution curves of different crop production areas at different times.

[0075] In a specific implementation manner, since agricultural production and land use conditions change over time, the data and parameters can be updated regularly, and the model can be retrained to ensure the accuracy and timeliness of the analysis results.

[0076] S104. Identify the key evolution nodes of each crop production area from the spatio-temporal dynamic evolution data, and obtain the evolution factors corresponding to the key evolution nodes;

[0077] Specifically, nodes in the spatio-temporal dynamic evolution data with a change rate exceeding a preset threshold can be used as the above-mentioned key evolution nodes.

[0078] Exemplarily, the preset threshold of the above change rate can be ±30%, or ±50%, etc., which can be set according to actual needs and actual evolution situations.

[0079] Exemplarily, when the preset threshold of the change rate is set to ±30%, if the greenhouse gas emission data at a certain time node t1 decreases by 30% or more compared to the previous time node t0, then t1 can be used as a key evolution node; if the crop yield at a certain time node t3 increases by 30% or more compared to the previous time node t2, then t2 can also be used as a key evolution node.

[0080] S105. Construct an agricultural land use pattern model including multiple objective functions and constraint conditions according to crop categories, key evolution nodes, and evolution factors;

[0081] Specifically, by constructing a variety of different objective functions and constraint conditions, decision-makers can select the optimization direction of agricultural land according to the actual needs of the target area, such as maximizing the agricultural production benefit function, or maximizing the land use efficiency function, or minimizing the carbon emission function, etc., which improves the flexibility of optimizing the agricultural land use pattern.

[0082] S106. Through the agricultural land use pattern model, output the optimized agricultural land use pattern according to the selected objective function and constraint conditions.

[0083] Specifically, after constructing the agricultural land use pattern model, the performance of the model can be evaluated and trained on the training set, validation set, or test set to ensure that the model can work effectively in practical problems and meet all relevant constraint conditions.

[0084] In this embodiment, preferably, the objective functions of the agricultural land use pattern model include: maximizing the agricultural production benefit function, maximizing the land use efficiency function, and minimizing the carbon emission function;

[0085] The constraint conditions of the agricultural land use pattern model include: land resource constraints, production resource constraints, and social and economic constraints.

[0086] Specifically, the constraint conditions corresponding to the maximizing agricultural production benefit function include land resource constraints and social and economic constraints; the constraint conditions corresponding to the maximizing land use efficiency function include land resource constraints, production resource constraints, and social and economic constraints; the constraint conditions corresponding to the minimizing carbon emission function include land resource constraints and production resource constraints.

[0087] In this embodiment, preferably, the maximizing agricultural production benefit function includes:

[0088]

[0089] Among them, i is the type of crop, I is the total number of crop types, YZi is the yield of the i-th crop, and PRi is the unit price of the i-th crop;

[0090] The function for maximizing land use efficiency includes:

[0091]

[0092] Among them, DA is the expected execution period of the optimized agricultural land use method, LF is the labor cost per unit time, TOi is the number of seeds of the i-th crop, PCi is the unit price of the seeds of the i-th crop, FE is the amount of chemical fertilizer applied per unit area, ARE is the agricultural land area of the target area, and WA is the amount of water irrigation per unit area;

[0093] The function for minimizing carbon emissions includes:

[0094] minf3 = FE × E fe × ARE + WA × E wa × ARE - C soil

[0095] Among them, E fe is the carbon emission rate generated by chemical fertilizer application, E wa is the carbon emission rate generated by water irrigation, and C soil is the carbon absorption of the soil.

[0096] In this embodiment, preferably, the land resource constraints include:

[0097] AR min ≤ ARE ≤ AR max ;

[0098] AR min ≤ YZi / PERYi ≤ AR max ;

[0099] Among them, ARE is the agricultural land area of the target area, AR min is the minimum value of the agricultural land area that can be invested in the target area, AR max is the maximum value of the agricultural land area that can be invested in the target area, YZi is the yield of the i-th crop, and PERYi is the yield per unit area of the i-th crop;

[0100] The production resource constraints include:

[0101] DA ≥ 0;

[0102] LF ≥ LF am ;

[0103] TOi ≥ YZi / rai;

[0104] PC min ≤ PCi ≤ PC max ;

[0105] FE min ≤ FE ≤ FE max ;

