CN114548747A - Spatial interpolation method and device for heavy metals in soil, electronic equipment and medium - Google Patents
Spatial interpolation method and device for heavy metals in soil, electronic equipment and medium Download PDFInfo
- Publication number
- CN114548747A CN114548747A CN202210153657.6A CN202210153657A CN114548747A CN 114548747 A CN114548747 A CN 114548747A CN 202210153657 A CN202210153657 A CN 202210153657A CN 114548747 A CN114548747 A CN 114548747A
- Authority
- CN
- China
- Prior art keywords
- soil
- model
- sample
- heavy metal
- spatial interpolation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention discloses a spatial interpolation method, a spatial interpolation device, electronic equipment and a medium for heavy metals in soil, wherein the method comprises the following steps: collecting soil samples from a plurality of sample plots in a target area, and acquiring related attribute data of the soil samples in the sample plots; inputting relevant attribute data of a soil sample in a sample plot into a constructed Stacking integration model for spatial interpolation of soil heavy metals, and preferably selecting an optimal integration model suitable for the soil heavy metals in a target area; carrying out transfer learning on the optimal integrated model by using the relevant attribute data of the soil samples in other sample plots to obtain an optimal soil heavy metal spatial interpolation model suitable for the target area; and inputting the relevant attribute data of the soil of the target area into an optimal soil heavy metal spatial interpolation model, and combining ArcGIS software to obtain a spatial interpolation result of the soil. The method, the device, the electronic equipment and the medium in the embodiment of the invention can better improve the spatial interpolation performance of the heavy metal in the soil, and are more suitable for the space environment.
Description
Technical Field
The invention belongs to the technical field of spatial simulation, and particularly relates to a soil heavy metal spatial interpolation method based on integrated learning and transfer learning.
Background
With the rapid development of industry, the increasing severity of environmental pollution, the increasing variety and quantity of agricultural chemicals, the change of land properties is more and more frequent, and pollutants containing heavy metals enter soil through various ways, so that the environmental problems of heavy metal accumulation and overproof of soil in China are increasingly prominent. Heavy metals in soil have the characteristics of high toxicity, difficult degradation, strong durability, strong carcinogenicity and the like, influence an ecological structure system in soil through ways of circulation, enrichment, migration and transformation and the like, inhibit microbial functions, not only can produce adverse effects on crops and cause the reduction of crop yield and the quality of agricultural products, but also can bring potential harm to human health because heavy metals accumulated by crops can enter human bodies through food chains. Therefore, the comprehensive prevention and control of heavy metal pollution in the soil system becomes a hotspot and a difficult point of domestic and foreign research.
The spatial distribution characteristics of various heavy metal pollutants in the soil can be known in detail by adopting a spatial interpolation method. The soil heavy metal pollution distribution has high spatial variation, and the reasonable selection of a spatial interpolation method has great significance for knowing the spatial distribution characteristics of the soil heavy metal pollution in detail. The soil heavy metal spatial interpolation method is influenced by many factors such as soil heavy metal content and spatial distribution, for example: data density, soil type, sample quantity, spatial distribution of samples, accuracy of data, and influence of factors such as manpower, material resources and financial resources. At present, the research on the spatial distribution of the heavy metal in the soil is mostly started from the spatial change characteristics of a single soil heavy metal element; or carrying out comparison analysis on interpolation accuracy of different numbers of samples in the same area, and carrying out accuracy comparison by using multiple interpolation methods. Clear and consistent conclusion is not formed about the spatial interpolation method for selecting the soil heavy metals, namely different interpolation methods have different applicability to different data, and at present, no spatial interpolation method which can be completely applied exists.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a soil heavy metal spatial interpolation method based on integrated learning and transfer learning aiming at the defects of the prior art. The method provides a soil heavy metal data spatial interpolation method based on integrated learning and transfer learning with strong applicability, can provide scientific basis for the spatial distribution condition of heavy metal pollution in soil of each polluted site, further provides data support for prevention and treatment work of heavy metal pollution, and also can provide reference for reasonable planning, development, environmental quality protection and sustainable utilization of urban development planning and land utilization.
