Crop planting space layout method and device, computer equipment and storage medium

Abstract

The invention relates to a crop planting space layout method and device, computer equipment and a storage medium. According to the crop planting spatial layout method, a random forest algorithm is used for training and estimating development suitability of different crop types, a neighborhood effect and land productivity constraint are introduced to simulate an interaction relationship among crops, and a wheel disc selection mechanism is used for describing uncertainty in crop type transformation; the method is used for quickly and accurately simulating a crop planting space pattern in a future scene. The problems that a traditional investigation method is too high in subjectivity and huge in workload, and a remote sensing technology is difficult to simulate a future crop planting structure spatial pattern are solved, and refined expression of the crop planting spatial pattern is promoted.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology, and in particular to a crop planting space layout method, device, computer equipment and storage medium. Background Art

[0002] The spatial pattern of crop planting is one of the core contents of the agricultural land use system. It can reflect the service functions within the agricultural land use system and the utilization of agricultural production resources by humans, and is an important basis for optimizing and adjusting the crop structure. At present, the global demand for food is increasing, and the demand for land and water resources is increasing accordingly. However, there is often a spatial mismatch between crop planting and resource and environmental endowments, and there is a problem of low refinement of the spatial pattern of crop planting. Summary of the invention

[0003] Based on this, it is necessary to provide a crop planting space layout method, device, computer equipment and storage medium that promote the refined expression of crop planting spatial pattern.

[0004] In order to achieve the above objectives, on the one hand, an embodiment of the present application provides a crop planting space layout method, comprising:

[0005] Determine land productivity and area required in the planting area;

[0006] The crop suitability probability of each pixel in the planting area is obtained through simulation;

[0007] Get the neighborhood effect value of each pixel;

[0008] Determine the limiting factor constraints; where the limiting factor constraints are determined by land productivity, food production requirements and crop growth factor constraints;

[0009] Determine the combined probability of pixel transformation to a specific crop type based on crop suitability probability, neighborhood effect value, and limiting factor constraints;

[0010] Roulette selection is performed according to the combined probability to determine the crop type change result of each pixel, and the allocated area of ​​each crop type is obtained according to the crop type change result and the current round of iteration is completed;

[0011] Execute the next round of iterations and end the task when the allocated area is equal to the required area.

[0012] In one embodiment, the step of obtaining the neighborhood effect value of each pixel includes:

[0013] Based on the clustering of crops of the same type, the neighborhood effect value of pixels converted into specific crop types is obtained.

[0014] In one embodiment, in the step of obtaining the neighborhood effect value of converting the pixel into a specific crop type based on the aggregation of the same type of crops, the neighborhood effect value is obtained based on the following formula:

[0015]

[0016] Where L is the planting type of pixel i, n is the radius of the field; Con is the objective function, whose value is 1 when L = q, otherwise it is 0.

[0017] In one embodiment, the step of obtaining the neighborhood effect value of each pixel includes:

[0018] Obtain resource requirements of various types of crops, and confirm the competitive effect value based on the resource requirements;

[0019] The symbiotic effect value is obtained, and the neighborhood effect value is obtained based on the competition effect value and the symbiotic effect value.

[0020] In one embodiment, the step of determining the land productivity of the planting area includes:

[0021] Obtain growth period parameters, thermal zone zoning parameters, soil property parameters, land resource stock parameters and input level values ​​of the planting area;

[0022] According to the growth period parameters and land resource stock parameters, the photosynthetic production potential is obtained;

[0023] According to the photosynthetic production potential and the thermal zone zoning parameters, the light and temperature production potential is obtained;

[0024] Based on the light-temperature production potential and water use parameters, the climate production potential is obtained;

[0025] Identify the land production potential based on climatic production potential and soil property parameters;

[0026] Confirm land productivity based on land production potential and input level values.

[0027] In one embodiment, the limiting factor is determined according to the following formula:

[0028] C=con(L=Crop e )

[0029] Where C represents the limiting factor of pixel i; con is the objective function, which means that the pixel takes the value of 1 when it meets the conversion conditions such as production period, thermal zone division, soil properties, land resource stock and input level, and takes the value of 0 otherwise; Crop e Indicates crop category e.

