CN116298190A - Screening and determining method for geochemical investigation index elements - Google Patents
Screening and determining method for geochemical investigation index elements Download PDFInfo
- Publication number
- CN116298190A CN116298190A CN202310099261.2A CN202310099261A CN116298190A CN 116298190 A CN116298190 A CN 116298190A CN 202310099261 A CN202310099261 A CN 202310099261A CN 116298190 A CN116298190 A CN 116298190A
- Authority
- CN
- China
- Prior art keywords
- geochemical
- sample
- elements
- samples
- training
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012216 screening Methods 0.000 title claims abstract description 24
- 238000011835 investigation Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 60
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000012795 verification Methods 0.000 claims abstract description 20
- 238000012706 support-vector machine Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 238000011160 research Methods 0.000 claims abstract description 8
- 230000008030 elimination Effects 0.000 claims abstract description 7
- 238000003379 elimination reaction Methods 0.000 claims abstract description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 8
- 239000011435 rock Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract description 2
- 238000002790 cross-validation Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 229910052500 inorganic mineral Inorganic materials 0.000 description 3
- 239000011707 mineral Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000000556 factor analysis Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 229910052729 chemical element Inorganic materials 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/24—Earth materials
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Geology (AREA)
- Evolutionary Computation (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
- Medical Informatics (AREA)
- Medicinal Chemistry (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Food Science & Technology (AREA)
- Environmental & Geological Engineering (AREA)
Abstract
The invention discloses a screening and determining method of geochemical investigation index elements, which comprises the steps of obtaining geochemical samples in a research area and preprocessing the samples; utilizing the obtained sample after pretreatment, constructing a training sample for machine learning according to an ore forming mode of a research area, wherein the training sample comprises a positive sample and a negative sample, and performing geochemical element analysis on the positive sample and the negative sample to obtain geochemical elements in the positive sample and the negative sample; screening geochemical elements with indication significance to the ores in the positive samples and the negative samples by using an iterative recursion elimination and cross verification method based on a support vector machine to form indication element combinations; and evaluating and screening out the geological interpretation meaning of the indicating elements, and carrying out analysis and test work of geochemistry acquisition samples according to the indicating element combination. The invention can reduce unnecessary geochemical element analysis and test work, thereby reducing the economic cost in geochemical investigation work.
Description
Technical Field
The invention belongs to the field of applied geochemistry, and in particular relates to a screening and determining method of geochemistry investigation index elements.
Background
The geochemical method of investigation is an important means of prospecting in the initial stage of mineral exploration. Reasonable and proper index elements in the geochemistry investigation work can improve the prospecting effect of prospecting; meanwhile, unnecessary test analysis can be reduced, and mineral exploration cost is reduced.
The determination of index elements in survey geochemistry is often determined in two ways. One is based on the prospecting experience and knowledge of geological specialists, and determining exploration geochemical index elements according to the enrichment characteristics of elements in a deposit model; another method utilizes principal component analysis, factor analysis and spatial analysis to determine the index elements of the survey geochemical prospecting.
Based on expert knowledge and experience, the determination of the geochemical index elements is often limited by the knowledge level of geological experts, and index elements possibly determined by different geological experts are combined differently, so that the method has high subjectivity and uncertainty. The data-driven method based on principal component analysis, factor analysis, space analysis and the like is often applied to determining index elements based on a large number of analysis test results of various elements after the analysis test of the geochemical sample is finished, and the working targets and scenes of the method are combinations of the determined index elements and define geochemical anomalies; instead of determining index elements after acquisition of the survey geochemical samples and before testing of all samples, unnecessary survey geochemical element analysis and test work is reduced. Therefore, in order to reduce the cost of the geochemical exploration, it is necessary to provide a method for determining index elements after the geochemical exploration sample collection to serve the test analysis, so as to avoid unnecessary element analysis tests and reduce the cost of the operation.
Chinese patent (CN 106908855A, a method for selecting a combination of geochemical elements based on GIS space analysis) comprehensively selects a combination of geochemical anomalies caused by ore formation by using a multi-fractal spectrum analysis, an asymmetry index and ROC curve method. The method is to screen the combination of geochemical elements and to define the geochemical anomalies. However, the method is based on complete geochemical analysis and test, and cannot well reduce the economic cost of chemical exploration.
