CN105184050A - Landslide hazard degree evaluation method under support of GIS (Geographic Information System) and artificial intelligence technology - Google Patents
Landslide hazard degree evaluation method under support of GIS (Geographic Information System) and artificial intelligence technology Download PDFInfo
- Publication number
- CN105184050A CN105184050A CN201510487556.2A CN201510487556A CN105184050A CN 105184050 A CN105184050 A CN 105184050A CN 201510487556 A CN201510487556 A CN 201510487556A CN 105184050 A CN105184050 A CN 105184050A
- Authority
- CN
- China
- Prior art keywords
- landslide
- slope
- mrow
- risk
- geographic environment
- 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
- 238000005516 engineering process Methods 0.000 title claims abstract description 17
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 10
- 238000011156 evaluation Methods 0.000 title claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 27
- 239000011435 rock Substances 0.000 claims description 30
- 230000015572 biosynthetic process Effects 0.000 claims description 16
- 238000011160 research Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000014509 gene expression Effects 0.000 claims description 2
- 238000007670 refining Methods 0.000 claims description 2
- 238000012502 risk assessment Methods 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 abstract description 8
- 230000007547 defect Effects 0.000 abstract description 4
- 230000002265 prevention Effects 0.000 abstract description 3
- 230000009467 reduction Effects 0.000 abstract description 3
- 238000012216 screening Methods 0.000 abstract 1
- 230000007423 decrease Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
Abstract
The present invention discloses a landslide hazard degree evaluation method under support of a GIS (Geographic Information System) and an artificial intelligence technology. The method comprises: acquiring knowledge about a relation between a landslide and a geographical environment by interviewing a landslide expert, and screening geographical environment factors according to conditions, such as a degree of influence of the geographical environment factors on the landslide, data source quality and an acquisition difficulty degree, in expert knowledge; extracting quantitative geographical environment factors by use of the GIS; expressing the expert knowledge about the relation between the landslide and the geographical environment factors by use of a fuzzy membership degree function, and constructing a fuzzy inference engine capable of calculating a landslide hazard degree value based on the geographical environment factors; and inputting the quantitative geographical environment factors into the fuzzy inference engine, and calculating spatial distribution of a regional landslide hazard degree. The method disclosed by the prevent invention effectively overcomes the defects such as high sample quality and quantity requirements, and poor interpretability and poor portability of a statistical method, improves precision and the detail level of landslide hazard degree spatial distribution speculation, and has extensive application prospects in the aspects of regional landslide hazard degree analysis and landslide disaster prevention and reduction.
Description
Technical Field
The invention relates to a landslide hazard degree evaluation method supported by a GIS and artificial intelligence technology, and belongs to the technical application field of landslide hazard degree evaluation and mapping.
Background
Landslides are a typical significant natural geological disaster. In recent years, with the increasing depth and breadth of human activities, landslide disasters are frequent, which causes great economic loss and casualties, and is not beneficial to the stability and development of society. The method for identifying the area where landslide is likely to occur in the future is an effective method for coping with landslide disasters and is also the key content in the current landslide disaster research. The landslide risk degree refers to the possibility of landslide in a certain area under the conditions of local terrain and the like, and the landslide risk degree is mapped to identify a landslide high-risk area, so that loss caused by landslide can be effectively reduced by pertinently implementing related measures, and the landslide risk degree has important reference significance for regional planning and construction.
At present, widely used landslide hazard mapping methods are statistical methods, namely data-driven methods, including conventional statistical methods and machine learning methods. The statistical method analyzes the existing landslide points and the geographic environment elements thereof to conclude the relationship between the landslide and the geographic environment elements, thereby realizing the estimation of the landslide risk degree. However, landslide hazard mapping based on a statistical method has two defects: firstly, the statistical method is a data-driven method, the result of which is deeply influenced by the quality of training samples, the uncertainty of the training samples is high, the quality cannot be guaranteed, the knowledge induced and learned by the statistical method is wrong, the relation between the real landslide and the environmental condition cannot be described, and the transportability is poor; in addition, the data-driven model requires a large number of training samples, and the increase of data cost greatly limits the practicability of the method, and the defect is particularly obvious in a large area. Secondly, most of statistical models are based on linear or generalized linear models, the models cannot describe complex nonlinear relations between landslide risk and geographic environment elements, although many machine learning methods can simulate the nonlinear relations, the relations cannot be explicitly expressed, and a 'black box' is inconvenient for people to understand and explain landslide occurrence mechanisms.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method utilizes expert experience knowledge which has high reliability and strong interpretability and can reasonably describe the complex nonlinear relation between the landslide risk and geographic environment elements to construct a fuzzy inference engine, fully utilizes the existing RS and GIS technologies and resources, quickly and accurately generates digital landslide risk spatial distribution information, and realizes landslide risk mapping.
