A method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil

Abstract

The present invention discloses a method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil, comprising: obtaining soil data and desulfurized gypsum data of desulfurized gypsum improving saline-alkali soil, wherein the soil data includes original soil data and improved soil data; predicting the original soil data to obtain predicted soil data, comparing the predicted soil data with the improved soil data to obtain the impact ratio; obtaining change characteristics according to the impact ratio and desulfurized gypsum data, and performing an impact analysis on the impact ratio based on the change characteristics to obtain a soil improvement index; constructing a soil improvement effect evaluation model according to the soil improvement index, and optimizing the soil improvement effect evaluation model; inputting the data to be evaluated into the soil improvement effect evaluation model, and outputting the evaluation result. The method can accurately evaluate the effect of desulfurized gypsum on improving saline-alkali soil by establishing a prediction model, screening change characteristics, calculating the soil improvement index, and optimizing the evaluation model, and provides a scientific basis for soil improvement.

Description

Technical Field

[0001] The invention relates to the technical field of soil improvement, and in particular to a method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil. Background Art

[0002] Saline-alkali soil is a widely distributed low-yield soil type, which is mainly characterized by high salt concentration in the soil solution and alkaline pH value. These characteristics seriously affect the growth of crops and the ecological balance of the soil. For a long time, people have tried to improve saline-alkali soil through various methods, such as deep plowing, irrigation and salt washing, and application of organic fertilizers, but these methods are often costly and the effects are difficult to sustain. With the development of industry, desulfurized gypsum has gradually come into people's view as an industrial by-product. Desulfurized gypsum contains a large amount of calcium ions, which can be replaced with sodium ions in the soil, thereby reducing the salinity and alkalinity of the soil, showing the potential for improving saline-alkali soil. However, how to scientifically and accurately evaluate the effect of desulfurized gypsum on improving saline-alkali soil is a key issue that needs to be solved urgently. Traditional evaluation methods lack systematicity and scientificity and cannot fully reflect the improvement effect. Therefore, it is particularly important to develop a new evaluation method. Summary of the invention

[0003] The purpose of the present invention is to provide a method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil.

[0004] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0005] The present invention comprises the following steps:

[0006] Acquire soil data of saline-alkali soil improved by desulfurized gypsum and desulfurized gypsum data, wherein the soil data includes original soil data and improved soil data;

[0007] Predicting the original soil data to obtain predicted soil data, and comparing the predicted soil data with the improved soil data to obtain an impact ratio;

[0008] Obtaining a change characteristic according to the impact ratio and the desulfurized gypsum data, and performing an impact analysis on the impact ratio based on the change characteristic to obtain a soil improvement index;

[0009] Constructing a soil improvement effect evaluation model according to the soil improvement index, and optimizing the soil improvement effect evaluation model;

[0010] The data to be evaluated is input into the soil improvement effect evaluation model, and the evaluation result is output.

[0011] Furthermore, a method for predicting the original soil data to obtain predicted soil data includes:

[0012] The original soil data is the saline-alkali soil data before improvement. The original soil data is arranged in chronological order to obtain time series data, and the stability of the time series data is tested:

[0013]

[0014] In the formula, Z t represents the value of the time series data at time t, γ is a constant term, αt is a time trend term, θ is the coefficient of the autoregressive part, ΔZ t-j Represents Z t The difference term of , m is the number of difference terms, δ j is the coefficient of the difference term, ζ t is the random disturbance term,

[0015] When θ=0, the time series data is stable. When θ<0, the time series data is non-stationary. The non-stationary time series data is differentiated to obtain the stable time series data.

