Comprehensive evaluation method for saline-alkaline tolerance of medicago sativa

Abstract

The invention discloses a comprehensive evaluation method for saline-alkaline tolerance of medicago sativa, and relates to the technical field of plant saline-alkaline tolerance testing, by integrating soil salinity S and soil permeability P in a soil environment data set SED and actual salinity accumulation rate Rac and leaf moisture content W of a root system and a leaf in a growth and salinity accumulation data set PGSA, the saline-alkaline tolerance of the medicago sativa is evaluated, and the saline-alkaline tolerance of the medicago sativa is evaluated. Scientific evaluation is provided for the adaptability of medicago sativa in saline-alkali soil, the saline-alkaline tolerance score T of medicago sativa is made by predicting the salinity accumulation rate Rpr, then the saline-alkaline tolerance score T is compared with a preset saline-alkaline tolerance evaluation threshold value Tth, the adaptability of plants is judged, and targeted intervention suggestions are given according to the comparison result. According to the method, the actual planting data and the plant growth data of the medicago sativa after intervention are collected, the fluctuation trend of the data is analyzed, and the salt accumulation model is further iteratively optimized, so that the prediction accuracy and adaptability of the model are continuously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of plant salt and alkali tolerance testing, and specifically provides a comprehensive evaluation method for the salt and alkali tolerance of alfalfa. Background Art

[0002] In the current fields of ecology and agricultural science, the salt and alkali tolerance of plants is an important research direction. Especially for agricultural production and ecological restoration and management work, how to improve the growth ability of plants in saline-alkali soil has become a challenge that needs to be solved urgently worldwide. Saline-alkali land is widely distributed in arid and semi-arid regions, which usually face problems of water shortage and soil salinization, making the growth of crops and plants encounter serious obstacles. Therefore, studying the salt and alkali tolerance of plants, especially evaluating and optimizing the growth performance of plants in saline-alkali environments, has become an important task in the fields of botany and agricultural engineering. Among them, alfalfa, as one of the most economically valuable leguminous forages and ecological restoration plants globally, is often used for the improvement of saline-alkali land and the restoration of plant diversity due to its high feeding nutritional value and yield, as well as its wide adaptability and strong stress resistance.

[0003] Currently, for the research on salt and alkali tolerant plants such as alfalfa, existing evaluation methods mostly focus on the analysis of single factors or short-term plant performance. For example, many evaluation methods only make a preliminary judgment by detecting the salt accumulation in plants or only relying on the salinity index of the soil, but these methods have certain limitations. The relationship between the salt accumulation rate and soil permeability has often not been fully emphasized. And soil permeability itself affects the flow of water and the water absorption ability of plants, thereby affecting the salt and alkali tolerance of plants. Many existing methods do not consider the interaction of these factors, resulting in poor accuracy and predictive ability of the evaluation results.

[0004] In addition, traditional evaluation methods usually rely on manual observation or laboratory analysis, which have great limitations in time and space and cannot comprehensively reflect the dynamic changes of the saline-alkali soil environment. Therefore, in practical applications of the existing technology, the changes in saline-alkali soil cannot be obtained in real time, nor can the growth status and salt and alkali tolerance of plants be evaluated in a timely manner, resulting in great limitations in its application effect. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology, the present invention provides a comprehensive evaluation method for the salt and alkali tolerance of alfalfa, which solves the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A comprehensive evaluation method for the salt and alkali tolerance of alfalfa, comprising the following steps: S1. Collect the soil salinity concentration S and soil permeability P of the alfalfa planting area through soil salinity sensors and permeability sensors to form the soil environment dataset SED of alfalfa. S2. Monitor the growth status and salt accumulation of alfalfa plants, obtain the actual salt accumulation rates Rac of alfalfa roots and leaves and the leaf water content W, and form the growth and salt accumulation dataset PGSA. S3. Based on the obtained soil environment dataset SED and growth and salt accumulation dataset PGSA, establish a salt accumulation model between the salt accumulation rate and soil permeability. After training the salt accumulation model, output the predicted salt accumulation rate Rpr. S4. Integrate the salt accumulation model with the growth and salt accumulation dataset PGSA to obtain the salt tolerance score T of alfalfa. S5. Compare the salt tolerance score T with the preset plant salt tolerance evaluation threshold Tth to obtain the soil adaptation result of the alfalfa planting area, and generate intervention suggestions for alfalfa according to the soil adaptation result. S6. Collect the actual planting data and plant growth data of alfalfa after implementing the intervention suggestions, and iteratively optimize the salt accumulation model according to the fluctuation trend of the data.

[0007] Preferably, S1 includes S11 and S12. S11. Use a soil salinity sensor to collect the soil salinity concentration data of the alfalfa planting area. The soil salinity sensor determines the concentration of dissolved salts in the soil by the conductivity measurement method, and marks it as the soil salinity concentration S of the alfalfa planting area. The soil salinity concentration S is obtained through the following calculation formula: ; In the formula, S(i) represents the soil salinity concentration at time point i, EC represents the conductivity, and k represents the calibration coefficient, which is set according to the specific preset measurement standard.

