Saline-alkali soil improvement effect evaluation method based on digital twinning

Abstract

The invention discloses a saline-alkali soil improvement effect evaluation method based on digital twinning, and relates to the technical field of saline-alkali soil improvement effect evaluation, and the method comprises the following steps: collecting saline-alkali soil improvement effect monitoring data including multi-dimensional soil data, crop growth data and meteorological data, and carrying out the preprocessing of the collected data, calculating the salinization index, fertility index, porosity and permeability of the soil, analyzing the soil improvement effect of the saline-alkali soil to obtain the grade of the soil improvement effect of the saline-alkali soil, and obtaining an improvement effect feedback coefficient by utilizing the preprocessed crop growth data and meteorological data and combining with a multiple linear regression algorithm; the multi-dimensional data acquisition technology, the multiple linear regression algorithm, the digital twinborn model construction technology and the model optimization technology are closely combined with the modern information technology, so that the problems of incomplete analysis data, inaccurate evaluation result and low intelligent degree possibly existing in a traditional evaluation method are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of saline-alkali soil improvement effect evaluation, and particularly relates to a method for evaluating the effect of saline-alkali soil improvement based on digital twin. Background Art

[0002] Globally, saline-alkali soils are widely distributed, posing a severe challenge to agricultural production and the ecological environment. The evaluation of the effectiveness of saline-alkali soil improvement work is of great significance. However, traditional evaluation methods have many limitations. They mainly rely on manual field sampling and simple laboratory analysis to evaluate the effect of saline-alkali soil improvement. This method is not only inefficient but also unable to achieve real-time and dynamic monitoring of large areas of saline-alkali soil. With the rise of digital twin technology, its applications in various fields are constantly expanding. In the evaluation of the effect of saline-alkali soil improvement, although there have been some attempts based on digital twin, there are still many problems. Therefore, there is an urgent need for a more perfect and accurate method for evaluating the effect of saline-alkali soil improvement based on digital twin to enhance the scientificity and effectiveness of saline-alkali soil improvement work. Although the existing technology has made great progress in the direction of saline-alkali soil improvement, there are still some problems to be optimized. Traditional saline-alkali soil improvement is difficult to comprehensively analyze multi-dimensional soil data, crop growth data, and meteorological data, and then evaluate the effect of saline-alkali soil improvement, resulting in the problem of low accuracy in evaluating the effect of saline-alkali soil improvement in the existing technology. Summary of the Invention

[0003] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for evaluating the effect of saline-alkali soil improvement based on digital twin, including the following steps: Step 1: Collect monitoring data on the effect of saline-alkali soil improvement, including multi-dimensional soil data, crop growth data, and meteorological data, and preprocess the collected data to provide a data basis for the implementation of subsequent steps; Step 2: Use the preprocessed monitoring data on the effect of saline-alkali soil improvement to calculate the salinization index, fertility index, porosity, and permeability of the soil, analyze the effect of saline-alkali soil improvement, and then obtain the grade of the effect of saline-alkali soil improvement; Step 3: Use the preprocessed crop growth data and meteorological data, combined with the multiple linear regression algorithm, to obtain the improvement effect feedback coefficient; Step 4: Based on the obtained improvement effect feedback coefficient, analyze the improvement effect feedback grade, and use the improvement effect feedback grade to update the grade of the effect of saline-alkali soil improvement, reducing the error in the result of evaluating the improvement effect relying only on saline-alkali soil data; Step 5: Combine the iterative optimization algorithm with the updated saline-alkali soil improvement effect level to construct a digital twin evaluation model, and optimize the digital twin evaluation model through the deep neural network algorithm, improving the accuracy of the digital twin evaluation model; Step 6: Based on the output results of the optimized digital twin evaluation model, send corresponding saline-alkali soil improvement effect signals, solving the problem that the traditional saline-alkali soil improvement effect evaluation method is difficult to comprehensively analyze multi-dimensional soil data, crop growth data, and meteorological data, resulting in low evaluation accuracy of the existing technology for the saline-alkali soil improvement effect.

[0004] A further improvement of the technical solution of the present invention is that in the said Step 1, the process of collecting the saline-alkali soil improvement effect monitoring data includes: Divide the target research area of the saline-alkali soil into several small saline-alkali soil areas with the same area, and number the divided small saline-alkali soil areas respectively; Deploy different collection devices to collect multi-dimensional soil data, crop growth data, and meteorological data of each small saline-alkali soil area. Among them, the collection devices include a pH meter, a conductivity meter, an ion chromatograph, a soil nitrogen, phosphorus, and potassium sensor, a soil corer, a mercury intrusion porosimeter, a laser particle size analyzer, a crop plant height measuring instrument, a crop included angle and stem diameter measuring instrument, a leaf area measuring instrument, a crop yield monitor, a tipping bucket rain gauge, a temperature sensor, and a sunshine duration sensor; The multi-dimensional soil data includes the pH value, total salt content, salt ion concentration, nitrogen content, phosphorus content, potassium content, total volume, particle size, and volume of the inter-particle voids of the soil; the crop growth data includes the plant height, stem diameter, leaf area, and yield per unit area of the crop; the meteorological data includes precipitation, temperature, and sunshine duration; Specifically, use a pH meter, a conductivity meter, an ion chromatograph, a soil nitrogen, phosphorus, and potassium sensor, a soil corer, a mercury intrusion porosimeter, and a laser particle size analyzer to collect the pH value, total salt content, salt ion concentration, nitrogen content, phosphorus content, potassium content, total volume, particle size, and volume of the inter-particle voids of the soil respectively; use a crop plant height measuring instrument, a crop included angle and stem diameter measuring instrument, a leaf area measuring instrument, and a crop yield monitor to collect the plant height, stem diameter, leaf area, and yield per unit area of the crop respectively. Among them, since the areas of each small saline-alkali soil area are the same, take the crop yield of each small saline-alkali soil area as the yield per unit area of the crop; use a tipping bucket rain gauge, a temperature sensor, and a sunshine duration sensor to collect precipitation, temperature, and sunshine duration respectively.

[0005] A further improvement of the technical solution of the present invention is that in the said Step 1, the process of preprocessing the collected saline-alkali soil improvement effect monitoring data includes: Clean and normalize the collected data on the improvement effect monitoring, assign timestamps to multi-dimensional soil data, crop growth data, and meteorological data, and adjust the timestamps to synchronize the collection times of multi-dimensional soil data, crop growth data, and meteorological data; Correspond the multi-dimensional soil data, crop growth data, and meteorological data with the numbers of their corresponding small saline-alkali soil areas, integrate the multi-dimensional soil data, crop growth data, and meteorological data to generate an improvement effect monitoring data set, and divide the improvement effect monitoring data set into a training set and a test set, where the ratio of the training set to the test set is 7:3.

[0006] A further improvement in the technical solution of the present invention lies in that: in the second step, the calculation processes of the salinization index, fertility index, porosity, and permeability of the soil include: According to the principle of soil salinization, weights are assigned to the pH value, total salt content, and salt ion concentration of the soil respectively, and the weighted average method is used to calculate the soil salinization index, and its calculation formula is: Among them, SI is the soil salinization index, , and are the weights of the soil pH value, the total salt content of the soil, and the salt ion concentration of the soil respectively, , and are the pH value, the total salt content, and the salt ion concentration of the soil respectively; The logarithm is taken after adding 1 to the nitrogen content, phosphorus content, and potassium content of the soil respectively to avoid meaningless logarithms. The logarithmic method is used to calculate the soil fertility index, and its calculation process is as follows: Among them, is the soil fertility index, is the nitrogen content of the soil, is the phosphorus content of the soil, is the potassium content of the soil; Calculate the proportion of the volume of the voids between soil particles in the total volume of the soil to obtain the soil porosity; calculate the average value of the soil particle diameters, and calculate the soil permeability based on the Kozeny-Carman equation. The calculation formula is as follows: Among them, is the soil permeability, is the Kozeny constant, is the soil porosity, is the average value of the soil particle diameters.

[0007] A further improvement of the technical solution of the present invention lies in: in the second step, the process of obtaining the saline-alkali land soil improvement effect level includes: According to the physical properties of the soil and the principle of chemical balance, weights are assigned to the soil salinization index, soil fertility index, soil porosity, and soil permeability respectively; Using the weighted average method, calculate the product of the soil salinization index and its weight, the product of the soil fertility index and its weight, the product of the soil porosity and its weight, and the product of the soil permeability and its weight respectively, and then sum up the calculation results to obtain the saline-alkali land soil improvement coefficient; Based on the saline-alkali land soil improvement coefficient, analyze the saline-alkali land soil improvement effect, and evaluate the saline-alkali land soil improvement effect level of each small saline-alkali land soil area. The saline-alkali land soil improvement effect level includes low improvement effect, medium improvement effect, and high improvement effect; When the saline-alkali land soil improvement coefficient is less than 0.3, the corresponding small saline-alkali land soil area has a low improvement effect; when the saline-alkali land soil improvement coefficient is between 0.3 and 0.6, the corresponding small saline-alkali land soil area has a medium improvement effect; when the saline-alkali land soil improvement coefficient is greater than 0.6, the corresponding small saline-alkali land soil area has a high improvement effect.