[0016] Using VAR model for forecasting:

[0017] Y t =β+A1Y t-1 +A2Y t-2 +…+A p Y t-p +BX t +μ t

[0018] where Y t is the k-dimensional endogenous variable column vector of the t-th time series data, is the historical data of the target time series data, t=1,2,...,T, T is the number of samples of the time series data, β is the k-dimensional intercept term column vector, X is the d-dimensional exogenous variable column vector, is the time series data other than the target time series data, A1,...,A p is a k×k dimensional matrix to be estimated, B is a k×d dimensional matrix to be estimated, p is the lag order of the VAR model, μ is a k dimensional error vector,

[0019] Log-likelihood function:

[0020]

[0021] Where N is the number of variables, Σ is the covariance matrix of the error term, ∈ t is the error term for the t-th observation,

[0022] Use the information criterion to select the optimal number of lags:

[0023]

[0024] Where AIC represents the Akaike information criterion, and the lag order that minimizes AIC is the optimal lag order.

[0025] Further, the method for obtaining the change characteristics according to the impact ratio and the desulfurization gypsum data includes:

[0026] The desulfurized gypsum data is the concentration data of the desulfurized gypsum applied. The desulfurized gypsum data and the impact ratio are normalized and preprocessed to establish data points. The desulfurized gypsum data is fitted with the impact ratio based on the SVR model to screen the change characteristics:

[0027] Decision function:

[0028]

[0029] in<w,x> represents the inner product of w and x, w is the weight vector, x is the feature matrix, b is the bias term, y i is the i-th desulfurization gypsum data, K(x i ,x) is the kernel function, K(x i ,x)=<φ(x i ),φ(x)>,φ(x) is the mapping function from the original feature space to the high-dimensional feature space,α i and is the Lagrange multiplier, is the number of data points,

[0030] The optimization goal of the SVR model is:

[0031]

[0032] Among them, ξ i is the slack variable, C is the penalty coefficient, w i and b i are the i-th weight coefficient of the weight vector and the i-th element of the bias term, respectively. λ is the regularization parameter that controls the complexity of the weight vector and the bias term.

[0033] The log-likelihood function of the SVR model is:

[0034]

[0035] in is the noise variance of the i-th desulfurization gypsum data,

[0036] The objective function of the SVR model is:

[0037]

[0038] The absolute value of the weight coefficient is taken as the feature importance, and the recursive feature elimination algorithm is used for feature screening.

[0039] Furthermore, a method for obtaining a soil improvement index by performing an impact analysis on the impact ratio based on the change characteristics includes:

[0040] Based on prior knowledge, the impact ratio is divided into positive impact and negative impact. For the impact ratio of positive impact, it is kept as a positive value, and for the impact ratio of negative impact, it is converted into a negative value. The desulfurized gypsum data, the characteristic importance of the change characteristics and the impact ratio are normalized and preprocessed to calculate the soil improvement index:

[0041]

[0042] Where L N is the desulfurized gypsum data, q is the index of the changing feature, Q is the number of changing features, w q is the feature importance of the qth changing feature, L Qq is the influence ratio of the qth changing feature.

[0043] Furthermore, a method for constructing a soil improvement effect evaluation model according to the soil improvement index comprises:

[0044] The soil data, desulfurization gypsum data and soil improvement index are divided into training sets and test sets. The training set is used to train an integrated model composed of multiple random forest algorithms to learn the prediction pattern of the soil improvement index, establish a soil improvement effect evaluation model, and use the test set to optimize the soil improvement effect evaluation model.

[0045] Furthermore, the method for optimizing the soil improvement effect evaluation model comprises:

[0046] Based on the test set, the simulated annealing algorithm is used to optimize the parameters of the soil improvement effect evaluation model:

[0047] Temperature update formula:

[0048]

[0049] Among them, T new is the new temperature value, T old is the old temperature value, ΔE avg is the average energy change in the last m iterations, ΔE max is the maximum value of energy change in the last m iterations, is the exponent of the control weight, γ is the decay factor, t is the current number of iterations,

[0050] Acceptance probability formula:

[0051]

[0052] Where P(ΔE) is the probability of accepting a new solution, ΔE is the energy difference between the new solution and the current solution, ∈ is the noise term drawn from the normal distribution to simulate randomness, k is the Boltzmann constant, T is the current temperature,

[0053] Solution update:

