A method, apparatus, device, and readable storage medium for predicting the effectiveness of heavy metals.

Abstract

This invention discloses a method for predicting the availability of heavy metals, applied in the field of pollution assessment technology. The method includes: acquiring compost to be predicted and extracting preset physicochemical indicators and total heavy metal content corresponding to the compost; calling a heavy metal availability prediction model; the heavy metal availability prediction model is a neural network model trained using the sample's physicochemical indicators, total heavy metal content, and heavy metal availability; and calculating the predicted heavy metal availability value corresponding to the compost to be predicted based on the preset physicochemical indicators, total heavy metal content, and the heavy metal availability prediction model. This invention utilizes a heavy metal availability prediction model composed of a neural network model to predict the heavy metal availability of the compost to be predicted, thereby quickly obtaining the heavy metal availability within the compost and proactively mitigating the environmental risks posed by heavy metals during the composting process. This invention also provides a heavy metal availability prediction device, equipment, and readable storage medium, which also possess the above-mentioned beneficial effects.

Description

Technical Field

[0001] This invention relates to the field of pollution assessment technology, and in particular to a method, apparatus, device, and readable storage medium for predicting the effectiveness of heavy metals. Background Technology

[0002] Composting, a common biological treatment method for agricultural waste, can not only mitigate the impact of agricultural pollution but also improve soil and enhance soil fertility. However, the addition of heavy metals to animal feed, pesticides, and fertilizers is widespread. Because heavy metals do not degrade during the composting process, and microbial respiration leads to the loss of carbon and water, heavy metal concentrations increase. The bioavailability of heavy metals refers to the extent to which heavy metals can be absorbed into the body from the environmental medium through a specific pathway. It can be used to measure and reflect the migration process of heavy metal elements and their true environmental effects. The bioavailability of heavy metals is not only related to the total amount but also closely related to their chemical forms; therefore, the chemical forms of heavy metals are more worthy of attention than their total amount. The BCR method (Sequential Extraction Speciation Standard of Heavy Metals in Soil) classifies heavy metals in the environment into four forms: exchangeable, reducible, oxidizable, and residual. Among these, exchangeable and reducible heavy metals are easily migrated and transformed after entering the environment, and are considered bioavailable. Safety and pollution-free operation are prerequisites for the use of compost products. Therefore, preventing heavy metal pollution in compost and predicting the availability of heavy metals are of more direct significance.

[0003] Currently, the availability of heavy metals in composting is still determined by detecting the content and total amount of available heavy metals. The acquisition of available heavy metals in compost is mainly based on actual detection. Existing heavy metal availability detection methods are mainly carried out manually using chemical extraction, gradient diffusion, and chemical analysis. In other words, the existing heavy metal availability detection methods lack intelligence, which makes it time-consuming and costly to detect the availability of heavy metals in compost. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, apparatus, device and readable storage medium for predicting the effectiveness of heavy metals, which solves the problems of long time and high cost in the prior art.

[0005] To address the aforementioned technical problems, this invention provides a method for predicting the availability of heavy metals, comprising:

[0006] Obtain the compost to be predicted, and extract the preset physicochemical indicators and total heavy metal content corresponding to the compost to be predicted;

[0007] The heavy metal effectiveness prediction model is invoked; wherein, the heavy metal effectiveness prediction model is a neural network model trained using the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal effectiveness of the sample;

[0008] Based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model, the predicted value of heavy metal availability corresponding to the compost to be predicted is calculated.

[0009] Optionally, after calculating the predicted heavy metal availability value corresponding to the compost to be predicted, the method further includes:

[0010] The proportions of exchangeable and reducible heavy metals are determined based on the predicted heavy metal availability values.

[0011] When the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals exceeds the corresponding preset threshold, the proportion of heavy metals corresponding to the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals is adjusted.

[0012] Optionally, adjusting the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals corresponding to the heavy metal ratio includes:

[0013] The proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals are adjusted by utilizing earthworm activity.

[0014] Optionally, the invocation of the heavy metal effectiveness prediction model includes:

[0015] Obtain the types of heavy metals to be predicted corresponding to the compost to be predicted;

[0016] Invoke the heavy metal effectiveness prediction model corresponding to the heavy metal species to be predicted.