[0008] Preferably, S12. Use a soil permeability sensor to collect the permeability data of the alfalfa planting area, which reflects the flow rate of water in the soil of the alfalfa planting area. The soil permeability sensor obtains the flow rate by measuring the infiltration rate of water in the soil of the alfalfa planting area using a permeameter, and marks it as the soil permeability P of the alfalfa planting area. Integrate the soil salinity concentration S and the soil permeability P to obtain the soil environment dataset SED of alfalfa, which reflects the root water absorption ability of alfalfa and its adaptability in the saline-alkali environment. Among them, the soil environment dataset SED = {S(i), P(i)|i ∈ N}, where N represents the total number of time points. The soil permeability P is obtained through the following calculation formula: ; In the formula, P(i) represents the soil permeability at time point i, V represents the volume of water flowing through the soil, A represents the cross-sectional area of the soil, and t represents the time required for infiltration.

[0009] Preferably, the S2 includes S21 and S22; S21. By placing a salt sensor in the alfalfa root system, the salt accumulation in the alfalfa root system is monitored in real time. By recording the rate of increase in the salt concentration in the alfalfa root system over a certain period of time, it is marked as the actual salt accumulation rate Rac of the alfalfa root system, which reflects the accumulation process of salt in the alfalfa root system and its adaptability in the saline-alkali environment; The actual salt accumulation rate Rac is obtained through the following calculation formula: ; In the formula, Rac(i) represents the salt accumulation rate at time point i, Sroot(i) and Sroot(i - 1) respectively represent the root system salt concentrations at time point i and time point i - 1, which are specifically obtained by recording with a salt sensor, and △t represents the time interval.

[0010] Preferably, S22. By using a leaf water sensor to monitor the water content W of the alfalfa plant leaves, the water content W reflects the water absorption ability of the alfalfa and its growth state in the saline-alkali environment. The leaf water sensor includes using a near-infrared water sensor for monitoring, and the growth and salt accumulation dataset PGSA is obtained by integrating the salt accumulation rate R and the water content W; The water content W is obtained through the following calculation formula: ; In the formula, W(i) represents the water content of the leaves at time point i, Mwet(i) represents the fresh weight of the leaves at time point i, and Mdry(i) represents the dry weight of the leaves at time point i.

[0011] Preferably, the S3 includes S31; S31. Based on the obtained soil environment dataset SED and growth and salt accumulation dataset PGSA, normalization processing is carried out to eliminate the influence of different dimensions between the data in the soil environment dataset SED and growth and salt accumulation dataset PGSA. The normalization processing includes using the Min-Max normalization processing method to establish a salt accumulation model between the salt accumulation rate and the soil permeability. The salt accumulation model includes using the linear regression method to establish. After training the salt accumulation model, the predicted salt accumulation rate Rpr is output; The predicted salt accumulation rate Rpr is obtained through the following calculation formula: ; In the formula, Rpr(i) represents the predicted salt accumulation rate at time point i, r1, r2, r3, and r4 respectively represent the regression coefficients of the soil salt concentration S, soil permeability P, water content W, and actual salt accumulation rate Rac at time point i, and r1 + 2 + r3 + r4 = 1. The specific values are set by the user, and γ represents the error term.

[0012] Preferably, the S4 includes S41; S41. Integrate the predicted salt accumulation rate Rpr(i) at time point i output by the salt accumulation model with the water content W and actual salt accumulation rate Rac at time point i in the normalized growth and salt accumulation dataset PGSA to obtain the salt tolerance score T of alfalfa, reflecting the comprehensive alkali tolerance adaptability of alfalfa; ; In the formula, T(i) represents the salt tolerance score at time point i, and β and λ respectively represent the influence coefficients of the actual salt accumulation rate Rac(i) and soil salt concentration S(i) at time point i. The specific values are set by the user.

[0013] Preferably, the S5 includes S51; S51. Compare the obtained salt tolerance score T(i) at time point i with the preset plant salt tolerance evaluation threshold Tth to obtain the soil adaptation result of the alfalfa planting area, and generate an intervention suggestion for alfalfa according to the soil adaptation result; The soil adaptation result is obtained through the following comparison method: When the salt tolerance score T(i) at time point i ≥ the plant salt tolerance evaluation threshold Tth, obtain the soil adaptation result as the adaptation result, obtain the current soil alkali tolerance adaptation result of alfalfa as adaptation, and generate an intervention suggestion for alfalfa, including continuing to plant alfalfa in the current planting area and maintaining the current alfalfa planting measures; When the salt tolerance score T(i) at time point i < the plant salt tolerance evaluation threshold Tth, obtain the soil adaptation result as the non - adaptation result, indicating that the current soil alkali tolerance adaptation result of alfalfa is non - adaptation, and generate an intervention suggestion for alfalfa, including improving the saline - alkali soil in the current alfalfa planting area. Improving the saline - alkali soil includes applying soil conditioners, adjusting the irrigation amount, and adjusting the soil organic matter content.

