CN117195750A - Landslide disaster sensitivity model construction method based on time sequence deformation - Google Patents
Landslide disaster sensitivity model construction method based on time sequence deformation Download PDFInfo
- Publication number
- CN117195750A CN117195750A CN202311464482.1A CN202311464482A CN117195750A CN 117195750 A CN117195750 A CN 117195750A CN 202311464482 A CN202311464482 A CN 202311464482A CN 117195750 A CN117195750 A CN 117195750A
- Authority
- CN
- China
- Prior art keywords
- landslide
- sensitivity
- model
- evaluation
- deformation
- 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.)
- Granted
Links
- 230000035945 sensitivity Effects 0.000 title claims abstract description 61
- 238000010276 construction Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000011156 evaluation Methods 0.000 claims abstract description 34
- 238000013210 evaluation model Methods 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims abstract description 7
- 238000011160 research Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 6
- 238000012706 support-vector machine Methods 0.000 claims abstract description 4
- 238000007637 random forest analysis Methods 0.000 claims description 5
- 238000011161 development Methods 0.000 claims description 4
- 230000000763 evoking effect Effects 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 241000251204 Chimaeridae Species 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000003062 neural network model Methods 0.000 abstract description 3
- 238000005192 partition Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
Abstract
The application discloses a landslide disaster sensitivity model construction method based on time sequence deformation, which relates to the technical field of geological disaster early warning, and comprises the following steps: constructing an influence factor database and extracting an evaluation index; performing optimal discretization on the evaluation index; screening the evaluation index; based on the screened evaluation index, constructing a landslide sensitivity evaluation model by adopting a deterministic factor model and a support vector machine model, and acquiring a landslide sensitivity value; verifying the accuracy of the landslide sensitivity evaluation model based on the ROC curve; dividing landslide sensitivity values based on a natural breakpoint method; combining the SBAS-InSAR model with the landslide sensitivity evaluation model to obtain a comprehensive evaluation result; and dividing the sensitive area of the research area based on the comprehensive evaluation result. The method combines the neural network model method with the InSAR technology to obtain an accurate and effective landslide sensitivity partition map, and has a good effect in judging the occurrence possibility of landslide.
Description
Technical Field
The application belongs to the technical field of geological disaster early warning, and particularly relates to a landslide disaster sensitivity model construction method based on time sequence deformation.
Background
Collapse, landslide and debris flow are the most common natural geological disasters in mountain areas, and due to the characteristics of high occurrence frequency, huge destructive power and the like, monitoring and investigation on the hidden danger areas of the geological disasters are urgently needed, so that knowledge is provided for a disaster early warning system. At present, the regional geological disaster early warning model mainly aims at a meteorological risk early warning model, and in practical application, the occurrence situation of the disaster is often contradicted with the geological disaster meteorological risk early warning grading situation, because the information collection about model early warning is not perfect, and the influence of reference artificial activity factors on the occurrence of the geological disaster is also lacking in early warning taking the meteorological model as a leading part.
Disclosure of Invention
The application aims to provide a landslide hazard sensitivity model construction method based on time sequence deformation, which aims to solve the problems in the prior art.
In order to achieve the above purpose, the application provides a landslide hazard sensitivity model construction method based on time sequence deformation, which comprises the following steps:
constructing an influence factor database of landslide disasters in a research area, and extracting evaluation indexes based on the influence factor database;
performing optimal discretization on the evaluation index based on a ChiMerge discretization method, and performing optimal distance division on linear factors;
screening the evaluation index;
based on the screened evaluation index, constructing a landslide sensitivity evaluation model by adopting a deterministic factor model and a support vector machine model, and acquiring a landslide sensitivity value based on the landslide sensitivity evaluation model;
verifying the accuracy of the landslide sensitivity evaluation model based on an ROC curve; dividing the landslide sensitivity value based on a natural breakpoint method;
combining the SBAS-InSAR model with the landslide sensitivity evaluation model to obtain a comprehensive evaluation result;
based on the comprehensive evaluation result, a natural breakpoint method is adopted to divide the sensitive area of the research area.
Optionally, the construction process of the influence factor database includes:
intrinsic driving and extrinsic evoked factor data associated with landslide development in the study area is collected, and an influence factor database is constructed based on the intrinsic driving and extrinsic evoked factor data.