In order to solve the technical problems, the invention adopts the technical scheme that: a soil heavy metal spatial interpolation method based on ensemble learning and transfer learning is characterized by comprising the following steps:
collecting soil samples from a plurality of sample plots in a target area, and acquiring related attribute data of the soil samples in the sample plots, wherein the related attribute data comprise the content of target heavy metals in sample plot soil;
inputting relevant attribute data of a soil sample in a sample plot into a constructed Stacking integration model for spatial interpolation of soil heavy metals, and preferably selecting an optimal integration model which is suitable for the soil heavy metals in the target area in the Stacking integration model;
carrying out transfer learning on the optimal integrated model by using the related attribute data of the soil samples in other sample plots to obtain an optimal soil heavy metal spatial interpolation model suitable for the target region;
and inputting the relevant attribute data of the soil of the target area into an optimal soil heavy metal spatial interpolation model, and combining ArcGIS software to obtain a spatial interpolation result of the soil.
Further, the related attribute dataset for the intra-plot soil sample comprises: sample plot number, sample longitude, sample latitude, sample elevation, sample grade, sample land utilization type, sample soil type and content of target heavy metal in sample soil.
Further, the standard weight metal is chromium, nickel content, mercury or lead; the chromium content, the nickel content and the lead content in the sample plot soil are measured by adopting an inductively coupled plasma atomic emission spectrometry; the mercury content in the soil of the sample plot is measured by reduction gasification-atomic fluorescence spectrometry.
Further, inputting relevant attribute data of a soil sample in one sample plot into the constructed Stacking integration model for spatial interpolation of soil heavy metals, and preferably selecting an optimal integration model suitable for the soil of the target area in the Stacking integration model; the method specifically comprises the following steps:
acquiring a soil heavy metal data set of a soil sample in a sample plot, and dividing the soil heavy metal data set into a training set and a verification set;
adopting a Stacking integration strategy, integrating a model of an inverse distance weight method, a model of a local polynomial method, a model of a radial basis function method, a model of a natural neighborhood method, a model of a spline function method, a model of a common kriging method, a model of a pan kriging method and a model of a collaborative kriging method as a model set of a primary learner, and adopting the training set to respectively carry out soil heavy metal spatial interpolation on the models in the model set of the primary learner;
and detecting the spatial interpolation precision of the soil heavy metal space interpolation result obtained by each model in the model set by adopting the verification set, selecting the optimal model as a secondary learner to carry out spatial interpolation, and obtaining a final interpolation result, namely preferably selecting the optimal integration model which is suitable for the soil metal in the target area in the Stacking integration models.
Further, the proportion of the training set and the validation set in the soil heavy metal data set is 80% and 20%, respectively.
Further, the method used for detecting the spatial interpolation precision by adopting the verification set is a cross-validation method, and the indexes for evaluating the precision comprise: average error, average absolute error, and root mean square error.
According to another aspect of the present invention, there is provided a soil heavy metal spatial interpolation device integrating learning and migration learning, including:
the extraction module is used for collecting soil samples of a plurality of sample plots in a target area and acquiring related attribute data of the soil samples in the sample plots, wherein the related attribute data comprise the content of target heavy metals in the soil of the sample plots;
the generating module is used for inputting relevant attribute data of a soil sample in one sample plot into the constructed Stacking integrated model to perform spatial interpolation of the soil heavy metal, and preferably selecting an optimal integrated model which is suitable for the soil heavy metal of the target area in the Stacking integrated model;
the optimization module is used for carrying out transfer learning on the optimal integrated model by utilizing the relevant attribute data of the soil samples in other sample plots to obtain an optimal soil heavy metal spatial interpolation model suitable for the target region;
and the result output module is used for inputting the relevant attribute data of the soil of the target area into an optimal soil heavy metal spatial interpolation model and obtaining a spatial interpolation result of the soil by combining ArcGIS software.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a soil heavy metal spatial interpolation method based on ensemble learning and migratory learning as described.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions, the computer instructions being operable to execute the method for spatial interpolation of soil heavy metals based on ensemble learning and migration learning.
Compared with the prior art, the invention has the following advantages: the invention solves the problem that the implicit valuation function of the common spatial interpolation method in the prior art can not adapt to specific complex data and space-related environment; the interpolation model combining the geological environment variables also has some defects, for example, many researches use single and same type of geological environment variables to solve the prediction problem of different regions, however, different regions are influenced by different factors, and the considered environment variables are different. The spatial interpolation method based on the combination of the ensemble learning method and the transfer learning method can better overcome the difficulty of the common spatial interpolation method and can better improve the interpolation performance. The method provided by the embodiment of the invention can obtain the spatial interpolation result of multiple soil heavy metals which accord with actual spatial distribution, and can provide effective theoretical basis for soil heavy metal risk management and control.