[0017] Optionally, the construction process of the heavy metal availability prediction model includes:

[0018] Obtain a preset number of compost samples, and detect the physicochemical indicators, total heavy metal content, and heavy metal availability of the compost samples.

[0019] Correlation analysis was performed on the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal availability of the sample to obtain the preset physicochemical indicators; wherein, the heavy metal availability of the sample includes the proportion of exchangeable heavy metals and the proportion of reducible heavy metals in the sample.

[0020] The preset physicochemical indicators, the total amount of heavy metals in the sample, and the effectiveness of heavy metals in the sample are normalized to obtain normalized training data.

[0021] The basic neural network model is trained using the normalized training data to obtain the heavy metal effectiveness prediction model.

[0022] Optionally, the normalization process for the preset physicochemical indicators, the total heavy metal content of the sample, and the heavy metal availability of the sample includes:

[0023] The preset physicochemical indicators, the total amount of heavy metals in the sample, and the effectiveness of heavy metals in the sample are normalized using maximum-minimum normalization.

[0024] Optionally, the step of calculating the predicted heavy metal availability value corresponding to the compost to be predicted based on the preset physicochemical indicators, the total heavy metal content, and the heavy metal availability prediction model includes:

[0025] Based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model, the predicted value of heavy metal availability corresponding to the compost to be predicted is calculated; wherein, the heavy metal availability prediction model is a BP neural network with a single hidden layer.

[0026] The present invention also provides a heavy metal availability prediction device, comprising:

[0027] A preset physicochemical index and heavy metal total extraction module is used to obtain the compost to be predicted and extract the preset physicochemical index and heavy metal total corresponding to the compost to be predicted.

[0028] The heavy metal validity prediction model calling module is used to call the heavy metal validity prediction model; wherein, the heavy metal validity prediction model is a neural network model trained using the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal validity of the sample;

[0029] The heavy metal availability prediction value calculation module is used to calculate the heavy metal availability prediction value corresponding to the compost to be predicted based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model.

[0030] The present invention also provides a heavy metal availability prediction device, comprising:

[0031] Memory, used to store computer programs;

[0032] A processor is used to implement the steps of the above-described heavy metal effectiveness prediction method when executing the computer program.

[0033] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described heavy metal effectiveness prediction method.

[0034] As can be seen, this invention obtains the compost to be predicted and extracts the corresponding preset physicochemical indicators and total heavy metal content; it then calls a heavy metal availability prediction model; wherein, the heavy metal availability prediction model is a neural network model trained using the sample's physicochemical indicators, total heavy metal content, and heavy metal availability; based on the preset physicochemical indicators, total heavy metal content, and the heavy metal availability prediction model, it calculates the predicted heavy metal availability value corresponding to the compost to be predicted. This invention uses a heavy metal availability prediction model composed of a neural network model to predict the heavy metal availability in compost. Compared with existing technologies that require manual heavy metal availability testing, predicting heavy metal availability through a heavy metal availability prediction model results in lower costs and faster testing speeds for heavy metal availability testing.

[0035] In addition, the present invention also provides a heavy metal availability prediction device, equipment and readable storage medium, which also have the above-mentioned beneficial effects. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0037] Figure 1 A flowchart of a method for predicting the effectiveness of heavy metals provided in an embodiment of the present invention;

[0038] Figure 2 A flowchart illustrating the construction of a heavy metal availability prediction model provided in an embodiment of the present invention;

[0039] Figure 3 A flowchart illustrating a method for predicting the effectiveness of heavy metals provided in an embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of the structure of a heavy metal availability prediction device provided in an embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of the structure of a heavy metal effectiveness prediction device provided in an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for predicting the availability of heavy metals provided in an embodiment of the present invention. The method may include:

[0044] S100: Obtain the compost to be predicted and extract the preset physicochemical indicators and total heavy metal content corresponding to the compost to be predicted.