[0008] A further improvement of the technical solution of the present invention lies in: in the third step, the process of obtaining the improvement effect feedback coefficient includes: Extract the crop growth data and meteorological data from the improvement effect monitoring dataset. Using the crop growth data and meteorological data in the training set, combined with the multiple linear regression algorithm, take the crop growth data and meteorological data as inputs and the improvement effect feedback coefficient as the output, learn the linear relationship between the crop growth data, meteorological data, and the improvement effect feedback coefficient, and train the improvement effect feedback model; Input the crop growth data and meteorological data in the test set into the improvement effect feedback model, evaluate the performance of the improvement effect feedback model, optimize the improvement effect feedback model by adjusting the intercept term and regression coefficient of the improvement effect feedback model, obtain the final improvement effect feedback model, and combine the current crop growth data and meteorological data of each small saline-alkali land soil area to output the corresponding improvement effect feedback coefficient; The expression of this improvement effect feedback model is: Among them, is the improvement effect feedback coefficient, , , , , , and The regression coefficients of crop plant height, crop stem diameter, crop leaf area, crop yield per unit area, precipitation, temperature, and sunshine duration are respectively, , , , , , and Crop plant height, crop stem diameter, crop leaf area, crop yield per unit area, precipitation, temperature, and sunshine duration are respectively, is the intercept term, is the error term.

[0009] A further improvement of the technical solution of the present invention lies in: in the step four, the process of analyzing the improvement effect feedback level and using the improvement effect feedback level to update the saline-alkali soil improvement effect level includes: Based on the improvement effect feedback coefficient output by the improvement effect feedback model, analyze the saline-alkali soil improvement effect level. When the improvement effect feedback coefficient is lower than 0.4, the corresponding small saline-alkali soil area has a low improvement effect; when the improvement effect feedback coefficient is between 0.4 and 0.75, the corresponding small saline-alkali soil area has a medium improvement effect; when the improvement effect feedback coefficient is higher than 0.75, the corresponding small saline-alkali soil area has a high improvement effect, and obtain the improvement effect feedback level; Based on the obtained improvement effect feedback level, when the saline-alkali soil improvement effect level is the same as the improvement effect feedback level, it is not updated; when the saline-alkali soil improvement effect level is different from the improvement effect feedback level, use the improvement effect feedback level to replace the saline-alkali soil improvement effect level and update the saline-alkali soil improvement effect level; Number the updated saline-alkali soil improvement effect level and integrate the number of the updated saline-alkali soil improvement effect level into the improvement effect monitoring dataset.

[0010] A further improvement of the technical solution of the present invention lies in: in the step five, the construction process of the digital twin evaluation model includes: Extract the multi-dimensional soil data and the number of the updated saline-alkali soil improvement effect level from the improvement effect monitoring dataset; Using the multi-dimensional soil data and the number of the updated saline-alkali soil improvement effect level in the training set, combined with the iterative optimization algorithm, use the multi-dimensional soil data as the input and the number of the updated saline-alkali soil improvement effect level as the output to learn the association between the multi-dimensional soil data and the number of the updated saline-alkali soil improvement effect level, and train the digital twin evaluation model; Input the multi-dimensional soil data in the test set into the digital twin evaluation model, compare the error between the output result of the digital twin evaluation model and the actual updated saline-alkali soil improvement effect level number, evaluate the performance of the digital twin evaluation model, adjust the parameters of the digital twin evaluation model, improve the performance of the digital twin evaluation model, and construct the digital twin evaluation model.

[0011] A further improvement of the technical solution of the present invention lies in: in step five, the optimization process of the digital twin evaluation model includes: Utilize the multi-dimensional soil data in the training set and the updated saline-alkali soil improvement effect level number, combine with the deep neural network algorithm, take the multi-dimensional soil data as the input, take the updated saline-alkali soil improvement effect level number as the output, learn the non-linear relationship between the multi-dimensional soil data and the updated saline-alkali soil improvement effect level number, and train the deep neural network model; Input the multi-dimensional soil data in the test set into the deep neural network model, compare the error between the output result of the deep neural network model and the actual updated saline-alkali soil improvement effect level number, feature the parameters of the deep neural network model, optimize the deep neural network model, obtain the final deep neural network model, and output the corresponding updated saline-alkali soil improvement effect level number through the current multi-dimensional soil data of each small saline-alkali soil area; Utilize the updated saline-alkali soil improvement effect level number output by the deep neural network model to train the digital twin evaluation model, adjust the parameters of the digital twin evaluation model again, optimize the digital twin evaluation model, obtain the final digital twin evaluation model, and combine with the current multi-dimensional soil data of each small saline-alkali soil area to output the corresponding updated saline-alkali soil improvement effect level number.

[0012] A further improvement of the technical solution of the present invention lies in: in step six, the process of sending the corresponding saline-alkali soil improvement effect signal based on the output result of the optimized digital twin evaluation model includes: Based on the updated saline-alkali soil improvement effect level number output by the optimized digital twin evaluation model, match the saline-alkali soil improvement effect level corresponding to the updated saline-alkali soil improvement effect level number; Set up an electronic display screen in the target research area of the saline-alkali soil, and in text form, the text form includes the electronic display screen showing low characters, the electronic display screen showing medium characters, and the electronic display screen showing high characters, and display the updated saline-alkali soil improvement effect level of each small saline-alkali soil area through the screen; When the improved effect level of the saline-alkali soil in the small saline-alkali soil area after update is low, the electronic display shows the word "low"; when the improved effect level of the saline-alkali soil in the small saline-alkali soil area after update is medium, the electronic display shows the word "medium"; when the improved effect level of the saline-alkali soil in the small saline-alkali soil area after update is high, the electronic display shows the word "high".

[0013] The beneficial effects of the present invention are as follows: For a method for evaluating the improvement effect of saline-alkali soil based on digital twin in the present invention, compared with the traditional method for evaluating the improvement effect of saline-alkali soil based on digital twin, the multi-dimensional data acquisition technology, multiple linear regression algorithm, digital twin model construction technology and model optimization technology in the method of the present invention are closely combined with modern information technology to accurately capture multi-dimensional soil data, crop growth data and meteorological data, and then obtain the salinization index, fertility index, porosity, permeability, improvement coefficient of saline-alkali soil and improvement effect feedback coefficient of the soil. Through the improvement coefficient of saline-alkali soil, the improvement effect level of saline-alkali soil is obtained, and through the improvement effect feedback coefficient, the improvement effect feedback level is obtained. Using the improvement effect feedback level, the improvement effect level of saline-alkali soil is updated, achieving real-time and comprehensive monitoring of the improvement effect of saline-alkali soil, solving the problems that may exist in traditional evaluation methods such as incomplete analysis data, inaccurate evaluation results and low intelligence level, ensuring that the method in the present invention can refine the dynamic monitoring standard for a method for evaluating the improvement effect of saline-alkali soil based on digital twin within a more accurate range, making the monitored data become more accurate indicators under the same conditions. The research and application of this method significantly enhance the intelligence level in the process of evaluating the improvement effect of saline-alkali soil based on digital twin. Brief Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a flowchart of a method for evaluating the improvement effect of saline-alkali soil based on digital twin of the present invention. Detailed Embodiments

[0016] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0017] As Figure 1 shown, the present invention provides a method for evaluating the improvement effect of saline-alkali soil based on digital twin, which consists of the following steps: Step 1: Collect monitoring data on the improvement effect of saline-alkali soil, including multi-dimensional soil data, crop growth data, and meteorological data, and preprocess the collected data to provide a data basis for the implementation of subsequent steps; Step 2: Use the preprocessed monitoring data on the improvement effect of saline-alkali soil to calculate the salinization index, fertility index, porosity, and permeability of the soil, analyze the improvement effect of saline-alkali soil, and then obtain the improvement effect level of saline-alkali soil; Step 3: Use the preprocessed crop growth data and meteorological data, combined with the multiple linear regression algorithm, to obtain the improvement effect feedback coefficient; Step 4: Based on the obtained improvement effect feedback coefficient, analyze the improvement effect feedback level, and use the improvement effect feedback level to update the improvement effect level of saline-alkali soil, reducing the error in the result of evaluating the improvement effect relying solely on the saline-alkali soil data; Step 5: Combine the iterative optimization algorithm with the updated improvement effect level of saline-alkali soil to construct a digital twin evaluation model, and optimize the digital twin evaluation model through the deep neural network algorithm, improving the accuracy of the digital twin evaluation model; Step 6: Based on the output result of the optimized digital twin evaluation model, send out a corresponding signal on the improvement effect of saline-alkali soil, solving the problem that the traditional method for evaluating the improvement effect of saline-alkali soil is difficult to comprehensively analyze multi-dimensional soil data, crop growth data, and meteorological data, resulting in low evaluation accuracy of the improvement effect of saline-alkali soil in the prior art.

[0018] Preferably, in Step 1, the process of collecting the monitoring data on the improvement effect of saline-alkali soil includes: Divide the target research area of the saline-alkali soil into several small saline-alkali soil areas with the same area, number the divided small saline-alkali soil areas respectively; Deploy different collection devices to collect multi-dimensional soil data, crop growth data, and meteorological data for each small saline-alkali soil area. Among them, the collection devices include a pH meter, a conductivity meter, an ion chromatograph, a soil nitrogen, phosphorus, and potassium sensor, a soil corer, a mercury intrusion porosimeter, a laser particle size analyzer, a crop plant height measuring instrument, a crop included angle and stem diameter measuring instrument, a leaf area measuring instrument, a crop yield monitor, a tipping bucket rain gauge, a temperature sensor, and a sunshine duration sensor; The multi-dimensional soil data includes the pH value, total salt content, salt ion concentration, nitrogen content, phosphorus content, potassium content, total volume, particle size, and the volume of voids between particles of the soil; the crop growth data includes the plant height, stem diameter, leaf area, and yield per unit area of the crop; the meteorological data includes precipitation, temperature, and sunshine duration; Specifically, use a pH meter, a conductivity meter, an ion chromatograph, a soil nitrogen, phosphorus, and potassium sensor, a soil corer, a mercury intrusion porosimeter, and a laser particle size analyzer to collect the pH value, total salt content, salt ion concentration, nitrogen content, phosphorus content, potassium content, total volume, particle size, and the volume of voids between particles of the soil respectively; use a crop plant height measuring instrument, a crop included angle and stem diameter measuring instrument, a leaf area measuring instrument, and a crop yield monitor to collect the plant height, stem diameter, leaf area, and yield per unit area of the crop respectively. Among them, since the areas of each small saline-alkali soil area are the same, the crop yield of each small saline-alkali soil area is regarded as the yield per unit area of the crop; use a tipping bucket rain gauge, a temperature sensor, and a sunshine duration sensor to collect precipitation, temperature, and sunshine duration respectively.

[0019] Preferably, in step one, the process of preprocessing the monitoring data of the improvement effect of the saline-alkali soil includes: Perform data cleaning and data normalization on the collected monitoring data of the improvement effect, assign time stamps to the multi-dimensional soil data, crop growth data, and meteorological data, and adjust the time stamps to achieve the synchronization of the collection times of the multi-dimensional soil data, crop growth data, and meteorological data; Correspond the multi-dimensional soil data, crop growth data, and meteorological data with the numbers of their corresponding small saline-alkali soil areas, integrate the multi-dimensional soil data, crop growth data, and meteorological data to generate a monitoring data set of the improvement effect, and divide the monitoring data set of the improvement effect into a training set and a test set, where the ratio of the training set to the test set is 7:3.

[0020] Preferably, in step two, the calculation processes of the salinization index, fertility index, porosity, and permeability of the soil include: According to the principle of soil salinization, assign weights to the pH value, total salt content, and salt ion concentration of the soil respectively, and use the weighted average method to calculate the soil salinization index. Its calculation formula is: Among them, SI is the soil salinization index, , and are the weights of soil pH value, total salt content of soil and concentration weight of soil salt ions respectively, , and are the pH value, total salt content and concentration of salt ions of the soil respectively; The logarithm is taken after adding 1 to the nitrogen content, phosphorus content and potassium content of the soil respectively to avoid meaningless logarithms. The logarithmic method is used to calculate the soil fertility index, and the calculation process is as follows: Among them, is the soil fertility index, is the nitrogen content of the soil, is the phosphorus content of the soil, is the potassium content of the soil; Calculate the proportion of the volume of the voids between soil particles in the total volume of the soil to obtain the soil porosity; calculate the average value of the soil particle size, and calculate the soil permeability based on the Kozeny-Carman equation. The calculation formula is as follows: Among them, is the soil permeability, is the Kozeny constant, is the soil porosity, is the average value of the soil particle size.

[0021] Preferably, in step two, the process of obtaining the improvement effect level of saline-alkali soil includes: According to the physical properties of the soil and the principle of chemical equilibrium, weights are assigned to the soil salinization index, soil fertility index, soil porosity and soil permeability respectively; Using the weighted average method, calculate the product of the soil salinization index and its weight, the product of the soil fertility index and its weight, the product of the soil porosity and its weight, and the product of the soil permeability and its weight respectively, and then sum the calculation results to obtain the improvement coefficient of saline-alkali soil; Analyze the improvement effect of saline-alkali soil through the improvement coefficient of saline-alkali soil, and evaluate the improvement effect level of saline-alkali soil in each small saline-alkali soil area. Among them, the improvement effect level of saline-alkali soil includes low improvement effect, medium improvement effect and high improvement effect; When the improvement coefficient of saline-alkali soil is less than 0.3, the corresponding small saline-alkali soil area has a low improvement effect; when the improvement coefficient of saline-alkali soil is between 0.3 and 0.6, the corresponding small saline-alkali soil area has a medium improvement effect; when the improvement coefficient of saline-alkali soil is greater than 0.6, the corresponding small saline-alkali soil area has a high improvement effect.

[0022] Preferably, in step three, the process of obtaining the improvement effect feedback coefficient includes: Extract the crop growth data and meteorological data from the improvement effect monitoring dataset. Using the crop growth data and meteorological data in the training set, combined with the multiple linear regression algorithm, take the crop growth data and meteorological data as inputs and the improvement effect feedback coefficient as the output, learn the linear relationship between the crop growth data, meteorological data and the improvement effect feedback coefficient, and train the improvement effect feedback model; Input the crop growth data and meteorological data in the test set into the improvement effect feedback model, evaluate the performance of the improvement effect feedback model, optimize the improvement effect feedback model by adjusting the intercept term and regression coefficient of the improvement effect feedback model, obtain the final improvement effect feedback model, and combine the current crop growth data and meteorological data of each small saline-alkali soil area to output the corresponding improvement effect feedback coefficient; The expression of the improvement effect feedback model is: Wherein, is the improvement effect feedback coefficient, , , , , , and are the regression coefficients of crop plant height, crop stem diameter, crop leaf area, crop yield per unit area, precipitation, air temperature and sunshine duration respectively, , , , , , and are crop plant height, crop stem diameter, crop leaf area, crop yield per unit area, precipitation, air temperature and sunshine duration respectively, is the intercept term, is the error term.

[0023] Preferably, in step four, the process of analyzing the improvement effect feedback level and updating the saline-alkali soil improvement effect level using the improvement effect feedback level includes: Based on the improvement effect feedback coefficient output by the improvement effect feedback model, analyze the saline-alkali soil improvement effect level. When the improvement effect feedback coefficient is lower than 0.4, the corresponding small saline-alkali soil area has a low improvement effect; when the improvement effect feedback coefficient is between 0.4 and 0.75, the corresponding small saline-alkali soil area has a medium improvement effect; when the improvement effect feedback coefficient is higher than 0.75, the corresponding small saline-alkali soil area has a high improvement effect, and obtain the improvement effect feedback level; Based on the obtained improvement effect feedback level, when the saline-alkali land soil improvement effect level is the same as the improvement effect feedback level, no update is performed; when the saline-alkali land soil improvement effect level is different from the improvement effect feedback level, the improvement effect feedback level is used to replace the saline-alkali land soil improvement effect level, and the saline-alkali land soil improvement effect level is updated; Number the updated saline-alkali land soil improvement effect level, and integrate the updated saline-alkali land soil improvement effect level number into the improvement effect monitoring dataset.

[0024] Preferably, in step five, the construction process of the digital twin evaluation model includes: Extract the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number from the improvement effect monitoring dataset; Using the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number in the training set, combined with the iterative optimization algorithm, taking the multi-dimensional soil data as the input and the updated saline-alkali land soil improvement effect level number as the output, learn the association between the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number, and train the digital twin evaluation model; Input the multi-dimensional soil data in the test set into the digital twin evaluation model, compare the error between the output result of the digital twin evaluation model and the actual updated saline-alkali land soil improvement effect level number, evaluate the performance of the digital twin evaluation model, adjust the parameters of the digital twin evaluation model, improve the performance of the digital twin evaluation model, and construct the digital twin evaluation model.

[0025] Preferably, in step five, the optimization process of the digital twin evaluation model includes: Using the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number in the training set, combined with the deep neural network algorithm, taking the multi-dimensional soil data as the input and the updated saline-alkali land soil improvement effect level number as the output, learn the non-linear relationship between the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number, and train the deep neural network model; Input the multi-dimensional soil data in the test set into the deep neural network model, compare the error between the output result of the deep neural network model and the actual updated saline-alkali land soil improvement effect level number, feature the parameters of the deep neural network model, optimize the deep neural network model, obtain the final deep neural network model, and output the corresponding updated saline-alkali land soil improvement effect level number through the current multi-dimensional soil data of each small saline-alkali land soil area; Using the updated saline-alkali land soil improvement effect level number output by the deep neural network model, train the digital twin evaluation model, adjust the parameters of the digital twin evaluation model again, optimize the digital twin evaluation model, obtain the final digital twin evaluation model, and combine the current multi-dimensional soil data of each small saline-alkali land soil area to output the corresponding updated saline-alkali land soil improvement effect level number.

[0026] Preferably, in step six, the process of sending the corresponding saline-alkali land soil improvement effect signal based on the output result of the optimized digital twin evaluation model includes: Based on the updated saline-alkali land soil improvement effect level number output by the optimized digital twin evaluation model, match the saline-alkali land soil improvement effect level corresponding to the updated saline-alkali land soil improvement effect level number; Set an electronic display screen in the target research area of the saline-alkali land soil, and in text form, the text form includes the electronic display screen displaying low characters, the electronic display screen displaying medium characters, and the electronic display screen displaying high characters, and display the updated saline-alkali land soil improvement effect level of each small saline-alkali land soil area through the screen; When the updated saline-alkali land soil improvement effect level of the small saline-alkali land soil area is a low improvement effect, the electronic display screen displays low characters; when the updated saline-alkali land soil improvement effect level of the small saline-alkali land soil area is a medium improvement effect, the electronic display screen displays medium characters; when the updated saline-alkali land soil improvement effect level of the small saline-alkali land soil area is a high improvement effect, the electronic display screen displays high characters.

[0027] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for evaluating the improvement effect of saline-alkali soil based on digital twin, characterized in that: It includes the following steps: Step 1: Collect monitoring data on the improvement effect of saline-alkali soil, including multi-dimensional soil data, crop growth data, and meteorological data, and preprocess the collected data; Step 2: Use the preprocessed multi-dimensional soil data to calculate the salinization index, fertility index, porosity, and permeability of the soil, analyze the improvement effect of the saline-alkali soil, and then obtain the improvement effect level of the saline-alkali soil; Step 3: Utilize the preprocessed crop growth data and meteorological data, and combine with the multiple linear regression algorithm to obtain the improvement effect feedback coefficient; Step 4: Based on the obtained improvement effect feedback coefficient, analyze the improvement effect feedback level, and use the improvement effect feedback level to update the improvement effect level of the saline-alkali soil; Step 5: Combine the iterative optimization algorithm with the updated improvement effect level of the saline-alkali soil to construct a digital twin evaluation model, and optimize the digital twin evaluation model through the deep neural network algorithm; Step 6: Based on the output result of the optimized digital twin evaluation model, send out the corresponding improvement effect signal of the saline-alkali soil.

2. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 1, wherein: In the above Step 1, the process of collecting the monitoring data on the improvement effect of the saline-alkali soil includes: Divide the target research area of the saline-alkali soil into several small saline-alkali soil areas with the same area, and number the divided small saline-alkali soil areas respectively; Deploy different collection devices to collect multi-dimensional soil data, crop growth data, and meteorological data of each small saline-alkali soil area. Among them, the collection devices include a pH meter, a conductivity meter, an ion chromatograph, a soil nitrogen, phosphorus, and potassium sensor, a soil corer, a mercury intrusion porosimeter, a laser particle size analyzer, a crop plant height measuring instrument, a crop included angle and stem diameter measuring instrument, a leaf area measuring instrument, a crop yield monitor, a tipping bucket rain gauge, a temperature sensor, and a sunshine duration sensor; The multi-dimensional soil data includes the pH value, total salt content, salt ion concentration, nitrogen content, phosphorus content, potassium content, total volume, particle size, and volume of the inter-particle voids of the soil; the crop growth data includes the plant height, stem diameter, leaf area, and unit area yield of the crop; the meteorological data includes precipitation, temperature, and sunshine duration.

3. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 2, wherein: In the above Step 1, the process of preprocessing the collected monitoring data on the improvement effect includes: Perform data cleaning and data normalization processing on the collected monitoring data on the improvement effect, assign time stamps to the multi-dimensional soil data, crop growth data, and meteorological data, and adjust the time stamps to achieve the synchronization of the collection times of the multi-dimensional soil data, crop growth data, and meteorological data; Correspond the multi-dimensional soil data, crop growth data, and meteorological data with the numbers of their corresponding small saline-alkali soil areas, integrate the multi-dimensional soil data, crop growth data, and meteorological data to generate a monitoring data set on the improvement effect, and divide the monitoring data set on the improvement effect into a training set and a test set.

4. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 3, wherein: In the above Step 2, the calculation process of the salinization index, fertility index, porosity, and permeability of the soil includes: According to the principle of soil salinization, assign weights to the pH value, total salt content, and salt ion concentration of the soil respectively, and use the weighted average method to calculate the soil salinization index; The nitrogen content, phosphorus content, and potassium content of the soil are respectively added with 1 and then the logarithm is taken. Using the logarithmic method, the soil fertility index is calculated. Calculate the proportion of the volume of the voids between soil particles in the total volume of the soil to obtain the soil porosity. Calculate the average value of the soil particle size, and based on the Kozeny-Carman equation, calculate the soil permeability.

5. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 4, wherein: In the second step, the process of obtaining the improvement effect level of saline-alkali soil includes: According to the physical properties of the soil and the principle of chemical equilibrium, weights are respectively assigned to the soil salinization index, soil fertility index, soil porosity, and soil permeability. Using the weighted average method, calculate the product of the soil salinization index and its weight, the product of the soil fertility index and its weight, the product of the soil porosity and its weight, and the product of the soil permeability and its weight respectively, and then sum up the calculation results to obtain the improvement coefficient of saline-alkali soil. Based on the improvement coefficient of saline-alkali soil, analyze the improvement effect of saline-alkali soil, and evaluate the improvement effect level of each small saline-alkali soil area. The improvement effect level of saline-alkali soil includes low improvement effect, medium improvement effect, and high improvement effect. When the improvement coefficient of saline-alkali soil is less than 0.3, the corresponding small saline-alkali soil area has a low improvement effect; when the improvement coefficient of saline-alkali soil is between 0.3 and 0.6, the corresponding small saline-alkali soil area has a medium improvement effect; when the improvement coefficient of saline-alkali soil is greater than 0.6, the corresponding small saline-alkali soil area has a high improvement effect.

6. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 5, wherein: In the third step, the process of obtaining the improvement effect feedback coefficient includes: Extract the crop growth data and meteorological data from the improvement effect monitoring dataset. Using the crop growth data and meteorological data in the training set, combined with the multiple linear regression algorithm, take the crop growth data and meteorological data as inputs and the improvement effect feedback coefficient as the output, learn the linear relationship between the crop growth data, meteorological data, and the improvement effect feedback coefficient, and train the improvement effect feedback model. Input the crop growth data and meteorological data in the test set into the improvement effect feedback model, evaluate the performance of the improvement effect feedback model, optimize the improvement effect feedback model by adjusting the intercept term and regression coefficient of the improvement effect feedback model, obtain the final improvement effect feedback model, and combine the current crop growth data and meteorological data of each small saline-alkali soil area to output the corresponding improvement effect feedback coefficient.

7. A method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 6, characterized in that: In the fourth step, the process of analyzing the improvement effect feedback level and using the improvement effect feedback level to update the improvement effect level of saline-alkali soil includes: Based on the improvement effect feedback coefficient output by the improvement effect feedback model, analyze the improvement effect level of saline-alkali soil. When the improvement effect feedback coefficient is lower than 0.4, the corresponding small saline-alkali soil area has a low improvement effect; when the improvement effect feedback coefficient is between 0.4 and 0.75, the corresponding small saline-alkali soil area has a medium improvement effect; when the improvement effect feedback coefficient is higher than 0.75, the corresponding small saline-alkali soil area has a high improvement effect, and obtain the improvement effect feedback level. Based on the obtained improvement effect feedback level, when the saline-alkali land soil improvement effect level is the same as the improvement effect feedback level, no update is performed; when the saline-alkali land soil improvement effect level is different from the improvement effect feedback level, the improvement effect feedback level is used to replace the saline-alkali land soil improvement effect level, and the saline-alkali land soil improvement effect level is updated; Number the updated saline-alkali land soil improvement effect level, and integrate the updated saline-alkali land soil improvement effect level number into the improvement effect monitoring dataset.

8. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 7, wherein: In step five mentioned above, the construction process of the digital twin evaluation model includes: Extract the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number from the improvement effect monitoring dataset; Using the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number in the training set, combined with the iterative optimization algorithm, taking the multi-dimensional soil data as the input and the updated saline-alkali land soil improvement effect level number as the output, learn the association between the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number, and train the digital twin evaluation model; Input the multi-dimensional soil data in the test set into the digital twin evaluation model, compare the error between the output result of the digital twin evaluation model and the actual updated saline-alkali land soil improvement effect level number, evaluate the performance of the digital twin evaluation model, adjust the parameters of the digital twin evaluation model, improve the performance of the digital twin evaluation model, and construct the digital twin evaluation model.

9. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 8, characterized in that: In step five mentioned above, the optimization process of the digital twin evaluation model includes: Using the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number in the training set, combined with the deep neural network algorithm, taking the multi-dimensional soil data as the input and the updated saline-alkali land soil improvement effect level number as the output, learn the non-linear relationship between the multi-dimensional soil data and the updated saline-alkali land soil improvement effect level number, and train the deep neural network model; Input the multi-dimensional soil data in the test set into the deep neural network model, compare the error between the output result of the deep neural network model and the actual updated saline-alkali land soil improvement effect level number, feature the parameters of the deep neural network model, optimize the deep neural network model, obtain the final deep neural network model, and output the corresponding updated saline-alkali land soil improvement effect level number through the current multi-dimensional soil data of each small saline-alkali land soil area; Use the updated saline-alkali land soil improvement effect level number output by the deep neural network model to train the digital twin evaluation model, adjust the parameters of the digital twin evaluation model again, optimize the digital twin evaluation model, obtain the final digital twin evaluation model, and combine the current multi-dimensional soil data of each small saline-alkali land soil area to output the corresponding updated saline-alkali land soil improvement effect level number.

10. The method for evaluating the improvement effect of saline-alkali soil based on digital twin according to claim 9, characterized in that: In step six mentioned above, the process of sending the corresponding saline-alkali land soil improvement effect signal based on the output result of the digital twin evaluation model includes: The updated saline-alkali soil improvement effect level number output based on the optimized digital twin evaluation model is matched with the saline-alkali soil improvement effect level corresponding to the updated saline-alkali soil improvement effect level number; An electronic display screen is set in the target research area of the saline-alkali soil, and in text form, the text form includes low characters displayed on the electronic display screen, medium characters displayed on the electronic display screen, and high characters displayed on the electronic display screen, and the updated saline-alkali soil improvement effect levels of each small saline-alkali soil area are displayed through the screen; When the updated saline-alkali soil improvement effect level of the small saline-alkali soil area is a low improvement effect, low characters are displayed on the electronic display screen; when the updated saline-alkali soil improvement effect level of the small saline-alkali soil area is a medium improvement effect, medium characters are displayed on the electronic display screen; when the updated saline-alkali soil improvement effect level of the small saline-alkali soil area is a high improvement effect, high characters are displayed on the electronic display screen.

Images