[0054]

[0055] where F new (x) is the updated objective function value, w i is the weight of the i-th objective function, n is the number of objective functions, f i (x) is the i-th objective function, p is the number of objective functions, ν j is the penalty weight of the jth constraint function, g j (x) is the jth constraint function,

[0056] Parameter update formula:

[0057]

[0058] where x new is the updated parameter value, x old is the current parameter value, η is the current learning rate, is the objective function at x old The gradient at, ζ is the parameter that controls the influence of global information, G is the global search direction, indicating the direction of the historical optimal solution, N(0,σ 2 ) is the normal distribution disturbance, σ is the standard deviation of the normal distribution disturbance,

[0059] Search based on dynamic neighborhood size and historical best solutions:

[0060]

[0061] Where Δx is the change in the parameter, σ nb is a parameter that controls the size of the neighborhood, T max is the maximum number of iterations, x best and x worst are the best solution and the worst solution found so far, respectively.

[0062] Learning rate update:

[0063]

[0064] Among them, η0 is the initial learning rate, accept rate is the current acceptance rate, is the target acceptance rate and δ is an exponent that adjusts the sensitivity of the learning rate.

[0065] In a second aspect, an embodiment of the present application further provides an electronic device, including:

[0066] A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.

[0067] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0068] The beneficial effects of the present invention are:

[0069] The present invention is a method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil. Compared with the prior art, the present invention has the following technical effects:

[0070] The present invention can scientifically and accurately evaluate the effect of desulfurized gypsum on improving saline-alkali soil, optimize the improvement strategy, and improve the economic and ecological benefits of soil improvement through prediction model establishment, impact ratio analysis, change feature screening, soil improvement index calculation and evaluation model optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A flowchart of the steps of a method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil according to the present invention;

[0072] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0073] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0074] A method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil of the present invention comprises the following steps:

[0075] like Figure 1 As shown, in this embodiment, the following steps are included:

[0076] Obtain soil data of saline-alkali soil improved by desulfurized gypsum and desulfurized gypsum data, wherein the soil data includes original soil data and improved soil data; the soil data includes soil pH value at 0 to 20 cm, soil exchangeable sodium percentage, soil extract conductivity, salt content and soil organic matter content;

[0077] In the actual evaluation, two groups of original soil data at different times were collected: salt content (mg / kg): [15000, 16000, 14000, 15500, 16500], [15500, 16500, 14500, 15500, 17000], pH value: [8.2, 8.3, 8.1, 8.4, 8.5], [8.3, 8.4, 8.2, 8.5, 8.6], soil exchangeable sodium percentage (%): [0.15, 0.16, 0.14, 0.15, 0.16], [0.16, 0.17, 0.15, 0.16, 0.17], soil extract conductivity (dS / m): [4.2, 4.3, 4.1, 4.2, 4.4], [4.3, 4.4, 4.2, 4.3, 4.5], soil organic matter Content (%): [1.2, 1.1, 1.3, 1.2, 1.1], [1.3, 1.2, 1.4, 1.3, 1.2]; Improved soil data: Salt content (mg / kg): [10000, 11000, 9000, 10500, 11500], pH value: [7.8, 7.9, 7.7, 7.85, 7.95], soil exchangeable sodium percentage (% ): [0.08, 0.09, 0.07, 0.08, 0.09], soil extract conductivity (dS / m): [2.1, 2.2, 2.0, 2.1, 2.3], soil organic matter content (%): [1.5, 1.4, 1.6, 1.5, 1.4]; desulfurized gypsum data are desulfurized gypsum concentration: [0.05, 0.06, 0.04, 0.05, 0.06];

[0078] Predicting the original soil data to obtain predicted soil data, and comparing the predicted soil data with the improved soil data to obtain an impact ratio;