Optionally, the method for performing optimal discretization on the evaluation index based on the chimere discretization method and performing optimal distance division on the linear factor comprises the following steps:
wherein x represents an optimal distance, and k represents a category number; a is that ij Representing the number of j types of samples in the i interval; e (E) ij The number of j types of samples in the interval i is represented according to the proportion of the j types of samples in the whole; r is R i The table is the number of samples in interval i; c (C) j The table is the number of j class samples; n represents the total number of samples.
Optionally, the process of screening the evaluation index includes:
and (3) checking and evaluating the index collinearity based on the variance expansion factor and the tolerance, and checking and evaluating the importance of the index based on the random forest out-of-bag error.
Optionally, the deterministic factor model includes:
wherein,deterministic coefficient representing landslide, ++>Representing the number N of landslide of the type in the data i Area S of the same kind of landslide i Ratio of->Representing the ratio of the total number N of landslide to the total area S, indicating the certainty of landslide occurrence and +.>The values are positively correlated, +.>The value is [ -1, 1]Within the interval, when->When the value approaches 1, this indicates a high probability of occurrence of landslide.
Optionally, the method for verifying the accuracy of the landslide sensitivity evaluation model based on the ROC curve comprises the following steps:
AUC values under the ROC curve are in the [0,1] interval, and when the AUC values are close to zero, the effect of the landslide sensitivity evaluation model is poor, and the accuracy of the model is higher as the AUC values are close to 1.
Optionally, the method for dividing the landslide sensitivity value based on the natural breakpoint method comprises the following steps:
wherein,the sum of squares of the deviations is expressed, i and j respectively denote the number of the ith and jth elements C of the class N group, K denotes the number between i and j, K denotes the kth element of the C group, and N denotes the total number of samples.
Optionally, the process of combining the SBAS-InSAR model with the landslide sensitivity evaluation model includes:
acquiring a deformation rate based on the SBAS-InSAR model, and respectively giving weight to the deformation rate and the landslide sensitivity value by adopting weighted superposition operation so as to combine the deformation rate and the landslide sensitivity value;
and carrying out normalization treatment on the deformation rate to obtain an improved landslide sensitivity distribution map.
Optionally, the sensitive area division is performed on the research area by adopting a natural breakpoint method, which specifically comprises the following steps: the natural breakpoint method is used to divide the investigation region into very low, medium, high and very high sensitive regions.
The application has the technical effects that:
the application provides a landslide disaster sensitivity model construction method based on time sequence deformation, which combines a traditional machine learning neural network model method with an InSAR technology, can obtain an accurate and effective landslide sensitivity partition map, and has a good effect in judging the occurrence possibility of landslide. The method breaks through the limitation of the traditional landslide sensitivity result, and realizes the refined analysis of the geological disasters. The method can be applied to susceptibility evaluation of geological disasters, villages and houses, provides basis for disaster prevention and reduction, further provides a reasonable solution, ensures life and property safety, promotes sustainable development, and has important practical significance.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a flowchart of a landslide hazard sensitivity model method in an embodiment of the application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Example 1
As shown in fig. 1, in this embodiment, a landslide hazard sensitivity model construction method with reference to time sequence deformation is provided, which includes the following steps:
step one, data collection and landslide influence factor database construction, namely collecting intrinsic drive and extrinsic induction factor data related to landslide generation such as geology, topography, meteorological hydrology, earth surface coverage, soil type and the like to construct a landslide evaluation index space database, and extracting an evaluation index.
Step two, performing optimal discretization on the evaluation index, performing discretization on the continuous evaluation factor by adopting a ChiMerge discretization method, and performing optimal distance division on the linear factor, wherein the calculation formula is as follows:
wherein k is the category number; a is that ij Representing the number of j types of samples in the i interval; e (E) ij The number of j types of samples in the interval i is represented according to the proportion of the j types of samples in the whole; r is R i The table is the number of samples in interval i; c (C) j The table is the number of j class samples; the N table is the total number of samples.
Step three, screening evaluation indexes, wherein before machine learning modeling, multiple collinearity among the evaluation indexes is required to be checked, and the collinearity of the evaluation indexes is checked by adopting a variance expansion factor (Variance Inflation Factor, VIF) and a Tolerance (TOL),
standard deviation formula for index measured by T and VIF
Wherein A is 2 Is the variance between the independent variables. When VIF>10 or T<0.1, indicates that the selected factors are co-linear. Importance meter for evaluating index Fj using importance analysis of random forest out-of-bag error (OOB error)Calculation formula
Where NT represents the number of decision trees, VIM (F j ) Indicating index F j Importance of (A), errOOB t Is the out-of-bag error of classification tree in random forest under the condition of containing all indexes, errOOB t j Representing the removal variable F j Post-classification tree out-of-bag errors. VIM (F) j ) The larger the value, the greater the impact of this index variable on the overall random forest classification and the results that it produces, and hence the higher the importance of the index, and vice versa.
And fourthly, constructing a landslide sensitivity evaluation model, adopting a deterministic factor (MF) model, and adopting a method for quantitatively evaluating landslide susceptibility influence factors by using a probability function, so that the dimensionality of different types of data can be unified, and the accuracy of the data is improved.
Wherein,deterministic coefficient representing landslide, ++>Representing the number N of landslide of the type in the data i Area S of the same kind of landslide i Ratio of->Representing the ratio of the total number N of landslide to the total area S, indicating the certainty of landslide occurrence and +.>The values are positively correlated, +.>The value is [ -1, 1]Within the interval, when->When the value approaches 1, this indicates a high probability of occurrence of landslide. The support vector machine model (SVM) is used for maximizing the interval between positive samples and negative samples on a training set, and can be used for solving the problems of linear, nonlinear and high-dimensional pattern recognition based on a statistical learning theory. The two models are combined into an MF-SVM model, and the method has higher precision and applicability.
And fifthly, verifying the accuracy of the model and evaluating the landslide sensitivity level, and verifying a landslide susceptibility evaluation result by utilizing an ROC curve to reflect the relation between the selected method and the sensitivity, wherein the area under the ROC curve (AUC) value is within the [0,1] interval. When the AUC value is close to zero, this indicates that the model is less effective. Thus, the closer the AUC value is to 1, the higher the accuracy of the model. The landslide sensitivity value is divided by adopting a natural breakpoint method, so that the difference of the same level is reduced, and the difference between the levels is increased. The formula is as follows
Wherein,the sum of squares of the deviations is expressed, i and j respectively denote the number of the ith and jth elements C of the class N group, K denotes the number between i and j, K denotes the kth element of the C group, and N denotes the total number of samples.
And step six, introducing an SBAS-InSAR technology, combining an MF-SVM model with the result of SBAS-InSAR (MFSI), and improving the sensitivity of the surface deformation so that the evaluation result of the model is more reasonable. And weighting superposition operation is adopted to respectively assign weights to the MF-SVM model and the SBAS-InSAR result, so that the deformation rate is combined with the original landslide susceptibility evaluation result. The deformation ratio needs to be normalized, then an improved landslide sensitivity profile is obtained, and the study area is divided into Very Low (VL), low (L), medium (M), high (H) and Very High (VH) sensitivity areas using the natural breakpoint method.
The application combines the traditional machine learning neural network model method with the InSAR technology, and has better effect in judging the occurrence possibility of landslide. The method breaks through the limitation of the traditional landslide sensitivity result, and realizes the refined analysis of the geological disasters. The method can be applied to susceptibility evaluation of geological disasters, villages and houses, provides basis for disaster prevention and reduction, further provides a reasonable solution, ensures life and property safety, promotes sustainable development, and has important practical significance.
The present application is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present application are intended to be included in the scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims (9)
1. The landslide disaster sensitivity model construction method based on the time sequence deformation is characterized by comprising the following steps of:
constructing an influence factor database of landslide disasters in a research area, and extracting evaluation indexes based on the influence factor database;
performing optimal discretization on the evaluation index based on a ChiMerge discretization method, and performing optimal distance division on linear factors;
screening the evaluation index;
based on the screened evaluation index, constructing a landslide sensitivity evaluation model by adopting a deterministic factor model and a support vector machine model, and acquiring a landslide sensitivity value based on the landslide sensitivity evaluation model;
verifying the accuracy of the landslide sensitivity evaluation model based on an ROC curve; dividing the landslide sensitivity value based on a natural breakpoint method;
combining the SBAS-InSAR model with the landslide sensitivity evaluation model to obtain a comprehensive evaluation result;
based on the comprehensive evaluation result, a natural breakpoint method is adopted to divide the sensitive area of the research area.
2. The landslide hazard sensitivity model construction method of reference time series deformation of claim 1, wherein the construction process of the influence factor database comprises the following steps:
intrinsic driving and extrinsic evoked factor data associated with landslide development in the study area is collected, and an influence factor database is constructed based on the intrinsic driving and extrinsic evoked factor data.