[0030] In one embodiment, in the step of determining the combined probability of a pixel being transformed into a specific crop type according to the crop suitability probability, the neighborhood effect value, and the constraint of the limiting factor, the combined probability is obtained based on the following formula:

[0031]

[0032] in, is the combined probability; is the crop suitability probability; is the neighborhood effect value; C is the restriction factor constraint.

[0033] On the one hand, an embodiment of the present invention further provides a crop planting space layout device, comprising:

[0034] Determination module to determine land productivity and required area in the planting area;

[0035] The crop suitability probability acquisition module is used to simulate the crop suitability probability of each pixel in the planting area using the conditional random forest algorithm;

[0036] A neighborhood effect value acquisition module is used to obtain the neighborhood effect value of each pixel;

[0037] A constraint module is used to determine the limiting factor constraints; wherein the limiting factor constraints are determined by land productivity, food production requirements and crop growth factor constraints;

[0038] A combined probability acquisition module is used to determine the combined probability of a pixel being transformed into a specific crop type based on the crop suitability probability, the neighborhood effect value, and the constraint of the limiting factor;

[0039] A roulette wheel selection module is used to perform roulette wheel selection according to the combination probability, determine the crop type change result of each pixel, obtain the allocated area of ​​each crop type according to the crop type change result, and complete the iteration of the current round;

[0040] The iteration module is used to execute the next round of iterations and end the task when the allocated area is equal to the required area.

[0041] On the one hand, an embodiment of the present application further provides a computer device, including a memory and a processor, the memory storing a computer program, and a computer-readable storage medium storing the computer program, wherein the computer program is configured to execute the steps of the above method when running.

[0042] On the other hand, an embodiment of the present invention further provides a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0043] One of the above technical solutions has the following advantages and beneficial effects:

[0044] The above method uses the random forest algorithm to train and estimate the development suitability of different crop types, introduces neighborhood effects and land productivity constraints to simulate the interaction between crops, and uses a roulette wheel selection mechanism to characterize the uncertainty in crop type transitions, which is used to quickly and accurately simulate the spatial pattern of crop planting in future scenarios. This application solves the problem that traditional survey methods are too subjective and have a huge workload, and remote sensing technology is difficult to simulate the spatial pattern of future crop planting structures, and promotes the refined expression of crop planting spatial patterns. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 is a schematic flow chart of a crop planting space layout method in one embodiment;

[0048] Figure 2 A schematic flow chart of the steps of determining the land productivity of a planting area in one embodiment;

[0049] Figure 3 It is a structural block diagram of a crop planting space layout device in one embodiment. DETAILED DESCRIPTION

[0050] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0052] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application and have no specific meaning. Therefore, "module" and "component" can be used interchangeably.

[0053] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the presence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof.

[0054] At present, the global demand for food is increasing, and the demand for land and water resources is growing accordingly. However, there is often a spatial mismatch between crop planting and resource and environmental endowments. For example, the North China Plain uses 21% of the country's arable land and 3.72% of the country's water resources to produce more than 24% of the country's food. Therefore, developing a method for simulating the spatial pattern of crop planting will not only help provide an effective solution for optimizing the spatial pattern of crop planting, but will also provide solutions for achieving the multi-dimensional synergistic goals of maximizing food production, reducing resource demand, and reducing environmental impact, and provide refined guidance for optimizing the spatial pattern of crop planting. At present, remote sensing technology is regarded as an effective method for extracting crop spatial distribution information, but it is difficult to simulate the spatial pattern of future crop planting structure. Traditional future land use models have good effects in land use simulation, but currently rarely involve the simulation expression of crop planting spatial pattern, and factors such as climate, soil and topography related to crop growth have not been taken into account. At the same time, due to the use of artificial neural networks (ANN), there is an overfitting problem.

[0055] The crop planting space layout method provided in this application can effectively solve the above problems.

[0056] In one embodiment, Figure 1 As shown, a crop planting space layout method is provided, comprising:

[0057] S110, determine the land productivity and required area of ​​the planting area;

[0058] Among them, the demand area refers to the total planting area of ​​various crops in the planting area, which can be determined based on the estimated output and market demand.