The technical solution of the invention is as follows:
a landslide hazard degree evaluation method supported by a GIS and an artificial intelligence technology comprises the following specific steps:
(1) obtaining expert knowledge
Based on the Kelly's personal structure theory, it is believed that the long-term accumulated knowledge of the relationship between landslide and the geographic environment by landslide experts is re-extractable. And acquiring knowledge of the relation between the landslide and the geographical environment element combination by the expert through interviewing the expert and refining the knowledge step by step. If the attitude of the rock stratum is greatly related to the slope gradient, when the rock stratum trend is consistent with the slope gradient and the inclination angle of the rock stratum is equal to or slightly smaller than the slope gradient, the risk of landslide is high, and the risk of landslide is reduced along with the increase of the difference between the rock stratum trend and the slope gradient or the increase of the angle difference between the inclination angle and the slope gradient.
(2) Quantitatively describing elements of geographic environment
And selecting the geographic environment elements according to the expert opinions and the importance of the geographic environment elements. Extracting geographic environment elements from a topographic map and a geological map based on a geographic information system technology: the method comprises the following steps of storing data in a grid mode, wherein the data comprise stratum lithology, ground gradient, ground slope direction, rock stratum inclination angle, rock stratum inclination, free face height difference and slope surface form.
(3) Construction of fuzzy inference engine
Based on expert knowledge, a combination of typical geographical environmental elements where landslide occurs and a change in landslide hazard when a deviation of the typical environmental elements occurs are determined. If the lithology and the gradient influence the danger degree of the landslide, the lithology which is not suitable for generating the landslide increases the danger degree of the landslide when the gradient increases (the gradient is more than 20 degrees, the landslide is easy to generate when the gradient is more than 30 degrees, the landslide is easy to generate when the gradient is more than 40 degrees), and the landslide danger degree is also large when the lithology which is easy to generate the landslide is slightly inclined.
And expressing the obtained quantitative landslide risk degree and the single geographic environment element combination relation into a fuzzy membership curve form by using an artificial intelligence technology, and constructing a fuzzy inference engine. The fuzzy membership curve expresses the change situation of the landslide risk degree value of a certain grid point along with the change of the elements of the geographic environment. The discrete geographic environment elements can set different landslide risk weights according to expert knowledge; the continuous geographic environment elements are expressed by fuzzy membership curve similar to Gaussian function, and there are three types: bell type, S type and Z type, the basic functions are as follows:
wherein S iskIs the landslide hazard value under the k-th combination of geographic environment elements, v is the value of the geographic environment elements at a certain grid point, v0Is a typical value of the geographical environmental element where landslide occurs and w is the effective range of the influence of the geographical environmental element on landslide occurrence, i.e. the distance from the typical value. V is0And the specific values of w are determined by expert knowledge.
Calculating the landslide fuzzy risk value under each combination of the geographic environment elements for a certain grid point, and synthesizing through weighted average to obtain the comprehensive landslide risk value of the grid point:
wherein, WkIs the weight of the kth combination of geographic environmental elements, SkIs the landslide fuzzy risk under the kth combination of geographic environment elements; and n is the total number of the geographical environment element combinations.
(4) Landslide hazard mapping
Inputting the quantified geographic environment elements into a fuzzy inference machine, traversing each grid unit in the research area, and calculating as follows: the landslide risk degree under the combination of the single geographic environment elements in the single grid point is calculated, and then the landslide risk degree under the combination of the single geographic environment elements is weighted and averaged to obtain the landslide fuzzy risk degree of the point. The calculation result of the step is a spatial distribution map of the landslide risk of the research area.