[0079] In the actual evaluation, the predicted soil data are: predicted salt content (mg / kg): [16000, 17000, 15000, 16000, 17500], predicted pH value: [8.3, 8.4, 8.2, 8.5, 8.7], predicted soil exchangeable sodium percentage (%): [0.17, 0.18, 0.16, 0.17, 0.18], predicted soil extract conductivity (dS / m): [4.4, 4.5, 4.3, 4.4, 4.6], predicted soil organic matter content (%): [1 .3, 1.2, 1.4, 1.3, 1.2]; affected proportions: salt content: [-38%, -35%, -40%, -34%, -34%], pH value: [-6%, -6%, -6%, -8%, -9%], soil exchangeable sodium percentage: [-53%, -50%, -56%, -53%, -50%], soil extract conductivity: [-52%, -51%, -53%, -52%, -50%], soil organic matter content: [15%, 17%, 14%, 15%, 17%];

[0080] Obtaining a change characteristic according to the impact ratio and the desulfurized gypsum data, and performing an impact analysis on the impact ratio based on the change characteristic to obtain a soil improvement index;

[0081] In the actual evaluation, the change characteristics are soil pH, soil exchangeable sodium percentage and soil extract conductivity. The positive effects in the soil improvement index are the reduction rate of soil pH, the reduction rate of soil exchangeable sodium percentage and the reduction rate of soil extract conductivity. The soil improvement index is: [0.83, 0.8, 0.86, 0.83, 0.8];

[0082] Constructing a soil improvement effect evaluation model according to the soil improvement index, and optimizing the soil improvement effect evaluation model;

[0083] The data to be evaluated is input into the soil improvement effect evaluation model, and the evaluation result is output.

[0084] In this embodiment, the method of predicting the original soil data to obtain predicted soil data includes:

[0085] The original soil data is the saline-alkali soil data before improvement. The original soil data is arranged in chronological order to obtain time series data, and the stability of the time series data is tested:

[0086]

[0087] In the formula, Z t represents the value of the time series data at time t, γ is a constant term, αt is a time trend term, θ is the coefficient of the autoregressive part, ΔZ t-j Represents Z tThe difference term of , m is the number of difference terms, δ j is the coefficient of the difference term, ζ t is the random disturbance term,

[0088] When θ=0, the time series data is stable. When θ<0, the time series data is non-stationary. The non-stationary time series data is differentiated to obtain the stable time series data.

[0089] Using VAR model for forecasting:

[0090] Y t =β+A1Y t-1 +A2Y t-2 +…+A p Y t-p +BX t +μ t

[0091] where Y t is the k-dimensional endogenous variable column vector of the t-th time series data, is the historical data of the target time series data, t=1,2,...,T, T is the number of samples of the time series data, β is the k-dimensional intercept term column vector, X is the d-dimensional exogenous variable column vector, is the time series data other than the target time series data, A1,...,A p is a k×k dimensional matrix to be estimated, B is a k×d dimensional matrix to be estimated, p is the lag order of the VAR model, μ is a k dimensional error vector,

[0092] Log-likelihood function:

[0093]

[0094] Where N is the number of variables, Σ is the covariance matrix of the error term, ∈ t is the error term for the t-th observation,

[0095] Use the information criterion to select the optimal number of lags:

[0096]

[0097] Where AIC represents the Akaike information criterion, and the lag order that minimizes AIC is the optimal lag order.

[0098] In this embodiment, the method for obtaining the change characteristics according to the impact ratio and the desulfurization gypsum data includes:

[0099] The desulfurized gypsum data is the concentration data of the desulfurized gypsum applied. The desulfurized gypsum data and the impact ratio are normalized and preprocessed to establish data points. The desulfurized gypsum data is fitted with the impact ratio based on the SVR model to screen the change characteristics:

[0100] Decision function:

[0101]

[0102] in<w,x> represents the inner product of w and x, w is the weight vector, x is the feature matrix, b is the bias term, y i is the i-th desulfurization gypsum data, K(x i ,x) is the kernel function, K(x i ,x)=<φ(x i ),φ(x)>,φ(x) is the mapping function from the original feature space to the high-dimensional feature space,α i and is the Lagrange multiplier, is the number of data points,

[0103] The optimization goal of the SVR model is:

[0104]

[0105] Among them, ξ i is the slack variable, C is the penalty coefficient, w i and b i are the i-th weight coefficient of the weight vector and the i-th element of the bias term, respectively. λ is the regularization parameter that controls the complexity of the weight vector and the bias term.