[0059] S120, simulate and obtain the crop suitability probability of each pixel in the planting area. This method has strong performance and can take into account the mutual influence between factors. It has good performance in crop planting spatial layout simulation, especially in large-scale simulation;

[0060] Specifically, the conditional random forest algorithm can be used for simulation. First, a stratified random sampling method is used to collect training samples from the base year crop planting structure data, and these samples are evenly distributed among various crops. 60% of the collected samples are used as training samples, 20% as validation samples, and 20% as test samples to train the random forest algorithm and verify the fitting accuracy. Then, a bootstrap sample set X is randomly selected from the original training set X with replacement using the Bootstrap method. i Finally, for each bootstrapped sample set X i , generate an unpruned decision tree: suppose there are M original variables in total, and a positive integer m is given, satisfying m<<M. At each internal node, randomly select m prediction variables from the M original variables as candidate variables for the split node, and select the best splitting method from the m candidate variables to split the node. In the process of generating the entire forest, m remains unchanged. Repeat the above steps until M decision trees are generated (M is large enough). When predicting data of unknown categories, the output category label is determined by the majority vote of the M trees, that is:

[0061]

[0062] In the formula, H(x) represents the combined classification model, h(·) represents the decision tree model, Y represents the output variable (target variable), I(·) is the indicative function, and argmax Y Denotes that ∑I(h(X,Θ k )=Y) takes the maximum value.

[0063] Use the random forest method above to obtain suitability probabilities When classifying, random forests decide the prediction category based on the voting results of multiple decision trees. In addition, since randomness is introduced to the original training set X and the original spatial variables in the process of training and generating random forests, the classification results of each decision tree are not completely consistent in many cases. For the same pixel, some decision trees may be transformed into other crop types, while others may not be transformed into other crop types. The suitability probability S of crop q in each pixel i is i q It is expressed as:

[0064]

[0065] In the formula, h m(i) represents the estimation result of a single decision tree m for pixel i; M represents the number of decision trees.

[0066] The step of S120 can also be replaced by the GBDT algorithm (gradient boosting decision tree). The random forest and GBDT algorithms are two generally recognized effective crop planting space classification methods. The random forest algorithm is a typical representative of the bagging ensemble strategy, and the GBDT algorithm is a more common method in the boosting ensemble strategy. The random forest algorithm improves performance by reducing model variance, and the GBDT algorithm improves performance by reducing model bias. The GBDT algorithm has higher accuracy than the random forest algorithm, but is more sensitive to outliers.

[0067] Specifically, the GBDT algorithm is used to generate local correlation graphs to illustrate the potential nonlinear relationship between crop suitability and crop planting spatial layout. The approximate function f(x) of a set of independent variables can be expressed as the basis function g(x; a n ) is the addition expansion:

[0068]

[0069] Where N is the number of decision trees, a n is a decision tree g(x; a n )’s segmentation position and leaf node average value, ω n is the weight estimated by minimizing the loss function. The iterative steps to optimize this loss function are as follows:

[0070] First, define the initial function:

[0071]

[0072] In each iteration, the negative gradient function r in as follows:

[0073]

[0074] According to the above formula r in To set g(x; a n ), and thus the optimal gradient is calculated:

[0075]

[0076] Based on the above function equation, add the learning rate μ (0<μ<1) for update:

[0077] f n (x) = f n-1 (x)+μω n g(x;an )

[0078] The GBDT algorithm can identify the relative importance of predictors. By summing up all decision trees T, the square importance of predictors can be obtained:

[0079]

[0080] Predictor variables x = {x1, x2, …, x p} is divided into two parts, including the interest set z to be explained S and other predictor variables z c =x\z S For z S , further estimate f s Some of its dependencies:

[0081]

[0082] When the root mean square error reaches the minimum, the final model of suitability probability of each crop type is obtained, and the suitability probability of the crop is obtained.

[0083] 3. Assessment of the neighborhood effect of crop planting

[0084] S130, obtaining the neighborhood effect value of each pixel;

[0085] The neighborhood effect value indicates the influence of neighboring plots around a plot on the selection of the crop type to be planted. Specifically, the neighborhood effect value of each pixel can be obtained by any means in the art.

[0086] S140, determining the limiting factor constraints; wherein the limiting factor constraints are determined by land productivity, food production demand and crop growth factor constraints;

[0087] Among them, the crop growth factor restrictions are the restrictions on irrigation water and fertilizer. Specifically, in the actual development process of crop planting space, due to the constraints of land productivity, the crop planting space is not changed in a disorderly manner. Therefore, the restriction factor is introduced to constrain this constraint condition, and then the crop planting space layout is constrained not to exceed the local land productivity limit of this type of crop, while being able to meet the food production and residents' nutritional needs. Since the assessment of land productivity takes into account natural, social and economic factors including production period, thermal zone zoning, soil properties, land resource stock and input level, the restriction factor can be expressed as:

[0088] C=con(L=Crop e )

[0089] Where C represents the limiting factor of pixel i; con is the objective function, which means that the pixel takes the value of 1 when it meets the conversion conditions such as production period, thermal zone division, soil properties, land resource stock and input level, and takes the value of 0 otherwise; Crop e Indicates crop category e.

[0090] S150, determining the combined probability of pixel transformation into a specific crop type based on the crop suitability probability, the neighborhood effect value, and the limiting factor constraints;

[0091] The combined probability of a pixel transforming into a specific crop type is the comprehensive probability of growing a specific crop type in the pixel.

[0092] Specifically, the combination probability is obtained based on the following formula:

[0093]

[0094] in, is the combined probability; is the suitability probability of the crop; is the neighborhood effect value; C is the limiting factor constraint.

[0095] S160, performing roulette selection according to the combined probability, determining the crop type change result of each pixel, and obtaining the allocated area of ​​each crop type according to the crop type change result and completing the current round of iteration;

[0096] Specifically, a roulette wheel selection mechanism is introduced, and the dominant crop type with the highest combination probability is more likely to be converted, but the remaining types with relatively low combination probabilities still have the opportunity to be assigned to the current pixel. The core of the roulette wheel selection mechanism is adaptive inertia (inertia coefficient), that is, the inertia coefficient of each type of crop is determined by the difference between the existing quantity and demand, and is adaptively adjusted during the iteration process, so that the quantity of each crop type develops towards the predetermined target. If the macro demand of a certain crop type is inconsistent with the development trend, the inertia coefficient will increase the inheritance of the type so that the utilization trajectory of the crop can be corrected in the next iteration to promote the mutual conversion of other crop types to this type, narrow the gap between the quantity of the crop type and the predetermined target, and ultimately meet the various crop needs of macro development to the greatest extent. The formula is:

[0097]

[0098] In the formula, represents the inertia coefficient of crop type q at time t; and They represent the difference between the macro demand and allocation of crop type q at time t-1 and time t-2 respectively. The inertia coefficient is determined by the crop type currently occupying the grid. In each grid, if it is not currently occupied by the demand crop type, the inertia coefficient of the crop will be set to 1, and it will not affect the overall combination probability of the crop in the grid unit.

[0099] According to the above probability coefficient equation, the adaptive inertia coefficient is defined into three cases: when the development trend of the target crop type meets the macro demand and the gap between the two is narrowing, the inertia coefficient does not change; when the development trend of the crop type is in conflict with the macro demand, if the macro demand is less than the current supply, the inertia coefficient is reduced; if the current supply does not meet the macro demand, the inertia coefficient is increased.

[0100] According to the roulette wheel selection mechanism, the crop type change results of each pixel can be confirmed, and finally the crop type of each pixel can be confirmed and the allocated area of ​​each crop type can be counted.

[0101] S170, executing the next round of iterations, and ending the task when the allocated area is equal to the required area.

[0102] This application uses a random forest algorithm to train and estimate the development suitability of different crop types, introduces neighborhood effects and land productivity constraints to simulate the interaction between crops, and uses a roulette wheel selection mechanism to characterize the uncertainty in crop type transitions, which is used to quickly and accurately simulate the spatial pattern of crop planting in future scenarios. This application solves the problem that traditional survey methods are too subjective and have a huge workload, and remote sensing technology is difficult to simulate the spatial pattern of future crop planting structures, and promotes the refined expression of crop planting spatial patterns.

[0103] In one embodiment, the step of obtaining the neighborhood effect value of each pixel includes:

[0104] Based on the clustering of crops of the same type, the neighborhood effect value of pixels converted into specific crop types is obtained.