[0106] Among them, DA is the period expected to be executed for the optimized agricultural land use method, LF is the labor cost per unit time, and LF am is the minimum value of the labor cost per unit time in the target area, TOi is the number of seeds of the i-th crop, rai is the seed-crop conversion rate of the i-th crop, PCi is the unit price of the seeds of the i-th crop, and PC min is the minimum value of the market price of the seeds of the i-th crop, and PC max is the maximum value of the market price of the seeds of the i-th crop, FE is the amount of chemical fertilizer applied per unit area, and FE min is the minimum value of the amount of chemical fertilizer applied per unit area, and FE max is the maximum value of the amount of chemical fertilizer applied per unit area, WA is the amount of water irrigation per unit area, and WA min is the minimum value of the amount of water irrigation per unit area, and WA max is the maximum value of the amount of water irrigation per unit area;

[0107] Socio-economic constraints include:

[0108] PR min ≤ PRi ≤ PR max ;

[0109] Among them, PRi is the unit price of the i-th crop, and PR min is the minimum value of the market price of the i-th crop, and PR max is the maximum value of the market price of the i-th crop.

[0110] Furthermore, in a specific implementation manner, the constraint conditions corresponding to maximizing the agricultural production benefit function may further include crop ratio constraints. At this time, the function for maximizing the agricultural production benefit is:

[0111]

[0112] Among them, j is the type of food crop, J is the total number of types of food crops, and Ygrain j is the yield of the j-th food crop, and Pgrain j is the unit price of the j-th food crop; k is the type of cash crop, K is the total number of types of cash crops, and Ycashk is the yield of the k-th cash crop, and Pcash k is the unit price of the k-th cash crop; l is the type of specialty crop, L is the total number of specialty crop types, and Yspec l is the yield of the l-th specialty crop, and Pspec l is the unit price of the l-th specialty crop.

[0113] The crop ratio constraint is:

[0114] 0 ≤ Ygrain j / Ycash k ≤ 1;

[0115] 0 ≤ Ygrain j / Yspec l ≤ 1;

[0116] 0 ≤ Ycash k / Yspec l ≤ 1;

[0117] Y min ≤ Ygrain j + Ycash k + Yspec l ≤ Y max ;

[0118] Among them, Y min is the minimum value of the crop yield in the target area, and Y max is the maximum value of the crop yield in the target area.

[0119] In a specific implementation manner, the maximized agricultural production benefit function maxf4 is an extensible objective function. For example, the products of vegetable crops, fruit crops, herbaceous crops, ornamental crops, medicinal crops and their corresponding unit prices can be accumulated in maxf4, and corresponding constraint conditions can be added. The constraint conditions can be corrected according to the actual situation of the target area, which will not be elaborated in this embodiment.

[0120] In this embodiment, preferably, based on the agricultural land feature data, the crop production areas corresponding to different crop categories are identified in the target area, including:

[0121] Obtain a dataset containing agricultural land features; among them, the dataset includes land use type, soil type, topography and climate conditions;

[0122] Perform data analysis on the dataset, and use a geographic information system to obtain the correlation between agricultural land features and different crop categories;

[0123] Use a clustering algorithm to identify the planting areas of different crops under different land features.

[0124] Specifically, by collecting detailed information on various aspects such as land use type, soil type, topography, and climate conditions, comprehensive and accurate agricultural land characteristic data are provided, thereby obtaining a more accurate identification result of crop production areas.

[0125] Specifically, an appropriate clustering algorithm can be selected, such as K-means clustering, hierarchical clustering, etc., to perform clustering analysis on the data, identify the planting areas of different crops under different land characteristics, and based on the clustering results, the characteristics of each planting area and the corresponding crop types can be obtained.

[0126] In this embodiment, preferably, key evolution nodes of each crop production area are identified from the spatio-temporal dynamic evolution data, and the evolution factors corresponding to the key evolution nodes are obtained, including:

[0127] Based on the spatio-temporal dynamic evolution data, evolution curves corresponding to production resource parameters, greenhouse gas emission data, and land resource parameters are generated;

[0128] The evolution curves are standardized to the same data points and data range by interpolation or resampling method and aligned in time;

[0129] The three evolution curves are weighted and summed according to preset weights to obtain an integrated curve;

[0130] Derivative calculation is performed on the integrated curve, and the data points with derivatives greater than the preset derivative value are used as key evolution nodes;

[0131] The time data corresponding to the key evolution nodes is obtained, and the change events of land resources, production resources, or social economy corresponding to the time data are obtained.

[0132] Specifically, before aligning the three curves in time, smoothing processing can also be performed to eliminate noise and reduce the fluctuation of the curves. For example, moving average, Loess smoothing method, etc. can be used.