Disclosure of Invention
In view of the above, the present invention provides a method for screening and determining index elements of geochemical exploration, comprising the following steps:
s1, acquiring a geochemical sample in a research area, and performing pretreatment on the sample according to a survey geochemical specification to obtain a pretreated sample;
s2, constructing a training sample for machine learning according to an ore forming mode of the research area by using the obtained sample after pretreatment, wherein the training sample comprises a positive sample and a negative sample, and performing geochemical element analysis on the positive sample and the negative sample to obtain geochemical elements in the positive sample and the negative sample;
s3, screening geochemical elements with indication significance for ore formation in the positive sample and the negative sample by using an iterative recursion elimination and cross verification method based on a support vector machine to form indication element combinations;
s4, evaluating and screening out geological interpretation significance of the indicating elements, and carrying out analysis and test work of geochemical acquisition samples according to the combination of the indicating elements.
Further, the step S2 specifically includes:
s21, selecting a geochemical sample acquired in a known area of a deposit and a sampling interval radius range as a positive sample;
s22, randomly selecting samples with the same number as positive samples as negative samples in a rock stratum distribution area which cannot be mineralized and away from a fault area according to an ore formation mode of a deposit;
s23, analyzing and testing the selected positive samples and negative samples for relevant geochemical elements to obtain the content of the geochemical elements in the positive samples and the negative samples, and constructing an instruction geochemical element screening machine learning training data set according to the content of the geochemical elements in the positive samples and the negative samples.
Further, the step S3 specifically includes:
s31, determining the number n of cross verification, dividing a training data set into n parts at random according to a proportion, selecting j parts as verification data, and other parts as training data, wherein j is more than or equal to 1 and less than or equal to n;
s32, training a support vector machine classifier according to the constructed training data;
s33, removing geochemical elements with the smallest score according to the sorting criterion score of the geochemical elements in the training data set, constructing a new training set, retraining the new training set to support the vector machine classifier, and obtaining the classification precision of the support vector machine classifier and the sorting criterion score of the geochemical elements until the geochemical elements in the training data set are removed.
S34, calculating an average value of precision of 5-fold cross verification, searching points with the minimum number of the types of the geochemical elements in the training data set and the highest cross verification precision according to the change rule of the number of the types of the geochemical elements in the training data set and the cross verification precision, and determining the number of the indication elements; and determining the indication element combination according to the geochemical element ordering criterion score in the training dataset.
Further, in step S32, the training support vector machine classifier specifically includes:
searching the classification hyperplane with the optimal training number of all elements, so that omega.x+b=0, and specifically performing according to the following formula:
wherein N is the number of samples of training data in the training data set, ω is a weight, x is the content of each element in the samples, b is a constant, α i And alpha j Lagrangian multipliers, x for the ith and jth samples, respectively i Representing the content of each element in the ith sample, y i Equal to 0 represents a negative sample, y i A value equal to 1 represents a positive sample;
training a vector-holding machine classifier model, and obtaining a ranking criterion score of the ith geochemical element, wherein the ranking criterion score is defined as c i ＝ω i 2 Wherein c i Ranking criterion score, ω, for the ith geochemical element i Is the i-th geochemical element weight coefficient.
The technical scheme provided by the invention has the beneficial effects that:
the invention screens out the most robust exploration geochemical indicating element combination based on the method of iterative recursion elimination cross validation and calculation simulation by selecting a small amount of representative training positive and negative samples after acquisition of the exploration geochemical samples. And then, analyzing and testing are carried out according to the selected indication elements, so that unnecessary element analysis and testing work is reduced, unnecessary element analysis and testing of geochemistry samples in geochemistry exploration work is reduced, and exploration work cost is reduced.
Drawings
FIG. 1 is a flow chart of a method of screening and determining index elements for a geochemical survey in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a method for screening and determining index elements for a geochemical survey in accordance with an embodiment of the present invention;
FIG. 3 is a graph of cross-validation accuracy versus number of elements for an embodiment of the present invention;
FIG. 4 is a graph of the spatial correspondence of geochemical anomalies with known deposits (points) for selected elements of an embodiment of the invention, wherein darker color indicates greater mineral potential in the region with higher element content and five stars represent deposits (points).
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be further described with reference to the accompanying drawings.
Referring to fig. 1 and 2, fig. 1 is a flowchart of a method for screening and determining a geochemical survey index element according to an embodiment of the present invention, and fig. 2 is a flowchart of a method for screening and determining a geochemical survey index element according to an embodiment of the present invention.
The embodiment of the invention provides a screening and determining method of geochemical investigation index elements, which comprises the following steps:
s1, acquiring a geochemical sample in an acquisition research area, and preprocessing the sample according to the survey geochemical specification (DZ/T0011-91) to obtain a preprocessed sample.
In this example, a comparative study was performed using a geochemical sample from a survey in a region of the west of the river, and 7403 geochemical samples were collected during the geochemical survey in that region.
S2, constructing a training sample for machine learning according to an ore forming mode of the research area by using the obtained sample after pretreatment, wherein the training sample comprises a positive sample and a negative sample, and performing geochemical element analysis on the positive sample and the negative sample to obtain geochemical elements in the positive sample and the negative sample.
S21, selecting a geochemical sample acquired within a region where a known deposit (chemical) point is located and a radius range of 1.4 times of a sampling interval as a positive sample;
s22, randomly selecting samples with the same number as positive samples as negative samples in a rock stratum distribution area which cannot be mineralized and away from a fault area according to an ore formation mode of a deposit;
s23, performing analysis and test on the relevant geochemical elements on the selected positive and negative samples to obtain the content of the geochemical elements in the positive and negative samples, and constructing a machine learning training data set for indicating geochemical element screening according to the content of the geochemical elements in the positive and negative samples.
In the embodiment, 52 groups of positive samples and negative samples are selected based on expert knowledge, and the exploration work of W-Cu ore is carried out on the Au, ag, cu, pb, zn, W, sn, mo, bi, as, sb, cr, co, cd, hg, ni, ba elements, the F elements and other 18 elements.
S3, screening geochemical elements with indication significance for ore formation in the positive sample and the negative sample by using an iterative recursion elimination and cross verification method based on a support vector machine.
S31, determining the number n of cross verification, dividing a training data set into n parts at random according to a proportion, selecting j parts as verification data, and other parts as training data, wherein j is more than or equal to 1 and less than or equal to n; in this embodiment, the number of folds of the cross-validation is determined to be n 5.
S32, training a support vector machine classifier according to the constructed training data;
searching the classification hyperplane with the optimal training number of all elements, so that omega.x+b=0, and specifically performing according to the following formula:
wherein ω is a weight, x represents the content of each element in the sample, b is a constant, N is the number of samples, α i And alpha j Lagrangian multipliers, x for the ith and jth samples, respectively i Representing the content of each element in the ith sample, y i Equal to 0 represents a negative sample, y i A value equal to 1 represents a positive sample, and the samples mentioned in the formula are samples of training data in the training data set.
Training a vector holding machine classifier model, and obtaining a ranking criterion score of the ith element, wherein the ranking criterion score is defined as c i ＝ω i 2 Wherein c i Ranking criterion score, ω, for the ith geochemical element i Is the i-th element weight coefficient.
S33, removing geochemical elements in the training data set with the smallest score according to the sorting criterion score of the geochemical elements in the training data set, constructing a new training set, retraining the training set with the support vector machine classifier, and obtaining the classification precision of the support vector machine classifier and the sorting criterion score of the geochemical elements in the training data set until the geochemical elements in the training data set are removed.
S34, calculating an average value of the accuracy of the 5-fold cross validation, referring to FIG. 3, FIG. 3 is a graph showing the relationship between the accuracy of the cross validation and the number of elements in the embodiment of the invention. Searching points with the least geochemical element types and the highest cross verification precision in the training data set according to the change rule of the element types and the cross verification precision, and determining the number of the indication elements according to inflection points with the cross verification precision which is not obviously increased along with the element numbers on the two line diagrams; and then determining the indicated element combination according to the element ordering criterion score.
By the technical process proposed by the patent of the invention, referring to fig. 3, it is found that when the ore-forming element is 8, the verification accuracy is highest and then reduced based on the iterative recursion elimination crossing method of the support vector machine, and according to the variable ordering, 8 elements such as Co, cd, sb, bi, mo, sn, W and Ag are selected as the indication element combination.
S4, evaluating geological interpretation of the screened elements, and analyzing and testing the collected samples according to the combined detection of the screened indication elements.
The selected indicator elements are closely related not only to the type of ore formation in the study area, but also spatially to known deposits (spots).
Compared with the prior art that the analysis test element combination is determined based on expert knowledge, the method provided by the invention greatly reduces the corresponding analysis test cost, and compared with the prior art that the analysis test element combination is determined based on expert knowledge, the process provided by the invention can achieve similar effect by only testing 8 elements, and at least can reduce the analysis test cost by 55.56%. Referring to fig. 4, fig. 4 is a graph showing the spatial correspondence of geochemical anomalies with known deposits (points) for selected elements in accordance with an embodiment of the present invention, wherein darker colors indicate higher levels of elements and greater mineralisation potential for the region, and five stars indicate deposits (points).
The invention solves the basic problem of analyzing and testing chemical elements in geochemistry investigation work by utilizing a machine learning algorithm, and aims to analyze the minimum geochemistry elements in the investigation geochemistry work on the premise of guaranteeing the prospecting effect so as to reduce the economic cost of the investigation geochemistry work and improve the work benefit.
The invention screens out the most robust indication element combination based on the method of iterative recursion elimination cross-validation and calculation simulation by selecting a small amount of representative training positive and negative samples after acquisition of the geochemical samples. And then, analyzing and testing are carried out according to the selected indication element combination, so that unnecessary element analysis and testing work is reduced, unnecessary element analysis and testing of geochemistry samples in the geochemistry exploration work is reduced, and the economic investment cost of the exploration work is reduced.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (4)
1. The screening and determining method of the geochemical investigation index element is characterized by comprising the following steps:
s1, acquiring a geochemical sample in a research area, and performing pretreatment on the sample according to a survey geochemical specification to obtain a pretreated sample;
s2, constructing a training sample for machine learning according to an ore forming mode of the research area by using the obtained sample after pretreatment, wherein the training sample comprises a positive sample and a negative sample, and performing geochemical element analysis on the positive sample and the negative sample to obtain geochemical elements in the positive sample and the negative sample;
s3, screening geochemical elements with indication significance for ore formation in the positive sample and the negative sample by using an iterative recursion elimination and cross verification method based on a support vector machine to form indication element combinations;
s4, evaluating and screening out geological interpretation significance of the indicating elements, and carrying out analysis and test work of geochemical acquisition samples according to the combination of the indicating elements.
2. The method for screening and determining a geochemical survey index element according to claim 1, wherein step S2 specifically comprises:
s21, selecting a sample which is acquired in a known area of the deposit and a time of the radius of the sampling interval and is subjected to pretreatment as a positive sample;
s22, randomly selecting the pretreated samples with the same number as positive samples as negative samples in a rock stratum distribution area which cannot be mineralized and away from a fault area according to an ore formation mode of a deposit;
s23, analyzing and testing the selected positive samples and negative samples for relevant geochemical elements to obtain the content of the geochemical elements in the positive samples and the negative samples, and constructing an instruction geochemical element screening machine learning training data set according to the content of the geochemical elements in the positive samples and the negative samples.
3. The method for screening and determining a geochemical survey index element according to claim 2, wherein step S3 specifically comprises:
s31, determining the number n of cross verification, dividing a training data set into n parts at random according to a proportion, selecting j parts as verification data, and other parts as training data, wherein j is more than or equal to 1 and less than or equal to n;
s32, training a support vector machine classifier according to the constructed training data;
s33, removing geochemical elements with the smallest score according to the sorting criterion score of the geochemical elements in the training data set, constructing a new training set, retraining the new training set to support the vector machine classifier, and obtaining the classification precision of the support vector machine classifier and the sorting criterion score of the geochemical elements until the geochemical elements in the training data set are removed.
S34, calculating an average value of precision of 5-fold cross verification, searching points with the minimum number of the types of the geochemical elements in the training data set and the highest cross verification precision according to a change rule of the number of the types of the geochemical elements in the training data set and the cross verification precision, determining the number of the indicating elements, and determining the combination of the indicating elements according to a score of a sorting criterion of the geochemical elements in the training data set.
4. A method for screening and determining a geochemical survey index element according to claim 3, wherein in step S32, the training support vector machine classifier is specifically:
searching the classification hyperplane with the optimal training number of all elements, so that omega.x+b=0, and specifically performing according to the following formula:
wherein N is the number of samples of training data in the training data set, ω is a weight, x is the content of each element in the samples, b is a constant, α i And alpha j Lagrangian multipliers, x for the ith and jth samples, respectively i Representing the content of each element in the ith sample, y i Equal to 0 represents a negative sample, y i A value equal to 1 represents a positive sample;
training a vector-holding machine classifier model, and obtaining a ranking criterion score of the ith geochemical element, wherein the ranking criterion score is defined as c i ＝ω i 2 Wherein c i Ranking criterion score, ω, for the ith geochemical element i Is the i-th geochemical element weight coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310099261.2A CN116298190A (en) | 2023-02-01 | 2023-02-01 | Screening and determining method for geochemical investigation index elements |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310099261.2A CN116298190A (en) | 2023-02-01 | 2023-02-01 | Screening and determining method for geochemical investigation index elements |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116298190A true CN116298190A (en) | 2023-06-23 |
Family
ID=86782544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310099261.2A Pending CN116298190A (en) | 2023-02-01 | 2023-02-01 | Screening and determining method for geochemical investigation index elements |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116298190A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117129656A (en) * | 2023-09-19 | 2023-11-28 | 昆明理工大学 | Screening and determining method and device for geochemical investigation index elements |
-
2023
- 2023-02-01 CN CN202310099261.2A patent/CN116298190A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117129656A (en) * | 2023-09-19 | 2023-11-28 | 昆明理工大学 | Screening and determining method and device for geochemical investigation index elements |
| CN117129656B (en) * | 2023-09-19 | 2024-03-19 | 昆明理工大学 | Screening and determining method and device for geochemical investigation index elements |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110442666B (en) | Mineral resource prediction method and system based on neural network model | |
| CN103345566B (en) | Based on the geochemical anomaly discrimination and evaluation method of Geological Connotation | |
| CN106503689A (en) | Neutral net local discharge signal mode identification method based on particle cluster algorithm | |
| CN110378070A (en) | Based on PSO-SVR and the united Prediction of Displacement in Landslide method of DES | |
| CN110674841A (en) | Logging curve identification method based on clustering algorithm | |
| CN108038081B (en) | Landslide disaster logistic regression analysis method based on characteristic function spatial filtering value | |
| CN114898109B (en) | Zeolite type mineral product prediction method and system based on deep learning | |
| CN117272181B (en) | Method for discriminating zircon host rock and ore forming environment by machine learning modeling | |
| CN116298190A (en) | Screening and determining method for geochemical investigation index elements | |
| CN106779086A (en) | A kind of integrated learning approach and device based on Active Learning and model beta pruning | |
| CN115327616B (en) | Automatic positioning method for mine microseism focus driven by massive data | |
| CN110232334A (en) | A kind of steel construction corrosion recognition methods based on convolutional neural networks | |
| Zhang et al. | Research on surface defect detection algorithm of strip steel based on improved YOLOV3 | |
| CN107632010A (en) | A kind of quantitative approach of combination LIBS to steel samples | |
| CN114926299A (en) | Prediction method for predicting vehicle accident risk based on big data analysis | |
| CN115598162B (en) | Soil heavy metal content detection method based on stacked model | |
| CN110427957A (en) | A kind of classification method and device of the geochemistry data based on machine learning | |
| CN113283467B (en) | Weak supervision picture classification method based on average loss and category-by-category selection | |
| CN117994240A (en) | Multi-scale two-level optical remote sensing image stripe noise intelligent detection method and device | |
| CN117911677A (en) | Tunnel lining crack intelligent identification method based on small target identification algorithm | |
| CN111580179B (en) | Method, device and system for determining organic carbon content | |
| CN110118994A (en) | A kind of nonmarine source rock quantitative forecasting technique based on seismic inversion and machine learning | |
| CN113720952B (en) | Method, device, equipment and medium for generating image plate for reservoir interpretation evaluation | |
| CN115203970A (en) | Diagenetic parameter prediction model training method and prediction method based on artificial intelligence algorithm | |
| CN114997666A (en) | Method for evaluating easiness of region debris flow |
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 |