[0105] Specifically, in the step of converting pixels into neighborhood effect values ​​of specific crop types based on the aggregation of crops of the same type, the neighborhood effect value is obtained based on the following formula:

[0106]

[0107] Where L is the planting type of pixel i, n is the radius of the field; Con is the objective function, whose value is 1 when L = q, otherwise it is 0.

[0108] In one embodiment, the step of obtaining the neighborhood effect value of each pixel includes:

[0109] Obtain resource requirements of various types of crops, and confirm the competitive effect value based on the resource requirements;

[0110] The symbiotic effect value is obtained, and the neighborhood effect value is obtained based on the competition effect value and the symbiotic effect value.

[0111] Specifically, the resource demand is the demand for resources (such as water, light, and nutrition) of each type of crop during the growth cycle. The crop type with the highest probability of crop suitability is selected and confirmed as the current crop type. Then, the geographical location data (such as longitude and latitude, raster data, etc.) of each currently planted crop type is obtained, and clustering algorithms such as DBSCAN and K-means are applied to identify the spatial clustering areas of different crop types. The neighborhood is defined based on the clustering area, and then the competition and symbiotic relationships are calculated. The demand for resources by different crops will lead to competition. It can be quantified using a competition index (such as C-score). There may be a mutually beneficial relationship between some crops, such as the relationship between nitrogen-fixing plants and other crops. It can be determined through ecological literature or experimental data. For each pair of neighboring crops, the competitive effect value is calculated. For example, if crops A and B are both high-demand crops, the competitive effect between them will be higher, and the competitive effect value can be taken from 0 to 0.5. For crop pairs with a symbiotic relationship, the symbiotic effect value is calculated, and the interval can be taken from 0 to 0.5. Total neighborhood effect value: NE = Σ(competition effect value) + Σ(symbiotic effect value) where NE is the neighborhood effect value and Σ represents the sum of all related crop pairs in the neighborhood. Furthermore, the symbiotic effect value and the competition effect value can also be preset, that is, the competition effect value and the symbiotic effect value of the two crops are preset. The stronger the competition effect between the two crops, the smaller its value, and the stronger the symbiotic effect between the two crops, the larger its value.

[0112] In one embodiment, if Figure 2 As shown, the steps to determine the land productivity of a planted area include:

[0113] S210, obtaining growth period parameters, heat zone zoning parameters, soil property parameters, land resource stock parameters and input level values ​​of the planting area;

[0114] S220, obtain the photosynthetic production potential according to the growth period parameters and land resource stock parameters;

[0115] Among them, the growth period parameters refer to various parameters of crops during the period from sowing to maturity; the land resource stock parameters can be the area coefficient; specifically, the photosynthetic production potential is obtained by the following formula:

[0116] Y1=Cf(Q)=KΩεφ(1-α)(1-β)(1-ρ)(1-γ)(1-ω)·(1-d)sf(L)(1-η) -1 (1-δ)- 1 q -1 ∑Q j

[0117] In the formula, Y1 is the photosynthetic production potential; C is the unit conversion coefficient; K is the area coefficient; ∑Q j is the total solar radiation during the crop growth period; Ω is the efficiency of crops in utilizing light intensity; ε is the proportion of photosynthetically active radiation to total radiation; φ is the light quantum conversion efficiency; α is the reflectivity of the plant population; β is the transmittance of the lush plant population; ρ is the proportion of radiation intercepted by the non-photosynthetic organs of the crop; γ is the proportion of light exceeding the light saturation point; ω is the proportion of respiratory consumption to photosynthetic products; d is the crop stem and leaf abscission rate; s is the crop economic coefficient; f(L) is the corrected value of the dynamic change of crop leaf area; η is the moisture content of mature grains; δ is the ash content; q is the caloric content per unit dry matter.

[0118] S230, obtaining the photosynthetic production potential according to the photosynthetic production potential and the heat zone zoning parameters;

[0119] Specifically, the heat zone zoning parameter is the temperature correction function of crop photosynthesis; the light and temperature production potential is obtained by the following formula:

[0120] Y2=f(T)·Y1

[0121] Where Y2 is the light-temperature production potential; f(T) is the temperature correction function of crop photosynthesis.