[0133] Specifically, the three curves can be aligned in time by timestamp or spatial coordinates.

[0134] Specifically, the above weights can be set according to the importance or credibility of each curve.

[0135] Specifically, the integrated curve can be visually displayed together with the three original evolution curves before integration, so as to facilitate researchers to compare and analyze. For example, a curve graph is used to display the integrated curve, and the original curves are marked in the graph for reference.

[0136] In specific embodiments, the evolution factors may include land resources, production resources, or social and economic change events, such as adjustments to the divided area of crop production regions, adjustments to production resources, changes in agricultural policies, etc. As long as it conforms to objective facts, specific limitations are not made in this implementation.

[0137] In this embodiment, preferably, through the agricultural land use mode model, according to the selected objective function and constraint conditions, an optimized agricultural land use mode is output, including:

[0138] Select an objective function based on the characteristics of the target area;

[0139] The agricultural land use mode model calls the constraint conditions corresponding to the selected objective function;

[0140] Output agricultural land data that meets the constraint conditions corresponding to the selected objective function to form an agricultural land use mode.

[0141] Specifically, in order to achieve targeted optimization of the agricultural land use mode, it is necessary to select a suitable objective function based on the characteristics of the target area. The setting of the objective function should comprehensively consider multiple aspects such as the suitability of agricultural production, the sustainability of the ecological environment, and the rationality of social economy.

[0142] After selecting the objective function, it is necessary to call the constraint conditions corresponding to the objective function in the agricultural land use mode model. Through the limitation of these constraint conditions, it can be ensured that the optimized agricultural land use mode can take into account ecological environmental protection and sustainable development while meeting production requirements.

[0143] In summary, in the embodiments of the present invention, through agricultural land characteristic data, production resource parameters of each crop production area, greenhouse gas emission data, and land resource parameters, it is possible to help identify key evolution nodes and evolution factors of crop production areas, and construct an agricultural land use mode model, thereby optimizing the agricultural land use mode, improving resource utilization rate, reducing greenhouse gas emissions, and improving land resource parameters; by constructing a variety of different objective functions and constraint conditions, decision-makers can selectively obtain the agricultural land optimization direction according to the actual demand situation of the target area, thereby improving the pertinence of the optimization of the agricultural land use mode to ensure that the implementation of the optimization method can truly meet the agricultural land requirements of the target area.

[0144] See Figure 2 , which is a schematic structural diagram of an agricultural land use mode optimization system provided by an embodiment of the present invention, including:

[0145] A feature data acquisition module 201 for acquiring agricultural land characteristic data of the target area;

[0146] The crop production area identification module 202 is used to identify the crop production areas corresponding to different crop categories in the target area based on agricultural land feature data;

[0147] The evolution data acquisition module 203 is used to calculate the production resource parameters, greenhouse gas emission data, and land resource parameters of each crop production area, and obtain the spatio-temporal dynamic evolution data of each crop production area based on the production resource parameters, greenhouse gas emission data, and land resource parameters;

[0148] The evolution factor acquisition module 204 is used to identify the key evolution nodes of each crop production area from the spatio-temporal dynamic evolution data, and obtain the evolution factors corresponding to the key evolution nodes;

[0149] The target model construction module 205 is used to construct an agricultural land use model including multiple objective functions and constraint conditions according to the crop category, key evolution nodes, and evolution factors;

[0150] The agricultural land optimization module 206 is used to output the optimized agricultural land use method through the agricultural land use model according to the selected objective function and constraint conditions.

[0151] Furthermore, the objective functions of the agricultural land use model include: the agricultural production benefit maximization function, the land use efficiency maximization function, and the carbon emission minimization function;

[0152] The constraint conditions of the agricultural land use model include: land resource constraint, production resource constraint, and social and economic constraint.

[0153] Furthermore, the agricultural production benefit maximization function includes:

[0154]

[0155] where i is the crop type, I is the total number of crop types, YZi is the yield of the i-th crop, and PRi is the unit price of the i-th crop;

[0156] The land use efficiency maximization function includes:

[0157]

[0158] where DA is the period expected to execute the optimized agricultural land use method, LF is the labor cost per unit time, TOi is the number of seeds of the i-th crop, PCi is the unit price of the seeds of the i-th crop, FE is the amount of chemical fertilizer applied per unit area, ARE is the agricultural land area of the target area, and WA is the amount of water irrigation per unit area;

[0159] The carbon emission minimization function includes:

[0160] minf3 = FE × E fe × ARE + WA × E wa × ARE - C soil

[0161] Among them, E fe is the carbon emission rate generated by chemical fertilizer application, E wa is the carbon emission rate generated by water irrigation, C soil is the carbon absorption of the soil.