[0045] This embodiment does not limit the method of obtaining the compost to be predicted, as long as it can be obtained. For example, the compost to be predicted can be obtained online; or it can be obtained offline. This embodiment does not limit the preset physicochemical indicators corresponding to the compost to be predicted, as long as they are preset physicochemical indicators required by the heavy metal availability prediction model in the process of predicting the availability of heavy metals. For example, the preset physicochemical indicators can be temperature, electrical conductivity, pH (acidity / alkalinity), organic matter, total nitrogen, and total phosphorus; or the preset physicochemical indicators can also be temperature, pH, electrical conductivity, and organic matter; or the preset physicochemical indicators can also be sand content, organic matter, humidity, total nitrogen, and total phosphorus. This embodiment does not limit the specific heavy metal types in the total heavy metal content. For example, the total heavy metal content can be the total Zn (zinc); or the total heavy metal content can also be the total Cu (copper); or the total heavy metal content can also be the total cadmium (Cd).

[0046] S101, invoke the heavy metal validity prediction model; wherein, the heavy metal validity prediction model is a neural network model trained using the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the validity of heavy metals in the sample.

[0047] This embodiment does not limit the specific heavy metal availability prediction model, as long as it can calculate the heavy metal availability of the compost to be predicted based on the input factors. For example, the heavy metal availability prediction model can be a linear neural network; or it can be a back propagation (BP) neural network; or it can be a self-organizing neural network. The heavy metal availability prediction model in this embodiment is a neural network model trained using the sample's physicochemical indicators, the total heavy metal content of the sample, and the heavy metal availability of the sample.

[0048] S102, based on the preset physicochemical indicators, total heavy metal content, and heavy metal availability prediction model, calculate the predicted heavy metal availability value corresponding to the compost to be predicted.

[0049] This embodiment calculates the predicted heavy metal availability value for the compost to be predicted based on preset physicochemical indicators, total heavy metal content, and a heavy metal availability prediction model. This embodiment does not limit the specific predicted heavy metal availability value. For example, the predicted heavy metal availability value could be 23% exchangeable Cu and 18% reducible Cu; or 10% exchangeable Zn and 25% reducible Zn; or 14% exchangeable Cd and 23% reducible Cd.

[0050] Furthermore, in order to predict the availability of heavy metals in compost in a timely manner, after calculating the predicted value of heavy metal availability for the compost to be predicted, the following may also be included:

[0051] The proportions of exchangeable and reducible heavy metals are determined based on the predicted values ​​of heavy metal availability.

[0052] When the proportion of exchangeable heavy metals and / or reducible heavy metals exceeds the corresponding preset threshold, the proportion of heavy metals corresponding to the proportion of exchangeable heavy metals and / or reducible heavy metals is adjusted.

[0053] This embodiment adjusts the proportion of heavy metals corresponding to the proportion of exchangeable and / or reducible heavy metals when the proportion of exchangeable and / or reducible heavy metals exceeds a corresponding preset threshold. This embodiment does not limit the preset thresholds for the proportion of exchangeable and / or reducible heavy metals. For example, the preset thresholds for the proportion of exchangeable and / or reducible heavy metals can be 5% and 20%, respectively. Alternatively, the preset thresholds can be 13% and 17%, respectively. Or, the preset thresholds can be 25% and 21%, respectively. This embodiment does not limit the specific method for adjusting the proportion of heavy metals corresponding to the proportion of exchangeable and / or reducible heavy metals. For example, the proportion of heavy metals corresponding to the proportion of exchangeable and / or reducible heavy metals can be adjusted by chemical methods; or by physical methods.

[0054] Furthermore, to make the adjustment of the heavy metal ratio more accurate, the above-mentioned adjustment of the ratio of exchangeable heavy metals and / or reducible heavy metals may include:

[0055] The proportion of heavy metals corresponding to the proportion of exchangeable and / or reducible heavy metals can be adjusted by utilizing earthworm activity.

