Multi-source data analysis-based straw returning decay promotion effect evaluation method and system

Abstract

The invention discloses a straw returning decay promotion effect evaluation method and system based on multi-source data analysis, and relates to the technical field of straw returning. A neural network model with influence factor parameters in the straw decomposition process as input samples and straw quality variation as output samples is constructed, the neural network model is trained, and the number of neurons in a hidden layer of the neural network model is adjusted according to a training result until a prediction result reaches an expected value. The method comprises the following steps: acquiring an incidence relation mapped from an influence factor parameter sample to a straw quality variation sample through a constructed neural network model, acquiring time sequence data of influence factors in a straw decomposition process in a monitoring area, acquiring a straw quality variation when the influence factors change once in the decomposition process according to the incidence relation, and calculating the straw quality variation according to the straw quality variation. Calculating and acquiring an accumulated value of the straw mass variation from the initial moment of the decomposition process to the moment t, and calculating the decomposition rate at the moment t according to the acquired accumulated value of the straw mass variation.

Description

Technical Field

[0001] The present invention relates to the technical field of returning straw to fields, and in particular to a method and system for evaluating the decomposition-promoting effect of returning straw to fields based on multi-source data analysis. Background Art

[0002] Returning straw to the field is one of the important ways to utilize straw resources. Straw can supplement organic matter in the soil, and its rapid decomposition plays an important role in balancing soil C / N and improving soil fertility.

[0003] Determining the straw decomposition rate is one of the important methods to measure the decomposition effect of rice straw. The size of the straw decomposition percentage can directly reflect the decomposition effect of the straw. Straw decomposition is a cumulative process under the influence of multiple factors. The decomposition rate of straw when it is returned to the field is mainly affected by factors such as straw size, soil properties, and environmental water and heat conditions. Lu's research shows that the smaller the rice grains, the larger their specific surface area, which is more conducive to the contact between microorganisms and enzymes in the soil and straw, accelerating the decomposition of straw. Some scholars have conducted research on soil texture, pH, nutrients, etc., and found that the straw decomposition rate is different in soils of different textures, among which the decomposition rate is the highest in sandy soil, the second is in silt soil, and the lowest is in clay; pH ​​mainly affects the decomposition rate of straw by affecting microbial activity.

[0004] At present, the decomposition degree of straw is mainly reflected by measuring the change of straw weight during decomposition by sampling method. It is impossible to obtain the decomposition status of straw in the monitoring area by analyzing the changing trend of environmental water and heat conditions, and there is a lack of evaluation mechanism for the decomposition degree of straw under the influence of multiple influencing factors. Therefore, we propose a method and system for evaluating the decomposition effect of returning straw to the field based on multi-source data analysis. Summary of the invention

[0005] The main purpose of the present invention is to provide a method and system for evaluating the effect of returning straw to the field to promote decomposition based on multi-source data analysis, which can effectively solve the problems in the background technology.

[0006] To achieve the above object, the technical solution adopted by the present invention is:

[0007] The evaluation method of the effect of returning straw to the field to promote decomposition based on multi-source data analysis includes:

[0008] A neural network model is constructed with the influencing factor parameters in the straw decomposition process as input samples and the straw mass change as output samples. The neural network model is trained, and the number of neurons in the hidden layer of the neural network model is adjusted according to the training results until the prediction result reaches the expected value. The association relationship f mapped from the influencing factor parameter samples to the straw mass change samples is obtained through the constructed neural network model. The expression of the association relationship is: f = {x i x i∈X}→{Y}, where x i It is expressed as the parameter of the i-th influencing factor in the straw decomposition process; {x i x i ∈X} represents the influencing factor parameter set; {Y} represents the straw mass change amount set, wherein the influencing factors include temperature, humidity, soil pH, and decomposition time;

[0009] The neural network model is a BP neural network model with a three-layer structure of an input layer, an intermediate layer, and an output layer, wherein the number of neurons in the intermediate layer is determined by the following formula:

[0010]

[0011] In the formula, s represents the number of neurons in the middle layer; p represents the number of neurons in the input layer; q represents the number of neurons in the output layer; Expressed as a pair The value of is rounded up; a is a constant coefficient, and a is an integer in the interval [1,9]; where the number of neurons in the input layer is equal to the type of influencing factors. In this model, p = 4, q = 1;