[0162] Furthermore, the land resource constraints include:

[0163] AR min ≤ ARE ≤ AR max ;

[0164] AR min ≤ YZi / PERYi ≤ AR max ;

[0165] Among them, ARE is the agricultural land area of the target area, AR min is the minimum value of the agricultural land area that can be invested in the target area, AR max is the maximum value of the agricultural land area that can be invested in the target area, YZi is the yield of the i-th crop, and PERYi is the yield per unit area of the i-th crop;

[0166] The production resource constraints include:

[0167] DA ≥ 0;

[0168] LF ≥ LF am ;

[0169] TOi ≥ YZi / rai;

[0170] PC min ≤ PCi ≤ PC max ;

[0171] FE min ≤ FE ≤ FE max ;

[0172] Among them, DA is the period expected to implement the optimized agricultural land use method, LF is the labor cost per unit time, LF am is the minimum value of the labor cost per unit time in the target area, TOi is the number of seeds of the i-th crop, rai is the seed-crop conversion rate of the i-th crop, PCi is the unit price of the seeds of the i-th crop, PC min is the minimum value of the market price of the seeds of the i-th crop, PC maxis the maximum value of the market price of the seeds of the i-th crop, FE is the amount of chemical fertilizer applied per unit area, FE min is the minimum value of the amount of chemical fertilizer applied per unit area, FE max is the maximum value of the amount of chemical fertilizer applied per unit area, WA is the amount of water irrigation per unit area, WA min is the minimum value of the amount of water irrigation per unit area, WA max is the maximum value of the amount of water irrigation per unit area;

[0173] Socio-economic constraints include:

[0174] PR min ≤PRi≤PR max ;

[0175] where PRi is the unit price of the i-th crop, PR min is the minimum value of the market price of the i-th crop, PR max is the maximum value of the market price of the i-th crop.

[0176] Furthermore, based on the agricultural land characteristic data, crop production areas corresponding to different crop categories are identified in the target area, including:

[0177] Obtain a dataset containing agricultural land characteristics; among them, the dataset includes land use type, soil type, topography and climate conditions;

[0178] Perform data analysis on the dataset, and use geographic information system to obtain the correlation between agricultural land characteristics and different crop categories;

[0179] Use clustering algorithm to identify the planting areas of different crops under different land characteristics.

[0180] Furthermore, key evolution nodes of each crop production area are identified from the spatio-temporal dynamic evolution data, and evolution factors corresponding to the key evolution nodes are obtained, including:

[0181] Based on the spatio-temporal dynamic evolution data, generate evolution curves corresponding to production resource parameters, greenhouse gas emission data and land resource parameters;

[0182] Standardize the evolution curves to the same data points and data ranges by interpolation or resampling method, and align them in time;

[0183] Perform weighted summation on the three evolution curves according to the preset weights to obtain an integrated curve;

[0184] Perform derivative calculation on the integrated curve, and use the data points with derivatives greater than the preset derivative value as key evolution nodes;

[0185] Obtain the time data corresponding to the key evolution nodes, and obtain the change events of land resources, production resources, or social economy corresponding to the time data.

[0186] Further, through the agricultural land use mode model, according to the selected objective function and constraint conditions, output the optimized agricultural land use mode, including:

[0187] Select the objective function based on the characteristics of the target area;

[0188] The agricultural land use mode model calls the constraint conditions corresponding to the selected objective function;

[0189] Output the agricultural land data that meets the constraint conditions corresponding to the selected objective function to form the agricultural land use mode.

[0190] In summary, in the embodiments of the present invention, through the agricultural land characteristic data, the production resource parameters, greenhouse gas emission data, and land resource parameters of each crop production area, it is possible to help identify the key evolution nodes and evolution factors of the crop production area, and construct an agricultural land use mode model, thereby optimizing the agricultural land use mode, improving resource utilization rate, reducing greenhouse gas emissions, and improving land resource parameters; by constructing a variety of different objective functions and constraint conditions, decision-makers can selectively obtain the agricultural land optimization direction according to the actual demand situation of the target area, thereby improving the pertinence of the optimization of the agricultural land use mode to ensure that the implementation of the optimization mode can truly meet the agricultural land needs of the target area.

[0191] See Figure 3 , which is a schematic diagram of an agricultural land use mode optimization system provided by an embodiment of the present invention. The agricultural land use mode optimization system 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 an agricultural land use mode optimization program. When the processor 1 executes the computer program, the steps in the above-mentioned various embodiments of the agricultural land use mode optimization method 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.

[0192] Exemplarily, the computer program can be divided into one or more modules / units. One or more modules / units are stored in the memory and executed by the processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the agricultural land use mode optimization system.

[0193] The agricultural land use mode optimization system may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the schematic diagram is only an example of the agricultural land use mode optimization system, and does not constitute a limitation on the agricultural land use mode optimization system. It may include more or fewer components than those shown, or combine certain components, or different components. For example, the agricultural land use mode optimization system may also include input / output devices, network access devices, CAN buses, etc.

[0194] The embodiment of the present invention correspondingly provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the agricultural land use mode optimization method as in Embodiment 1 of the present invention.

[0195] The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the agricultural land use mode optimization system, and uses various interfaces and lines to connect all parts of the entire agricultural land use mode optimization system.

[0196] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the agricultural land use mode optimization 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 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0197] Among them, if the modules / units integrated in the agricultural land use mode optimization system are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included 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 electrical carrier signals and telecommunication signals.

[0198] It should be noted that the device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached 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 can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0199] The above are the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for optimizing agricultural land use, characterized in that: include: Collect data on agricultural land characteristics in the target area; Based on the agricultural land characteristic data, identifying crop production areas corresponding to different crop categories in the target area; Calculating production resource parameters, greenhouse gas emission data and land resource parameters of each of the crop production areas, and obtaining spatiotemporal dynamic evolution data of each of the crop production areas based on the production resource parameters, the greenhouse gas emission data and the land resource parameters; Based on the spatiotemporal dynamic evolution data, generating evolution curves corresponding to the production resource parameters, the greenhouse gas emission data and the land resource parameters; The evolution curves are normalized to the same data points and data range by interpolation or resampling, and aligned in time; Performing weighted summation on the three evolution curves according to preset weights to obtain an integrated curve; Performing derivative calculation on the integrated curve, and taking data points whose derivatives are greater than a preset derivative value as key evolution nodes; Acquire time data corresponding to the key evolution node, and acquire change events of land resources, production resources or social economy corresponding to the time data as evolution factors corresponding to the key evolution node; Constructing an agricultural land use model including multiple objective functions and constraint conditions according to the crop categories, the key evolution nodes and the evolution factors; Outputting an optimized agricultural land use mode according to the selected objective function and the constraint conditions through the agricultural land use mode model; The objective function of the agricultural land use model includes: maximizing agricultural production benefit function, maximizing land use efficiency function and minimizing carbon emission function; the constraint conditions of the agricultural land use model include: land resource constraint, production resource constraint, socio-economic constraint and crop ratio constraint; The function of maximizing agricultural production benefits also includes: ； in, i For crop types, I is the total number of crop types, YZ i For the i The yield of crops, PR i For the i The unit price of growing crops; The function for maximizing land use efficiency includes: ； Among them, DA is the expected execution period of the optimized agricultural land use mode, LF is the labor cost per unit time, TO is i For the i The number of seeds for growing crops, PC i For the i The unit price of the seeds of the crops planted, FE is the amount of fertilizer applied per unit area, ARE is the agricultural land area of ​​the target area, and WA is the amount of water irrigation per unit area; The carbon emission minimization function includes: minf 3=FE× E fe ×ARE+WA× E wa ×ARE− C soil ; in, E fe The carbon emission rate caused by fertilizer application, E wa Carbon emission rate for irrigation water, C soil is the amount of carbon absorbed by the soil.

2. The method for optimizing agricultural land use according to claim 1, characterized in that: The land resource constraints include: WITH min ≤ARE≤AR max ; AR min ≤YZ i / LEAVES i ≤AR max ; Among them, ARE is the agricultural land area of ​​the target area, AR min is the minimum area of ​​agricultural land available in the target area, AR max is the maximum value of the agricultural land area that can be invested in the target area, YZ i For the i The yield of crops, PERY i For the i The yield per unit area of ​​crops grown; The production resource constraints include: DA ≥ 0; LF≥LF am ; TO i ≥YZ i / ra i ; PC min ≤PC i ≤PC max ; FE min ≤FE≤FE max ; Among them, DA is the expected execution period of the optimized agricultural land use mode, LF is the labor cost per unit time, and LF am is the minimum labor cost per unit time in the target area, TO i For the i The number of seeds for growing crops, ra i For the i Seed-crop conversion rate of crops, PC i For the i The unit price of seeds for crops, PC min For the i The minimum market price of seeds for crops, PC max For the i The maximum market price of the seeds of the crops, FE is the amount of fertilizer applied per unit area, FE min is the minimum amount of fertilizer applied per unit area, FE max is the maximum amount of fertilizer applied per unit area, WA is the amount of water irrigation per unit area; The socio-economic constraints include: PR min ≤PR i ≤PR max ; Among them, PR i For the i Unit price of crops, PR min For the i The minimum market price of crops, PR max For the i The maximum market price of a crop.

3. The method for optimizing agricultural land use according to claim 1, characterized in that: The step of identifying, in the target area, crop production areas corresponding to different crop categories based on the agricultural land characteristic data comprises: Acquire a data set containing the characteristics of the agricultural land; wherein the data set includes land use type, soil type, topography, and climate conditions; Performing data analysis on the data set, and obtaining the correlation between the agricultural land characteristics and different crop categories using a geographic information system; Clustering algorithms are used to identify planting areas for different crops under different land characteristics.

4. The method for optimizing agricultural land use according to claim 3, characterized in that: The method of outputting an optimized agricultural land use mode through the agricultural land use mode model according to the selected objective function and the constraint conditions includes: Selecting the objective function based on the characteristics of the target area; The agricultural land use model calls the constraint conditions corresponding to the selected objective function; Output the agricultural land data that meets the constraint conditions corresponding to the selected objective function to form the agricultural land use mode.

5. An agricultural land use optimization system, characterized in that: include: A characteristic data collection module is used to collect characteristic data of agricultural land in the target area; A crop production area identification module, used for identifying crop production areas corresponding to different crop categories in the target area based on the agricultural land characteristic data; An evolution data acquisition module, used to measure the production resource parameters, greenhouse gas emission data and land resource parameters of each of the crop production areas, and obtain the spatiotemporal dynamic evolution data of each of the crop production areas according to the production resource parameters, the greenhouse gas emission data and the land resource parameters; An evolution factor acquisition module is used to generate evolution curves corresponding to the production resource parameters, the greenhouse gas emission data and the land resource parameters based on the spatiotemporal dynamic evolution data; standardize the evolution curves to the same data points and data range by interpolation or resampling method, and align them in time; perform weighted summation on the three evolution curves according to preset weights to obtain an integrated curve; perform derivative calculation on the integrated curve, and take the data points whose derivatives are greater than the preset derivative values ​​as key evolution nodes; obtain the time data corresponding to the key evolution nodes, and obtain the land resources, production resources or social economic change events corresponding to the time data as the evolution factors corresponding to the key evolution nodes; A target model building module, used to build an agricultural land use model including multiple target functions and constraint conditions according to the crop categories, the key evolution nodes and the evolution factors; An agricultural land optimization module, used to output an optimized agricultural land utilization mode according to the selected objective function and the constraint conditions through the agricultural land utilization mode model; The objective function of the agricultural land use model includes: maximizing agricultural production benefit function, maximizing land use efficiency function and minimizing carbon emission function; the constraint conditions of the agricultural land use model include: land resource constraint, production resource constraint, socio-economic constraint and crop ratio constraint; The function of maximizing agricultural production benefits also includes: ； in, i For crop types, I is the total number of crop types, YZ i For the i The yield of crops, PR i For the i The unit price of growing crops; The function for maximizing land use efficiency includes: ； Among them, DA is the expected execution period of the optimized agricultural land use mode, LF is the labor cost per unit time, TO is i For the i The number of seeds for growing crops, PC i For the i The unit price of the seeds of the crops planted, FE is the amount of fertilizer applied per unit area, ARE is the agricultural land area of ​​the target area, and WA is the amount of water irrigation per unit area; The carbon emission minimization function includes: minf 3=FE× E fe ×ARE+WA× E wa ×ARE− C soil ; in, E fe The carbon emission rate caused by fertilizer application, E wa Carbon emission rate for irrigation water, C soil is the amount of carbon absorbed by the soil.

6. An agricultural land use optimization system, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, an agricultural land utilization optimization method as described in any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the agricultural land utilization optimization method as described in any one of claims 1 to 4.

Images