[0056] In this embodiment, earthworm activity is used to adjust the heavy metal ratio. Earthworms are a common type of terrestrial annelid that lives in the soil, is nocturnal, and feeds on decaying organic matter, ingesting it along with the soil. Earthworms also consume plant stems and leaves. Earthworms can loosen and improve soil, increase fertility, and promote agricultural production. Earthworms can significantly increase the content of total nitrogen and available nitrogen, phosphorus, and potassium nutrients in the soil, and can increase the activity of urease, sucrase, and microorganisms in the soil, enhancing the soil's fertility. Numerous studies have confirmed that earthworm activity can promote plant growth. In uncontaminated soil, earthworm activity can promote plant yield; studies have shown that in Cu and Cd contaminated soil, earthworm activity can significantly increase the aboveground biomass of ryegrass; earthworm activity increased ryegrass yield in soils contaminated with three different concentrations of Cd, Fe (iron), Zn, Cu, and Pb (lead). After introducing earthworms into sandy soil and reclaimed soil, the stem length, root length, and dry weight of tomatoes were significantly higher than the control. Under laboratory conditions, the introduction of earthworms significantly promoted the growth of Poaannua (annual bluegrass). In experiments involving intercropping wheat and alfalfa, earthworms significantly increased wheat biomass.

[0057] Furthermore, to improve the accuracy of heavy metal availability prediction, the aforementioned call to the heavy metal availability prediction model may include:

[0058] Obtain the types of heavy metals to be predicted for the compost to be predicted;

[0059] Call the heavy metal effectiveness prediction model corresponding to the type of heavy metal to be predicted.

[0060] This embodiment considers that the parameters, indicators, and neural network types in the heavy metal effectiveness prediction models may differ for different heavy metals. Different heavy metal effectiveness prediction models are established for predicting the effectiveness of different heavy metals. The correct heavy metal effectiveness prediction model is called based on the type of heavy metal to be predicted, which can improve the accuracy of heavy metal effectiveness prediction. This embodiment does not limit the specific heavy metal type. For example, when the heavy metal to be predicted is Zn, the heavy metal effectiveness prediction model corresponding to Zn is called. Or, when the heavy metal to be predicted is Cu, the heavy metal effectiveness prediction model corresponding to Cu is called; when the heavy metal to be predicted is Cd, the heavy metal effectiveness prediction model corresponding to Cd is called.

[0061] Furthermore, in order to improve the accuracy of heavy metal availability prediction models, the construction process of the aforementioned heavy metal availability prediction models may include:

[0062] Obtain a preset number of compost samples and test the corresponding physicochemical indicators, total heavy metal content, and heavy metal availability of the compost samples.

[0063] Correlation analysis was performed on the physicochemical indicators, total heavy metal content, and heavy metal availability of the samples to obtain the preset physicochemical indicators; among them, the heavy metal availability of the samples includes the proportion of exchangeable heavy metals and the proportion of reducible heavy metals.

[0064] The preset physicochemical indicators, total heavy metal content in the sample, and the effectiveness of heavy metals in the sample were normalized to obtain normalized training data.

[0065] A basic neural network model was trained using normalized training data to obtain a heavy metal effectiveness prediction model.

[0066] This embodiment aims to construct a heavy metal availability prediction model by acquiring a predetermined number of compost samples and predicting the corresponding physicochemical indicators, total heavy metal content, and heavy metal availability of the compost samples. Correlation analysis is performed on the physicochemical indicators, total heavy metal content, and heavy metal availability to obtain predetermined physicochemical indicators. The heavy metal availability includes the proportion of exchangeable heavy metals and the proportion of reducible heavy metals. The predetermined physicochemical indicators, total heavy metal content, and heavy metal availability are normalized to obtain normalized training data. This normalized training data is then used to train a basic neural network model to obtain the heavy metal availability prediction model. Before constructing the heavy metal availability prediction model, this embodiment first performs correlation analysis on the physicochemical indicators, total heavy metal content, and heavy metal availability to obtain predetermined physicochemical indicators, and then uses the data corresponding to these predetermined physicochemical indicators to train the heavy metal availability prediction model. This embodiment does not limit the relationship between the sample physicochemical indicators and the predetermined physicochemical indicators, as long as the predetermined physicochemical indicators are obtained from the sample physicochemical indicators. For example, there can be a one-to-one correspondence between the sample's physicochemical indicators and the preset physicochemical indicators; or the number of preset physicochemical indicators can be less than the sample's physicochemical indicators, and there can be a partial correspondence between them.

