Plant variety zoning and yield prediction method, system, equipment, medium and product

Abstract

The invention discloses a plant variety zoning and yield prediction method, system and device, a medium and a product, and relates to the field of plant variety distribution analysis, and the method comprises the steps: obtaining ecological factor data of a research region and point location data of existing distribution points of a target plant variety based on literature mining; the ecological factor data comprises a contemporary climate variable, a future climate variable, a soil variable and a terrain factor variable; the point location data comprises distribution point data and yield data; according to the ecological factor data of the research area and the point location data of the existing distribution points of the target plant variety, determining suitable growth area distribution of the target plant variety in the research area by adopting a maximum entropy model; and predicting the yield of the target plant variety in the research area by adopting a machine learning model according to the future climate variable and the soil variable of the research area. The method for predicting the suitable growth area and the yield of the target plant variety is established, and the precision is improved.

Description

Technical Field

[0001] The present application relates to the field of plant variety distribution analysis, and particularly to a method, system, device, medium and product for plant variety zoning and yield prediction based on data driving. Background Art

[0002] Climate change significantly affects the geographical distribution of plant species. The relationship between the geographical distribution pattern of plant varieties and climate change has always been one of the research hotspots in global climate change and plant variety geography. Under the background of global warming, global terrestrial monsoon precipitation may increase, especially in the northern hemisphere monsoon region, which will change the composition, structure and function of ecosystems, resulting in weakened vegetation adaptability. In addition, environmental changes have also changed species dynamics and interactions, leading to rapid changes in biodiversity at different spatial scales. However, frequent occurrence of extreme weather caused by global climate change poses a serious threat to global food security. Therefore, it is necessary to accurately predict the suitable growing areas and yields of plant varieties in different regions to improve the yields of plant varieties. Summary of the Invention

[0003] The purpose of the present application is to provide a method, system, device, medium and product for plant variety zoning and yield prediction, which can accurately predict the suitable growing areas and yields of target plant varieties in different research regions.

[0004] To achieve the above purpose, the present application provides the following solutions:

[0005] In the first aspect, the present application provides a method for plant variety zoning and yield prediction, including:

[0006] Obtaining ecological factor data of a research region and location data of existing distribution points of a target plant variety; the ecological factor data includes contemporary climate variables, future climate variables, soil variables and topographic factor variables; the location data includes distribution point data and yield data;

[0007] Determining the distribution of suitable growing areas of the target plant variety in the research region by using the maximum entropy model according to the ecological factor data of the research region and the location data of existing distribution points of the target plant variety;

[0008] Predicting the yield of the target plant variety in the research region by using a machine learning model according to the future climate variables and soil variables of the research region; the machine learning model is obtained by pre-training with a training sample set, and each sample in the training sample set includes contemporary climate variables, soil variables and measured yields of existing distribution points of the target plant variety.

[0009] In the second aspect, the present application provides a system for plant variety zoning and yield prediction, including:

[0010] A data acquisition module for acquiring ecological factor data of the study area and location data of existing distribution points of the target plant variety; the ecological factor data includes contemporary climate variables, future climate variables, soil variables, and topographic factor variables; the location data includes distribution point data and yield data;

[0011] A suitable habitat determination module for determining the suitable habitat distribution of the target plant variety in the study area by using the maximum entropy model according to the ecological factor data of the study area and the location data of existing distribution points of the target plant variety;

[0012] A yield prediction module for predicting the yield of the target plant variety in the study area by using a machine learning model according to the future climate variables and soil variables of the study area; the machine learning model is obtained by pre-training with a training sample set, and each sample in the training sample set includes contemporary climate variables, soil variables, and measured yield of existing distribution points of the target plant variety.

[0013] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the above-mentioned plant variety zoning and yield prediction method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the above-mentioned plant variety zoning and yield prediction method.

[0015] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above-mentioned plant variety zoning and yield prediction method.