[0106] The log-likelihood function of the SVR model is:

[0107]

[0108] in is the noise variance of the i-th desulfurization gypsum data,

[0109] The objective function of the SVR model is:

[0110]

[0111] The absolute value of the weight coefficient is taken as the feature importance, and the recursive feature elimination algorithm is used for feature screening.

[0112] In this embodiment, the method for obtaining the soil improvement index by performing an impact analysis on the impact ratio based on the change characteristics includes:

[0113] Based on prior knowledge, the impact ratio is divided into positive impact and negative impact. For the impact ratio of positive impact, it is kept as a positive value, and for the impact ratio of negative impact, it is converted into a negative value. The desulfurized gypsum data, the characteristic importance of the change characteristics and the impact ratio are normalized and preprocessed to calculate the soil improvement index:

[0114]

[0115] Where L N is the desulfurized gypsum data, q is the index of the changing feature, Q is the number of changing features, w q is the feature importance of the qth changing feature, L Qq is the influence ratio of the qth changing feature.

[0116] In this embodiment, the method for constructing a soil improvement effect evaluation model according to the soil improvement index includes:

[0117] The soil data, desulfurization gypsum data and soil improvement index are divided into training sets and test sets. The training set is used to train an integrated model composed of multiple random forest algorithms to learn the prediction pattern of the soil improvement index, establish a soil improvement effect evaluation model, and use the test set to optimize the soil improvement effect evaluation model.

[0118] In this embodiment, the method for optimizing the soil improvement effect evaluation model includes:

[0119] Based on the test set, the simulated annealing algorithm is used to optimize the parameters of the soil improvement effect evaluation model:

[0120] Temperature update formula:

[0121]

[0122] Among them, T new is the new temperature value, T old is the old temperature value, ΔE avg is the average energy change in the last m iterations, ΔE max is the maximum value of energy change in the last m iterations, is the exponent of the control weight, γ is the decay factor, t is the current number of iterations,

[0123] Acceptance probability formula:

[0124]

[0125] Where P(ΔE) is the probability of accepting a new solution, ΔE is the energy difference between the new solution and the current solution, ∈ is the noise term drawn from the normal distribution to simulate randomness, k is the Boltzmann constant, T is the current temperature,

[0126] Solution update:

[0127]

[0128] where F new (x) is the updated objective function value, w i is the weight of the i-th objective function, n is the number of objective functions, f i(x) is the i-th objective function, p is the number of objective functions, ν j is the penalty weight of the jth constraint function, g j (x) is the jth constraint function,

[0129] Parameter update formula:

[0130]

[0131] where x new is the updated parameter value, x old is the current parameter value, η is the current learning rate, is the objective function at x old The gradient at, ζ is the parameter that controls the influence of global information, G is the global search direction, indicating the direction of the historical optimal solution, N(0,σ 2 ) is the normal distribution disturbance, σ is the standard deviation of the normal distribution disturbance,

[0132] Search based on dynamic neighborhood size and historical best solutions:

[0133]

[0134] Where Δx is the change in the parameter, σ nb is a parameter that controls the size of the neighborhood, T max is the maximum number of iterations, x best and x worst are the best solution and the worst solution found so far, respectively.

[0135] Learning rate update:

[0136]

[0137] Among them, η0 is the initial learning rate, accept rate is the current acceptance rate, is the target acceptance rate and δ is an exponent that adjusts the sensitivity of the learning rate.

[0138] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0139] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0140] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0141] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for evaluating the effect of desulfurized gypsum on improving saline-alkali soil at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the above-mentioned methods for evaluating the effect of desulfurized gypsum on improving saline-alkali soil.

[0142] The above application Figure 1The method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0143] The electronic device may also perform Figure 1 A method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0144] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, any one of the aforementioned methods for evaluating the effect of desulfurization gypsum on improving saline-alkali soil is executed.

[0145] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0146] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0147] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0148] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0149] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0150] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0151] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0152] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0153] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0154] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil, characterized in that: The following steps are involved: Acquire soil data of saline-alkali soil improved by desulfurized gypsum and desulfurized gypsum data, wherein the soil data includes original soil data and improved soil data; Predicting the original soil data to obtain predicted soil data, and comparing the predicted soil data with the improved soil data to obtain an impact ratio; Obtaining a change characteristic according to the impact ratio and the desulfurized gypsum data, and performing an impact analysis on the impact ratio based on the change characteristic to obtain a soil improvement index; Constructing a soil improvement effect evaluation model according to the soil improvement index, and optimizing the soil improvement effect evaluation model; Inputting the data to be evaluated into the soil improvement effect evaluation model and outputting the evaluation result; The method for predicting the original soil data to obtain predicted soil data comprises: The original soil data is the saline-alkali soil data before improvement. The original soil data is arranged in chronological order to obtain time series data, and the stability of the time series data is tested: In the formula, Z t represents the value of the time series data at time t, γ is a constant term, αt is a time trend term, θ is the coefficient of the autoregressive part, ΔZ t-j Represents Z t The difference term of , m is the number of difference terms, δ j is the coefficient of the difference term, ζ t is the random disturbance term, When θ=0, the time series data is stable, and when θ<0, the time series data is non-stationary. The non-stationary time series data is differentiated to obtain stable time series data. The method for obtaining the change characteristics according to the impact ratio and the desulfurization gypsum data comprises: The desulfurization gypsum data is the concentration data of the applied desulfurization gypsum. The desulfurization gypsum data and the influence ratio are normalized and preprocessed to establish data points. The desulfurization gypsum data is fitted with the influence ratio based on the SVR model to screen the change characteristics.

2. The method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil according to claim 1, characterized in that: The method for optimizing the soil improvement effect evaluation model comprises: Based on the test set, the simulated annealing algorithm is used to optimize the parameters of the soil improvement effect evaluation model: Temperature update formula: Among them, T new is the new temperature value, T old is the old temperature value, ΔE avg is the average energy change in the last m iterations, ΔE max is the maximum value of energy change in the last m iterations, is the exponent of the control weight, γ is the decay factor, t is the current number of iterations, Acceptance probability formula: Where P(ΔE) is the probability of accepting a new solution, ΔE is the energy difference between the new solution and the current solution, ∈ is the noise term drawn from the normal distribution to simulate randomness, k is the Boltzmann constant, T is the current temperature, Solution update: Among them, F new (x) is the updated objective function value, w i is the weight of the i-th objective function, n is the number of objective functions, f i (x) is the i-th objective function, p is the number of objective functions, ν j is the penalty weight of the jth constraint function, g j (x) is the jth constraint function, Parameter update formula: where x new is the updated parameter value, x old is the current parameter value, η is the current learning rate, is the objective function at x old The gradient at, ζ is the parameter that controls the influence of global information, G is the global search direction, indicating the direction of the historical optimal solution, N(0,σ 2 ) is the normal distribution disturbance, σ is the standard deviation of the normal distribution disturbance, Search based on dynamic neighborhood size and historical best solutions: Where Δx is the change in the parameter, σ nb is a parameter that controls the size of the neighborhood, T max is the maximum number of iterations, x best and x worst are the best solution and the worst solution found so far, respectively. Learning rate update: Among them, η0 is the initial learning rate, accept rate is the current acceptance rate, target acceptrate is the target acceptance rate and δ is an exponent that adjusts the sensitivity of the learning rate.

3. The method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil according to claim 1, characterized in that: The method for predicting the original soil data to obtain predicted soil data comprises: The original soil data is the saline-alkali soil data before improvement. The original soil data is arranged in chronological order to obtain time series data, and the stability of the time series data is tested: In the formula, Z t represents the value of the time series data at time t, γ is a constant term, αt is a time trend term, θ is the coefficient of the autoregressive part, ΔZ t-j Represents Z t The difference term of , m is the number of difference terms, δ j is the coefficient of the difference term, ζ t is the random disturbance term, When θ=0, the time series data is stable. When θ<0, the time series data is non-stationary. The non-stationary time series data is differentiated to obtain the stable time series data. Using VAR model for forecasting: Y t =β+A1Y t-1 +A2Y t-2 +…+A p Y t-p +BX t +m t where Y t is the k-dimensional endogenous variable column vector of the t-th time series data, is the historical data of the target time series data, t=1,2,...,T, T is the number of samples of the time series data, β is the k-dimensional intercept term column vector, X is the d-dimensional exogenous variable column vector, is the time series data other than the target time series data, A1,...,A p is a k×k dimensional matrix to be estimated, B is a k×d dimensional matrix to be estimated, p is the lag order of the VAR model, μ is a k dimensional error vector, Log-likelihood function: Where N is the number of variables, Σ is the covariance matrix of the error term, ∈ t is the error term for the t-th observation, Use the information criterion to select the optimal number of lags: Where AIC represents the Akaike information criterion, and the lag order that minimizes AIC is the optimal lag order.

4. The method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil according to claim 1, characterized in that: The method for obtaining the change characteristics according to the impact ratio and the desulfurization gypsum data comprises: The desulfurized gypsum data is the concentration data of the desulfurized gypsum applied. The desulfurized gypsum data and the impact ratio are normalized and preprocessed to establish data points. The desulfurized gypsum data is fitted with the impact ratio based on the SVR model to screen the change characteristics: Decision function: in<w,x> represents the inner product of w and x, w is the weight vector, x is the feature matrix, b is the bias term, y i is the i-th desulfurization gypsum data, K(x i ,x) is the kernel function, K(x i ,x)=<φ(x i ),φ(x)>,φ(x) is the mapping function from the original feature space to the high-dimensional feature space,α i and is the Lagrange multiplier, is the number of data points, The optimization goal of the SVR model is: Among them, ξ i is the slack variable, C is the penalty coefficient, w i and b i are the i-th weight coefficient of the weight vector and the i-th element of the bias term, respectively. λ is the regularization parameter that controls the complexity of the weight vector and the bias term. The log-likelihood function of the SVR model is: in is the noise variance of the i-th desulfurization gypsum data, The objective function of the SVR model is: The absolute value of the weight coefficient is taken as the feature importance, and the recursive feature elimination algorithm is used for feature screening.

5. The method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil according to claim 1, characterized in that: The method for obtaining a soil improvement index by performing an impact analysis on the impact ratio based on the change characteristics includes: Based on prior knowledge, the impact ratio is divided into positive impact and negative impact. For the impact ratio of positive impact, it is kept as a positive value, and for the impact ratio of negative impact, it is converted into a negative value. The desulfurized gypsum data, the characteristic importance of the change characteristics and the impact ratio are normalized and preprocessed to calculate the soil improvement index: Where L N is the desulfurized gypsum data, q is the index of the changing feature, Q is the number of changing features, w q is the feature importance of the qth changing feature, L Qq is the influence ratio of the qth changing feature.

6. The method for evaluating the effect of desulfurized gypsum on improving saline-alkali soil according to claim 1, characterized in that: The method for constructing a soil improvement effect evaluation model according to the soil improvement index comprises: The soil data, desulfurization gypsum data and soil improvement index are divided into training sets and test sets. The training set is used to train an integrated model composed of multiple random forest algorithms to learn the prediction pattern of the soil improvement index, establish a soil improvement effect evaluation model, and use the test set to optimize the soil improvement effect evaluation model.

7. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the method according to any one of claims 1 to 6.

8. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 6.

Images