[0067] Furthermore, to improve the convergence speed of the heavy metal availability prediction model, the above-mentioned normalization processing of the preset physicochemical indicators, the total amount of heavy metals in the sample, and the availability of heavy metals in the sample may include:

[0068] The preset physicochemical indicators, total heavy metal content in the sample, and the effectiveness of heavy metals in the sample were normalized using maximum-minimum normalization.

[0069] In this embodiment, max-min normalization is performed by standardizing the data using the maximum and minimum values ​​in the data column. The standardized values ​​are between [0,1]. The calculation method is to subtract the minimum value of the data from the minimum value of the column and then divide by the range. Max-min normalization speeds up the gradient descent process to find the optimal solution.

[0070] To facilitate understanding of this embodiment, please refer to... Figure 2 , Figure 2 The flowchart illustrating the construction of a heavy metal availability prediction model provided in this embodiment of the invention includes: collecting a certain number of compost samples; detecting the physicochemical indicators, reducible Zn content, exchangeable Zn content, and total Zn content of the compost samples; obtaining Zn availability based on the reducible Zn content, exchangeable Zn content, and total Zn content; analyzing the correlation between Zn availability and the physicochemical indicators of the samples to obtain preset physicochemical indicators; normalizing the preset physicochemical indicators and total Zn content of the compost samples using the max-min normalization method; and constructing a Zn availability prediction model by using the preset physicochemical indicators and total Zn content of the compost samples as input factors and Zn availability as the output factor.

[0071] Furthermore, to improve the training speed of the heavy metal availability prediction model, the above-mentioned calculation of the predicted heavy metal availability value corresponding to the compost to be predicted, based on preset physicochemical indicators, total heavy metal content, and the heavy metal availability prediction model, may include:

[0072] Based on the preset physicochemical indicators, total heavy metal content, and heavy metal availability prediction model, the predicted heavy metal availability value corresponding to the compost to be predicted is calculated; wherein, the heavy metal availability prediction model is a BP neural network with a single hidden layer.

[0073] In this embodiment, a backpropagation (BP) neural network is used as the base model for the heavy metal effectiveness prediction model; that is, the heavy metal effectiveness prediction model is a BP neural network. Through repeated experiments, this scheme sets the hidden layer to a single layer.

[0074] The heavy metal availability prediction method provided in this invention includes: acquiring the compost to be tested and extracting the preset physicochemical indicators and total heavy metal content corresponding to the compost; calling the heavy metal availability prediction model; wherein the heavy metal availability prediction model is a neural network model trained using the sample's physicochemical indicators, total heavy metal content, and heavy metal availability; and calculating the predicted heavy metal availability value corresponding to the compost to be tested based on the preset physicochemical indicators, total heavy metal content, and the heavy metal availability prediction model. This invention uses a heavy metal availability prediction model composed of a neural network model to predict the heavy metal availability in compost. Compared with existing technologies that require manual heavy metal availability testing, predicting heavy metal availability using a heavy metal availability prediction model results in lower costs and faster testing speeds for heavy metal availability testing. Furthermore, the physicochemical environment can be adjusted in a timely manner based on the proportions of exchangeable and reducible heavy metals to reduce pollution. Earthworm activity can be used to adjust the proportions of exchangeable and / or reducible heavy metals, making the adjustment more accurate. The types of heavy metals to be predicted in the compost can be obtained, and the corresponding heavy metal availability prediction model can be invoked to improve the accuracy of heavy metal availability prediction. Multiple sample physicochemical indicators can be screened to obtain preset physicochemical indicators, thereby improving the accuracy of the heavy metal availability prediction model. Max-min normalization can be used for normalization to improve the convergence speed of the heavy metal availability prediction model. Finally, a BP neural network model is used as the base model to train the heavy metal availability prediction model, improving the efficiency and accuracy of heavy metal availability prediction model formation.