3. The landslide hazard sensitivity model construction method of reference time series deformation of claim 1, wherein the method for optimally discretizing the evaluation index based on a chimere discretization method and optimally dividing the distance of the linear factors comprises:；
wherein x represents an optimal distance, and k represents a category number; a is that ij Representing the number of j types of samples in the i interval; e (E) ij The number of j types of samples in the interval i is represented according to the proportion of the j types of samples in the whole; r is R i The table is the number of samples in interval i; c (C) j The table is the number of j class samples; n represents the total number of samples.
4. The landslide hazard sensitivity model construction method of reference time series deformation of claim 1, wherein the process of screening the evaluation index comprises:
and (3) checking and evaluating the index collinearity based on the variance expansion factor and the tolerance, and checking and evaluating the importance of the index based on the random forest out-of-bag error.
5. The landslide hazard sensitivity model construction method of reference time series deformation of claim 1, wherein the deterministic factor model comprises:
；
wherein,deterministic coefficient representing landslide, ++>Representing the number N of landslide of the type in the data i Area S of the same kind of landslide i Ratio of->Representing the ratio of the total number N of landslide to the total area S, indicating the certainty of landslide occurrence and +.>The values are in a positive correlation and,the value is [ -1, 1]Within the interval, when->When the value approaches 1, this indicates a high probability of occurrence of landslide.
6. The landslide hazard sensitivity model construction method of reference time series deformation of claim 1, wherein the method of verifying the accuracy of the landslide sensitivity evaluation model based on ROC curve comprises:
AUC values under the ROC curve are in the [0,1] interval, and when the AUC values are close to zero, the effect of the landslide sensitivity evaluation model is poor, and the accuracy of the model is higher as the AUC values are close to 1.
7. The landslide hazard sensitivity model construction method of reference time series deformation of claim 1, wherein the method of dividing the landslide sensitivity value based on a natural breakpoint method comprises:
；
wherein,the sum of squares of the deviations is expressed, i and j respectively denote the number of the ith and jth elements C of the class N group, K denotes the number between i and j, K denotes the kth element of the C group, and N denotes the total number of samples.
8. The landslide hazard sensitivity model construction method of reference time series deformation of claim 1, wherein the process of combining an SBAS-InSAR model with the landslide sensitivity evaluation model comprises:
acquiring a deformation rate based on the SBAS-InSAR model, and respectively giving weight to the deformation rate and the landslide sensitivity value by adopting weighted superposition operation so as to combine the deformation rate and the landslide sensitivity value;
and carrying out normalization treatment on the deformation rate to obtain an improved landslide sensitivity distribution map.
9. The landslide hazard sensitivity model construction method based on the reference time sequence deformation of claim 1, wherein the sensitivity region division is performed on the research region by adopting a natural breakpoint method, and specifically comprises the following steps: the natural breakpoint method is used to divide the investigation region into very low, medium, high and very high sensitive regions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311464482.1A CN117195750B (en) | 2023-11-07 | 2023-11-07 | Landslide disaster sensitivity model construction method based on time sequence deformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311464482.1A CN117195750B (en) | 2023-11-07 | 2023-11-07 | Landslide disaster sensitivity model construction method based on time sequence deformation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117195750A true CN117195750A (en) | 2023-12-08 |
| CN117195750B CN117195750B (en) | 2024-02-02 |
Family
ID=88994645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311464482.1A Active CN117195750B (en) | 2023-11-07 | 2023-11-07 | Landslide disaster sensitivity model construction method based on time sequence deformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117195750B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011220986A (en) * | 2010-04-05 | 2011-11-04 | Advanced Technology:Kk | Disaster prevention fiber optic sensor and device for landslide monitoring |
| KR20160137100A (en) * | 2015-05-22 | 2016-11-30 | 한국과학기술원 | Empirical Formula for the Mobilization Criteria between Landslide and Debris Flow and Generation Method thereof |
| CN109541592A (en) * | 2018-10-30 | 2019-03-29 | 长安大学 | Loess Landslide type and sliding-modes analysis method based on InSAR multidimensional deformation data |
| CN110362949A (en) * | 2019-07-23 | 2019-10-22 | 电子科技大学 | A kind of landslide sensitivity assessment method neural network based |
| CN114201922A (en) * | 2021-12-22 | 2022-03-18 | 云南大学 | Dynamic landslide sensitivity prediction method and system based on InSAR technology |
| CN114330812A (en) * | 2021-10-29 | 2022-04-12 | 西北大学 | Landslide disaster risk assessment method based on machine learning |
| CN115935640A (en) * | 2022-12-02 | 2023-04-07 | 国家基础地理信息中心 | Landslide sensitivity prediction model establishment method and landslide sensitivity evaluation method |
-
2023
- 2023-11-07 CN CN202311464482.1A patent/CN117195750B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011220986A (en) * | 2010-04-05 | 2011-11-04 | Advanced Technology:Kk | Disaster prevention fiber optic sensor and device for landslide monitoring |
| KR20160137100A (en) * | 2015-05-22 | 2016-11-30 | 한국과학기술원 | Empirical Formula for the Mobilization Criteria between Landslide and Debris Flow and Generation Method thereof |
| CN109541592A (en) * | 2018-10-30 | 2019-03-29 | 长安大学 | Loess Landslide type and sliding-modes analysis method based on InSAR multidimensional deformation data |
| CN110362949A (en) * | 2019-07-23 | 2019-10-22 | 电子科技大学 | A kind of landslide sensitivity assessment method neural network based |
| CN114330812A (en) * | 2021-10-29 | 2022-04-12 | 西北大学 | Landslide disaster risk assessment method based on machine learning |
| CN114201922A (en) * | 2021-12-22 | 2022-03-18 | 云南大学 | Dynamic landslide sensitivity prediction method and system based on InSAR technology |
| CN115935640A (en) * | 2022-12-02 | 2023-04-07 | 国家基础地理信息中心 | Landslide sensitivity prediction model establishment method and landslide sensitivity evaluation method |
Non-Patent Citations (3)
| Title |
|---|
| JUN ZHANG.ET.: "Eco-geological environment quality assessment in a mining city: a case study of Jiangxia District, Wuhan City", 《GEOCARTO INTERNATIONAL》, vol. 38, no. 1, pages 1 - 27 * |
| 周晓亭: "基于多源数据的滑坡识别及其易发性动态评价", 《中国博士学位论文全文数据库基础科学辑》, no. 2, pages 011 - 21 * |
| 蒋万钰等: "基于卷积神经网络模型的区域滑坡敏感性评价——以川藏铁路沿线为例", 《兰州大学学报(自然科学版)》, vol. 58, no. 2, pages 203 - 211 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117195750B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113642849B (en) | Geological disaster risk comprehensive evaluation method and device considering spatial distribution characteristics | |
| CN110362949B (en) | Landslide sensitivity evaluation method based on neural network | |
| CN110929939B (en) | Landslide hazard susceptibility spatial prediction method based on clustering-information coupling model | |
| CN114563150B (en) | Bridge health online detection module generation method, detection method, tool box and device | |
| CN115688404B (en) | Rainfall landslide early warning method based on SVM-RF model | |
| CN102435910A (en) | Power electronic circuit health monitoring method based on support vector classification | |
| CN105487526A (en) | FastRVM (fast relevance vector machine) wastewater treatment fault diagnosis method | |
| CN111539450B (en) | Landslide susceptibility evaluation method in earthquake region | |
| CN115828140A (en) | Neighborhood mutual information and random forest fusion fault detection method, system and application | |
| CN116341901B (en) | Integrated evaluation method for landslide surface domain-monomer hazard early warning | |
| Matkan et al. | Detecting the spatial–temporal autocorrelation among crash frequencies in urban areas | |
| CN111898385B (en) | Earthquake disaster assessment method and system | |
| CN111144637A (en) | Regional power grid geological disaster forecasting model construction method based on machine learning | |
| CN114330812A (en) | Landslide disaster risk assessment method based on machine learning | |
| CN106384507A (en) | Travel time real-time estimation method based on sparse detector | |
| CN117238126A (en) | Traffic accident risk assessment method under continuous flow road scene | |
| CN113191642B (en) | Regional landslide sensitivity analysis method based on optimal combination strategy | |
| CN107944219A (en) | A kind of method and apparatus for characterizing different periods drought and waterlogging and causing calamity feature | |
| CN117195750B (en) | Landslide disaster sensitivity model construction method based on time sequence deformation | |
| CN112232689A (en) | Ecological geological vulnerability evaluation method for tea leaf continuous planting area | |
| CN111652522A (en) | Ecological risk assessment method for natural protected area | |
| CN112579849A (en) | Structure safety influence factor correlation analysis method based on full data | |
| CN109657795A (en) | A kind of hard disk failure prediction technique based on Attributions selection | |
| CN118114994B (en) | Geological disaster risk self-adaptive evaluation method and system based on multiple algorithm integration | |
| CN118296961A (en) | Dynamic landslide susceptibility evaluation 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |