Potato yield evaluation method and device, electronic equipment and storage medium

Abstract

The invention provides a potato yield evaluation method and device, electronic equipment and a storage medium, and relates to the technical field of agriculture, and the method comprises the steps: obtaining remote sensing image data, meteorological data, a soil nutrient comprehensive evaluation index and potato yield data of a potato planting region in a key growth period; acquiring various vegetation indexes of the potato planting area according to the remote sensing image data; screening out a plurality of second vegetation indexes with relatively high correlation from the plurality of vegetation indexes according to correlation coefficients of each vegetation index in the plurality of vegetation indexes and the potato yield data, and then constructing a plurality of initial yield evaluation models in one-to-one correspondence with the plurality of second vegetation indexes; determining the initial yield evaluation model with the highest precision in the plurality of initial yield evaluation models as a target yield evaluation model; and predicting the potato yield in the potato planting area according to the target yield evaluation model. The potato yield evaluation efficiency and evaluation accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to a potato yield evaluation method and device, electronic equipment and storage medium. Background Art

[0002] As one of the most important food crops in the world, potato yield forecast is of great significance to agricultural management, market regulation and food security.

[0003] At present, potato yield assessment relies on manual field surveys and sampling analysis. This method is not only time-consuming and labor-intensive, but also easily affected by factors such as the environment and human errors. Especially in areas with large planting areas and complex and changeable terrain, the limiting factors are further increased, resulting in low accuracy and efficiency of potato yield assessment, which brings many inconveniences to the potato yield assessment process. Summary of the invention

[0004] The present invention provides a potato yield assessment method and device, an electronic device and a storage medium, which are used to solve the defects in the prior art that potato yield assessment relies on manual measurement and analysis, resulting in low assessment efficiency and low assessment result accuracy, and achieve the purpose of improving potato yield assessment efficiency and assessment accuracy.

[0005] The invention provides a potato yield evaluation method, comprising the following steps.

[0006] The invention relates to a method for obtaining remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of a potato planting area during a key growth period; obtaining multiple vegetation indices of the potato planting area according to the remote sensing image data; calculating the correlation coefficient between each vegetation index in the multiple vegetation indices and the potato yield data, and obtaining multiple correlation coefficients corresponding to the multiple vegetation indices; determining the first vegetation index as the second vegetation index when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, and obtaining multiple second vegetation indices; wherein the first vegetation index is any one of the multiple vegetation indices; constructing an initial yield evaluation model corresponding to the target vegetation index according to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index in the multiple second vegetation indices, and the potato yield data, and obtaining multiple initial yield evaluation models corresponding to the multiple second vegetation indices; evaluating the accuracy of the multiple initial yield evaluation models, and determining the target yield evaluation model in the multiple initial yield evaluation models according to the evaluation results; and predicting the potato yield in the potato planting area according to the target yield evaluation model.

[0007] According to a potato yield assessment method provided by the present invention, the accuracy of multiple initial yield assessment models is assessed, and a target yield assessment model is determined from the multiple initial yield assessment models according to the assessment results, including: obtaining sample assessment data of a first initial yield assessment model; wherein the sample assessment data includes: a sample vegetation index, sample meteorological data, a sample soil nutrient comprehensive evaluation index and an actual potato yield of each sample area among multiple sample areas, the sample vegetation index is a vegetation index corresponding to the first initial yield assessment model, and the first initial yield assessment model is any one of the multiple initial yield assessment models; the sample vegetation index, sample meteorological data and sample soil nutrient comprehensive evaluation index of each sample area are input into the first initial yield assessment model, and the predicted potato yield of each sample area output by the first initial yield assessment model is obtained; according to the predicted potato yield and the actual potato yield of each sample area, an assessment parameter corresponding to the first initial yield assessment model is obtained; among the multiple assessment parameters corresponding to the multiple initial yield assessment models, the initial yield assessment model corresponding to the target assessment parameter is determined as the target yield assessment model; wherein the target assessment parameter is greater than other assessment parameters among the multiple assessment parameters.

[0008] According to a potato yield assessment method provided by the present invention, based on the predicted potato yield and the actual potato yield of each sample area, an assessment parameter corresponding to a first initial yield assessment model is obtained, including: based on the predicted potato yield and the actual potato yield of each sample area, a determination coefficient corresponding to the first initial yield assessment model is obtained; and the determination coefficient is determined as an assessment parameter.