[0075] For a clearer understanding of this invention, please refer to the following details. Figure 3 , Figure 3 A flowchart illustrating a method for predicting the effectiveness of heavy metals provided in this embodiment of the invention may specifically include:

[0076] The compost to be predicted was obtained, and its temperature, pH, electrical conductivity, organic matter, total nitrogen, total phosphorus, and total Cu were measured using different methods. Table 1 shows the raw materials and their physicochemical indicators for the compost to be predicted. Here, SWM represents pig manure; MS represents straw; MC represents moisture content; EC represents electrical conductivity; pH ​​represents acidity / alkalinity; TOC represents total organic carbon; TN represents total nitrogen; and TP represents total phosphorus. Table 2 shows the methods used to measure the physicochemical indicators of the compost to be predicted. The temperature, pH, electrical conductivity, organic matter, total nitrogen, total phosphorus, and total Cu were normalized. A Cu availability prediction model was then used to calculate the predicted heavy metal availability values ​​based on the normalized values, yielding a reducible Cu ratio of 25% and an exchangeable Cu ratio of 15%. When the preset threshold corresponding to the proportion of reducible heavy metal Cu is 20% and the preset threshold corresponding to the proportion of exchangeable Cu is 10%, heavy metal pollution is determined. Then, the preset physicochemical indicators corresponding to the compost to be predicted by earthworm activity are used to adjust the proportion of exchangeable Cu and / or reducible Cu to reduce heavy metal pollution.

[0077] Table 1. Information on raw and auxiliary materials for composting to be predicted and their physicochemical properties.

[0078]

[0079] Table 2. Methods for determining the physicochemical properties of compost to be predicted

[0080]

[0081] The heavy metal availability prediction device provided in the embodiments of the present invention will be described below. The heavy metal availability prediction device described below can be referred to in correspondence with the heavy metal availability prediction method described above.

[0082] Please refer to the details. Figure 4 , Figure 4 A schematic diagram of a heavy metal availability prediction device provided in an embodiment of the present invention may include:

[0083] The preset physicochemical index and heavy metal total extraction module 100 is used to obtain the compost to be predicted and extract the preset physicochemical index and heavy metal total corresponding to the compost to be predicted.

[0084] The heavy metal validity prediction model calling module 200 is used to call the heavy metal validity prediction model; wherein, the heavy metal validity prediction model is a neural network model trained using the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal validity of the sample.

[0085] The heavy metal availability prediction calculation module 300 is used to calculate the heavy metal availability prediction value corresponding to the compost to be predicted based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model.

[0086] Furthermore, based on the above embodiments, the heavy metal availability prediction device may further include:

[0087] A module for determining the proportion of exchangeable heavy metals and the proportion of reducible heavy metals is used to determine the proportion of exchangeable heavy metals and the proportion of reducible heavy metals based on the predicted value of heavy metal effectiveness.

[0088] The heavy metal effectiveness adjustment module is used to adjust the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals when the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals exceeds the corresponding preset threshold.

[0089] Furthermore, based on the above embodiments, the heavy metal effectiveness adjustment module includes:

[0090] A heavy metal availability adjustment unit is used to adjust the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals corresponding to earthworm activity.

[0091] Furthermore, based on any of the above embodiments, the heavy metal effectiveness prediction model invocation module 200 may include:

[0092] The unit for obtaining the type of heavy metal to be predicted is used to obtain the type of heavy metal to be predicted corresponding to the compost to be predicted.

[0093] The heavy metal effectiveness prediction model invocation unit is used to invoke the heavy metal effectiveness prediction model corresponding to the heavy metal species to be predicted.

[0094] Furthermore, based on any of the above embodiments, the heavy metal availability prediction device may further include:

[0095] The compost sample index acquisition module is used to acquire a preset number of compost samples and predict the physicochemical index, total heavy metal content, and heavy metal availability of the compost samples.

[0096] The correlation analysis module is used to perform correlation analysis on the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal effectiveness of the sample to obtain the preset physicochemical indicators; wherein, the heavy metal effectiveness of the sample includes the proportion of exchangeable heavy metals and the proportion of reducible heavy metals in the sample.

[0097] The normalization processing module is used to normalize the preset physicochemical indicators, the total amount of heavy metals in the sample, and the effectiveness of heavy metals in the sample to obtain normalized training data.

[0098] The heavy metal effectiveness prediction model construction module is used to train the basic neural network model using the normalized training data to obtain the heavy metal effectiveness prediction model.

[0099] Furthermore, based on the above embodiments, the normalization processing module may include:

[0100] The maximum-minimum normalization processing unit is used to normalize the preset physicochemical indicators, the total amount of heavy metals in the sample, and the effectiveness of heavy metals in the sample using maximum-minimum normalization.