In the invention, in the process of migration learning of the ensemble learning model, after the target heavy metal data in one sample plot in the same region is constructed into the optimal ensemble model, the data of the target heavy metal in other sample plots in the same region are used for migration learning of the existing optimal ensemble model, retraining of the whole model from beginning to end is not needed, and only a new data set is input on the basis of the trained optimal ensemble model for optimization iteration, so that the learning efficiency of the model is accelerated and optimized.
The technical solution of the present invention is further described in detail by the accompanying drawings and examples.
Drawings
Fig. 1 is a flowchart of a soil heavy metal data spatial interpolation method based on ensemble learning and transfer learning according to the present invention.
FIG. 2 is a flow chart for constructing a Stacking integration model provided by the present invention.
Detailed Description
Example 1
Fig. 1 is a flowchart of a spatial interpolation method for soil heavy metal data based on ensemble learning and migration learning according to an embodiment of the present invention, and as shown in fig. 1, the present invention provides a spatial interpolation method for soil heavy metal data based on ensemble learning and migration learning, including the steps of:
s1, collecting soil samples for a plurality of sample plots in the target area, and obtaining related attribute data of the soil samples in the sample plots, wherein the related attribute data comprise the content of the target heavy metal in the sample plot soil.
S2, inputting the relevant attribute data of the soil sample in one sample plot into the constructed Stacking integration model for spatial interpolation of the soil heavy metals, and preferably selecting an optimal integration model suitable for the soil heavy metals in the target area in the Stacking integration model, as shown in fig. 2, specifically including:
s201, acquiring a soil heavy metal data set of a soil sample in a sample plot, and dividing the soil heavy metal data set into a training set and a verification set;
s202, adopting a Stacking integration strategy, integrating a model of an inverse distance weight method, a model of a local polynomial method, a model of a radial basis function method, a model of a natural neighborhood method, a model of a spline function method, a model of a common Kriging method, a model of a pan Kriging method and a model of a collaborative Kriging method as a model set of a primary learner, and adopting the training set to perform soil heavy metal spatial interpolation on the models in the model set of the primary learner respectively;
s203, detecting spatial interpolation precision of the verification set is adopted for soil heavy metal spatial interpolation results obtained by each model in the model set, the optimal model is selected as a secondary learner to carry out spatial interpolation, and a final interpolation result is obtained, namely the optimal integration model which is suitable for the soil metal in the target area in the Stacking integration model is selected preferably.
And S3, carrying out transfer learning on the optimal integrated model by using the related attribute data of the soil samples in other sample plots to obtain an optimal soil heavy metal spatial interpolation model suitable for the target region.
And S4, inputting the relevant attribute data of the soil of the target area into an optimal soil heavy metal spatial interpolation model, and combining ArcGIS software to obtain a spatial interpolation result of the soil.
In this embodiment, the related attribute data set of the intra-specimen soil sample includes: sample plot number, sample longitude, sample latitude, sample elevation, sample gradient, sample land utilization type, sample soil type and content of target heavy metal in sample soil; the standard weight metal is chromium, nickel content, mercury or lead;
in the embodiment, factors such as climate conditions, soil texture, geological landform and soil utilization type of a target area are comprehensively considered, soil sampling points are arranged in a gridding mode, 200 sampling points with the depth of 0-20cm are selected, geographic longitude and latitude coordinates and elevation values are accurately measured through a GPS, and basic information such as the gradient of the sampling points, the soil utilization type and the soil type is recorded in detail. Collecting a soil sample by using a stainless steel soil drill, and vertically burying the soil sample to a specified depth; the soil sampling depth, the soil weight and the proportion of the upper layer and the lower layer of each sampling point are kept uniform and consistent. The soil sample is reserved by about 1kg from soil of various points according to a quartering method. After the soil sample is taken back to the laboratory, the sample in the sample bag is taken back to the laboratory, the impurities such as stones, plant residues and the like in the sample bag are removed by a screen after the sample bag is naturally air-dried at room temperature in a dust-free environment, a stick is used for grinding, and the soil sample is digested and boiled by strong acid.
Grinding the soil sample into powder, sieving the powder by a nylon sieve of 100 meshes, and digesting the total amount of the heavy metals in the soil by adopting a standard method established by American EPA to prepare a soil sample standard solution.
The contents of chromium (Cr), nickel (Ni) and lead (Pb) are measured by an inductively coupled plasma atomic emission spectrometry; measuring the content of mercury (Hg) by reduction gasification-atomic fluorescence spectrometry; and carrying out statistics on the obtained soil heavy metal content data by using Excel.
In this embodiment, the division of the data in the soil heavy metal data set in S201 is uniformly distributed and randomly generated based on a randomness principle by using a ground statistic analysis module in the Arcgis software, so that the occurrence of results such as uneven data distribution and one-sidedness during manual selection is avoided, and the working efficiency is improved. Respectively selecting samples accounting for 80% of the total weight as a training set, and selecting samples accounting for 20% of the total weight as a verification set;
in the embodiment, the problem of insufficient detection precision of the independent verification model exists, and the quality of the interpolation method can be evaluated more optimally by using cross verification; the cross validation method assumes that the element value of one sampling point is unknown each time, estimates the element value by using the observed values of the rest sampling points so as to obtain the estimated value of each sampling point, and judges the quality of the interpolation method according to the error magnitude of the actual observed values and the estimated values of all the sampling points;
in this embodiment, the method used for detecting the spatial interpolation precision by using the validation set is a cross validation method, and the evaluation precision index includes: mean Error (ME), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE);
ME is a measure of unbiasedness, with closer to 0 indicating unbiased methods;
MAE and RMSE reflect the estimated value sensitivity and extreme value effect of the model, and the smaller the value is, the higher the interpolation precision is;
in the formula: n is the number of sampling points used for verification; z (X)i) The calculation result of the spatial interpolation method of the target heavy metal content in the sampling point soil is obtained; z (X)i) The method is an actual measurement value of the content of target heavy metal in the soil of the sampling point.
In this embodiment, the model of the inverse distance weight method, the model of the local polynomial method, the radial basis function method, the model of the natural neighborhood method, the model of the spline function method, and the model of the ordinary kriging method: the input values contain spatial information (X, Y, Z coordinates of the target heavy metal distribution): sample longitude, sample latitude, sample elevation and target heavy metal content in sample soil; and (3) outputting a value: grid data (spatial interpolation plot) of the target heavy metal; the input values of the model of the pan kriging method and the model of the collaborative kriging method need to be added with covariates besides the spatial information; specific input values include: sample longitude, sample latitude, sample elevation, sample gradient, sample land utilization type, sample soil type and content of target metal in sample soil; and (3) outputting a value: grid data of target heavy metal (space interpolation graph)
According to the embodiment of the invention, after the target heavy metal data in one sample plot in the same region is constructed into the optimal integration model, the data of the target heavy metal in other sample plots in the same region is used for carrying out transfer learning on the existing optimal integration model, the whole model does not need to be retrained from beginning to end, and only a new data set needs to be input on the basis of the trained optimal integration model for optimization iteration, so that the learning efficiency of the model is accelerated and optimized.
The embodiment of the invention also provides a soil heavy metal spatial interpolation device integrating learning and transfer learning, which comprises:
the extraction module is used for collecting soil samples of a plurality of sample plots in a target area and acquiring related attribute data of the soil samples in the sample plots, wherein the related attribute data comprise the content of target heavy metals in the soil of the sample plots;
the generating module is used for inputting relevant attribute data of a soil sample in one sample plot into the constructed Stacking integrated model to perform spatial interpolation of the soil heavy metal, and preferably selecting an optimal integrated model which is suitable for the soil heavy metal of the target area in the Stacking integrated model;
the optimization module is used for carrying out transfer learning on the optimal integrated model by utilizing the relevant attribute data of the soil samples in other sample plots to obtain an optimal soil heavy metal spatial interpolation model suitable for the target region;
and the result output module is used for inputting the relevant attribute data of the soil of the target area into an optimal soil heavy metal spatial interpolation model and obtaining a spatial interpolation result of the soil by combining ArcGIS software.
An embodiment of the present invention further provides an electronic device, where the electronic device includes:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method for spatial interpolation of soil heavy metals based on ensemble learning and migratory learning as described.
The embodiment of the invention also provides a computer-readable storage medium, which stores computer instructions, wherein the computer instructions are operated to execute the soil heavy metal spatial interpolation method based on the ensemble learning and the transfer learning.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way. Any simple modification, change and equivalent changes of the above embodiments according to the technical essence of the invention are still within the protection scope of the technical solution of the invention.
Claims (9)
1. A soil heavy metal spatial interpolation method based on ensemble learning and transfer learning is characterized by comprising the following steps:
collecting soil samples from a plurality of sample plots in a target area, and acquiring related attribute data of the soil samples in the sample plots, wherein the related attribute data comprise the content of target heavy metals in sample plot soil;
inputting relevant attribute data of a soil sample in a sample plot into a constructed Stacking integration model for spatial interpolation of soil heavy metals, and preferably selecting an optimal integration model which is suitable for the soil heavy metals in the target area in the Stacking integration model;
carrying out transfer learning on the optimal integrated model by using the related attribute data of the soil samples in other sample plots to obtain an optimal soil heavy metal spatial interpolation model suitable for the target region;
and inputting the relevant attribute data of the soil of the target area into an optimal soil heavy metal spatial interpolation model, and combining ArcGIS software to obtain a spatial interpolation result of the soil.
2. The soil heavy metal spatial interpolation method based on ensemble learning and migration learning of claim 1, wherein the related attribute data set of the in-situ soil sample comprises: sample plot number, sample longitude, sample latitude, sample elevation, sample grade, sample land utilization type, sample soil type and content of target heavy metal in sample soil.
3. The soil heavy metal spatial interpolation method based on ensemble learning and transfer learning of claim 2, wherein the target heavy metal is chromium, nickel, mercury or lead; the chromium content, the nickel content and the lead content in the sample plot soil are measured by adopting an inductively coupled plasma atomic emission spectrometry; the mercury content in the soil of the sample plot is measured by reduction gasification-atomic fluorescence spectrometry.
4. The soil heavy metal spatial interpolation method based on ensemble learning and migration learning of claim 1, wherein the soil heavy metal spatial interpolation is performed by inputting the relevant attribute data of the soil sample in one sample plot into the constructed Stacking integration model, and the optimal integration model suitable for the soil in the target area in the Stacking integration model is preferably selected; the method specifically comprises the following steps:
acquiring a soil heavy metal data set of a soil sample in a sample plot, and dividing the soil heavy metal data set into a training set and a verification set;
adopting a Stacking integration strategy, integrating a model of an inverse distance weight method, a model of a local polynomial method, a model of a radial basis function method, a model of a natural neighborhood method, a model of a spline function method, a model of a common kriging method, a model of a pan kriging method and a model of a collaborative kriging method as a model set of a primary learner, and adopting the training set to respectively carry out soil heavy metal spatial interpolation on the models in the model set of the primary learner;
and detecting the spatial interpolation precision of the soil heavy metal space interpolation result obtained by each model in the model set by adopting the verification set, selecting the optimal model as a secondary learner to carry out spatial interpolation, and obtaining a final interpolation result, namely preferably selecting the optimal integration model which is suitable for the soil metal in the target area in the Stacking integration models.
5. The soil heavy metal spatial interpolation method based on ensemble learning and migration learning of claim 4, wherein the proportion of the training set and the validation set in the soil heavy metal data set is 80% and 20%, respectively.
6. The soil heavy metal spatial interpolation method based on ensemble learning and migration learning of claim 4, wherein the method for detecting the spatial interpolation precision by using the validation set is a cross validation method, and the evaluation precision index comprises: average error, average absolute error, and root mean square error.
7. The utility model provides a soil heavy metal's of integrated study and migratory learning spatial interpolation device which characterized in that includes:
the extraction module is used for collecting soil samples of a plurality of sample plots in a target area and acquiring related attribute data of the soil samples in the sample plots, wherein the related attribute data comprise the content of target heavy metals in the soil of the sample plots;
the generating module is used for inputting relevant attribute data of a soil sample in one sample plot into the constructed Stacking integrated model to perform spatial interpolation of the soil heavy metal, and preferably selecting an optimal integrated model which is suitable for the soil heavy metal of the target area in the Stacking integrated model;
the optimization module is used for carrying out transfer learning on the optimal integrated model by utilizing the relevant attribute data of the soil samples in other sample plots to obtain an optimal soil heavy metal spatial interpolation model suitable for the target region;
and the result output module is used for inputting the relevant attribute data of the soil of the target area into an optimal soil heavy metal spatial interpolation model and obtaining a spatial interpolation result of the soil by combining ArcGIS software.
8. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for soil heavy metal spatial interpolation based on ensemble learning and migration learning of any one of claims 1-6.