[0122] S240, based on the light-temperature production potential and water use parameters, obtain the climate production potential;

[0123] Specifically, the water use parameter is a moisture correction function; the climate production potential is further corrected for moisture based on the light and temperature production potential, taking into account not only the natural precipitation but also the economic input irrigation water. Specifically:

[0124] Y w =Y1·f(W)(1-I r )+Y2·I r

[0125] In the formula, I r is the irrigation coefficient; Y2 is the light and temperature production potential; Y w is the climate production potential; F(W) is the moisture correction function.

[0126] S250, confirming the land production potential based on climate production potential and soil property parameters;

[0127] Specifically, the soil property parameter is the soil effectiveness coefficient, and the land production potential is obtained by the following formula:

[0128] YL =f(s)·Y w

[0129] Where Y L is the land production potential; f(s) is the soil effectiveness coefficient.

[0130] S260, confirm land productivity based on land production potential and input level values.

[0131] Specifically, the input level value is the total socio-economic input. The land productivity of each pixel is calculated through multi-objective analysis.

[0132] Y=f(I0,Y L )

[0133] In the formula, Y is land productivity; I0 is the total socio-economic input, satisfying the benefit maximization condition:

[0134]

[0135] Where Pe is the expected price.

[0136] In one embodiment, Figure 3 As shown, an embodiment of the present invention further provides a crop planting space layout device, comprising:

[0137] Determination module to determine land productivity and required area in the planting area;

[0138] The crop suitability probability acquisition module is used to simulate and obtain the crop suitability probability of each pixel in the planting area;

[0139] A neighborhood effect value acquisition module is used to obtain the neighborhood effect value of each pixel;

[0140] A constraint module is used to determine the limiting factor constraints; wherein the limiting factor constraints are determined by land productivity, food production requirements and crop growth factor constraints;

[0141] A combined probability acquisition module is used to determine the combined probability of a pixel being transformed into a specific crop type based on the crop suitability probability, the neighborhood effect value, and the constraint of the limiting factor;

[0142] A roulette wheel selection module is used to perform roulette wheel selection according to the combination probability, determine the crop type change result of each pixel, obtain the allocated area of ​​each crop type according to the crop type change result, and complete the iteration of the current round;

[0143] The iteration module is used to execute the next round of iterations and end the task when the allocated area is equal to the required area.

[0144] For the specific limitations of the crop planting space layout device, please refer to the limitations of the crop planting space layout method above, which will not be repeated here. Each module in the above-mentioned crop planting space layout device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0145] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0146] Determine land productivity and area required in the planting area;

[0147] The crop suitability probability of each pixel in the planting area is obtained through simulation;

[0148] Get the neighborhood effect value of each pixel;

[0149] Determine the limiting factor constraints; where the limiting factor constraints are determined by the characteristics of land planting potential, food production requirements and crop growth factor restrictions;

[0150] Determine the combined probability of pixel transformation to a specific crop type based on crop suitability probability, neighborhood effect value, and limiting factor constraints;

[0151] Roulette selection is performed according to the combined probability to determine the crop type change result of each pixel, and the allocated area of ​​each crop type is obtained according to the crop type change result and the current round of iteration is completed;

[0152] Execute the next round of iterations and end the task when the allocated area is equal to the required area.

[0153] In one embodiment, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented.

[0154] Determine land productivity and area required in the planting area;

[0155] The crop suitability probability of each pixel in the planting area is obtained through simulation;

[0156] Get the neighborhood effect value of each pixel;

[0157] Determine the limiting factor constraints; where the limiting factor constraints are determined by the characteristics of land planting potential, food production requirements and crop growth factor restrictions;

[0158] Determine the combined probability of pixel transformation to a specific crop type based on crop suitability probability, neighborhood effect value, and limiting factor constraints;

[0159] Roulette selection is performed according to the combined probability to determine the crop type change result of each pixel, and the allocated area of ​​each crop type is obtained according to the crop type change result and the current round of iteration is completed;

[0160] Execute the next round of iterations and end the task when the allocated area is equal to the required area.

[0161] When the embodiments of the present application are specifically implemented, reference may be made to the above-mentioned embodiments, which have corresponding technical effects.

[0162] It is understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in the present application, or a combination thereof.

[0163] For software implementation, the technology described herein can be implemented by a unit that performs the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or outside the processor.

[0164] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0165] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0166] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0167] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0169] If the function 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 such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk. It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0170] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A crop planting space layout method, characterized in that: include: Determine land productivity and area required in the planting area; Simulating and obtaining the crop suitability probability of each pixel in the planting area; Obtaining the neighborhood effect value of each pixel; Determining limiting factor constraints; wherein the limiting factor constraints are confirmed by the land productivity, food production requirements and crop growth factor constraints; Determining a combined probability of a pixel being transformed into a specific crop type based on the crop suitability probability, the neighborhood effect value, and the limiting factor constraint; Performing roulette selection according to the combined probability, determining the crop type change result of each pixel, and obtaining the allocated area of ​​each crop type according to the crop type change result and completing the current round of iteration; The next round of iterations is performed, and the task is terminated when the allocated area is equal to the required area.

2. The crop planting space layout method according to claim 1, characterized in that: The step of obtaining the neighborhood effect value of each pixel comprises: Based on the clustering of crops of the same type, the neighborhood effect value of pixels converted into specific crop types is obtained.

3. The crop planting space layout method according to claim 2, characterized in that: In the step of converting pixels into neighborhood effect values ​​of specific crop types based on the aggregation of crops of the same type, the neighborhood effect value is obtained based on the following formula: Where L is the planting type of pixel i, n is the radius of the field; Con is the objective function, whose value is 1 when L = q, otherwise it is 0.

4. The crop planting space layout method according to claim 1, characterized in that: The step of obtaining the neighborhood effect value of each pixel comprises: Obtaining resource requirements of various types of crops, and determining competition effect values ​​according to the resource requirements; A symbiotic effect value is obtained, and the neighborhood effect value is obtained based on the competition effect value and the symbiotic effect value.

5. The crop planting space layout method according to claim 1, characterized in that: The steps to determine land productivity in a cropping area include: Obtain growth period parameters, thermal zone zoning parameters, soil property parameters, land resource stock parameters and input level values ​​of the planting area; Obtaining the photosynthetic production potential according to the growth period parameter and the land resource stock parameter; According to the photosynthetic production potential and the thermal zone zoning parameters, the light and temperature production potential is obtained; According to the light and temperature production potential and water use parameters, the climate production potential is obtained; Determining the land production potential according to the climate production potential and the soil property parameters; The land productivity is determined based on the land production potential and the input level value.

6. The crop planting space layout method according to claim 1, characterized in that: The limiting factor is determined according to the following formula: C=con(L=Crop e ) Where C represents the limiting factor of pixel i; L is the planting type of pixel i; con is the objective function, which means that the pixel takes the value of 1 when it meets the conversion conditions such as production period, thermal zone division, soil properties, land resource stock and input level, and takes the value of 0 otherwise; Crop e Indicates crop category e.

7. The crop planting space layout method according to claim 1, characterized in that: In the step of determining the combined probability of a pixel being transformed into a specific crop type according to the crop suitability probability, the neighborhood effect value and the limiting factor constraint, the combined probability is obtained based on the following formula: in, is the combined probability; is the suitability probability of the crop; is the neighborhood effect value; C is the limiting factor constraint.

8. A crop planting space layout device, characterized in that: include: Determination module to determine land productivity and required area in the planting area; A crop suitability probability acquisition module, used to simulate and obtain the crop suitability probability of each pixel in the planting area using a conditional random forest algorithm; A neighborhood effect value acquisition module, used to acquire the neighborhood effect value of each pixel; A constraint module, used for determining limiting factor constraints; wherein the limiting factor constraints are confirmed by the land productivity, food production demand and crop growth factor constraints; A combined probability acquisition module, used for determining the combined probability of a pixel being transformed into a specific crop type according to the crop suitability probability, the neighborhood effect value and the limiting factor constraint; A roulette wheel selection module, configured to perform roulette wheel selection according to the combined probability, determine the crop type change result of each pixel, obtain the allocated area of ​​each crop type according to the crop type change result and complete the current round of iteration; The iteration module is used to execute the next round of iteration and end the task when the allocated area is equal to the required area.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the steps of the method according to any one of claims 1 to 7 when executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images