[0101] Furthermore, based on any of the above embodiments, the heavy metal availability prediction calculation module 300 may include:

[0102] The heavy metal availability prediction unit is used to calculate the heavy metal availability prediction value corresponding to the compost to be predicted based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model; wherein the heavy metal availability prediction model is a BP neural network with a single hidden layer.

[0103] It should be noted that the order of the modules and units in the above-mentioned heavy metal effectiveness prediction device can be changed without affecting the logic.

[0104] The heavy metal availability prediction device provided in this invention includes a preset physicochemical index and heavy metal total amount extraction module 100, used to acquire the compost to be predicted and extract the preset physicochemical index and heavy metal total amount corresponding to the compost to be predicted; a heavy metal availability prediction model invocation module 200, used to invoke the heavy metal availability prediction model; wherein, the heavy metal availability prediction model is a neural network model trained using the sample physicochemical index, the sample heavy metal total amount, and the sample heavy metal availability; and a heavy metal availability prediction value calculation module 300, used to calculate the heavy metal availability prediction value corresponding to the compost to be predicted based on the preset physicochemical index, the heavy metal total amount, and the heavy metal availability prediction model. This invention uses a heavy metal availability prediction model composed of a neural network model to predict the heavy metal availability in compost. Compared with the prior art which requires manual heavy metal availability prediction, predicting heavy metal availability using a heavy metal availability prediction model results in higher accuracy and faster detection speed for heavy metal availability. Furthermore, the physicochemical environment can be adjusted in a timely manner based on the proportions of exchangeable and reducible heavy metals to reduce pollution. Earthworm activity can be used to adjust the proportions of exchangeable and / or reducible heavy metals, making the adjustment more accurate. The types of heavy metals to be predicted in the compost can be obtained, and the corresponding heavy metal effectiveness prediction model can be invoked to improve the accuracy of heavy metal effectiveness prediction. Multiple sample physicochemical indicators can be screened to obtain preset physicochemical indicators, thereby improving the accuracy of the heavy metal effectiveness prediction model. Max-min normalization can be used for normalization to improve the convergence speed of the heavy metal effectiveness prediction model. A BP neural network model is used as the base model to train the heavy metal effectiveness prediction model, improving the efficiency and accuracy of its formation.

[0105] The heavy metal availability prediction device provided in the embodiments of the present invention will be described below. The heavy metal availability prediction device described below can be referred to in correspondence with the heavy metal availability prediction method described above.

[0106] Please refer to Figure 5 , Figure 5 A schematic diagram of a heavy metal availability prediction device provided in an embodiment of the present invention may include:

[0107] Memory 10 is used to store computer programs;

[0108] Processor 20 is used to execute computer programs to implement the steps of the above-described method for predicting the effectiveness of heavy metals.

[0109] The memory 10, processor 20, and communication interface 31 all communicate with each other through the communication bus 32.

[0110] In this embodiment of the invention, the memory 10 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment, the memory 10 may store programs for implementing the following functions:

[0111] Obtain the compost to be predicted, and extract the preset physicochemical indicators and total heavy metal content corresponding to the compost to be predicted;

[0112] The heavy metal validity prediction model is invoked; the heavy metal validity prediction model is a neural network model trained using the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal validity of the sample.

[0113] Based on the preset physicochemical indicators, total heavy metal content, and heavy metal availability prediction model, the predicted heavy metal availability value corresponding to the compost to be predicted is calculated.

[0114] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0115] Furthermore, memory 10 may include read-only memory and random access memory, providing instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores operating systems and operating instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and handling hardware-based tasks.

[0116] Processor 20 can be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic device. Processor 20 can be a microprocessor or any conventional processor. Processor 20 can call programs stored in memory 10.

[0117] Communication interface 31 can be an interface for the communication module, used to connect with other devices or systems.

[0118] Of course, it should be noted that, Figure 5 The structure shown does not constitute a limitation on the heavy metal effectiveness prediction device in the embodiments of this application. In practical applications, the heavy metal effectiveness prediction device may include more than Figure 5More or fewer components as shown, or combinations of certain components.