[0012] The calculation formula of the expected value is:

[0013]

[0014] Among them, E(Y) represents the expected value; N represents the number of neural network input samples; f(x i ) is represented as the output function of the neural network; x i Represented as the i-th output sample of the neural network;

[0015] Obtain the time series data of the influencing factors of the straw decomposition process in the monitoring area, and obtain the change ΔDr of the straw mass when the influencing factors change once during the decomposition process according to the correlation relationship f k , ΔDr k It is expressed as the change in the mass of the straw when the influencing factor changes once for the kth time, wherein the change once is a change beyond the threshold value of any one of the influencing factors of temperature, humidity, and soil pH; the change thresholds of temperature, humidity, and soil pH are determined according to the following empirical formula:

[0016]

[0017] In the formula, ct j It is expressed as the change threshold of the jth influencing factor, j = 1, 2, 3; ΔDr jmax It is expressed as the parameter value of the jth influencing factor corresponding to the maximum change in straw mass when a change occurs; ΔDr jminIt is expressed as the parameter value of the jth influencing factor corresponding to the minimum change in straw mass when a change occurs; λ is the constant coefficient;

[0018] The range of constant coefficient λ is:

[0019] For the temperature change threshold, λ∈[2,10];

[0020] For the humidity change threshold, λ∈[2,10];

[0021] For the change threshold of soil pH, λ∈[1,5];

[0022] Calculate the cumulative value ΔDr of the straw mass change from the initial time of the decomposition process to time t t , the calculation formula is: In the formula, m is the total number of changes in the influencing factors from the initial moment of the decomposition process to moment t;

[0023] According to the accumulated value of straw mass change ΔDr t Calculate the decomposition rate Dr at time t t , the calculation formula is: Where qc is the initial mass of straw in the monitoring area.

[0024] The straw return to field decomposition effect evaluation system based on multi-source data analysis includes data acquisition module, neural network construction module, data processing module and decomposition rate calculation module;

[0025] The data acquisition module is used to obtain the time series data of the influencing factors of the straw decomposition process in the monitoring area and the statistical data of the straw mass change, wherein the influencing factors include temperature, humidity, soil pH, and decomposition time;

[0026] The neural network construction module is used to construct a neural network model with the influencing factor parameters in the straw decomposition process as input samples and the straw mass change as output samples, train the neural network model, adjust the number of neurons in the hidden layer of the neural network model according to the training results until the prediction result reaches the expected value, and obtain the association relationship f mapped from the influencing factor parameter samples to the straw mass change samples through the constructed neural network model. The expression of the association relationship is: f={x i x i ∈X}→{Y}, where x i It is expressed as the parameter of the i-th influencing factor in the straw decomposition process; {x i x i ∈X} represents the set of influencing factor parameters; {Y} represents the set of straw mass variation;

[0027] The data processing module is used to obtain the change amount ΔDr of the straw mass when any of the influencing factors of temperature, humidity and soil pH changes beyond the threshold value for the kth time during the decomposition process according to the association relationship f. k , and calculate the cumulative value ΔDr of the straw mass change from the initial time of the decomposition process to time t t , the calculation formula is: Where m is the total number of changes in the influencing factors from the initial moment of the decomposition process to moment t, among which the change thresholds of temperature, humidity, and soil pH are determined according to the following empirical formula:

[0028]

[0029] In the formula, ct j It is expressed as the change threshold of the jth influencing factor, j = 1, 2, 3; ΔDr jmax It is expressed as the parameter value of the jth influencing factor corresponding to the maximum change in straw mass when a change occurs; ΔDr jmin It is expressed as the parameter value of the jth influencing factor corresponding to the minimum change in straw mass when a change occurs; λ is the constant coefficient; the value range of the constant coefficient λ is:

[0030] For the temperature change threshold, λ∈[2,10];

[0031] For the humidity change threshold, λ∈[2,10];

[0032] For the change threshold of soil pH, λ∈[1,5];

[0033] The decomposition rate calculation module is used to obtain the cumulative value ΔDr of the straw mass change. t Calculate the decomposition rate Dr at time t t , the calculation formula is: In the formula, qc is the initial mass of straw in the monitoring area;