[0016] According to the specific embodiments provided by the present application, the present application has the following technical effects:

[0017] The present application provides a plant variety zoning and yield prediction method, system, device, medium, and product. By using the maximum entropy model according to contemporary climate variables and future climate variables, the suitable habitat distribution of the target plant variety in the study area is determined, taking into account the simulation analysis of the suitable habitat of the target plant variety under contemporary climate and future climate change scenarios, improving the prediction accuracy of the suitable habitat of the target plant variety. Further, a machine learning model is used to predict the yield of the target plant variety under future climate change scenarios, improving the accuracy of yield prediction. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0019] Figure 1 It is an application environment diagram of a method for plant variety zoning and yield prediction in an embodiment of the present application;

[0020] Figure 2 It is a schematic flowchart of a method for plant variety zoning and yield prediction provided in an embodiment of the present application;

[0021] Figure 3 It is a schematic diagram of the process of yield prediction in an embodiment of the present application;

[0022] Figure 4 It is a schematic diagram of the process of zoning and yield prediction for alfalfa in an embodiment of the present application;

[0023] Figure 5 It is a schematic diagram of the functional modules of a plant variety zoning and yield prediction system provided in an embodiment of the present application;

[0024] Figure 6 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. Detailed implementation manners

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0026] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0027] The method for plant variety zoning and yield prediction provided in the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, or it can be integrated on the server 104, or it can be placed on the cloud or other servers. The terminal 102 can send the ecological factor data of the study area and the point data of the existing distribution points of the target plant variety to the server 104. The server 104 determines the distribution of suitable areas and predicted yields of the target plant varieties in the study area based on the received ecological factor data of the study area and the point data of the existing distribution points of the target plant varieties. The server 104 can feedback the distribution of suitable areas and predicted yields of the target plant varieties in the study area to the terminal 102. In addition, in some embodiments, the plant variety zoning and yield prediction method can also be implemented by the server 104 or the terminal 102 alone.

[0028] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0029] In an exemplary embodiment, Figure 2 As shown, a method for plant variety zoning and yield prediction is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 203.

[0030] Step 201, obtain ecological factor data of the research area and point data of existing distribution points of the target plant species. In a specific application example, the target plant species is alfalfa and the research area is China.

[0031] The ecological factor data include contemporary climate variables, future climate variables, soil variables and terrain factor variables.

[0032] This application involves 52 ecological factor data. First, multiple bioclimatic factors, multiple soil factors and digital elevation models of the study area are obtained. Then, correlation analysis is performed on each bioclimatic factor and each soil factor in the study area, and bioclimatic factors and soil factors with correlation coefficients less than the set correlation threshold are eliminated to obtain contemporary climate variables, future climate variables and soil variables in the study area. The terrain factor variables of the study area are determined based on the digital elevation model.

[0033] Among them, bioclimatic factors are downloaded from the World Climate Database, including climate, precipitation, temperature variables, etc., with a spatial resolution of 30s, including data from 1970 to 2000, 2021 to 2040, 2041 to 2060, 2061 to 2080, and 2081 to 2100. Among them, future climate is obtained through climate prediction experiments. In the climate prediction experiments, 4 shared socioeconomic pathways are considered (sustainable development pathway SSP1-2.6, intermediate development pathway SSP2-4.5, regional competition pathway SSP3-7.0, fossil fuel development pathway SSP5-8.5).

[0034] Soil factors are downloaded from the Food and Agriculture Organization of the United Nations, divided into topsoil and deep soil, and the data are all in the ".tiff" format to ensure the spatial continuity of the data.

[0035] A digital elevation model with a resolution of 1 km is downloaded from the Geospatial Data Cloud platform. Through limited terrain elevation data, digital simulation of the ground terrain is realized (i.e., digital expression of the terrain surface form). The digital elevation model is a solid ground model that represents the ground elevation in the form of an ordered numerical array. The slope, aspect, and elevation are extracted using the spatial analysis tools of ArcGIS. In this application, when the projection coordinate system is "World Geodetic System-1984 CoordinateSystem (WGS1984)", the above variables are all extracted to China and converted into ASCII files according to the default processing range and pixel size.

[0036] Furthermore, Pearson correlation analysis is performed on bioclimatic factors and soil factors using ArcMap 10.8. When the absolute value of the correlation coefficient between two variables is less than 0.80, the relevant variables are retained. When the absolute value of the correlation coefficient between two variables is greater than 0.80, the variable with a smaller contribution rate is excluded. The correlation between factors is visualized through RStudio. Finally, 8 contemporary climate variables, 5 future climate variables, 14 soil variables, and 3 terrain factor variables are retained.