The method is based on expert knowledge, utilizes the fuzzy membership function to express the nonlinear relation between the landslide risk and the geographic environment elements, effectively overcomes the defects of high requirements of a statistical method on sample quality and quantity, poor interpretability of the method, poor transportability and the like, improves the precision and the detailed degree of the landslide risk spatial distribution conjecture, and has wide application prospects in the aspects of regional landslide risk analysis and landslide disaster prevention and reduction.
Drawings
FIG. 1 is a flow chart of an implementation of the present invention;
FIG. 2 shows three basic expressions of fuzzy membership curve of landslide hazard and continuous geographic environment element relationship, wherein (a) is bell type, (b) is S type, and (c) is Z type;
fig. 3 is a result diagram of estimating the landslide risk of the prefecture and county district of china based on the method of the present invention.
Detailed Description
The flow chart shown in FIG. 1 is combined to open county area (250 km)2) The landslide hazard degree chart is taken as an example to illustrate the specific implementation method of the invention:
1. and discussing with landslide experts having field experience for years in the local to obtain knowledge of the relationship between landslide risk and geographic environment elements.
(1) Rock formation attitude and slope direction impact on landslide hazard. When the inclination of the rock stratum is consistent with the slope direction and the inclination angle of the rock stratum is equal to or slightly smaller than the slope gradient, the risk of landslide is high; the risk of landslide decreases as the difference between the rock formation inclination and the slope direction increases or the difference between the inclination angle and the slope angle increases.
(2) Lithology and slope impact on landslide hazard. When the gradient is increased, the risk of landslide is increased (the gradient is more than 20 degrees, the landslide is easy to generate when the gradient is more than 30 degrees, and the landslide is easy to generate when the gradient is more than 40 degrees); the lithology which is easy to generate the landslide is high in landslide risk degree under the condition of slight slope.
(3) The influence of the height difference of the face and the lithology on the landslide risk. The lithology which is easy to generate landslide is high in landslide risk under the condition of slight height difference (the height difference of the free surface is greater than 20 meters, the height difference of the free surface is greater than 50 meters, the landslide is easy to generate, and the height difference of the free surface is greater than 100 meters, and the landslide is easy to generate); lithology, which is not conducive to landslide, increases the risk of landslide as the elevation difference between adjacent voids increases, particularly at high gradients.
(4) The impact of slope shape and lithology on landslide hazard. In general, the slope landslide risk degree of the hillside with convex and concave surfaces is high; the risk of a convex slope is also high; the straight slope risk degree is centered; the stability of the slope with the concave upper part and the concave lower part is good; in the zones with lithologic characteristics suitable for landslide, the landslide can be generated on any slope, but the danger degree of the zones with convex surfaces, concave surfaces and convex surfaces is greatly increased.
2. Quantitatively describing elements of geographic environment
And selecting the geographic environment elements according to the expert opinions and the importance of the geographic environment elements. Extracting geographic environment elements from a topographic map and a geological map based on a geographic information system technology: the method comprises the following steps of storing data in a grid mode, wherein the data comprise stratum lithology, ground slope direction, rock stratum inclination angle, rock stratum inclination, free face height difference and slope surface form.
(1) Formation lithology data: according to the knowledge of the relation between the stratum lithology and the landslide by experts, the stratum lithology is divided into three categories: high, medium, low risk;
(2) ground slope and heading data: the slope refers to the inclination degree of the slope surface, and the slope direction refers to the orientation of the slope surface, both of which can be calculated based on the geographic information system technology;
(3) dip and dip angle data for the formation: the spatial distribution of dip and dip is interpolated from the geological map. Firstly, digitalizing points with the direction of the rock stratum on a geological map, then interpolating the directions of the rock stratum of other points by using a minimum distance method and forming rock stratum direction (namely rock stratum tendency and dip angle) data;
(4) surface grade and formation dip differential data: is the difference between the ground slope and the rock formation inclination angle, and the difference is a negative value when the ground slope is smaller than the rock formation inclination angle;
(5) surface slope and formation dip difference data: is the absolute value of the difference between the surface slope and the rock formation inclination;
(6) elevation difference data of the adjacent space: is the difference between the top and bottom of the slope;
(7) slope surface form data: extracting slope information from a topographic map based on a geographic information system technology to determine the shape of the slope, and dividing the slope into the following six types: a flat slope (class 0 slope), a concave slope (class 1 slope), an up-concave down-convex slope (class 2 slope), a straight slope (class 3 slope), a convex slope (class 4 slope), and an up-convex down-concave slope (class 5 slope).
3. Construction of fuzzy inference engine
Expressing the acquired expert experience knowledge into a fuzzy inference engine, wherein the computation method of the inference engine comprises the following steps:
(1) the combination is as follows: effect of the difference between slope and formation dip and the difference between slope and formation inclination on landslide
The slope gradient (v) is equal to or slightly greater than the inclination angle (v) of the rock stratum0) The risk of landslide is high. When the gradient is smaller than the inclination angle, the risk degree is zero; the risk of landslide decreases as the difference in angle between the slope and the inclination increases to a certain extent (D). This relationship is in turn subject to formation dip (a)0) The difference from the slope direction (a) affects that the risk degree decreases as the difference increases. The risk of the combination is calculated by the following formula:
(2) combining two: influence of slope and lithology on landslide
Generally, the greater the gradient, the greater the risk of landslide, but the influence of the gradient on landslide is lithology dependent. The influence of different lithologies on landslide is different to weight (W)r) Is expressed in the form of (1). The high-risk lithology was 1.0, the medium-risk lithology was 0.5, and the low-risk lithology was 0.3. The risk of the combination is calculated by the following scheme:
when the gradient (g) is larger than the gradient (g) which is easy to generate landslide0) The method comprises the following steps:
S＝wr
otherwise:
g is the effective range of slope influence on landslide with a default value of 30 °.
(3) Combining three components: influence of elevation difference and lithology of free face on landslide
Generally, the higher the blank surface, the greater the landslide risk, but the influence of the blank surface on the landslide is related to lithology. Weighting the different lithologies (W)r) Different (as above). The risk of the combination is calculated by the following scheme:
when the height (l) of the face to the empty surface is more than the height (l) of the face to the empty surface which is easy to generate landslide0) The method comprises the following steps:
S＝Wr
otherwise:
l is the effective range of influence of the height of the sky on the landslide, and the default value is 300 meters.
(4) And (4) combining: influence of slope morphology and lithology on landslide
The six slope shapes have different degrees of influence on the landslide to weight (W)s) Is expressed in the form of (1). The flat slope (class 0 slope) and the concave slope (class 1 slope) are 0.1, the upper concave and lower convex slope (class 2 slope) is 0.3, the straight line slope (class 3 slope) is 0.5, the convex slope (class 4 slope) is 0.7, and the upper convex and lower concave slope (class 5 slope) landslide hazard level is 1. The effect of slope shape on landslide is related to lithology and to the degree (h) of slope protrusion. The risk of the combination is calculated by the following scheme:
when the slope surface is protruded (h is more than 0):
otherwise:
h is the effective range of the influence of the slope surface protrusion degree on the landslide, and the default value is 20 meters.
(5) Landslide hazard degree under combination of geographic environment elements
And carrying out weighted average on the landslide fuzzy risk calculated by each combination to obtain a final landslide risk graph (shown in figure 3).
WkIs the weight of the kth combination of geographic environmental elements, SkIs the landslide hazard value under the kth combination of geographic environment elements, and n is the total number of the combinations of geographic environment elements.
4. Landslide hazard mapping
And calculating the comprehensive landslide risk degree of each grid point of the research area, and finally realizing the landslide risk degree drawing of the whole research area.
In order to verify the effectiveness of the method in practical application, whether the fuzzy risk degree of the landslide area is obviously higher than the average fuzzy risk degree of the whole research area can be tested by an objective test method. Non-difference hypothesis (or original hypothesis), i.e. H0The mean value of the fuzzy risk for the landslide zone was assumed to be not significantly different from the mean value for the entire study zone. Opposite hypothesis, i.e. HAIt is assumed that the average value of the fuzzy risk degree of the landslide area is significantly higher than the average value of the whole area. If the no difference assumption is overridden, the inferred criticality ambiguity value may reflect the criticality of the landslide. A T-test is performed on this hypothesis.
Wherein,is in a landslide areaFuzzy risk average, mu0The fuzzy risk degree average value of the whole research area, S is the fuzzy risk degree standard variance of the landslide area, and n is the landslide number of the landslide area. The current mean blur risk value for 21 landslide points is 1.59, the standard deviation is 0.4545, and the mean value over the study area is 0.89. The final T value is 6.91, which is much greater than the threshold value for T with a probability of 99.5% and a degree of freedom of 20 (2.85). It follows that the no difference assumption does not hold and the opposite assumption is accepted. The method has higher precision in predicting the landslide risk degree, and has wide application prospect in the aspects of regional landslide risk degree evaluation and landslide disaster prevention and reduction.
Those skilled in the art will appreciate that the invention may be practiced without these specific details.
All the above are only preferred embodiments of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (3)
1. A landslide risk degree evaluation method under the support of GIS and artificial intelligence technology is characterized by comprising the following specific steps:
(1) obtaining expert knowledge
Acquiring knowledge of relation between landslide and the combination of geographic environment elements by an expert through interviewing the expert and refining the knowledge step by step;
(2) quantitatively describing elements of geographic environment
And selecting the geographic environment elements according to the expert opinions and the importance of the geographic environment elements. Extracting geographic environment elements from a topographic map and a geological map based on a geographic information system technology: the method comprises the following steps of (1) storing data in a grid form, wherein the data comprise stratum lithology, ground slope direction, rock stratum inclination angle, rock stratum inclination, free face height difference and slope form;
(3) construction of fuzzy inference engine
Based on expert knowledge, determining a typical geographical environment element combination of landslide occurrence and a change situation of landslide danger degree when an environment element is deviated from a typical environment element; expressing the obtained quantitative relation of the landslide risk degree and the combination of the single geographic environment elements into a fuzzy membership curve form by using an artificial intelligence technology, and constructing a fuzzy inference machine, wherein the fuzzy membership curve expresses the change condition of the landslide risk degree of a certain grid point along with the change of the geographic environment elements; the discrete geographic environment elements can set different landslide risk weights according to expert knowledge; the continuous geographic environment elements are expressed by fuzzy membership curve similar to Gaussian function, and the basic function is as follows:
wherein S iskIs the landslide hazard value under the k-th combination of geographic environment elements, v is the value of the geographic environment element at a certain grid point, v0Is the geographic environment in which the landslide occursThe typical value of the element, w, is the effective range of the effect of the element on landslide, i.e. the distance from the typical value. v. of0And the specific values of w are determined by expert knowledge;
calculating the landslide fuzzy risk value under each combination of the geographic environment elements for a certain grid point, and synthesizing through weighted average to obtain the comprehensive landslide risk value of the grid point:
wherein, WkIs the weight of the kth combination of geographic environmental elements, SkIs the landslide fuzzy risk under the kth combination of geographic environment elements; n is the total number of the geographical environment element combinations;
(4) landslide hazard mapping
Inputting the quantified geographic environment elements into a fuzzy inference machine, traversing each grid unit in the research area, and calculating as follows: firstly, calculating the landslide risk degree under the combination of single geographic environment elements in a single grid point, and then carrying out weighted average on the landslide risk degree under the combination of the single geographic environment elements to obtain the landslide risk degree of the point; the calculation result of the step is the spatial distribution of the landslide risk of the research area.
2. The landslide risk assessment method under support of GIS and artificial intelligence technology according to claim 1, wherein in said step (2), the extracted geographic environment elements are specifically as follows:
1) formation lithology data: according to knowledge of an expert on the relationship between the lithology of the stratum and the landslide risk, the lithology of the stratum is divided into three categories: high, medium, low risk;
2) ground slope and heading data: the slope refers to the inclination degree of the slope surface, and the slope direction refers to the orientation of the slope surface, both of which can be calculated based on the geographic information system technology;
3) dip and dip angle data for the formation: the method is characterized in that the spatial distribution of the inclination and the dip angle is obtained by interpolating point information on a geological map, and the specific method comprises the following steps: firstly, digitalizing points with the trend of the rock stratum on a geological map, then interpolating the trend of the rock stratum of other points by using a minimum distance method and forming rock stratum trend data, wherein the rock stratum trend is the rock stratum trend and the dip angle;
4) surface grade and formation dip differential data: calculating the difference value between the ground gradient and the rock stratum inclination angle, wherein the difference value is a negative value when the ground gradient is smaller than the rock stratum inclination angle;
5) surface slope and formation dip difference data: calculating the absolute value of the difference between the ground slope direction and the rock stratum tendency;
6) elevation difference data of the adjacent space: calculating the height difference between the top and the bottom of the slope;
7) slope surface form data: determining the shape of the slope according to slope information extracted from the topographic map, and dividing the slope shape into the following six types: a flat slope, i.e. a class 0 slope, a concave slope, i.e. a class 1 slope, an upward concave and downward convex slope, i.e. a class 2 slope, a straight slope, i.e. a class 3 slope, a convex slope, i.e. a class 4 slope, and an upward convex and downward concave slope, i.e. a class 5 slope.
3. The method for evaluating the risk of landslide with the support of GIS and artificial intelligence technology as claimed in claim 1 or 2, wherein in the step (3), there are three types of the fuzzy membership curve expression of the continuous type geographic environment elements: bell type, S type and Z type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510487556.2A CN105184050A (en) | 2015-08-10 | 2015-08-10 | Landslide hazard degree evaluation method under support of GIS (Geographic Information System) and artificial intelligence technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510487556.2A CN105184050A (en) | 2015-08-10 | 2015-08-10 | Landslide hazard degree evaluation method under support of GIS (Geographic Information System) and artificial intelligence technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105184050A true CN105184050A (en) | 2015-12-23 |
Family
ID=54906128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510487556.2A Pending CN105184050A (en) | 2015-08-10 | 2015-08-10 | Landslide hazard degree evaluation method under support of GIS (Geographic Information System) and artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105184050A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106370225A (en) * | 2016-08-18 | 2017-02-01 | 中国科学院、水利部成都山地灾害与环境研究所 | Rapid surveying and imaging method for accumulated layer landslide |
| CN107346361A (en) * | 2017-07-13 | 2017-11-14 | 重庆大学 | Slope stability principium identification method based on terrain and geologic map |
| CN109406755A (en) * | 2018-10-30 | 2019-03-01 | 四川安信科创科技有限公司 | A kind of mountain area falling and landslide hazards high position property discrimination method based on geomorphic unit |
| CN109918610A (en) * | 2019-02-25 | 2019-06-21 | 南京泛在地理信息产业研究院有限公司 | Negative sample confidence evaluation method and negative sample based on geographical environment similarity use method |
| CN112767544A (en) * | 2021-01-06 | 2021-05-07 | 成都理工大学 | Spatial case reasoning method for regional landslide risk evaluation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101403798A (en) * | 2008-11-12 | 2009-04-08 | 重庆大学 | Recognition method for main sliding direction of landslide |
| CN103364830A (en) * | 2013-07-24 | 2013-10-23 | 北京师范大学 | Predication method of happening position of slump disaster after earthquake based on multiple factors |
| CN103455711A (en) * | 2013-08-15 | 2013-12-18 | 广州地理研究所 | Small watershed region-oriented landslide hazard risk division method based on mechanism analysis |
-
2015
- 2015-08-10 CN CN201510487556.2A patent/CN105184050A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101403798A (en) * | 2008-11-12 | 2009-04-08 | 重庆大学 | Recognition method for main sliding direction of landslide |
| CN103364830A (en) * | 2013-07-24 | 2013-10-23 | 北京师范大学 | Predication method of happening position of slump disaster after earthquake based on multiple factors |
| CN103455711A (en) * | 2013-08-15 | 2013-12-18 | 广州地理研究所 | Small watershed region-oriented landslide hazard risk division method based on mechanism analysis |
Non-Patent Citations (1)
| Title |
|---|
| 朱阿兴: "《基于专家知识的滑坡危险性模糊评估方法》", 《地理科学进展》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106370225A (en) * | 2016-08-18 | 2017-02-01 | 中国科学院、水利部成都山地灾害与环境研究所 | Rapid surveying and imaging method for accumulated layer landslide |
| CN107346361A (en) * | 2017-07-13 | 2017-11-14 | 重庆大学 | Slope stability principium identification method based on terrain and geologic map |
| CN109406755A (en) * | 2018-10-30 | 2019-03-01 | 四川安信科创科技有限公司 | A kind of mountain area falling and landslide hazards high position property discrimination method based on geomorphic unit |
| CN109406755B (en) * | 2018-10-30 | 2020-08-18 | 四川安信科创科技有限公司 | Mountain landslide geological disaster high-order property identification method based on landform unit |
| CN109918610A (en) * | 2019-02-25 | 2019-06-21 | 南京泛在地理信息产业研究院有限公司 | Negative sample confidence evaluation method and negative sample based on geographical environment similarity use method |
| CN112767544A (en) * | 2021-01-06 | 2021-05-07 | 成都理工大学 | Spatial case reasoning method for regional landslide risk evaluation |
| CN112767544B (en) * | 2021-01-06 | 2022-04-01 | 成都理工大学 | Spatial case reasoning method for regional landslide risk evaluation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pyrcz et al. | Geostatistical reservoir modeling | |
| Fallatah et al. | Quantifying temporal variations in water resources of a vulnerable middle eastern transboundary aquifer system | |
| CN105184050A (en) | Landslide hazard degree evaluation method under support of GIS (Geographic Information System) and artificial intelligence technology | |
| CN113283802A (en) | Landslide risk assessment method for complex and difficult mountain area | |
| CN114201922A (en) | Dynamic landslide sensitivity prediction method and system based on InSAR technology | |
| Hamdi et al. | Evaluating the performance of SURFEXv5 as a new land surface scheme for the ALADINcy36 and ALARO-0 models | |
| Bartout et al. | A new approach to inventorying bodies of water, from local to global scale | |
| Pan et al. | Estimating root zone soil moisture at continental scale using neural networks | |
| Liu et al. | Quantitative analysis of planation surfaces of the upper Yangtze River in the Sichuan-Yunnan Region, Southwest China | |
| Das | Spatial statistical modelling for assessing landslide hazard and vulnerability | |
| Hengl | Pedometric Mapping Bridging the Gaps Between Conventional and Pedometric Approaches | |
| Chen et al. | The application of the genetic adaptive neural network in landslide disaster assessment | |
| CN107290800A (en) | Log Forecasting Methodology before practical brill | |
| Sarkar et al. | Landslide hazard zonation mapping and comparative analysis of hazard zonation maps | |
| Woldegebriel et al. | Evaluation of groundwater potential zone using remote sensing and geographical information system: in Kaffa zone, South Western Ethiopia | |
| Vanini et al. | Improving seismic hazard approaches for critical infrastructures: a pilot study in the Po Plain | |
| Steinberg et al. | Influence of Deep-Ocean Warming on Coastal Sea-Level Trends in the Gulf of Mexico | |
| Aslantaş Bostan | Analysis and modeling of spatially and temporally varying meteorological parameter: Precipitation over Turkey | |
| Pradhan et al. | Modeling groundwater levels in California's Central Valley by hierarchical Gaussian process and neural network regression | |
| Drăguţ et al. | Land-Surface Segmentation as sampling framework for soil mapping | |
| Laffan et al. | Predicting regolith properties using environmental correlation: a comparison of spatially global and spatially local approaches | |
| Cang | A" Warm" or" Cold" Early Mars: Evidence From Valley Networks | |
| Ritchie et al. | Optimization assessment of a groundwater-level observation network in the Middle Rio Grande Basin, New Mexico | |
| Prusova et al. | Comparison of geostatistical approaches dealing with the distribution of snow | |
| Weidemann | Hydrogeological analysis of groundwater occurrence within the Limpopo Province |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151223 |