[0014] Preferably, the S6 includes S61 and S62; S61. After the intervention suggestions are generated, they are sent to the relevant maintenance pending list for processing. When the intervention suggestions are processed in the pending list, the actual planting data and plant growth data of alfalfa after the application of the intervention suggestions are collected, including the soil salt concentration S, soil permeability P, actual salt accumulation rate Rac, and leaf water content W, to form a new soil environment dataset SED(new) and a growth and salt accumulation dataset PGSA(new).

[0015] Preferably, based on the obtained soil environment dataset SED(new) and growth and salt accumulation dataset PGSA(new), compare the soil environment dataset SED and growth and salt accumulation dataset PGSA at the time point i of the implementation of the intervention suggestions, obtain the fluctuation amounts of the soil salt concentration S, soil permeability P, actual salt accumulation rate Rac, and leaf water content W, and obtain the cumulative fluctuation amount △BL after accumulation. When |cumulative fluctuation amount △BL|≥0.3, perform iterative optimization on the salt accumulation model. The iterative optimization includes using the least squares method to optimize and iterate the regression coefficients r1, r2, r3, and r4.

[0016] The present invention provides a comprehensive evaluation method for the salt and alkali tolerance of alfalfa, having the following beneficial effects: (1) By integrating the soil salinity S and soil permeability P in the soil environment dataset SED, and the actual salt accumulation rate Rac and leaf water content W of the roots and leaves in the growth and salt accumulation dataset PGSA, it provides a scientific evaluation for the adaptability of alfalfa in saline-alkali soil. Based on the obtained soil environment dataset SED and growth and salt accumulation dataset PGSA, a salt accumulation model is established. The salt and alkali tolerance score T of alfalfa is obtained by predicting the salt accumulation rate Rpr, and then compared with the preset salt and alkali tolerance evaluation threshold Tth to judge the adaptability of the plant, and targeted intervention suggestions are given according to the comparison results. The actual planting data and plant growth data of alfalfa after the implementation of the intervention are collected, and their fluctuation trends are analyzed, and further iterative optimization is performed on the salt accumulation model, so as to continuously improve the prediction accuracy and adaptability of the model. It solves the problems of relying only on a single parameter, static evaluation, and lack of real-time monitoring of intervention effects in traditional evaluation methods.

[0017] (2) By installing a salt sensor and a water sensor in the root system and leaves of alfalfa respectively, the actual salt accumulation rate Rac of the alfalfa root system is calculated to reflect the salt accumulation process in the root system and the adaptability of alfalfa in saline-alkali environments. Then, the water content W of the alfalfa leaves is monitored using the leaf water sensor to reflect the plant's water absorption capacity and growth status in saline-alkali environments. By integrating the salt accumulation rate Rac and the water content W, a growth and salt accumulation dataset PGSA is generated, providing comprehensive and real-time growth data for subsequent salt tolerance assessment. The advantage is that by using the real-time data of the dynamic root salt accumulation rate Rac and the leaf water content W, the growth changes of alfalfa under different environmental conditions can be accurately captured, especially its performance under saline-alkali stress. Through the real-time monitoring of these two important physiological parameters, the saline-alkali adaptability of alfalfa can be evaluated more precisely.

[0018] (3) By comparing the salt tolerance score T with the preset plant salt tolerance assessment threshold Tth, the soil adaptation result of alfalfa is generated, and intervention suggestions are put forward based on the assessment result. Further, by collecting the actual planting and growth data after intervention and analyzing their fluctuation amounts, based on the changes in the cumulative fluctuation amounts, the salt accumulation model is iteratively optimized to ensure that the model is continuously optimized and can cope with the challenges of different environmental changes. In this way, the planting management of alfalfa can be more flexible and precise, taking effective improvement measures in a timely manner, avoiding the problems of being fixed and lacking dynamic adjustment in traditional methods, and thus ensuring the optimal production and ecological governance effects of alfalfa in saline-alkali environments. Brief Description of the Drawings

[0019] Figure 1 Schematic diagram of the steps of a comprehensive alfalfa salt tolerance assessment method of the present invention; Figure 2 For data fluctuation trend analysis. Detailed Embodiments

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0021] Embodiment 1 The present invention provides a comprehensive alfalfa salt tolerance assessment method. Please refer to Figure 1 , including the following steps: S1. Collect the soil salinity concentration S and soil permeability P of the alfalfa planting area through soil salinity sensors and permeability sensors to form the soil environment dataset SED of alfalfa; S2. Monitor the growth status and salt accumulation of alfalfa plants, obtain the actual salt accumulation rates Rac of the alfalfa roots and leaves and the leaf water content W, and form the growth and salt accumulation dataset PGSA; S3. Based on the obtained soil environment dataset SED and growth and salt accumulation dataset PGSA, establish a salt accumulation model between the salt accumulation rate and soil permeability. After training the salt accumulation model, output the predicted salt accumulation rate Rpr; S4. Integrate the salt accumulation model with the growth and salt accumulation dataset PGSA to obtain the salt tolerance score T of alfalfa; S5. Compare the salt tolerance score T with the preset plant salt tolerance evaluation threshold Tth to obtain the soil adaptation result of the alfalfa planting area, and generate intervention suggestions for alfalfa according to the soil adaptation result; S6. Collect the actual planting data and plant growth data of alfalfa after implementing the intervention suggestions, and iteratively optimize the salt accumulation model according to the fluctuation trend of the data.

[0022] In this embodiment, by integrating the soil salinity S and soil permeability P in the soil environment dataset SED, as well as the actual salt accumulation rates Rac of the roots and leaves and the leaf water content W in the growth and salt accumulation dataset PGSA, a scientific evaluation is provided for the adaptability of alfalfa in saline-alkali soil. Based on the obtained soil environment dataset SED and growth and salt accumulation dataset PGSA, a salt accumulation model is established. The salt tolerance score T of alfalfa is obtained by predicting the salt accumulation rate Rpr. Subsequently, the score T is compared with the preset salt tolerance evaluation threshold Tth to judge the adaptability of the plant, and targeted intervention suggestions are given according to the comparison result. The actual planting data and plant growth data of alfalfa after implementing the intervention are collected and their fluctuation trends are analyzed, and the salt accumulation model is further iteratively optimized, so as to continuously improve the prediction accuracy and adaptability of the model. It solves the problems of relying only on a single parameter, static evaluation, and lack of real-time intervention effect monitoring in traditional evaluation methods. Through dynamic optimization and multi-dimensional data integration, this method makes the salt tolerance evaluation of alfalfa more scientific, accurate and has the ability of continuous improvement, providing more reliable decision-making support for saline-alkali soil improvement and alfalfa planting.

[0023] Example 2 This embodiment is an explanatory description carried out in Example 1. Please refer to Figure 1 , specifically: The S1 includes S11 and S12; S11. Use a soil salinity sensor to collect the soil salinity concentration data of the alfalfa planting area. The soil salinity sensor determines the concentration of dissolved salts in the soil through the conductivity measurement method, and marks it as the soil salinity concentration S of the alfalfa planting area; The soil salinity concentration S is obtained through the following calculation formula: ; In the formula, S(i) represents the soil salinity concentration at time point i, EC represents the conductivity, and k represents the calibration coefficient, which is set according to the specific preset measurement standard.

[0024] S12. Use a soil permeability sensor to collect the permeability data of the alfalfa planting area, which reflects the flow rate of water in the soil of the alfalfa planting area. The soil permeability sensor obtains the flow rate by measuring the infiltration rate of water in the soil of the alfalfa planting area using a permeameter, and marks it as the soil permeability P of the alfalfa planting area. Integrate the soil salinity concentration S and the soil permeability P to obtain the soil environment dataset SED of alfalfa, which reflects the root water absorption ability of alfalfa and its adaptability in the saline-alkali environment; Among them, the soil environment dataset SED = {S(i), P(i)|i ∈ N}, where N represents the total number of time points; The soil permeability P is obtained through the following calculation formula: ; In the formula, P(i) represents the soil permeability at time point i, V represents the volume of water flowing through the soil. The volume of water flowing through the soil V represents the volume of water flowing through the soil, which is usually measured by the amount of water used in the infiltration experiment. In the permeability test, a certain volume of water is usually poured onto the soil sample, and then the amount of water passing through the soil is calculated. A represents the cross-sectional area of the soil. The cross-sectional area of the soil A represents the area of the soil through which the water flows. This area is the cross-sectional area of the soil sample, which is usually the defined area size in the permeability test, and this cross-sectional area can be calculated based on the shape and size of the soil sample. t represents the time required for infiltration. The time required for infiltration t represents the time for the water to flow through the soil, which is the time value measured through the experiment, that is, the time for the water to pass through the soil sample, usually referring to the time from when the water starts to infiltrate into the soil until it completely infiltrates.

[0025] In this embodiment, by using a soil salinity sensor and a soil permeability sensor to collect the soil salinity concentration S and soil permeability P data of the alfalfa planting area respectively, the soil salinity concentration is obtained by the conductivity measurement method, and then the soil permeability is calculated by combining the osmosis experiment data. Further integrating these two data forms a soil environment dataset SED, providing comprehensive basic soil environment data for the subsequent alfalfa adaptability evaluation. This dataset can reflect in detail the root water absorption ability of alfalfa in the saline-alkali environment and its adaptability to soil salinization. In addition, by accurately measuring and calculating the soil salinity concentration S and soil permeability P, the impact of saline-alkali soil on the growth of alfalfa can be captured more precisely, providing a scientific basis for improvement measures, thereby helping to improve the optimization effect of the growth environment of alfalfa in saline-alkali soil. The greatest advantage of this method is that through the precise quantification of the soil salinity concentration S and soil permeability P, more scientific decision-making support can be provided, thus ensuring the continuous evaluation and dynamic improvement of the salt tolerance of alfalfa.

[0026] Example 3 This embodiment is an explanatory description carried out in Example 2. Please refer to Figure 1 , specifically: S2 includes S21 and S22; S21. By placing a salinity sensor in the alfalfa root system, the salt accumulation in the alfalfa root system is monitored in real time. By recording the rate of increase in the salt concentration in the alfalfa root system over a certain period of time, it is marked as the actual salt accumulation rate Rac of the alfalfa root system, reflecting the cumulative process of salt in the alfalfa root system and its adaptability in the saline-alkali environment; The actual salt accumulation rate Rac is obtained through the following calculation formula: ; In the formula, Rac(i) represents the salt accumulation rate at time point i, Sroot(i) and Sroot(i - 1) respectively represent the root salt concentrations at time point i and time point i - 1, which are specifically obtained by recording with a salinity sensor, and △t represents the time interval.

[0027] S22. By using a leaf water sensor to monitor the water content W of the alfalfa plant leaves, the water content W reflects the water absorption ability of alfalfa and its growth state in the saline-alkali environment. A high water content W usually means that alfalfa has a good water absorption ability, while a low water content W may mean that alfalfa is facing water stress, especially in the saline-alkali environment. The leaf water sensor includes using a near-infrared water sensor for monitoring. By integrating the salt accumulation rate R and the water content W, a growth and salt accumulation dataset PGSA is obtained; The water content W is obtained through the following calculation formula: ; In the formula, W(i) represents the moisture content of the leaf at time point i, Mwet(i) represents the fresh weight of the leaf at time point i, and the fresh weight Mwet(i) of the leaf at time point i is obtained by collecting the mass of the alfalfa leaf without removing the moisture, and this parameter is obtained by directly weighing the fresh mass of the alfalfa leaf. Mdry(i) represents the dry weight of the leaf at time point i, and the dry weight Mdry(i) of the leaf at time point i is the mass of the solid part remaining after completely removing the moisture in the leaf, which is usually obtained by drying the leaf to a constant weight.

[0028] In this embodiment, by installing a salinity sensor and a moisture sensor in the roots and leaves of alfalfa respectively, the precise monitoring and dynamic evaluation of its growth in a saline-alkali environment are realized. By placing a salinity sensor in the roots of alfalfa, the salinity accumulation in the roots is monitored in real time, and the actual salinity accumulation rate Rac of the alfalfa roots is calculated to reflect the accumulation process of salinity in the roots and the adaptability of alfalfa in a saline-alkali environment. Then, a leaf moisture sensor is used to monitor the moisture content W of the alfalfa leaves, reflecting the plant's water absorption capacity and growth state in a saline-alkali environment. By integrating the salinity accumulation rate Rac and the moisture content W, a growth and salinity accumulation dataset PGSA is generated, providing comprehensive and real-time growth data for the subsequent evaluation of alfalfa salt tolerance. The advantage is that by using the real-time data of the dynamic root salinity accumulation rate Rac and the leaf moisture content W, the growth changes of alfalfa under different environmental conditions can be accurately captured, especially its performance under saline-alkali stress. Through the real-time monitoring of these two important physiological parameters, the saline-alkali adaptability of alfalfa can be evaluated more precisely, providing a scientific basis for saline-alkali soil improvement and alfalfa cultivation strategies, and avoiding the problem of relying only on limited static data in traditional methods.

[0029] Example 4 This embodiment is an explanatory description based on Embodiment 3. Please refer to Figure 1 and Figure 2 , specifically: S3 includes S31; S31. Based on the obtained soil environment dataset SED and growth and salinity accumulation dataset PGSA, normalization processing is performed to eliminate the influence of different dimensions between the data in the soil environment dataset SED and growth and salinity accumulation dataset PGSA. The normalization processing includes using the Min-Max normalization processing method to establish a salinity accumulation model between the salinity accumulation rate and soil permeability. The salinity accumulation model is established by using the linear regression method. After training the salinity accumulation model, the predicted salinity accumulation rate Rpr is output. The predicted salinity accumulation rate Rpr is obtained through the following calculation formula: ; In the formula, Rpr(i) represents the predicted salt accumulation rate at time point i, r1, r2, r3, and r4 represent the regression coefficients of the soil salt concentration S, soil permeability P, water content W, and actual salt accumulation rate Rac at time point i, respectively, and r1 + r2 + r3 + r4 = 1. The specific values are set by the user. γ represents the error term, and the soil salt concentration S, soil permeability P, water content W, and actual salt accumulation rate Rac at time point i are dimensionless data.

[0030] Specific data example description for obtaining the predicted salt accumulation rate Rpr: Suppose there are the following data: The soil environment dataset SED and the growth and salt accumulation dataset PGSA include: soil salt concentration S = 15 dS / m; soil permeability P = 1.5 cm / s; leaf water content W = 20%; actual salt accumulation rate Rac = 5 g / kg*h; After normalizing the soil environment dataset SED and the growth and salt accumulation dataset PGSA, we obtain: Soil salt concentration S = 0.5; soil permeability P = 0.5; leaf water content W = 0.5; actual salt accumulation rate Rac = 0.375; Set r1, r2, r3, and r4 to be 0.3, 0.2, 0.25, and 0.2 respectively; error term γ = 0.01; Substitute into the formula for calculating the predicted salt accumulation rate Rpr to obtain: Predicted salt accumulation rate Rpr = 0.3 * 0.5 + 0.2 * 0.5 + 0.25 * 0.5 + 0.2 * 0.375 = 0.41.

[0031] The said S4 includes S41; S41 integrates the predicted salt accumulation rate Rpr(i) at time point i output by the salt accumulation model, the water content W at time point i in the growth and salt accumulation dataset PGSA after normalization, and the actual salt accumulation rate Rac to obtain the salt tolerance score T of alfalfa, reflecting the comprehensive salt tolerance adaptation ability of alfalfa; ; In the formula, T(i) represents the salt tolerance score at time point i. The higher the value of the salt tolerance score T(i) at time point i, the more adaptable alfalfa is to the saline-alkali environment. β and λ represent the influence coefficients of the actual salt accumulation rate Rac(i) and soil salt concentration S(i) at time point i respectively. The specific values are set by the user.

[0032] In this embodiment, by performing Min-Max normalization on the data in the soil environment dataset SED and the growth and salt accumulation dataset PGSA, the influence between different dimensions is eliminated, enabling the data to be processed under the same standard. Based on the normalized data, a salt accumulation model is established using the linear regression method. By training the model, the predicted salt accumulation rate Rpr is output, providing a reliable basis for subsequent salt tolerance evaluation. Integrating the predicted salt accumulation rate Rpr with the actual salt accumulation rate Rac and water content W after normalization, the salt tolerance score T of alfalfa is obtained, which reflects the comprehensive adaptability of alfalfa in the saline-alkali environment. The higher the score, the stronger the adaptability of alfalfa to the saline-alkali environment. Through precise normalization and the salt accumulation model established based on actual data, the differences between environmental and growth data can be eliminated, making the prediction results more accurate. Moreover, based on the mutual relationship between soil salt concentration S, soil permeability P, water content W, and actual salt accumulation rate Rac, a comprehensive evaluation of the salt tolerance of alfalfa can be provided, not only improving the accuracy of the model but also flexibly adjusting the evaluation criteria according to different environmental conditions to ensure a more scientific evaluation of the adaptability of alfalfa to the saline-alkali environment.

[0033] Example 5 This example is an explanatory note based on Example 4. Please refer to Figure 1 , specifically: The S5 includes S51; S51. By comparing the salt tolerance score T(i) at time point i obtained with the preset plant salt tolerance evaluation threshold Tth, the soil adaptation result of the alfalfa planting area is obtained, and an intervention suggestion for alfalfa is generated according to the soil adaptation result; The soil adaptation result is obtained through the following comparison method: When the salt tolerance score T(i) at time point i ≥ the plant salt tolerance evaluation threshold Tth, the soil adaptation result is obtained as the adaptation result, indicating that the current soil salt tolerance adaptation result of alfalfa is adaptation. An intervention suggestion for alfalfa is generated, including continuing to plant alfalfa in the current planting area and maintaining the current alfalfa planting measures; When the salt tolerance score T(i) at time point i < the plant salt tolerance evaluation threshold Tth, the soil adaptation result is obtained as the non-adaptation result, indicating that the current soil alkali tolerance adaptation result of alfalfa is non-adaptation. An intervention suggestion for alfalfa is generated, including improving the saline-alkali soil in the current alfalfa planting area. Improving the saline-alkali soil includes applying modifiers, adjusting the irrigation amount, and adjusting the soil organic matter content.

[0034] The S6 includes S61 and S62; S61. After the intervention suggestions are generated, they are sent to the relevant management and protection pending list for processing. After the intervention suggestions are processed in the pending list, the actual alfalfa planting data and plant growth data after the application of the intervention suggestions are collected, including soil salt concentration S, soil permeability P, actual salt accumulation rate Rac, and leaf water content W, to form a new soil environment dataset SED(new) and a growth and salt accumulation dataset PGSA(new).

[0035] Based on the obtained soil environment dataset SED(new) and growth and salt accumulation dataset PGSA(new), compare the soil environment dataset SED and growth and salt accumulation dataset PGSA at the time point i of the intervention suggestions, obtain the fluctuation amounts of soil salt concentration S, soil permeability P, actual salt accumulation rate Rac, and leaf water content W, and after accumulation, obtain the cumulative fluctuation amount △BL. When |cumulative fluctuation amount △BL| ≥ 0.3, perform iterative optimization on the salt accumulation model. The iterative optimization includes using the least squares method to optimize and iterate the regression coefficients r1, r2, r3, and r4.

[0036] In this embodiment, by comparing the salt tolerance score T with the preset plant salt tolerance evaluation threshold Tth, the soil adaptation result of alfalfa is generated, and intervention suggestions are proposed based on the evaluation result. When the salt tolerance score T is greater than or equal to the plant salt tolerance evaluation threshold Tth, it indicates that alfalfa is suitable for the current soil environment and the current planting measures can be continued; when the salt tolerance score T is less than the plant salt tolerance evaluation threshold Tth, it indicates that the adaptability of alfalfa in the current environment is poor and the saline-alkali soil needs to be improved. Step S6 further analyzes the fluctuation amount by collecting the actual planting and growth data after the intervention, and based on the change of the cumulative fluctuation amount, performs iterative optimization on the salt accumulation model, optimizes the regression coefficients by the least squares method, improves the accuracy of the model, not only provides a soil adaptability evaluation based on real-time data feedback, but also ensures the continuous optimization of the model by dynamically adjusting the salt accumulation model, and can cope with the challenges of different environmental changes. In this way, the planting management of alfalfa can be more flexible and accurate, and effective improvement measures can be taken in a timely manner, avoiding the problems of being fixed and lacking dynamic adjustment in the traditional method, so as to ensure the optimal alfalfa production and ecological governance effect in the saline-alkali environment.

[0037] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirits of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A comprehensive evaluation method for salt-alkali tolerance of alfalfa, characterized in that: The following steps are involved: S1, collect the soil salt concentration S and soil permeability P of the alfalfa planting area through soil salinity sensors and permeability sensors to form the soil environment dataset SED of alfalfa; S2, monitor the growth status and salt accumulation of alfalfa plants, obtain the actual salt accumulation rate Rac and leaf water content W of alfalfa roots and leaves, and form the growth and salt accumulation data set PGSA; S3. Based on the acquired soil environment dataset SED and growth and salt accumulation dataset PGSA, a salt accumulation model between salt accumulation rate and soil permeability is established. After training the salt accumulation model, the predicted salt accumulation rate Rpr is output; S4, based on the integration of the salt accumulation model and the growth and salt accumulation dataset PGSA, the salt-alkaline tolerance score T of alfalfa was obtained; S5. Obtain soil adaptation results of alfalfa planting areas by comparing the salt-alkaline tolerance score T with the preset plant salt-alkaline tolerance assessment threshold Tth, and generate intervention recommendations for alfalfa based on the soil adaptation results; S6. Collect the actual planting data and plant growth data of alfalfa after implementing the intervention recommendations, and iteratively optimize the salt accumulation model based on the fluctuation trend of the data.

2. The method for comprehensive evaluation of salt-alkali tolerance of alfalfa according to claim 1, characterized in that: Said S1 includes S11 and S12; S11, using a soil salinity sensor to collect soil salt concentration data in the alfalfa planting area, the soil salinity sensor determines the concentration of dissolved salts in the soil by a conductivity measurement method, and marks it as the soil salt concentration S of the alfalfa planting area; The soil salt concentration S is obtained by the following calculation formula: ； Where S(i) represents the soil salt concentration at time point i, EC represents the electrical conductivity, k represents the calibration coefficient, and the specific preset measurement standard setting.

3. A method for comprehensive evaluation of salt-alkali tolerance of alfalfa according to claim 2, characterized in that: S12. Use a soil permeability sensor to collect permeability data of the alfalfa planting area to reflect the flow rate of water in the soil of the alfalfa planting area. The soil permeability sensor uses an infiltrator to measure the permeability rate of water in the soil of the alfalfa planting area to obtain the flow rate, which is marked as the soil permeability P of the alfalfa planting area. Integrate the soil salt concentration S and the soil permeability P to obtain the soil environment data set SED of alfalfa, which reflects the root water absorption capacity of alfalfa and its adaptability in saline-alkali environment. Among them, soil environment dataset SED={S(i), P(i)|i∈N}, N represents the total number of time points; The soil permeability P is obtained by the following calculation formula: ； Where P(i) represents the soil permeability at time point i, V represents the volume of water flowing through the soil, A represents the cross-sectional area of ​​the soil, and t represents the time required for infiltration.

4. The comprehensive evaluation method for salt-alkali tolerance of alfalfa according to claim 1, characterized in that: The S2 includes S21 and S22; S21. By placing a salt sensor in the root system of alfalfa, the salt accumulation of the alfalfa root system is monitored in real time. By recording the rate of increase of salt concentration in the alfalfa root system within a certain period of time, it is marked as the actual salt accumulation rate Rac of the alfalfa root system, reflecting the accumulation process of salt in the alfalfa root system and reflecting the adaptability to the saline-alkali environment; The actual salt accumulation rate Rac is obtained by the following calculation formula: ； Where Rac(i) represents the salt accumulation rate at time point i, Sroot(i) and Sroot(i-1) represent the root salt concentrations at time point i and time point i-1, respectively, which are recorded by the salt sensor, and △t represents the time interval.

5. A comprehensive evaluation method for salt-alkali tolerance of alfalfa according to claim 4, characterized in that: S22, monitoring the moisture content W of the leaves of alfalfa plants by using a leaf moisture sensor, wherein the moisture content W reflects the water absorption capacity of alfalfa and the growth state in a saline-alkali environment, and the leaf moisture sensor includes using a near-infrared moisture sensor for monitoring, and obtaining a growth and salt accumulation data set PGSA by integrating the salt accumulation rate R and the moisture content W; The moisture content W is obtained by the following calculation formula: ； Where W(i) represents the water content of the leaves at time point i, Mwet(i) represents the fresh weight of the leaves at time point i, and Mdry(i) represents the dry weight of the leaves at time point i.

6. A comprehensive evaluation method for salt-alkali tolerance of alfalfa according to claim 5, characterized in that: The S3 includes S31; S31, based on the obtained soil environment dataset SED and the growth and salt accumulation dataset PGSA, normalization processing is performed to eliminate the influence of different dimensions between the data in the soil environment dataset SED and the growth and salt accumulation dataset PGSA, the normalization processing includes using the Min-Max normalization processing method to establish a salt accumulation model between the salt accumulation rate and soil permeability, the salt accumulation model includes using a linear regression method to establish, after training the salt accumulation model, outputting a predicted salt accumulation rate Rpr; The predicted salt accumulation rate Rpr is obtained by the following calculation formula: ； Where Rpr(i) represents the predicted salt accumulation rate at time point i, r1, r2, r3 and r4 represent the regression coefficients of soil salt concentration S, soil permeability P, water content W and actual salt accumulation rate Rac at time point i, respectively, and r1+r2+r3+r4=1. The specific value is set by the user, and γ represents the error term.

7. A comprehensive evaluation method for salt-alkali tolerance of alfalfa according to claim 6, characterized in that: The S4 includes S41; S41, integrating the predicted salt accumulation rate Rpr(i) at time point i output by the salt accumulation model with the moisture content W at time point i in the normalized growth and salt accumulation data set PGSA and the actual salt accumulation rate Rac, to obtain the salt-alkaline tolerance score T of alfalfa, reflecting the comprehensive salt-alkaline tolerance adaptability of alfalfa; ； Where T(i) represents the salt-alkaline tolerance score at time point i, β and λ represent the influence coefficients of the actual salt accumulation rate Rac(i) and soil salt concentration S(i) at time point i, respectively. The specific values ​​are set by the user.

8. The comprehensive evaluation method for salt-alkali tolerance of alfalfa according to claim 7, characterized in that: The S5 includes S51; S51, obtaining the soil adaptation result of the alfalfa planting area by comparing the obtained salt-alkali tolerance score T(i) at time point i with the preset plant salt-alkali tolerance assessment threshold Tth, and generating intervention suggestions for alfalfa according to the soil adaptation result; The soil adaptation results were obtained by comparing: When the salt-alkaline tolerance score T(i) at time point i ≥ the plant salt-alkaline tolerance assessment threshold Tth, the soil adaptation result is obtained as the adaptation result, indicating that the current soil salt-alkaline tolerance adaptation result of alfalfa is adaptation, and intervention recommendations for alfalfa are generated, including continuing to plant alfalfa in the current planting area and maintaining the current alfalfa planting measures; When the salt-alkali tolerance score T(i) at time point i is less than the plant salt-alkali tolerance assessment threshold Tth, the soil adaptation result is obtained as unadaptable, indicating that the current soil salt-alkali tolerance adaptation result of alfalfa is unadaptable, and intervention recommendations for alfalfa are generated, including improving saline-alkali soil in the current alfalfa planting area. Improving saline-alkali soil includes applying amendments, adjusting irrigation amount and adjusting soil organic quality.

9. A comprehensive evaluation method for salt-alkali tolerance of alfalfa according to claim 8, characterized in that: The S6 includes S61 and S62; S61. After the intervention suggestion is generated, it is sent to the relevant maintenance waiting list for processing. When the intervention suggestion is processed in the waiting list, the actual planting data and plant growth data of alfalfa after the intervention suggestion is applied are collected, including soil salt concentration S, soil permeability P, actual salt accumulation rate Rac and leaf moisture content W, to form a new soil environment data set SED (new) and growth and salt accumulation data set PGSA (new).

10. A method for comprehensive evaluation of salt-alkali tolerance of alfalfa according to claim 9, characterized in that: Based on the acquired soil environment dataset SED (new) and growth and salt accumulation dataset PGSA (new), the soil environment dataset SED and growth and salt accumulation dataset PGSA at the intervention recommendation time point i were compared to obtain the fluctuations of soil salt concentration S, soil permeability P, actual salt accumulation rate Rac and leaf water content W. After accumulation, the cumulative fluctuation △BL was obtained. When |cumulative fluctuation △BL|≥0.3, the salt accumulation model was iteratively optimized. The iterative optimization included iteratively optimizing the r1, r2, r3 and r4 regression coefficients using the least squares method.

Images