[0034] The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0035] The present invention has the following beneficial effects:

[0036] Compared with the prior art, a neural network model is constructed with influencing factor parameters in the straw decomposition process as input samples and straw mass change as output samples, the neural network model is trained, the number of neurons in the hidden layer of the neural network model is adjusted according to the training results until the prediction result reaches the expected value, the association relationship f mapped from the influencing factor parameter samples to the straw mass change samples is obtained through the constructed neural network model, the time series data of the influencing factors of the straw decomposition process in the monitoring area is obtained, the change of the straw mass when the influencing factor changes once during the decomposition process is obtained according to the association relationship f, and the cumulative value of the straw mass change from the initial moment of the decomposition process to the moment t is calculated, the decomposition rate at the moment t is calculated according to the obtained cumulative value of the straw mass change, the decomposition situation of the straw in the monitoring area can be obtained by analyzing the changing trend of the environmental water and heat conditions, so as to obtain the evaluation result of the straw decomposition degree under the action of multiple influencing factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the method for evaluating the effect of returning straw to the field to promote decomposition based on multi-source data analysis of the present invention;

[0038] Figure 2 It is a structural block diagram of the straw return to field and decomposition promoting effect evaluation system based on multi-source data analysis of the present invention;

[0039] Figure 3 This is a structural diagram of the neural network constructed in the solution of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0041] The specific implementation process of the technical solution of the present invention includes the following steps:

[0042] Step 1: Construct a neural network model with the influencing factor parameters in the straw decomposition process as input samples and the straw mass change as output samples, train the neural network model, and adjust the number of neurons in the hidden layer of the neural network model according to the training results until the prediction result reaches the expected value;

[0043] It should be noted that the influencing factor parameters and straw quality change parameters used to construct the neural network can be sampled by designing a decomposition experiment. The specific experimental design content is as follows:

[0044] There are 15 small areas, each with an area of ​​40m2 , collect the rice straw crushed by the spreader, cut the longer ones to about 5cm, mix 50g of rice straw (dry basis) with 1kg of paddy soil and put them into nylon mesh bags (40 mesh) evenly, set up 12 nylon mesh bags, and bury them vertically into the soil tillage layer 10-15cm, randomly sample 3 bags each time, and sample 4 times in total, at 30d, 60d, 90d and 120d after transplanting. After each straw sampling, the nylon mesh bags were soaked and washed, and then dried at 60℃, and compared with the initial dry weight, and the change in straw mass was calculated;

[0045] Among them, the influencing factors include temperature, humidity, soil pH, and decomposition time;

[0046] The neural network model is a BP neural network model with three layers of input layer, middle layer and output layer. Figure 3 As shown, the number of neurons in the middle layer is determined by the following formula:

[0047]

[0048] In the formula, s represents the number of neurons in the middle layer; p represents the number of neurons in the input layer; q represents the number of neurons in the output layer; Expressed as a pair The value of is rounded up; a is a constant coefficient, and a is an integer in the interval [1,9]; where the number of neurons in the input layer is equal to the type of influencing factors. In this model, p = 4, q = 1;

[0049] The formula for calculating the expected value is,

[0050]

[0051] Among them, E(Y) represents the expected value; N represents the number of neural network input samples; f(x i ) is represented as the output function of the neural network; x i Represented as the i-th output sample of the neural network;

[0052] Step 2: Obtain the association relationship f from the influencing factor parameter samples to the straw mass change samples through the constructed neural network model. The expression of the association relationship is: f = {x i x i ∈X}→{Y}, where x i It is expressed as the parameter of the i-th influencing factor in the straw decomposition process; {x i x i ∈X} represents the set of influencing factor parameters; {Y} represents the set of straw mass variation;

[0053] Step 3: Obtain the real-time time series data of the influencing factors of the straw decomposition process in the monitoring area, and obtain the change in straw mass ΔDr when the influencing factors change during the decomposition process according to the correlation relationship f k , ΔDr k It is expressed as the change in straw mass when the influencing factor changes once for the kth time, where a change is a change beyond the threshold value of any influencing factor among temperature, humidity and soil pH. The change thresholds of temperature, humidity and soil pH are determined according to the following empirical formula:

[0054]

[0055] In the formula, ct j It is expressed as the change threshold of the jth influencing factor, j = 1, 2, 3; ΔDr jmax It is expressed as the parameter value of the jth influencing factor corresponding to the maximum change in straw mass when a change occurs; ΔDr jmin It is expressed as the parameter value of the jth influencing factor corresponding to the minimum change in straw mass when a change occurs; λ is the constant coefficient;

[0056] The range of constant coefficient λ is:

[0057] For the temperature change threshold, λ∈[2,10];

[0058] For the humidity change threshold, λ∈[2,10];

[0059] For the change threshold of soil pH, λ∈[1,5];

[0060] It should be noted that when an influencing factor changes once, that is, the sampling value of any influencing factor among temperature, humidity, and soil pH exceeds the change threshold, the influencing factor changes in this change, and each change corresponds to a decomposition time period. The decomposition process of straw can be regarded as the cumulative effect of several decomposition time periods. In the same decomposition time period, the temperature, humidity, and soil pH are maintained at the same level. In different decomposition time periods, at least one of the influencing factors among temperature, humidity, and soil pH changes beyond the threshold. From the initial decomposition moment to the current moment t, it is accumulated by several consecutive decomposition time periods. The changes in the mass of straw in several decomposition time periods are accumulated to obtain the total change in the mass of straw, which is the cumulative value of the change in the mass of straw.

[0061] Step 4: Calculate the cumulative value ΔDr of the change in straw mass from the initial time of the decomposition process to time t t , the calculation formula is: In the formula, m is the total number of changes in the influencing factors from the initial moment of the decomposition process to moment t;

[0062] Step 5: Based on the accumulated value of straw mass change ΔDr t Calculate the decomposition rate Dr at time t t , the calculation formula is: Where qc is the initial mass of straw in the monitoring area.

[0063] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for evaluating the effect of returning straw to the field to promote decomposition based on multi-source data analysis, characterized in that: include: A neural network model is constructed with the influencing factor parameters in the straw decomposition process as input samples and the straw mass change as output samples. The neural network model is trained, and the number of neurons in the hidden layer of the neural network model is adjusted according to the training results until the prediction result reaches the expected value. The association relationship f mapped from the influencing factor parameter samples to the straw mass change samples is obtained through the constructed neural network model. The expression of the association relationship is: f = {x i x i ∈X}→{Y}, where x i It is expressed as the parameter of the i-th influencing factor in the straw decomposition process; {x i x i ∈X} represents the set of influencing factor parameters; {Y} represents the set of straw mass variation; Obtain the time series data of the influencing factors of the straw decomposition process in the monitoring area, and obtain the change ΔDr of the straw mass when the influencing factors change once during the decomposition process according to the correlation relationship f k , ΔDr k It is expressed as the change in straw mass when the influencing factor changes for the kth time; Calculate the cumulative value ΔDr of the straw mass change from the initial time of the decomposition process to time t t , the calculation formula is: In the formula, m is the total number of changes in the influencing factors from the initial moment of the decomposition process to moment t; According to the accumulated value of straw mass change ΔDr t Calculate the decomposition rate Dr at time t t , the calculation formula is: Where qc is the initial mass of straw in the monitoring area.

2. The method for evaluating the effect of returning straw to the field and promoting its decay based on multi-source data analysis according to claim 1 is characterized in that: The influencing factors include temperature, humidity, soil pH, and decomposition time, and the one change is an over-threshold change in any one of the influencing factors of temperature, humidity, and soil pH.

3. The method for evaluating the effect of returning straw to the field and promoting its decay based on multi-source data analysis according to claim 1 is characterized in that: The neural network model is a BP neural network model with a three-layer structure of an input layer, an intermediate layer, and an output layer, wherein the number of neurons in the intermediate layer is determined by the following formula: In the formula, s represents the number of neurons in the middle layer; p represents the number of neurons in the input layer; q represents the number of neurons in the output layer; Expressed as a pair The value of is rounded up; a is a constant coefficient, and a is an integer in the interval [1,9]; where the number of neurons in the input layer is equal to the type of influencing factors. In this model, p = 4, q = 1.

4. The method for evaluating the effect of returning straw to the field and promoting its decay based on multi-source data analysis according to claim 1 is characterized in that: The calculation formula of the expected value is: Among them, E(Y) represents the expected value; N represents the number of neural network input samples; f(x i ) is represented as the output function of the neural network; x i Represented as the i-th output sample of the neural network.

5. The method for evaluating the effect of returning straw to the field and promoting its decay based on multi-source data analysis according to claim 2 is characterized in that: The threshold values ​​of temperature, humidity, and soil pH are determined according to the following empirical formula: In the formula, ct j It is expressed as the change threshold of the jth influencing factor, j = 1, 2, 3; ΔDr jmax It is expressed as the parameter value of the jth influencing factor corresponding to the maximum change in straw mass when a change occurs; ΔDr jmin It is expressed as the parameter value of the jth influencing factor corresponding to the minimum change in straw mass when a change occurs; λ is a constant coefficient.

6. The method for evaluating the effect of returning straw to the field and promoting its decay based on multi-source data analysis according to claim 5 is characterized in that: The range of constant coefficient λ is: For the temperature change threshold, λ∈[2,10]; For the humidity change threshold, λ∈[2,10]; For the soil pH change threshold, λ∈[1,5].

7. The straw return to field and decomposition promoting effect evaluation system based on multi-source data analysis is characterized by: It includes data acquisition module, neural network construction module, data processing module and decomposition rate calculation module; The data acquisition module is used to obtain the time series data of the influencing factors of the straw decomposition process in the monitoring area and the statistical data of the straw mass change, wherein the influencing factors include temperature, humidity, soil pH, and decomposition time; The neural network construction module is used to construct a neural network model with the influencing factor parameters in the straw decomposition process as input samples and the straw mass change as output samples, train the neural network model, adjust the number of neurons in the hidden layer of the neural network model according to the training results until the prediction result reaches the expected value, and obtain the association relationship f mapped from the influencing factor parameter samples to the straw mass change samples through the constructed neural network model. The expression of the association relationship is: f={x i x i ∈X}→{Y}, where x i It is expressed as the parameter of the i-th influencing factor in the straw decomposition process; {x i x i ∈X} represents the influencing factor parameter set; {Y} represents the straw quality change amount set, wherein the neural network model is a BP neural network model with a three-layer structure of input layer, middle layer and output layer, wherein the number of neurons in the middle layer is determined by the following formula: In the formula, s represents the number of neurons in the middle layer; p represents the number of neurons in the input layer; q represents the number of neurons in the output layer; Expressed as a pair The value of is rounded up; a is a constant coefficient, and a is an integer in the interval [1,9]; where the number of neurons in the input layer is equal to the type of influencing factor. In this model, p = 4, q = 1; the calculation formula of the expected value is, Among them, E(Y) represents the expected value; N represents the number of neural network input samples; f(x i ) is represented as the output function of the neural network; x i Represented as the i-th output sample of the neural network; The data processing module is used to obtain the change amount ΔDr of the straw mass when any of the influencing factors of temperature, humidity and soil pH changes beyond the threshold value for the kth time during the decomposition process according to the association relationship f. k , and calculate the cumulative value ΔDr of the straw mass change from the initial time of the decomposition process to time t t , the calculation formula is: Where m is the total number of changes in the influencing factors from the initial moment of the decomposition process to moment t, among which the change thresholds of temperature, humidity, and soil pH are determined according to the following empirical formula: In the formula, ct j It is expressed as the change threshold of the jth influencing factor, j = 1, 2, 3; ΔDr jmax It is expressed as the parameter value of the jth influencing factor corresponding to the maximum change in straw mass when a change occurs; ΔDr jmin It is expressed as the parameter value of the jth influencing factor corresponding to the minimum change in straw mass when a change occurs; λ is the constant coefficient; the value range of the constant coefficient λ is: For the temperature change threshold, λ∈[2,10]; For the humidity change threshold, λ∈[2,10]; For the change threshold of soil pH, λ∈[1,5]; The decomposition rate calculation module is used to obtain the cumulative value ΔDr of the straw mass change. t Calculate the decomposition rate Dr at time t t , the calculation formula is: Where qc is the initial mass of straw in the monitoring area.

8. The straw return to field and decomposition promoting effect evaluation system based on multi-source data analysis according to claim 7 is characterized in that: The system comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the method according to any one of claims 1 to 6 are implemented when the processor executes the program.

Images