9. A computer-readable storage medium storing computer instructions operable to perform the method for soil heavy metal spatial interpolation based on ensemble learning and migration learning of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210153657.6A CN114548747A (en) | 2022-02-19 | 2022-02-19 | Spatial interpolation method and device for heavy metals in soil, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210153657.6A CN114548747A (en) | 2022-02-19 | 2022-02-19 | Spatial interpolation method and device for heavy metals in soil, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114548747A true CN114548747A (en) | 2022-05-27 |
Family
ID=81674725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210153657.6A Pending CN114548747A (en) | 2022-02-19 | 2022-02-19 | Spatial interpolation method and device for heavy metals in soil, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114548747A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106996969A (en) * | 2017-03-03 | 2017-08-01 | 北京农业质量标准与检测技术研究中心 | A kind of heavy metal-polluted soil spatial distribution Forecasting Methodology and system |
| CN111678866A (en) * | 2020-05-28 | 2020-09-18 | 电子科技大学 | Soil water content inversion method for multi-model ensemble learning |
| CN113012771A (en) * | 2021-04-13 | 2021-06-22 | 广东工业大学 | Soil heavy metal spatial interpolation method and device and computer readable storage medium |
| AU2021102432A4 (en) * | 2021-05-10 | 2021-06-24 | Beijing Research Center For Agricultural Standards And Testing | Estimation method and apparatus for heavy metal content of soil |
-
2022
- 2022-02-19 CN CN202210153657.6A patent/CN114548747A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106996969A (en) * | 2017-03-03 | 2017-08-01 | 北京农业质量标准与检测技术研究中心 | A kind of heavy metal-polluted soil spatial distribution Forecasting Methodology and system |
| CN111678866A (en) * | 2020-05-28 | 2020-09-18 | 电子科技大学 | Soil water content inversion method for multi-model ensemble learning |
| CN113012771A (en) * | 2021-04-13 | 2021-06-22 | 广东工业大学 | Soil heavy metal spatial interpolation method and device and computer readable storage medium |
| AU2021102432A4 (en) * | 2021-05-10 | 2021-06-24 | Beijing Research Center For Agricultural Standards And Testing | Estimation method and apparatus for heavy metal content of soil |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Benaud et al. | National-scale geodata describe widespread accelerated soil erosion | |
| Moreau et al. | An approach for global sensitivity analysis of a complex environmental model to spatial inputs and parameters: A case study of an agro-hydrological model | |
| Dawson et al. | Quantifying pollen-vegetation relationships to reconstruct ancient forests using 19th-century forest composition and pollen data | |
| Groenendijk et al. | Performance assessment of nitrate leaching models for highly vulnerable soils used in low-input farming based on lysimeter data | |
| CN108918815B (en) | Method for predicting heavy metal risk of soil | |
| Hollaway et al. | The challenges of modelling phosphorus in a headwater catchment: Applying a ‘limits of acceptability’uncertainty framework to a water quality model | |
| Schillaci et al. | New pedotransfer approaches to predict soil bulk density using WoSIS soil data and environmental covariates in Mediterranean agro-ecosystems | |
| Li et al. | Modelling irrigated maize with a combination of coupled-model simulation and uncertainty analysis, in the northwest of China | |
| CN111707490B (en) | Agricultural land soil pollution investigation staged partition sampling method | |
| Duan et al. | Field capacity in black soil region, northeast China | |
| CN113011372B (en) | Automatic monitoring and identifying method for saline-alkali soil | |
| CN109118004B (en) | Prediction method for suitable area for engineering construction site selection | |
| CN108764527B (en) | Screening method for soil organic carbon library time-space dynamic prediction optimal environment variables | |
| Lena et al. | Determination of irrigation scheduling thresholds based on HYDRUS-1D simulations of field capacity for multilayered agronomic soils in Alabama, USA | |
| CN107679756B (en) | Soil suitability evaluation method and device | |
| CN115660407A (en) | Training method and training device for pollution site risk grade prediction model | |
| CN115758270A (en) | Soil mineral bound state organic carbon prediction method and device based on random forest and environment variables | |
| CN115345069A (en) | Lake water volume estimation method based on maximum water depth record and machine learning | |
| Fiener et al. | A compilation and meta-analysis of rainfall simulation data on arable soils | |
| Confalonieri et al. | An integrated procedure to evaluate hydrological models | |
| Zhao et al. | Uncertainty assessment of mapping mercury contaminated soils of a rapidly industrializing city in the Yangtze River Delta of China using sequential indicator co-simulation | |
| CN114548747A (en) | Spatial interpolation method and device for heavy metals in soil, electronic equipment and medium | |
| CN116608900A (en) | Dynamic evaluation method for geological ecological environment | |
| Cunningham et al. | Generating spatially and statistically representative maps of environmental variables to test the efficiency of alternative sampling protocols | |
| CN113157772A (en) | Lake proper ecological water level determination method based on ancient lake and marsh method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |