Method, system and equipment for optimizing simulation precision of regional scale process model

Abstract

The invention discloses a regional scale process model simulation precision optimization method, system and device, and relates to the field of model optimization, and the method comprises the steps: inputting a to-be-optimized crop parameter combination into a crop-water productivity model, and determining the result variable yield and canopy coverage; performing cross validation on the result variable yield and the canopy coverage to determine an evaluation index; constructing a multi-target index evaluation optimization model for optimizing the key parameters of the regional scale PCMs; wherein the multi-objective index evaluation optimization model takes the sum of Nash efficiency coefficients NSE of minimizing canopy coverage and result variable yield in a training set and a test set as an objective function, and takes a root-mean-square error RMSE as a constraint condition; and inputting the evaluation indexes into a multi-target index evaluation optimization model, and solving the multi-target index evaluation optimization model by adopting a parallel algorithm group formed by a plurality of meta-heuristic optimization methods so as to optimize the key parameters of the regional scale PCMs and obtain an optimal crop parameter combination.

Description

Technical Field

[0001] The present invention relates to the technical field of model optimization, and particularly relates to a method, system and device for optimizing the simulation accuracy of a regional-scale process model. Background Art

[0002] Process-based Crop Models (PCMs) are important tools for modern agricultural scientific research and resource management. Currently, based on the division of main driving factors, common PCMs include three categories: soil factors (hydrodynamics and water balance models), photosynthesis factors (CO2 and radiation-driven), and anthropogenic factor-driven.

[0003] From the perspective of model calibration, parameter values cannot be directly measured, are recommended in the form of ranges, and have a large number of possible combinations, etc., which make it difficult to obtain the optimal parameter combination by manually calibrating the model, and thus it is difficult to effectively improve the simulation accuracy of the regional-scale process model PCMs. Summary of the Invention

[0004] The present invention provides a method, system and device for optimizing the simulation accuracy of a regional-scale process model to solve the above problems existing in the prior art, that is, the problem of how to improve the simulation accuracy of the regional-scale process model PCMs in the prior art. The present invention provides a method for optimizing the simulation accuracy of a regional-scale process model, and the method includes:

[0005] Input the crop parameter combination to be optimized into the crop-water productivity model AquaCrop-OSPy to determine the simulated crop yield and canopy cover; wherein, the crop parameter combination includes product data, measured data and calibration data;

[0006] Perform cross-validation on the crop yield and canopy cover by using the Leave-One-Out Cross-Validation method (LOOCV) to determine the evaluation index corresponding to the crop parameter combination; wherein, the evaluation index includes the Nash-Sutcliffe Efficiency coefficient (NSE) and the Root Mean Square Error (RMSE).

[0007] Construct a multi-objective index evaluation and optimization model for optimizing the key parameters of regional-scale PCMs;

[0008] Take the sum of the Nash-Sutcliffe Efficiency coefficients (NSE) of the canopy cover and crop yield in the training set and the test set as the objective function to be minimized, and take the Root Mean Square Errors (RMSE) of the canopy cover and crop yield in the training set and the test set as the constraint conditions to train the multi-objective index evaluation and optimization model;

[0009] Input the evaluation indicators into the trained multi-objective indicator evaluation and optimization model, and use a parallel algorithm group composed of multiple meta-heuristic optimization methods to solve the multi-objective indicator evaluation and optimization model, optimize the crop parameter combination, and obtain the optimal crop parameter combination.

[0010] Optionally, the step of using a parallel algorithm group composed of multiple meta-heuristic optimization methods to solve the multi-objective indicator evaluation and optimization model specifically includes:

[0011] Use a parallel algorithm including UNSGA3, MOEA / D, SPEA2, AGEMOEA, CTAEA, and SMSEMOA to solve the multi-objective indicator evaluation and optimization model.

[0012] Optionally, the product data includes soil hydraulic parameters, soil texture, and meteorological data.

[0013] Optionally, the measured data includes yield, leaf area index LAI, irrigation data, and field management data.

[0014] Optionally, the calibration data includes the study area, research object, key crop parameters, search interval, and search step.

[0015] The present invention provides a system for optimizing the simulation accuracy of a regional-scale process model, including:

[0016] An acquisition module, configured to input the crop parameter combination to be optimized into the crop-water productivity model AquaCrop-OSPy to determine the simulated crop yield and canopy coverage; wherein the crop parameter combination includes product data, measured data, and calibration data;

[0017] A cross-validation module, configured to cross-validate the crop yield and canopy coverage by using the leave-one-out cross-validation method LOOCV to determine the evaluation indicators corresponding to the crop parameter combination; wherein the evaluation indicators include the Nash efficiency coefficient NSE and the root mean square error RMSE;

[0018] A construction module, configured to construct a multi-objective indicator evaluation and optimization model for optimizing the key parameters of regional-scale PCMs;

[0019] A training module, configured to use the sum of the Nash efficiency coefficients NSE of the canopy coverage and crop yield in the training set and the test set as the objective function, and use the root mean square error RMSE of the canopy coverage and crop yield in the training set and the test set as the constraint condition to train the multi-objective indicator evaluation and optimization model;

[0020] Optimization module, configured to input evaluation metrics into the trained multi-objective metric evaluation and optimization model, and use a parallel algorithm group composed of multiple meta-heuristic optimization methods to solve the multi-objective metric evaluation and optimization model, optimize the crop parameter combination, and obtain the optimal crop parameter combination.

[0021] The present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above-mentioned regional-scale process model simulation accuracy optimization method is implemented.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a regional-scale process model simulation accuracy optimization method, which combines the meta-heuristic optimization method with LOOCV to optimize the key crop parameter combinations of PCMs under limited measured data; according to the evaluation metrics obtained from the LOOCV process, with the goal of minimizing the sum of the Nash-Sutcliffe Efficiency (NSE) of canopy cover and result variable yield between the training set and the test set as the objective function, and the Root Mean Square Error (RMSE) as the constraint condition, a multi-objective metric evaluation and optimization model is constructed. Using a parallel algorithm group to solve the multi-objective metric evaluation and optimization model can obtain the optimal crop parameter combination, thereby effectively improving the simulation accuracy and calibration efficiency of PCMs at the regional scale. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0024] Figure 1 It is a flowchart of a regional-scale process model simulation accuracy optimization method provided by an embodiment of the present invention;

[0025] Figure 2 It is a technical roadmap of a regional-scale process model simulation accuracy optimization method provided by an embodiment of the present invention;

[0026] Figure 3 It is a schematic diagram of the leave-one-out cross-validation method provided by an embodiment of the present invention;

[0027] Figure 4 It is a schematic diagram of a computer device for a regional-scale process model simulation accuracy optimization method provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. 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.

[0029] The technical solutions of the present invention and how the technical solutions of the present invention solve the above technical problems will be described in detail below with specific embodiments. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0030] As Figure 1 and Figure 2 shown, an optimization method for the simulation accuracy of a regional-scale process model shown in this embodiment includes:

[0031] S1: Input the crop parameter combination to be optimized into the crop-water productivity model AquaCrop-OSPy to determine the simulated crop yield and canopy cover; wherein, the crop parameter combination includes product data, measured data, and calibration data.

[0032] Exemplarily, representative spatio-temporal difference product data, measured data, and calibration data can be retrieved from multiple academic databases.

[0033] Optionally, the product data includes soil hydraulic parameters, soil texture, and meteorological data, the measured data includes yield, LAI, and field management data, and the calibration data includes the study area, study object, key crop parameters, search interval, and search step.

[0034] S2: Cross-validate the crop yield and canopy cover by using the leave-one-out cross-validation method LOOCV to determine the evaluation index corresponding to the crop parameter combination; wherein, the evaluation index includes the Nash efficiency coefficient NSE and the root mean square error RMSE.

[0035] Generally, AquaCrop, which is driven by moisture, is a representative general crop model for daily scale water balance and is mainly applied to arid regions where water is a key limiting factor for crop production. AquaCrop only requires a small number of explicit parameters, and the input data is intuitive, clear, and easy to obtain. It has been widely used for the formulation of irrigation systems, optimization of management measures, and prediction of crop yields for various crops and different regions. It has the ability to simulate crop yields at different scales of point, county, and region, and has great potential in guiding agricultural irrigation water conservation in arid regions. In the AquaCrop model, CC is an intuitive indicator that is directly related to crop evapotranspiration and biomass.

[0036] Canopy cover development stage:

[0037]

[0038] Canopy cover senescence process:

[0039]

[0040] Among them, CC0 is the initial CC when the emergence rate is 90%, CC x is the maximum CC, CGC is the canopy growth coefficient, CDC is the canopy senescence coefficient, and t is the number of days after sowing.

[0041] The key process of converting CC into yield and biomass can be expressed as:

[0042] CC * = 1.72CC - CC 2 + 0.30CC 3

[0043]

[0044] B = Ks b WP * ΣTr / ET0

[0045] Y = f HI HI0B

[0046] Among them, CC * represents the corrected CC, mainly considering the change in inter-row reflectance and masking effect caused by partial canopy overlap; T r is the crop transpiration; K s is the soil water stress coefficient, including soil water stress, stomatal closure stress, and soil salinity stress; is the maximum crop transpiration coefficient corresponding to fully irrigated soil and fully covered canopy; Ks b is the air temperature stress coefficient; WP * is the normalized water productivity; Y represents crop yield; fHI It is an adjustment factor for water stress before yield formation, the impact of pollination failure, and water stress during yield formation; HI0 is the reference harvest index; B is the final biomass.

[0047] The relationship between canopy cover CC and leaf area index LAI can be expressed as:

[0048] CC = 1.005·(1 - e -0.6*LAI ) 1.2

[0049] S3: Construct a multi-objective index evaluation and optimization model for optimizing the key parameters of PCMs at the regional scale.

[0050] S4: Take the sum of the Nash-Sutcliffe efficiency coefficient NSE of canopy cover and crop yield in the training set and the test set as the objective function, and use the root mean square error RMSE of canopy cover and crop yield in the training set and the test set as the constraint conditions to train the multi-objective index evaluation and optimization model.

[0051] Among them, the multi-objective index evaluation and optimization model takes the sum of the Nash-Sutcliffe efficiency coefficient NSE of canopy cover and the resulting variable yield in the training set and the test set as the objective function, and uses the root mean square error RMSE as the constraint condition.

[0052] As Figure 3 shown, by adopting the leave-one-out cross-validation method LOOCV, by removing one sample each time and using the remaining samples to estimate the regression model parameters, it is suitable for learning small sample data sets. LOOCV can avoid the errors caused by the random division of the data set, can better reflect the distribution characteristics of the original samples, and the verification process is completely repeatable; Figure 2 where: RMSE_Train i and NSE_Train i respectively represent the root mean square error and the Nash-Sutcliffe efficiency coefficient of the training set during the i-th cross-validation (i = 1, 2,..., n); RMSE_Test and NSE_Test respectively represent the root mean square error and the Nash-Sutcliffe efficiency coefficient of the test set after all cross-validations are completed.

[0053] S5: Input the evaluation index into the trained multi-objective index evaluation and optimization model, use a parallel algorithm group composed of multiple meta-heuristic optimization methods to solve the multi-objective index evaluation and optimization model, optimize the crop parameter combination, and obtain the optimal crop parameter combination.

[0054] Exemplarily, according to the limitations of actual collectible data and research objectives, this application uses the measured process variable canopy cover CC and the result variable yield as the calibration indicators of the model, and selects the dimensionless NSE as the optimization objective and the dimensional RMSE as the constraint on the training set and the test set, respectively.

[0055] Objective 1: Minimize the NSE of the training set:

[0056]

[0057] where: F1 is the sum of the average NSE of the crop yield and CC training set obtained by the leave-one-out cross-validation method, and "-" is to set the fitness value as the negative value of the objective function; is the average NSE of the training set yield; is the average NSE of the training set CC.

[0058] Objective 2: Minimize the NSE of the test set:

[0059] Min F2 = -{NSE Y,Test + NSE CC,Test}

[0060] where: F2 is the sum of the NSE of the yield and CC test set obtained by the leave-one-out cross-validation method, and "-" is to set the fitness value as the negative value of the objective function; NSE Y,Test is the NSE of the test set yield; NSE CC,Test is the NSE of the test set CC.

[0061] Constraint conditions:

[0062]

[0063] where, and are the average RMSE of the yield and CC training set respectively; RMSE Y,Test and RMSE CC,Test are the RMSE of the yield and CC test set respectively; RMSE Y,crop and RMSE CC,crop are the constraint values of the yield and CC respectively, and take different values according to different calibrated crops. The penalty function method is used to handle the constraints, and the constraints play a role in accelerating the convergence of the algorithm and meeting the minimum simulation accuracy requirements of the model.

[0064] S5: By inputting the evaluation indicators into the multi-objective indicator evaluation and optimization model, a parallel algorithm group composed of multiple meta-heuristic optimization methods is used to solve the multi-objective indicator evaluation and optimization model, and the optimal crop parameter combination is iteratively obtained.

[0065] Exemplarily, each parameter in the crop parameter combination has its own search range and search step size. There are N combinations of crop parameters formed by the parameters, and this application needs to find the optimal combination. The search range is comprehensively determined based on the range values of the default parameters of the model, existing knowledge, historical data, or through random search and multiple runs; the search step size can be set according to the actual requirements of each parameter to achieve the best balance. During the iteration process, by substituting the crop parameter combination into the PCMs, the better combinations will be retained according to the evaluation indicators and the optimization model. Then the algorithm will generate new combinations and substitute the new and old crop parameter combinations into the PCMs again, continuously repeating the above process. Its output constitutes the state variables of the optimization model in the next time period: substituting into the PCMs will obtain evaluation indicators, and optimizing according to these indicators, that is, the state variables of the optimization model in the next time period.

[0066] The above is the method for optimizing the simulation accuracy of the regional scale process model provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding system for optimizing the simulation accuracy of the regional scale process model, including:

[0067] An acquisition module, configured to input the crop parameter combination to be optimized into the crop-water productivity model AquaCrop-OSPy to determine the simulated crop yield and canopy coverage; wherein, the crop parameter combination includes product data, measured data, and calibration data;

[0068] A cross-validation module, configured to perform cross-validation on the crop yield and canopy coverage by using the leave-one-out cross-validation method LOOCV to determine the evaluation indicators corresponding to the crop parameter combination; wherein, the evaluation indicators include the Nash efficiency coefficient NSE and the root mean square error RMSE;

[0069] A construction module, configured to construct a multi-objective index evaluation and optimization model for optimizing the key parameters of the regional scale PCMs;

[0070] A training module, configured to use the sum of the Nash efficiency coefficients NSE of the canopy coverage and crop yield in the training set and the test set as the objective function to be minimized, and use the root mean square errors RMSE of the canopy coverage and crop yield in the training set and the test set as the constraint conditions to train the multi-objective index evaluation and optimization model;

[0071] An optimization module, configured to input the evaluation indicators into the trained multi-objective index evaluation and optimization model, and use a parallel algorithm group composed of multiple meta-heuristic optimization methods to solve the multi-objective index evaluation and optimization model, optimize the crop parameter combination, and obtain the optimal crop parameter combination.

[0072] For the specific limitations of the regional-scale process model simulation accuracy optimization system, reference can be made to the limitations of the regional-scale process model simulation accuracy optimization method in the foregoing text, which will not be elaborated here. Each module in the above regional-scale process model simulation accuracy optimization system can be implemented in whole or in part by software, hardware, and their combinations. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0073] The present invention also provides Figure 4 a schematic structural diagram of the computer device shown in, as Figure 4 shown, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, other hardware required for other services may also be included. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the regional-scale process model simulation accuracy optimization method provided in the above embodiments.

[0074] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in the present invention.

Claims

1. A method for optimizing the simulation accuracy of a regional-scale process model, characterized in that Including: Input the crop parameter combination to be optimized into the crop-water productivity model AquaCrop-OSPy to determine the simulated crop yield and canopy cover; wherein, the crop parameter combination includes product data, measured data, and calibration data; Through cross-validation of the crop yield and canopy cover using the leave-one-out cross-validation method LOOCV, determine the evaluation indicators corresponding to the crop parameter combination; wherein, the evaluation indicators include the Nash-Sutcliffe efficiency coefficient NSE and the root mean square error RMSE; Construct a multi-objective index evaluation and optimization model for optimizing the key parameters of PCMs at the regional scale; Taking the minimization of the sum of the Nash-Sutcliffe efficiency coefficients NSE of the canopy cover and crop yield in the training set and the test set as the objective function, and taking the root mean square errors RMSE of the canopy cover and crop yield in the training set and the test set as the constraints, train the multi-objective index evaluation and optimization model; Input the evaluation indicators into the trained multi-objective index evaluation and optimization model, and use a parallel algorithm group composed of multiple metaheuristic optimization methods to solve the multi-objective index evaluation and optimization model, optimize the crop parameter combination, and obtain the optimal crop parameter combination.

2. The method for optimizing the simulation accuracy of the regional scale process model according to claim 1, wherein The use of a parallel algorithm group composed of multiple metaheuristic optimization methods to solve the multi-objective index evaluation and optimization model specifically includes: Using a parallel algorithm including UNSGA3, MOEA / D, SPEA2, AGEMOEA, CTAEA, and SMSEMOA to solve the multi-objective index evaluation and optimization model.

3. The method for optimizing the simulation accuracy of the regional scale process model according to claim 1, wherein The product data includes soil hydraulic parameters, soil texture, and meteorological data.

4. The method for optimizing the simulation accuracy of the regional scale process model according to claim 1, wherein The measured data includes yield, leaf area index LAI, irrigation data, and field management data.

5. The method for optimizing the simulation accuracy of the regional scale process model according to claim 1, wherein, The calibration data includes the study area, the study object, the key crop parameters, the search interval, and the search step.

6. An optimization system for the simulation accuracy of a regional-scale process model, characterized in that, Including: An acquisition module for inputting the crop parameter combination to be optimized into the crop-water productivity model AquaCrop-OSPy to determine the simulated crop yield and canopy cover; wherein, the crop parameter combination includes product data, measured data, and calibration data; A cross-validation module for cross-validating the crop yield and canopy cover using the leave-one-out cross-validation method LOOCV to determine the evaluation indicators corresponding to the crop parameter combination; wherein, the evaluation indicators include the Nash-Sutcliffe efficiency coefficient NSE and the root mean square error RMSE; A construction module for constructing a multi-objective index evaluation and optimization model for optimizing the key parameters of PCMs at the regional scale; A training module for taking the minimization of the sum of the Nash-Sutcliffe efficiency coefficients NSE of the canopy cover and crop yield in the training set and the test set as the objective function, and taking the root mean square errors RMSE of the canopy cover and crop yield in the training set and the test set as the constraints, to train the multi-objective index evaluation and optimization model; An optimization module for inputting the evaluation indicators into the trained multi-objective index evaluation and optimization model, and using a parallel algorithm group composed of multiple metaheuristic optimization methods to solve the multi-objective index evaluation and optimization model, optimize the crop parameter combination, and obtain the optimal crop parameter combination.

7. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method for optimizing the simulation accuracy of the regional scale process model according to any one of claims 1 to 5 above.

Images