[0037] As shown in Table 1, contemporary climate variables include: annual average temperature, daily temperature range of annual average temperature, isothermality, average temperature in the wettest season, precipitation in the wettest month, precipitation in the driest month, coefficient of seasonal variability of precipitation, and precipitation in the wettest season. Future climate variables include: annual average temperature, standard deviation of seasonal change in temperature, annual temperature range, precipitation in the wettest month, and precipitation in the driest month. Soil variables include: clay content in topsoil, reference bulk density of topsoil, gravel content in topsoil, calcium carbonate content in topsoil, base saturation of topsoil, total exchangeable base in subsoil, pH value of subsoil, organic carbon content in subsoil, gravel content in sub-bottom soil, salinity of subsoil, clay proportion in subsoil, cation exchange capacity of subsoil, cation exchange capacity of clay fraction in subsoil, and base saturation of subsoil. Topographic factor variables include: aspect, slope, and elevation.

[0038] The point data described above includes conducting an advanced search on CNKI with the name of the target plant variety as the keyword and full text, collecting the field trial data of the target plant variety in the target literature, and determining the distribution point data and yield data of the target plant variety, mainly including the name of the target plant variety, longitude and latitude of the test site, climate type, altitude, cultivation time, annual average temperature, annual average precipitation, annual average sunshine hours, soil type, soil organic matter content, soil pH value, soil water content, alfalfa phenotypic traits and nutritional indicators, annual yield (recorded from the second year), etc.

[0039] Table 1 List of ecological factor data

[0040]

[0041]

[0042] Step 202: According to the ecological factor data of the research area and the point data of the existing distribution points of the target plant variety, use the maximum entropy model to determine the suitable habitat distribution of the target plant variety in the research area.

[0043] In an exemplary embodiment, the maximum entropy model is used to analyze the areas in the research area that are similar to the existing distribution points of the target plant variety to determine the suitable habitat. The operation results of the maximum entropy model include response curves, variable contribution degrees, ROC curves (mainly expressing the prediction accuracy of the maximum entropy model), and prediction result distribution maps (***_avg.asc).

[0044] The prediction performance of the MaxEnt model is affected by the selection of two parameters: the Regularization Multiplier (RM) value and the Feature Combination (FC). The magnitude of the RM value affects the concentration degree of the output distribution. As the RM value increases, the applicable range of the MaxEnt model also expands; conversely, when the RM value is small, the output distribution will be more concentrated, which is more suitable for specific distribution records, but it will also increase the risk of overfitting, making it difficult for the MaxEnt model to cope with changes in the new environment. Therefore, this situation is not applicable to the prediction of distribution changes under environmental changes. FC is generated from climate variable layers and affects the calculation of probability distributions. The available feature types include Linear features (L), Quadratic features (Q), Product features (P), Threshold features (T), and Hinge features (H).

[0045] In this application, 31 feature combinations ("L", "Q", "P", "T", "H", "LQ", "LP", "LT", "LH", "QP", "QT", "QH", "PT", "HP", "HT", "LQP", "LQT", "LQH", "LPT", "LHP", "LHT", "QPT", "QHP", "QHT", "HPT", "LQPT", "LQHP", "LQHT", "LHPT", "QHPT", "LQHPT") were set using RStudio to conduct MaxEnt model tests. Eight RM values were set, ranging from 0.5 to 4.0 with an interval of 0.5. Finally, the MaxEnt model with the smallest delta.AICc value was selected. That is, when the point data > 50, the MaxEnt model selects FC = T and RM = 3.0; when the point data < 50, the MaxEnt model selects FC = LPT and RM = 2.5.

[0046] In an exemplary embodiment, the maximum entropy model is optimized based on the R language. In the MaxEnt interface, browse and select the point data of the existing distribution points of the target plant variety and the ecological factor data of the research area respectively. To reduce the uncertainty of the maximum entropy model, each sample with point data > 50 is repeated 10 times, and each sample with point data < 50 is repeated 20 times. The repeated operation type is Bootstrap, and the random test percentages of the training set and the test set are 80% and 20% respectively, and the results are averaged. The output format is set to Logistic, and the output file type is.asc to allow ArcGIS to recognize the predicted layer file. A Jackknife experiment is performed on all environmental variables to analyze and evaluate the contribution degree of the environmental variables, determine the main environmental factors affecting the distribution of the target plant variety, that is, determine the robust variables, to create a response curve. Among them, each sample represents a variety of the target plant variety.

[0047] In a specific application example, step 202 includes the following steps 21 to 24.

[0048] Step 21, according to the contemporary climate variables, soil variables, topographic factor variables of the research area and the point data of the existing distribution points of the target plant variety, use the maximum entropy model to determine the contemporary suitability habitat index at each location in the research area.

[0049] Step 22, according to the contemporary suitability habitat index, draw a contemporary suitable habitat distribution map of the target plant variety in the research area to determine the contemporary suitable habitat distribution of the target plant variety in the research area.

[0050] Step 23, according to the future climate variables, soil variables, topographic factor variables of the research area and the point data of the existing distribution points of the target plant variety, use the maximum entropy model to determine the future suitability habitat index at each location in the research area.

[0051] The.asc file output by the maximum entropy model can be opened in ArcGIS to determine the contemporary suitability habitat index and the future suitability habitat index at each location in the research area. Among them, the value ranges of the contemporary suitability habitat index and the future suitability habitat index are 0 to 1. The closer to 0, the less suitable the target plant variety is to survive here, and the closer to 1, the more suitable the target plant variety is to survive here.

[0052] Step 24, according to the future suitability habitat index, draw a future suitable habitat distribution map of the target plant variety in the research area to determine the future suitable habitat distribution of the target plant variety in the research area.

[0053] This application further uses the ArcGIS 10.8 reclassification tool to visualize the suitable area distribution map graphically.

[0054] To more intuitively display the suitable area area and distribution characteristics, this application further manually divides the suitable area of the target plant variety in the research area into high-suitability areas, medium-suitability areas, low-suitability areas, and non-suitable areas according to the contemporary suitability habitat index or future adaptability habitat index at each location in the research area.

[0055] Among them, the suitability habitat index (including the contemporary suitability habitat index and the future suitability habitat index) is within 0.60 - 1 for the high-suitability area, within 0.40 - 0.60 for the medium-suitability area, within 0.20 - 0.40 for the low-suitability area, and within 0.00 - 0.20 for the non-suitability area.

[0056] Step 203, according to the future climate variables and soil variables of the research area, use a machine learning model to predict the yield of the target plant variety in the research area.

[0057] The machine learning model is pre-trained using a training sample set, and each sample in the training sample set includes the contemporary climate variables, soil variables, and measured yield of the existing distribution points of the target plant variety.

[0058] In a specific application example, the machine learning model is a random forest model.

[0059] This application uses the forest-based classification and regression tool in ArcGIS Pro and PyCharm software to predict the yield of the target plant variety in the research area. As Figure 3 shown, use the contemporary climate variables, soil variables, and measured yield, use the forest-based classification and regression tool for training, and select the result with a validation data P value less than 0.1 as the training result. The training result includes the highest variable and its importance.

[0060] In actual use, use the future climate variables, soil variables, and random seed number as the prediction basis for yield prediction to obtain the yield prediction result of the target plant variety under future climate change. Among them, the random seed number is a small variable when using the forest-based classification and regression tool, and the validation P values are different for different seed numbers, so select the random seed number corresponding to the result with a P value less than 0.1 during training for prediction.

[0061] Due to the limited conditions for obtaining soil factors, there are null values for some soil variables in the study area obtained in this application. After default generating graphical results with data, they are all redrawn using RStudio to generate graphs without data results, and redrawn using the image digitization tool in Origin 2022.

[0062] Based on collecting and extracting information related to target plant varieties scattered in the literature, this application establishes a target plant variety database to provide a basis for the simulation analysis and zoning of target plant varieties. Technologies such as geographic remote sensing, CMIP6, and the maximum entropy model are applied to the simulation of the suitable growth areas of target plant varieties. At the same time, the simulation analysis of the suitable growth areas of target plant varieties under contemporary climate and future climate change scenarios is taken into account: taking the time span as a variable and the growth suitability evaluation of each target plant variety at different growth stages as the dependent variable, considering the changes in geographical environmental factors, the distribution of the suitable growth areas of different target plant varieties is drawn. Finally, under the influence of future climate evolution and human activities, the distribution and changes of the suitable growth areas of different target plant varieties are predicted. Further, machine learning methods such as random forest are used to predict the yield changes of target plant varieties under future climate change scenarios, improving the prediction accuracy of the suitable growth areas and yields of target plant varieties.

[0063] This application also provides an application scenario that applies the above-mentioned plant variety zoning and yield prediction method. Specifically: The plant variety zoning and yield prediction method provided in this embodiment can be applied to the alfalfa zoning and yield prediction scenario within the scope of China.

[0064] Alfalfa, as a high-quality leguminous plant, is one of the forages with the widest planting area and the longest planting time in the world. Due to its rich nutritional value, high yield, good quality, and good adaptability, and having a deep root system, it can utilize the moisture in the deep soil, has strong drought resistance, its biological nitrogen fixation function can reduce the application of nitrogen fertilizer, has the characteristics of energy conservation and environmental protection, and is also the main source of vegetable protein feed and a high-quality and productive forage crop. Compared with annual crops, alfalfa grows vigorously in summer, has a developed root system, and has a high yield. It has made great contributions to improving the ecosystem, nutrition, and food security.

[0065] The planting areas of alfalfa are mainly in areas with relatively harsh environments such as high altitude, cold, and drought. Therefore, in the process of alfalfa cultivation, phenomena such as low overwintering rate and difficulty in turning green occur, resulting in a large area reduction in alfalfa yield and affecting the industrialization and large-scale development of alfalfa. Since the early 1990s, the phenomenon of rural hollowing has been widespread and serious. A large amount of land has low utilization efficiency and is idle, which is likely to cause the deterioration of land and the environment. A large amount of land is abandoned, resulting in a waste of land resources, but there is a large potential for improving production capacity.

[0066] This application uses the MaxEnt model and ArcGIS spatial analysis after optimizing parameters to simulate and predict the suitable area distribution of alfalfa under current and future climate scenarios, and clarifies the ecological factors and changes in suitable areas that affect the suitable area distribution of different alfalfa varieties. It has important practical significance for the rational development and utilization of marginal land, abandoned land, etc. Specifically, suitability evaluations and yield predictions are carried out for 27 alfalfa varieties. Based on the MaxEnt simulation, combined with ecological factors and future climate models, the future distribution of alfalfa is simulated and predicted, and the changes in the suitable growing areas of different alfalfa varieties are explored, laying a foundation for understanding the distribution pattern of different alfalfa varieties, rationally using existing grasslands and developing marginal land, and providing an important theoretical basis and scientific basis for the scientific cultivation of alfalfa.

[0067] As Figure 4 shown, in the alfalfa zoning and yield prediction scenario, 30 soil factors, bioclimatic factors, slope, aspect, and elevation of the study area are obtained, Pearson correlation analysis is performed on the bioclimatic factors and soil factors to obtain the eliminated climate variables and soil variables, and ecological factor data for the study area is generated. Using "alfalfa" as the keyword and full text for advanced search on CNKI (https: / / www.cnki.net / ), the alfalfa field trial data in the target literature is collected, the alfalfa distribution points and yield data are determined, and an alfalfa information Excel table is generated. Point data is formed through Geographic Information System (GIS) software to obtain Chinese alfalfa variety data. It mainly includes alfalfa variety names, longitude and latitude of the test sites, climate types, altitudes, cultivation times, annual average temperatures, annual average precipitation, annual average sunshine hours, soil types, soil organic matter content, soil pH value, soil water content, alfalfa phenotypic traits and nutritional indicators, annual yields (recorded starting from the second year), etc. Then, an ecological suitability evaluation index system is constructed based on the ecological factor data of the study area and Chinese alfalfa variety data, and the distribution of suitable planting areas for the main alfalfa varieties planted in China is determined in combination with the maximum entropy model. Based on Chinese alfalfa variety data, the Shared Socioeconomic Pathways (SSPs) model, and the maximum entropy model, the evolution of suitable planting areas for alfalfa under future climate change is determined. The yield of alfalfa varieties in highly suitable growing areas under future climate change is predicted based on the random forest model. This application can also expand and reduce the suitable distribution and highly suitable growing areas of each alfalfa variety. Furthermore, a decision support system is used for the priority recommendation and demonstration application of suitable varieties in different alfalfa planting areas.

[0068] This application takes the alfalfa variety data cultivated in China from 1980 to 2023 as the object, and uses models such as MaxEnt and CMIP6, combined with relevant software such as GIS, to mainly solve the following problems:

[0069] (1) Alfalfa variety data integration problem: Collect the field planting data in relevant alfalfa literature in CNKI from 1980 to 2023, and record and organize the corresponding alfalfa variety information, planting area geographical information, alfalfa yield information, etc.

[0070] (2) Solving the problem of suitable growth area zoning of alfalfa varieties at a large regional scale based on data and models: Use MaxEnt to analyze the collected alfalfa variety field data and climate data, simulate the distribution of suitable growth areas of the main alfalfa varieties planted in China, and the distribution and displacement of suitable growth areas under future climate scenario changes. It breaks through the limitation of promoting alfalfa varieties mainly based on traditional experience in the past.

[0071] (3) Problem of priority recommendation of regional varieties: In the main alfalfa planting areas in China, according to the suitable growth characteristics of different alfalfa varieties, combined with the climate and environmental characteristics of the suitable growth areas, form a dynamic recommendation list of suitable varieties in the main alfalfa planting areas in China.

[0072] Based on the same inventive concept, the embodiment of the present application also provides a plant variety zoning and yield prediction system for implementing the above-mentioned plant variety zoning and yield prediction method. The implementation solutions provided by this system to solve problems are similar to the implementation solutions recorded in the above method. Therefore, the specific limitations in one or more embodiments of the following plant variety zoning and yield prediction system can refer to the limitations on the plant variety zoning and yield prediction method in the above text, and will not be repeated here.

[0073] In an exemplary embodiment, as Figure 5 shown, a plant variety zoning and yield prediction system is provided, including: a data acquisition module 501, a suitable growth area determination module 502, and a yield prediction module 503.

[0074] The data acquisition module 501 is used to acquire the ecological factor data of the research area and the location data of the existing distribution points of the target plant variety. The ecological factor data includes contemporary climate variables, future climate variables, soil variables, and topographic factor variables. The location data includes distribution point data and yield data.

[0075] The suitable growth area determination module 502 is used to determine the distribution of the suitable growth area of the target plant variety in the research area by using the maximum entropy model according to the ecological factor data of the research area and the location data of the existing distribution points of the target plant variety.

[0076] The yield prediction module 503 is used to predict the yield of the target plant variety in the research area by using a machine learning model based on the future climate variables and soil variables in the research area. The machine learning model is pre-trained by using a training sample set, and each sample in the training sample set includes the contemporary climate variables, soil variables and measured yield of the existing distribution points of the target plant variety.

[0077] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the ecological factor data of the research area and the point data of the existing distribution points of the target plant variety. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for plant variety zoning and yield prediction.

[0078] Those skilled in the art can understand that Figure 6 the structure shown in

[0079] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0080] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, it implements the steps in the above method embodiments.

[0081] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, it implements the steps in the above method embodiments.

[0082] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0083] In this application, all actions of obtaining signals, information, or data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining authorization from the owner of the corresponding device.

[0084] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0085] The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0086] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0087] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for plant variety zoning and yield prediction, characterized in that: The plant variety zoning and yield prediction method comprises: Obtain ecological factor data of the study area and point data of existing distribution points of target plant species; the ecological factor data include contemporary climate variables, future climate variables, soil variables and terrain factor variables; the point data include distribution point data and yield data; According to the ecological factor data of the study area and the point data of the existing distribution points of the target plant species, the maximum entropy model is used to determine the distribution of the suitable areas for the target plant species in the study area; Based on the future climate variables and soil variables in the study area, a machine learning model is used to predict the yield of the target plant varieties in the study area; the machine learning model is pre-trained using a training sample set, and each sample in the training sample set includes the contemporary climate variables, soil variables and measured yields of the existing distribution points of the target plant varieties.

2. The plant variety zoning and yield prediction method according to claim 1, characterized in that: Obtain ecological factor data for the study area, including: Obtain multiple bioclimatic factors, multiple soil factors and digital elevation models of the study area; Conduct correlation analysis on each bioclimatic factor and each soil factor in the study area, eliminate bioclimatic factors and soil factors with correlation coefficients less than a set correlation threshold, and obtain contemporary climate variables, future climate variables and soil variables in the study area; The terrain factor variables of the study area are determined based on the digital elevation model.

3. The plant variety zoning and yield prediction method according to claim 1, characterized in that: The contemporary climate variables include: annual mean temperature, annual mean temperature diurnal range, isothermality, mean temperature of the wettest season, precipitation of the wettest month, precipitation of the driest month, seasonal variability coefficient of precipitation, and precipitation of the wettest season; The future climate variables include: annual mean temperature, standard deviation of temperature seasonal variation, annual temperature range, precipitation in the wettest month and precipitation in the driest month; The soil variables include: topsoil mud content, topsoil reference bulk density, topsoil gravel content, topsoil calcium carbonate content, topsoil base saturation, subsoil total exchangeable base, subsoil pH, subsoil organic carbon content, subsoil gravel content, subsoil salinity, subsoil clay percentage, subsoil cation exchange capacity, subsoil cation exchange capacity of clay fraction in subsoil and subsoil base saturation; The terrain factor variables include: slope aspect, slope gradient and elevation.

4. The plant variety zoning and yield prediction method according to claim 1, characterized in that: Based on the ecological factor data of the study area and the point data of the existing distribution points of the target plant species, the maximum entropy model is used to determine the distribution of the suitable areas for the target plant species in the study area, specifically including: According to the contemporary climate variables, soil variables, terrain factor variables and the point data of the existing distribution points of the target plant species in the study area, the maximum entropy model is used to determine the contemporary habitat suitability index at each location in the study area; Based on the contemporary habitat suitability index, a contemporary suitable habitat distribution map of the target plant species in the study area is drawn to determine the contemporary suitable habitat distribution of the target plant species in the study area; According to the future climate variables, soil variables, terrain factor variables and the point data of the existing distribution points of the target plant species in the study area, the maximum entropy model is used to determine the future suitability habitat index at each location in the study area; According to the future suitability habitat index, a future suitable habitat distribution map of the target plant species in the study area is drawn to determine the future suitable habitat distribution of the target plant species in the study area.

5. The plant variety zoning and yield prediction method according to claim 4, characterized in that: The plant variety zoning and yield prediction method also includes: According to the contemporary suitability habitat index or future adaptability habitat index at various locations in the study area, the suitable habitats of the target plant species in the study area are divided into high suitability areas, medium suitability areas, low suitability areas and non-suitability areas.

6. The plant variety zoning and yield prediction method according to claim 1, characterized in that: The machine learning model is a random forest model.

7. A plant variety zoning and yield prediction system, applied to the plant variety zoning and yield prediction method according to any one of claims 1 to 6, characterized in that: The plant variety zoning and yield prediction system comprises: A data acquisition module is used to acquire ecological factor data of the research area and point data of existing distribution points of target plant varieties; the ecological factor data include contemporary climate variables, future climate variables, soil variables and terrain factor variables; the point data include distribution point data and yield data; A suitable growth zone determination module is used to determine the distribution of suitable growth zones of target plant species in the study area using a maximum entropy model based on the ecological factor data of the study area and the point data of the existing distribution points of the target plant species; The yield prediction module is used to predict the yield of the target plant variety in the study area based on the future climate variables and soil variables of the study area using a machine learning model; the machine learning model is pre-trained using a training sample set, and each sample in the training sample set includes the contemporary climate variables, soil variables and measured yields of the existing distribution points of the target plant variety.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the plant variety zoning and yield prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the plant variety zoning and yield prediction method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the plant variety zoning and yield prediction method described in any one of claims 1 to 6 is implemented.

Images