[0009] According to a potato yield assessment method provided by the present invention, based on the predicted potato yield and the actual potato yield of each sample area, the assessment parameters corresponding to the first initial yield assessment model are obtained, including: based on the predicted potato yield and the actual potato yield of each sample area, first assessment data and second assessment data corresponding to the first initial yield assessment model are obtained; wherein the first assessment data includes a determination coefficient, and the second assessment data includes at least one of the following: a root mean square error, a mean absolute error, and a relative analytical error; based on the first assessment data and the second assessment data, the assessment parameters corresponding to the first initial yield assessment model are obtained.

[0010] According to a potato yield assessment method provided by the present invention, the accuracy of multiple initial yield assessment models is evaluated, and after a target yield assessment model is determined among the multiple initial yield assessment models based on the evaluation results, the method further includes: importing the potato yield predicted by the target yield assessment model into a geographic information system, and making a monitoring map based on the import results.

[0011] According to a potato yield assessment method provided by the present invention, an initial yield assessment model corresponding to the target vegetation index is constructed according to meteorological data, a soil nutrient comprehensive evaluation index, any target vegetation index among a plurality of second vegetation indexes, and potato yield data, including: constructing an initial yield assessment model corresponding to the target vegetation index based on a multivariate linear regression model or a multivariate power function model according to meteorological data, a soil nutrient comprehensive evaluation index, any target vegetation index among a plurality of second vegetation indexes, and potato yield data.

[0012] The present invention also provides a potato yield evaluation device, comprising the following modules: a first acquisition module, a second acquisition module, a calculation module, a processing module, a model building module, a model determination module, and a prediction module.

[0013] The first acquisition module is used to obtain remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of potato planting areas during the key growth period.

[0014] The second acquisition module is used to obtain multiple vegetation indexes of the potato planting area based on remote sensing image data.

[0015] The calculation module is used to calculate the correlation coefficient between each vegetation index and potato yield data among the multiple vegetation indexes, and obtain multiple correlation coefficients corresponding to the multiple vegetation indexes.

[0016] The processing module is used to determine the first vegetation index as the second vegetation index when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, and obtain multiple second vegetation indices; wherein the first vegetation index is any one of the multiple vegetation indices.

[0017] The model building module is used to build an initial yield evaluation model corresponding to the target vegetation index based on meteorological data, soil nutrient comprehensive evaluation index, any target vegetation index among multiple second vegetation indexes, and potato yield data, and obtain multiple initial yield evaluation models corresponding to multiple second vegetation indexes.

[0018] A model determination module is used to evaluate the accuracy of multiple initial yield evaluation models and determine a target yield evaluation model from the multiple initial yield evaluation models according to the evaluation results; The prediction module is used to predict the potato yield in the potato planting area according to the target yield assessment model.

[0019] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned potato yield evaluation methods is implemented.

[0020] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the potato yield evaluation method described in any one of the above methods is implemented.

[0021] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the potato yield evaluation method described above is implemented.

[0022] The potato yield evaluation method and device, electronic device and storage medium provided by the present invention obtain remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index and potato yield data of a potato planting area in a key growth period; obtain multiple vegetation indexes of the potato planting area according to the remote sensing image data; calculate the correlation coefficient between each vegetation index and the potato yield data in the multiple vegetation indexes, and obtain multiple correlation coefficients corresponding to the multiple vegetation indexes one by one; when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, determine the first vegetation index as the second vegetation index; number, and obtain multiple second vegetation indices; wherein the first vegetation index is any one of the multiple vegetation indices; according to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index among the multiple second vegetation indices, and the potato yield data, an initial yield evaluation model corresponding to the target vegetation index is constructed to obtain multiple initial yield evaluation models corresponding to the multiple second vegetation indices; the accuracy of the multiple initial yield evaluation models is evaluated, and the target yield evaluation model is determined from the multiple initial yield evaluation models according to the evaluation results; and the potato yield in the potato planting area is predicted according to the target yield evaluation model. It can be seen that the present invention no longer relies on manual field investigation and sampling analysis to evaluate potato yield, but uses remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index and historical yield data to construct a potato yield evaluation model, so as to effectively overcome the limitations of the traditional reliance on manual measurement and analysis of potato yield process, so that the potato yield evaluation process is no longer affected by factors such as environment and human errors, and solves the defects of low evaluation efficiency and low accuracy of evaluation results in the prior art due to the reliance on manual measurement and analysis of potato yield evaluation, thereby achieving the purpose of improving the potato yield evaluation efficiency and evaluation accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1This is one of the flow charts of the potato yield evaluation method provided by the present invention.

[0025] Figure 2 This is the second flow chart of the potato yield evaluation method provided by the present invention.

[0026] Figure 3 This is the third flow chart of the potato yield evaluation method provided by the present invention.

[0027] Figure 4 It is a schematic diagram of the structure of the potato yield evaluation device provided by the present invention.

[0028] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] At present, with the rapid development of remote sensing technology, especially the application of multispectral remote sensing images, new possibilities have been provided for the accurate estimation of crop yields. Multispectral remote sensing images can capture the reflection characteristics of surface objects at different wavelengths, thereby reflecting key information such as crop growth status, vegetation coverage, soil moisture, etc. This information is crucial for understanding the growth cycle, health status and yield potential of potatoes. At the same time, combined with meteorological data and soil comprehensive evaluation index data, the analysis of the potato growth environment can be further refined. Meteorological data such as temperature, precipitation, light intensity, etc. are key factors affecting the growth and development of potatoes. Through real-time monitoring and data analysis, the changes in meteorological conditions during the growth of potatoes can be accurately grasped, providing a scientific basis for yield prediction. The soil comprehensive evaluation index integrates information on soil texture, nutrient content, moisture status, etc., and is an important indicator for evaluating soil productivity and crop growth potential.

[0031] Based on this, a potato yield estimation model can be constructed based on remote sensing multispectral images, meteorological data and soil comprehensive evaluation index data to achieve comprehensive monitoring and accurate analysis of the potato growth environment, overcome the limitations of traditional manual yield measurement methods, and improve the accuracy and efficiency of yield prediction. At the same time, the model can also provide timely decision-making support for agricultural producers, guide them to scientifically plant, rationally fertilize, and accurately irrigate, thereby achieving high-yield, high-quality and sustainable development of potatoes, which is of great significance for improving the level of agricultural informatization, ensuring food security, and promoting agricultural modernization.

[0032] Combine the following Figure 1-Figure 3 The potato yield assessment method of the present invention is described.

[0033] Figure 1 FIG. 1 is one of the flow charts of the potato yield evaluation method provided by the present invention, such as Figure 1 As shown, the method includes the following S110~S170.

[0034] S110: Acquire remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of potato planting areas during key growth periods.

[0035] The critical growing period is the critical growing period of potatoes, usually from June to July.

[0036] Meteorological data may include, for example, effective accumulated temperature and total precipitation.

[0037] The effective accumulated temperature during the critical growth period refers to the sum of the effective temperatures of the crop during the critical growth period. The effective accumulated temperature during the critical growth period can be calculated by the following formula: K=N(TC); wherein K is the effective accumulated temperature during the critical growth period, N is the number of days during the critical growth period, T is the average temperature during the critical growth period, and C is the development threshold temperature of the crop, which is 2°C for potato development in the embodiment of the present invention.

[0038] Total precipitation refers to the sum of precipitation during the key growth period.

[0039] S120: Obtain multiple vegetation indexes of the potato planting area according to the remote sensing image data.

[0040] Multiple vegetation indices may include, for example: Normalized Difference Vegetation Index (NDVI), Renormalized Difference Vegetation Index (RDVI), Ratio Vegetation Index (RVI), Green Normalized Difference Vegetation Index (GNDVI), Triangular Vegetation Index (TVI), Enhanced Vegetation Index (EVI), Modified Soil Adjusted Vegetation Index (MSAVI), and Optimized Soil Adjusted Vegetation Index (OSAVI).

[0041] After obtaining the remote sensing image data of the potato planting area, various vegetation indices can be calculated in the following way.

[0042] Normalized Difference Vegetation Index NDVI: NDVI=(NIR-RED) / (NIR+RED); where NIR is the reflectivity of the near-infrared band in the remote sensing image data, and RED is the reflectivity of the red light band in the remote sensing image data.

[0043] Renormalized Difference Vegetation Index RDVI: .

[0044] Ratio vegetation index RI: RI=NIR / RED.

[0045] Green Normalized Vegetation Index GNDVI: GNDVI=(NIR-GREEN) / (NIR+GREEN); where GREEN is the reflectance of the green light band in the remote sensing image data.

[0046] Triangular vegetation index TVI: TVI=[120×(NIR-GREEN)-200×(RED-GREEN)] / 2.

[0047] Enhanced Vegetation Index EVI: EVI=2.4×(NIR-RED) / (NIR+RED+1).

[0048] Modified Soil Adjusted Vegetation Index MSAVI: / 2.

[0049] Optimized soil adjusted vegetation index OSAVI: OSAVI = (NIR-RED) / (NIR+RED+0.16).

[0050] Soil nutrients can be inverted based on the soil pseudo model and the soil nutrient comprehensive evaluation index (Cloud Fuzzy Fomprehensive Index, CFCI) can be comprehensively evaluated.

[0051] S130: Calculate the correlation coefficient between each vegetation index among the plurality of vegetation indexes and the potato yield data, and obtain a plurality of correlation coefficients corresponding to the plurality of vegetation indexes.

[0052] For example, based on Pearson Correlation Analysis, the Pearson correlation coefficient between each vegetation index and potato yield data can be calculated to obtain multiple Pearson correlation coefficients corresponding to multiple vegetation indices.

[0053] S140: When the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, the first vegetation index is determined as a second vegetation index to obtain a plurality of second vegetation indices; wherein the first vegetation index is any one of the plurality of vegetation indices.

[0054] The threshold value may be set by those skilled in the art according to actual conditions, and the embodiment of the present invention does not limit this.

[0055] S150: constructing an initial yield evaluation model corresponding to the target vegetation index according to meteorological data, soil nutrient comprehensive evaluation index, any target vegetation index among multiple second vegetation indexes, and potato yield data, and obtaining multiple initial yield evaluation models corresponding to multiple second vegetation indexes.

[0056] An initial yield assessment model corresponding to the target vegetation index can be constructed based on a multivariate linear regression model or a multivariate power function model according to meteorological data, a soil nutrient comprehensive evaluation index, any target vegetation index among a plurality of second vegetation indices, and potato yield data.

[0057] For example, an initial yield assessment model corresponding to the target vegetation index is constructed based on a multiple linear regression model. The slope and intercept of the linear fit can be obtained by the least squares method. The multiple linear regression model can be expressed as follows: Y = a0 + a1 × VI + a2 × T + a3 × P; Among them, Y is the predicted potato yield (the training data during training is potato yield data), VI is the target vegetation index, T is the effective accumulated temperature during the key growth period (in Celsius day·degree (d·℃)), and P is the precipitation during the key growth period (in millimeters (mm)).

[0058] Meteorological data, soil nutrient comprehensive evaluation index and target vegetation index are used to determine a0, a1, a2 and a3 in the multivariate linear regression model Y=a0+a1×VI+a2×T+a3×P, and the initial yield evaluation model corresponding to the target vegetation index is obtained.

[0059] It can be understood that the process of constructing the initial yield assessment model corresponding to the target vegetation index based on the multivariate power function model is similar to the process of constructing the initial yield assessment model corresponding to the target vegetation index based on the multivariate linear regression model mentioned above. Please refer to the process of constructing the initial yield assessment model corresponding to the target vegetation index based on the multivariate linear regression model mentioned above, which will not be repeated here.

[0060] When constructing the initial yield assessment model, the data set (meteorological data, soil nutrient comprehensive evaluation index, any target vegetation index among multiple second vegetation indices, and potato yield data) was divided into 7:3, of which 70% of the data set was the training data set and 30% of the data set was the verification data set.

[0061] S160: Evaluate the accuracy of multiple initial yield evaluation models, and determine a target yield evaluation model from the multiple initial yield evaluation models according to the evaluation results.

[0062] In some embodiments, Figure 2 As shown, the execution process of S160 may include the following S210~S240.

[0063] S210: Obtain sample evaluation data of the first initial yield evaluation model; wherein the sample evaluation data includes: a sample vegetation index, sample meteorological data, a sample soil nutrient comprehensive evaluation index and actual potato yield of each sample area in multiple sample areas, the sample vegetation index is a vegetation index corresponding to the first initial yield evaluation model, and the first initial yield evaluation model is any one of the multiple initial yield evaluation models.

[0064] S220: Inputting the sample vegetation index, sample meteorological data and sample soil nutrient comprehensive evaluation index of each sample area into the first initial yield assessment model to obtain the predicted potato yield of each sample area output by the first initial yield assessment model.

[0065] S230: Obtaining evaluation parameters corresponding to the first initial yield evaluation model according to the predicted potato yield and the actual potato yield of each sample area.

[0066] In some embodiments, the evaluation parameter is a determination coefficient, and the execution process of S230 is specifically as follows: according to the predicted potato yield and the actual potato yield of each sample area, the determination coefficient corresponding to the first initial yield evaluation model is obtained, and the determination coefficient is determined as the evaluation parameter.

[0067] In a specific implementation, the determination coefficient corresponding to the first initial yield assessment model can be calculated according to the following formula: ; in, is the coefficient of determination, n is the number of sample areas, is the actual potato yield in the i-th sample area, Predicted potato yield for the ith sample area.

[0068] In some embodiments, Figure 3 As shown, the execution process of S230 may include the following S310~S320.

[0069] S310: Obtain first evaluation data and second evaluation data corresponding to a first initial yield evaluation model based on the predicted potato yield and the actual potato yield of each sample area; wherein the first evaluation data includes a determination coefficient, and the second evaluation data includes at least one of the following: a root mean square error, a mean absolute error, and a relative analysis error.

[0070] S320: Obtaining evaluation parameters corresponding to a first initial yield evaluation model according to the first evaluation data and the second evaluation data.

[0071] For each parameter in the coefficient of determination, square root error, mean absolute error, and relative prediction deviation (RPD), the weighting coefficient corresponding to each parameter can be set in advance, and the product of each parameter and its corresponding weighting coefficient can be obtained as the weighted parameter corresponding to each parameter. Finally, all weighted parameters are summed and the sum result is used as the evaluation parameter.

[0072] The weighting coefficient corresponding to each parameter can be set by those skilled in the art according to actual conditions, and the embodiment of the present invention is not limited to this.

[0073] S240: Among the multiple evaluation parameters corresponding to the multiple initial yield evaluation models, determine the initial yield evaluation model corresponding to the target evaluation parameter as the target yield evaluation model; wherein the target evaluation parameter is greater than other evaluation parameters among the multiple evaluation parameters.

[0074] Among the multiple evaluation parameters corresponding to the multiple initial yield evaluation models, the initial yield evaluation model corresponding to the largest evaluation parameter is determined as the target yield evaluation model.

[0075] S170: Predicting potato yield in a potato planting area according to a target yield assessment model.

[0076] In some embodiments, after executing S170, the potato yield predicted by the target yield assessment model may be imported into a geographic information system, and a monitoring map may be prepared based on the import result so that relevant technicians can analyze the potato yield in combination with geographic information.

[0077] The potato yield evaluation method provided by the present invention obtains remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of a potato planting area in a key growth period; obtains multiple vegetation indexes of the potato planting area according to the remote sensing image data; calculates the correlation coefficient between each vegetation index in the multiple vegetation indexes and the potato yield data, and obtains multiple correlation coefficients corresponding to the multiple vegetation indexes; when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, determines the first vegetation index as a second vegetation index, and obtains multiple second vegetation indexes; wherein the first vegetation index is any one of the multiple vegetation indexes; constructs an initial yield evaluation model corresponding to the target vegetation index according to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index among the multiple second vegetation indexes, and the potato yield data, and obtains multiple initial yield evaluation models corresponding to the multiple second vegetation indexes; evaluates the accuracy of the multiple initial yield evaluation models, and determines the target yield evaluation model among the multiple initial yield evaluation models according to the evaluation results; and predicts the potato yield in the potato planting area according to the target yield evaluation model. It can be seen that the present invention no longer relies on manual field investigation and sampling analysis to evaluate potato yield, but uses remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index and historical yield data to construct a potato yield evaluation model, so as to effectively overcome the limitations of the traditional reliance on manual measurement and analysis of potato yield process, so that the potato yield evaluation process is no longer affected by factors such as environment and human errors, and solves the defects of low evaluation efficiency and low accuracy of evaluation results in the prior art due to the reliance on manual measurement and analysis of potato yield evaluation, thereby achieving the purpose of improving the potato yield evaluation efficiency and evaluation accuracy.

[0078] The purpose of the present invention is to provide an efficient and accurate potato yield assessment model, which realizes comprehensive monitoring and accurate analysis of the potato growth environment by integrating multi-dimensional data sources such as remote sensing multispectral images, real-time meteorological data and soil nutrient comprehensive evaluation index, thereby significantly improving the accuracy and efficiency of yield prediction, overcoming the limitations of traditional manual yield measurement methods, providing scientific basis and decision-making support for agricultural producers, promoting the refined management of potato planting, promoting the intelligent and information-based development of agricultural production, and ensuring food security and sustainable development of agriculture.

[0079] The embodiments of the present invention can achieve the following beneficial effects: Fusion of multi-dimensional data sources: This invention integrates multi-dimensional data sources such as remote sensing multispectral images, meteorological data, and soil nutrient comprehensive evaluation index. By extracting vegetation index to reflect the growth status and vegetation coverage of potatoes, combining real-time meteorological data to evaluate the growth environment, and using soil nutrient comprehensive evaluation index to evaluate soil production potential, a comprehensive and accurate description of the potato growth environment is achieved.

[0080] Remote sensing inversion technology and statistical modeling methods, such as building multivariate linear regression models and multivariate power function models, are used to conduct in-depth mining and comprehensive analysis of multidimensional data sources. These models can fully consider the interactions and influences between various factors and improve the accuracy and reliability of yield forecasts.

[0081] High-precision production estimation model construction: By introducing statistical indicators such as the coefficient of determination (R²) and RPD (Residual Prediction Deviation, relative analytical error), the accuracy of the model is comprehensively evaluated and optimized. R² is used to measure the degree of fit between the model's predicted value and the actual value, while RPD is used to evaluate the model's predictive ability and stability. By continuously optimizing the model parameters and structure, the model is ensured to be optimal in terms of high accuracy and reliability.

[0082] Intelligent decision support: Based on the potato yield estimation model, intelligent decision support is provided for agricultural producers. By real-time monitoring of potato growth status and predicting yield, it helps producers to scientifically formulate planting plans, optimize water and fertilizer management, adjust planting structure, etc., to achieve high yield, high quality and sustainable development of potatoes. At the same time, the model can also provide important reference for agricultural insurance, market regulation and other fields.

[0083] The application of the present invention promotes the intelligent and refined management of agricultural production. Based on the analysis and prediction of real-time data, agricultural producers can formulate planting strategies more scientifically, optimize resource allocation, improve water and fertilizer utilization efficiency, and reduce unnecessary waste, thereby achieving cost saving and efficiency improvement in agricultural production.

[0084] The potato yield evaluation device provided by the present invention is described below. The potato yield evaluation device described below and the potato yield evaluation method described above can be referred to each other.

[0085] Figure 4 FIG. 1 is a schematic diagram of the structure of the potato yield evaluation device provided by the present invention. Figure 4As shown, the potato yield evaluation device 400 includes: a first acquisition module 401, a second acquisition module 402, a calculation module 403, a processing module 404, a model building module 405, a model determination module 406, and a prediction module 407.

[0086] The first acquisition module 401 is used to acquire remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of potato planting areas during the key growth period.

[0087] The second acquisition module 402 is used to acquire multiple vegetation indexes of the potato planting area according to the remote sensing image data.

[0088] The calculation module 403 is used to calculate the correlation coefficient between each vegetation index among the multiple vegetation indexes and the potato yield data, and obtain multiple correlation coefficients corresponding to the multiple vegetation indexes.

[0089] The processing module 404 is used to determine the first vegetation index as the second vegetation index when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, and obtain multiple second vegetation indices; wherein the first vegetation index is any one of the multiple vegetation indices.

[0090] The model building module 405 is used to build an initial yield evaluation model corresponding to the target vegetation index based on meteorological data, soil nutrient comprehensive evaluation index, any target vegetation index among multiple second vegetation indices, and potato yield data, and obtain multiple initial yield evaluation models corresponding to multiple second vegetation indices.

[0091] The model determination module 406 is used to evaluate the accuracy of multiple initial yield estimation models and determine a target yield estimation model from the multiple initial yield estimation models according to the evaluation results.

[0092] The prediction module 407 is used to predict the potato yield in the potato planting area according to the target yield assessment model.

[0093] The potato yield evaluation device provided by the present invention obtains remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of a potato planting area in a key growth period; obtains multiple vegetation indexes of the potato planting area according to the remote sensing image data; calculates the correlation coefficient between each vegetation index in the multiple vegetation indexes and the potato yield data, and obtains multiple correlation coefficients corresponding to the multiple vegetation indexes; when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, determines the first vegetation index as a second vegetation index, and obtains multiple second vegetation indexes; wherein the first vegetation index is any one of the multiple vegetation indexes; constructs an initial yield evaluation model corresponding to the target vegetation index according to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index among the multiple second vegetation indexes, and the potato yield data, and obtains multiple initial yield evaluation models corresponding to the multiple second vegetation indexes; evaluates the accuracy of the multiple initial yield evaluation models, and determines the target yield evaluation model among the multiple initial yield evaluation models according to the evaluation results; and predicts the potato yield in the potato planting area according to the target yield evaluation model. It can be seen that the present invention no longer relies on manual field investigation and sampling analysis to evaluate potato yield, but uses remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index and historical yield data to construct a potato yield evaluation model, so as to effectively overcome the limitations of the traditional reliance on manual measurement and analysis of potato yield process, so that the potato yield evaluation process is no longer affected by factors such as environment and human errors, and solves the defects of low evaluation efficiency and low accuracy of evaluation results in the prior art due to the reliance on manual measurement and analysis of potato yield evaluation, thereby achieving the purpose of improving the potato yield evaluation efficiency and evaluation accuracy.

[0094] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530 and a communications bus 540, wherein the processor 510, the communications interface 520 and the memory 530 communicate with each other via the communications bus 540. The processor 510 may call the logic instructions in the memory 530 to execute a potato yield assessment method, which includes: obtaining remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of a potato planting area during a critical growth period; obtaining multiple vegetation indexes of the potato planting area based on the remote sensing image data; calculating the correlation coefficient between each vegetation index in the multiple vegetation indexes and the potato yield data, and obtaining multiple correlation coefficients corresponding to the multiple vegetation indexes; when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, determining the first vegetation index as The invention relates to a method for predicting potato yield in a potato planting area by using a target vegetation index and a second vegetation index. The method comprises the following steps: a) determining a first vegetation index and a second vegetation index, wherein the first vegetation index is any one of the plurality of vegetation indices; b) constructing an initial yield evaluation model corresponding to the target vegetation index according to meteorological data, a soil nutrient comprehensive evaluation index, any target vegetation index among the plurality of second vegetation indices, and potato yield data, and obtaining a plurality of initial yield evaluation models corresponding to the plurality of second vegetation indices; estimating the accuracy of the plurality of initial yield evaluation models, and determining a target yield evaluation model among the plurality of initial yield evaluation models according to the evaluation results; and c) predicting potato yield in a potato planting area according to the target yield evaluation model.

[0095] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0096] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the potato yield evaluation method provided by the above methods. The method includes: obtaining remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of a potato planting area during a critical growth period; obtaining multiple vegetation indices of the potato planting area based on the remote sensing image data; calculating the correlation coefficient between each vegetation index of the multiple vegetation indices and the potato yield data, and obtaining multiple correlation coefficients corresponding to the multiple vegetation indices; and calculating the correlation coefficients between the first vegetation index and the potato yield data. When the correlation coefficient of potato yield data is greater than a set threshold, the first vegetation index is determined as the second vegetation index, and multiple second vegetation indices are obtained; wherein the first vegetation index is any one of the multiple vegetation indices; an initial yield assessment model corresponding to the target vegetation index is constructed according to meteorological data, a comprehensive soil nutrient evaluation index, any target vegetation index among the multiple second vegetation indices, and potato yield data, and multiple initial yield assessment models corresponding to the multiple second vegetation indices are obtained; the accuracy of the multiple initial yield assessment models is evaluated, and a target yield assessment model is determined among the multiple initial yield assessment models according to the evaluation results; and the potato yield in the potato planting area is predicted according to the target yield assessment model.

[0097] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the potato yield evaluation method provided by the above methods is implemented, the method comprising: obtaining remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of a potato planting area during a key growth period; obtaining multiple vegetation indexes of the potato planting area according to the remote sensing image data; calculating the correlation coefficient between each of the multiple vegetation indexes and the potato yield data, and obtaining multiple correlation coefficients corresponding to the multiple vegetation indexes; when the correlation coefficient between the first vegetation index and the potato yield data is greater than When a threshold is set, the first vegetation index is determined as the second vegetation index, and multiple second vegetation indices are obtained; wherein the first vegetation index is any one of the multiple vegetation indices; an initial yield assessment model corresponding to the target vegetation index is constructed according to meteorological data, a comprehensive soil nutrient evaluation index, any target vegetation index among the multiple second vegetation indices, and potato yield data, and multiple initial yield assessment models corresponding to the multiple second vegetation indices are obtained; the accuracy of the multiple initial yield assessment models is evaluated, and a target yield assessment model is determined among the multiple initial yield assessment models according to the evaluation results; and the potato yield in the potato planting area is predicted according to the target yield assessment model.

[0098] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A potato yield assessment method, characterized in that: include: Obtain remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of potato planting areas during the key growth period; Acquiring multiple vegetation indexes of the potato planting area according to the remote sensing image data; Calculating the correlation coefficient between each of the plurality of vegetation indices and the potato yield data to obtain a plurality of correlation coefficients corresponding to the plurality of vegetation indices; When the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, the first vegetation index is determined as a second vegetation index to obtain a plurality of second vegetation indices; wherein the first vegetation index is any one of the plurality of vegetation indices; According to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index among the plurality of second vegetation indexes, and the potato yield data, an initial yield evaluation model corresponding to the target vegetation index is constructed to obtain a plurality of initial yield evaluation models corresponding to the plurality of second vegetation indexes one by one; Evaluating the accuracy of the multiple initial yield estimation models, and determining a target yield estimation model from the multiple initial yield estimation models according to the evaluation results; The potato yield in the potato planting area is predicted according to the target yield assessment model.

2. The potato yield assessment method according to claim 1, characterized in that: The step of evaluating the accuracy of the multiple initial yield evaluation models and determining a target yield evaluation model from the multiple initial yield evaluation models according to the evaluation result includes: Acquire sample evaluation data of a first initial yield evaluation model; wherein the sample evaluation data includes: a sample vegetation index, sample meteorological data, a sample soil nutrient comprehensive evaluation index, and actual potato yield of each sample area in a plurality of sample areas, the sample vegetation index is a vegetation index corresponding to the first initial yield evaluation model, and the first initial yield evaluation model is any one of the plurality of initial yield evaluation models; Inputting the sample vegetation index, the sample meteorological data and the sample soil nutrient comprehensive evaluation index of each sample area into the first initial yield assessment model, and obtaining the predicted potato yield of each sample area output by the first initial yield assessment model; Obtaining evaluation parameters corresponding to the first initial yield evaluation model according to the predicted potato yield and the actual potato yield of each sample area; Among the multiple evaluation parameters corresponding one to one of the multiple initial yield evaluation models, the initial yield evaluation model corresponding to the target evaluation parameter is determined as the target yield evaluation model; wherein the target evaluation parameter is greater than other evaluation parameters among the multiple evaluation parameters.

3. The potato yield assessment method according to claim 2, characterized in that: The step of obtaining the evaluation parameters corresponding to the first initial yield evaluation model according to the predicted potato yield and the actual potato yield of each sample area includes: Obtaining a determination coefficient corresponding to the first initial yield assessment model according to the predicted potato yield and the actual potato yield of each sample area; The coefficient of determination is determined as the evaluation parameter.

4. The potato yield assessment method according to claim 2, characterized in that: The step of obtaining the evaluation parameters corresponding to the first initial yield evaluation model according to the predicted potato yield and the actual potato yield of each sample area includes: According to the predicted potato yield and the actual potato yield of each sample area, obtaining first evaluation data and second evaluation data corresponding to the first initial yield evaluation model; wherein the first evaluation data includes a determination coefficient, and the second evaluation data includes at least one of the following: a root mean square error, a mean absolute error, and a relative analytical error; According to the first evaluation data and the second evaluation data, evaluation parameters corresponding to the first initial yield evaluation model are obtained.

5. The potato yield evaluation method according to any one of claims 1 to 4, characterized in that: After evaluating the accuracy of the multiple initial yield evaluation models and determining the target yield evaluation model from the multiple initial yield evaluation models according to the evaluation results, the method further includes: The potato yield predicted by the target yield assessment model is imported into a geographic information system, and a monitoring map is prepared according to the import result.

6. The potato yield assessment method according to claim 1, characterized in that: The step of constructing an initial yield assessment model corresponding to the target vegetation index according to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index among the plurality of second vegetation indexes, and the potato yield data comprises: According to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index among the multiple second vegetation indices, and the potato yield data, an initial yield evaluation model corresponding to the target vegetation index is constructed based on a multivariate linear regression model or a multivariate power function model.

7. A potato yield assessment device, characterized in that: include: The first acquisition module is used to obtain remote sensing image data, meteorological data, soil nutrient comprehensive evaluation index, and potato yield data of potato planting areas during the key growth period; A second acquisition module is used to acquire multiple vegetation indexes of the potato planting area according to the remote sensing image data; A calculation module, used to calculate the correlation coefficient between each of the plurality of vegetation indexes and the potato yield data, and obtain a plurality of correlation coefficients corresponding to the plurality of vegetation indexes; A processing module, configured to determine the first vegetation index as a second vegetation index when the correlation coefficient between the first vegetation index and the potato yield data is greater than a set threshold, and obtain a plurality of second vegetation indices; wherein the first vegetation index is any one of the plurality of vegetation indices; A model building module, used to build an initial yield evaluation model corresponding to the target vegetation index according to the meteorological data, the soil nutrient comprehensive evaluation index, any target vegetation index among the multiple second vegetation indexes, and the potato yield data, and obtain multiple initial yield evaluation models corresponding to the multiple second vegetation indexes one by one; A model determination module, used to evaluate the accuracy of the multiple initial yield estimation models, and determine a target yield estimation model from the multiple initial yield estimation models according to the evaluation results; A prediction module is used to predict the potato yield in the potato planting area according to the target yield assessment model.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the potato yield evaluation method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the potato yield evaluation method according to 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 potato yield evaluation method according to any one of claims 1 to 6 is implemented.

Images