[0119] The following describes the computer-readable storage medium provided in the embodiments of the present invention. The computer-readable storage medium described below can be referred to in correspondence with the heavy metal effectiveness prediction method described above.

[0120] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described heavy metal effectiveness prediction method.

[0121] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0122] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0123] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0124] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0125] The above provides a detailed description of the heavy metal effectiveness prediction method, apparatus, device, and readable storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting the availability of heavy metals, characterized in that, include: Obtain compost samples to be predicted, and extract the corresponding preset physicochemical indicators and total heavy metal content. Specifically, obtain a preset number of compost samples, and predict the corresponding physicochemical indicators, total heavy metal content, and heavy metal availability of each sample. Perform correlation analysis on the sample physicochemical indicators, total heavy metal content, and heavy metal availability to obtain the preset physicochemical indicators. The preset physicochemical indicators include temperature, conductivity, pH, organic matter, total nitrogen, and total phosphorus. The sample heavy metal availability includes the proportion of exchangeable heavy metals and the proportion of reducible heavy metals. The heavy metal effectiveness prediction model is invoked; wherein, the heavy metal effectiveness prediction model is a neural network model trained using the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal effectiveness of the sample; Based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model, the predicted value of heavy metal availability corresponding to the compost to be predicted is calculated; wherein, the heavy metal availability prediction model is a BP neural network with a single hidden layer. The proportions of exchangeable and reducible heavy metals are determined based on the predicted heavy metal availability values. When the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals exceeds the corresponding preset threshold, the proportion of heavy metals corresponding to the proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals is adjusted.

2. The method for predicting the availability of heavy metals according to claim 1, characterized in that, The adjustment of the heavy metal ratio corresponding to the ratio of exchangeable heavy metals and / or the ratio of reducible heavy metals includes: The proportion of exchangeable heavy metals and / or the proportion of reducible heavy metals are adjusted by utilizing earthworm activity.

3. The method for predicting the availability of heavy metals according to claim 1, characterized in that, The invocation of the heavy metal effectiveness prediction model includes: Obtain the types of heavy metals to be predicted corresponding to the compost to be predicted; Invoke the heavy metal effectiveness prediction model corresponding to the heavy metal species to be predicted.

4. The method for predicting the availability of heavy metals according to any one of claims 1 to 3, characterized in that, The construction process of the heavy metal availability prediction model includes: The preset physicochemical indicators, the total amount of heavy metals in the sample, and the effectiveness of heavy metals in the sample are normalized to obtain normalized training data. The basic neural network model is trained using the normalized training data to obtain the heavy metal effectiveness prediction model.

5. The method for predicting the availability of heavy metals according to claim 4, characterized in that, The normalization process for the preset physicochemical indicators, the total heavy metal content of the sample, and the heavy metal availability of the sample includes: The preset physicochemical indicators, the total amount of heavy metals in the sample, and the effectiveness of heavy metals in the sample are normalized using maximum-minimum normalization.

6. The method for predicting the availability of heavy metals according to claim 1, characterized in that, The step of calculating the predicted heavy metal availability value for the compost to be predicted based on the preset physicochemical indicators, the total heavy metal content, and the heavy metal availability prediction model includes: Based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model, the predicted value of heavy metal availability corresponding to the compost to be predicted is calculated.

7. A heavy metal availability prediction device, characterized in that, The heavy metal availability prediction method according to any one of claims 1 to 6 includes: A preset physicochemical index and heavy metal total extraction module is used to obtain the compost to be predicted and extract the preset physicochemical index and heavy metal total corresponding to the compost to be predicted. The heavy metal validity prediction model calling module is used to call the heavy metal validity prediction model; wherein, the heavy metal validity prediction model is a neural network model trained using the physicochemical indicators of the sample, the total amount of heavy metals in the sample, and the heavy metal validity of the sample; The heavy metal availability prediction value calculation module is used to calculate the heavy metal availability prediction value corresponding to the compost to be predicted based on the preset physicochemical indicators, the total amount of heavy metals, and the heavy metal availability prediction model.

8. A heavy metal availability prediction device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the heavy metal availability prediction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the heavy metals effectiveness prediction method as described in any one of claims 1 to 6.

Images