CN115830804A - Intelligent early warning negative sample sampling method for pipeline geological disasters under constraint of easily-issued subareas - Google Patents
Intelligent early warning negative sample sampling method for pipeline geological disasters under constraint of easily-issued subareas Download PDFInfo
- Publication number
- CN115830804A CN115830804A CN202211298958.4A CN202211298958A CN115830804A CN 115830804 A CN115830804 A CN 115830804A CN 202211298958 A CN202211298958 A CN 202211298958A CN 115830804 A CN115830804 A CN 115830804A
- Authority
- CN
- China
- Prior art keywords
- negative sample
- disaster
- rainfall
- geological
- geological disaster
- 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
Images
Landscapes
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
Abstract
The invention discloses an intelligent early warning negative sample sampling method for pipeline geological disasters under the constraint of easily-issued subareas, which comprises the following steps: selecting factors required by early warning of a pipeline geological disaster area, including a pregnant disaster environment and induction factors; drawing a corresponding FR grid map by using historical geological disaster points along the pipeline and map layer data of each disaster-pregnant environment by using a GIS technology; drawing an accumulated rainfall map of a rainfall process till the occurrence date of each geological disaster point by combining the pipeline geological disaster easy-to-occur subareas; and superposing the FR image layer and the volatile partition image layer, defining a negative sample acquisition unit area, acquiring the spatial attribute and the time attribute of a negative sample in the negative sample acquisition unit, and extracting the disaster-pregnant environment factor data of the spatial geographic position corresponding to each negative sample point and the induction factor data of the corresponding time to form a negative sample set. The invention improves the effectiveness, representativeness and collection quality of the intelligent early warning negative sample of the pipeline geological disaster.
Description
Field of the invention
The invention belongs to the technical field of prevention and control of oil and gas pipeline geological disasters, and particularly relates to an intelligent early warning negative sample sampling method for pipeline geological disasters under constraint of easily-occurring districts.
Technical Field
Regional geological disaster monitoring and early warning is an important pipeline geological disaster risk prevention and control means, and can be used for pre-judging the geological disaster risk along a pipeline in advance, so that risk prevention is performed in advance. However, the traditional geological disaster area early warning model always has the problems of low early warning accuracy rate and high missing report rate, and the regional geological disaster monitoring early warning model needs to be continuously researched and perfected. In recent years, along with the development of artificial intelligence technology, the artificial intelligence technology has been gradually applied to the field of geological disaster prevention and control, but the intelligent early warning of oil and gas pipeline geological disasters is rarely researched. The development of the artificial intelligence technology provides a new technical means for the early warning of the pipeline geological disaster area. Although a large amount of data of geological disaster points which have occurred are accumulated in the pipeline geological disaster investigation, non-geological disaster points required by an artificial intelligence algorithm are difficult to obtain, the non-geological disaster points are called negative sample points, and the effective selection of the negative sample points is a key problem encountered in the construction of an intelligent pipeline area geological disaster early warning model. In the past, the problem of negative sample selection is solved, and selection is mostly carried out in a random mode, but the negative samples selected randomly are not necessarily all effective, so that the precision of the intelligent early warning model is restricted, and the application effect of the early warning model is influenced.
Disclosure of Invention
Aiming at the problems, the invention provides an intelligent pipeline geological disaster early warning negative sample sampling method under the constraint of an easily-issued partition, which can effectively select negative sample points under the constraint of an FR model and the easily-issued partition, overcomes the defect that the negative sample points are randomly adopted outside the occurred geological disaster points, is favorable for constructing an early warning sample set of a pipeline geological disaster area based on artificial intelligence, and is favorable for improving the precision of the area early warning model.
The invention is realized by the following technical scheme, which comprises the following technical steps:
(1) And selecting factors required by early warning in the pipeline geological disaster area. The early warning of the pipeline geological disaster area is restricted by two factors, namely a pregnant disaster environment and an inducing factor. The disaster-pregnant environment comprises stratum, rock-soil body type, elevation, gradient, slope direction, plane curvature, water system, fault, annual average rainfall and the like; the inducing factor mainly refers to rainfall, which is the accumulated rainfall in one rainfall process.
(2) And (5) dividing early warning analysis units. According to the grid units with the uniform size, the pipeline area along the line is divided into square early warning analysis units, namely one of the early warning analysis units is a grid unit and is also used as the smallest geospatial unit in artificial intelligence training. And processing the pregnant disaster environment and the inducing factors into grid files with consistent standards by using a GIS technology.
(3) Calculating FR and drawing FR grid graph. And calculating the FR of each disaster-prone environment factor by using the geological disaster point obtained by the pipeline geological disaster investigation and each disaster-prone environment map layer data and using an FR model (probability ratio model), wherein the FR comprises a stratum FR, a rock and soil body type FR, an elevation FR, a slope FR, a plane curvature FR, a water system FR, a fault FR and an annual rainfall FR, and calculating the total FR of the disaster-prone environment. And drawing a corresponding FR raster graph by using a GIS technology.
The FR calculation formula is as follows:
FR is the probability ratio of j factor i class, and Np (LXi) is the number of i class geological disaster evaluation units for the factor variable X. Np (Xj) is the evaluation unit data of the factor variable Xj, and m is the number of secondary classification factors of the factor variable Xi. n represents the number of factors.
(4) And (5) manufacturing a pipeline geological disaster easily-occurring subarea. The pipeline geological disaster easily-occurring partition map is drawn by geological disaster investigation technicians, the pipeline geological disaster investigation technicians divide the pipeline geological disaster easily-occurring partitions according to geological environment background, geological disaster development characteristics, distribution rules and main induction conditions along pipelines and according to the principle of 'similarity in regions and difference between regions', namely, the geological environment background conditions, the main induction conditions and the geological disaster development characteristics are basically similar in the regions of the same type, and the regions of different types have obvious differences, and draw the pipeline geological disaster easily-occurring partition map.
(5) And counting and drawing an accumulated rainfall map of a rainfall process till the occurrence date of each geological disaster point. And each geological disaster point corresponds to one rainfall accumulation graph, and the n geological disaster points correspond to the n rainfall accumulation graphs. The accumulated rainfall in the process of one rainfall is up to the day when the disaster happens, and the process of one rainfall means the rainfall process which is not continuously interrupted for more than two days.
(6) And superposing the FR image layer and the distribution image layer to define a negative sample acquisition unit area. And one negative sample acquisition unit comprises a plurality of early warning analysis units, and the negative samples are respectively sampled in each negative sample acquisition unit area.
(7) And counting the total FR value range of each negative sample acquisition unit, counting the total FR value of the early warning analysis unit where each geological disaster point is located, and solving the average Mi of the total FR value of the early warning analysis unit where each geological disaster point is located and the minimum total FR value of the negative sample acquisition units.
(8) The spatial and temporal properties of the negative examples are collected in a negative example collection unit. The occurring geological disaster point is called as a positive sample point, the positive sample has spatial attribute and time attribute, and the negative sample point also has spatial attribute and time attribute. And each geological disaster point correspondingly collects two negative sample points, wherein one negative sample point is sampled at a position where the total FR value is equal to Mi and rainfall is the same, and the other negative sample point is sampled at a position where the total FR value is the same but rainfall is less. The time attributes of the two negative sample points are equivalent to the date the geological disaster occurred.
(9) And constructing a negative sample set. And forming negative sample points which are 2 times of the positive samples through sampling of the negative sample points, wherein each negative sample point has a spatial attribute and a temporal attribute. And extracting disaster-pregnant environment factor (including stratum, rock and soil body type, elevation, gradient, slope direction, plane curvature, water system, fault and annual average rainfall) data of the corresponding space geographic position of each negative sample point and extracting induction factor (the induction factor is the accumulated rainfall in one rainfall process) data of the corresponding time to form a negative sample set. The negative sample set and the positive sample set jointly form a sample set of the pipeline intelligent geological disaster area early warning model.
Preferably: the negative sample sampling method is based on two types of data of a pregnant disaster environment and induction factors, an early warning analysis unit is divided by using a GIS technology, an FR grid map of the pregnant disaster environment is calculated and drawn by using an FR model and the GIS technology, an accumulated rainfall map of a rainfall process of each geological disaster point occurrence date is drawn by using the GIS technology, and each geological disaster point corresponds to one accumulated rainfall map.
Preferably: based on an FR model and volatile partition constraint, the area and the boundary of negative sample sampling are determined, the concept of a negative sample acquisition unit is defined, the sampling method of the specific position of the negative sample in the negative sample acquisition unit area is determined, and the acquisition boundary and the acquisition position of the negative sample are defined.
Preferably: the method comprises the steps that two negative sample points are collected corresponding to each geological disaster point, one negative sample point is sampled at a position where the total FR value is equal to Mi and rainfall is the same, the other negative sample point is sampled at a position where the total FR value of the geological disaster point is similar but rainfall is less, the time attributes of the two negative sample points are equal to the date of the occurrence of the geological disaster point, and the collected negative sample points are provided with space attributes and time attributes.
Preferably: and each negative sample point extracts the disaster-prone environment factor data of the corresponding space geographic position and the induction factor data of the corresponding time, and the negative sample point positions are used for extracting the disaster-prone environment and the induction factor data, and stratum, rock and soil body type, elevation, gradient, slope direction, plane curvature, water system, fault, annual average rainfall value and the accumulated rainfall value in the rainfall process are endowed to each negative sample point to form a complete negative sample set with time, space position, induction factor and disaster-prone environment numerical value.
Preferably: the negative sample collection method fully considers the influence of pregnant disaster environment and induction factors on geological disasters, avoids collecting potential geological disaster hidden danger points, simultaneously avoids collecting extreme negative sample points, simultaneously avoids the spatial distribution randomness of negative samples, defines the sampling position and the sampling proportion, ensures that the negative samples have higher effectiveness and high representativeness, improves the collection quality of the negative samples, and is beneficial to improving the accuracy of the intelligent pipeline geological disaster area early warning model and reducing the missing report rate.
The intelligent early warning negative sample sampling method overcomes the defect that randomly selecting negative samples can select undetected hidden danger points of geological disasters as negative sample points, and also overcomes the defect that when only FR values are used, selecting points at spatial positions with lower FR values as the negative sample points causes extreme representativeness of the negative sample points and no regional representativeness. The pipeline geological disaster intelligent early warning negative sample sampling method based on the FR model and the volatile partition constraint can avoid selecting potential geological disaster hidden danger points and avoid extreme negative sample points, and has better non-geological disaster area representativeness. The invention solves the problem of sampling proportion of the negative sample and the positive sample, and the negative sample and the positive sample collected by the method form 2:1 proportion relation.
Drawings
FIG. 1 is a flow chart of an intelligent early warning negative sample sampling method for pipeline geological disasters under the constraint of an FR model and a volatile partition;
fig. 2 is a grid diagram of the FR in the pregnancy disaster environment in an embodiment of the present invention;
FIG. 3 is a diagram of a pipeline geological disaster prone zone in an embodiment of the present invention;
FIG. 4 is a negative sample acquisition cell section divided along a pipeline in an embodiment of the invention;
FIG. 5 is a graph of cumulative rainfall over a rainfall event corresponding to one of the geological disaster points in accordance with an embodiment of the present invention;
FIG. 6 is a negative sample sampling corresponding to one of the geological disaster points in an embodiment of the present invention;
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
The present invention will be further described with reference to the following examples, which are intended to illustrate only some, but not all, of the embodiments of the present invention. Other embodiments used by those skilled in the art can be obtained without any creative effort based on the embodiments in the present invention, and all of them belong to the protection scope of the present invention.
The method flow of this embodiment is shown in fig. 1. The main flow of the pipeline geological disaster intelligent early warning negative sample sampling method under the restraint of an FR model and an easy-to-occur partition is as follows: firstly, confirming pregnant disaster environment factors and induction factors required by geological disaster areas of the pipeline-along regions, and processing the pregnant disaster environment factors and the induction factors into grid files with consistent standards according to a unified early warning analysis unit; then, calculating FR by using an FR model, drawing an FR diagram, drawing an easy-to-send partition diagram according to the result of the investigation of the pipeline geological disasters, and drawing an accumulated rainfall diagram of each geological disaster point in the rainfall process; then, superposing the FR image layers and the distribution area image layers, defining a negative sample acquisition unit area, counting the total FR value range of each negative sample acquisition unit, and counting the total FR value of the early warning analysis unit where each geological disaster point is located; and finally, acquiring the spatial attribute and the time attribute of the negative sample in a negative sample acquisition unit, and extracting pregnant disaster environment factor data corresponding to the spatial geographic position and induction factor data corresponding to time to form a negative sample set of the intelligent geological disaster area early warning model of the pipeline.
Factors playing a main disaster recovery role for geological disasters along pipelines in the embodiment include: stratum, rock-soil body type, elevation, gradient, slope, plane curvature, water system, fault and annual average rainfall. Dividing the pipeline into early warning analysis units with the size of 500 multiplied by 500m along the pipeline, and dividing the pregnancy disaster environment factors: the stratum, the rock-soil body type, the elevation, the gradient, the slope direction, the plane curvature, the water system, the fault and the annual average rainfall are drawn into a grid file with the size of 500 multiplied by 500m and consistent standard by using a GIS technology. And calculating the FR of each pregnancy disaster environment factor by using an FR model (probability ratio model), wherein the FR comprises a stratum FR, a rock and soil body type FR, an elevation FR, a slope FR, a plane curvature FR, a water system FR, a fault FR and an annual average rainfall FR, and calculating the total FR of the pregnancy disaster environment. And drawing a corresponding FR raster image by using a GIS technology.
The FR calculation formula is as follows:
FR is an approximate numerical ratio of j factor i classes, and Np (LXi) is the number of geological disaster evaluation units of i classes of factor variable X. Np (Xj) is the evaluation unit data of the factor variable Xj, and m is the number of secondary classification factors of the factor variable Xi. n represents the number of factors.
The high FR value represents that the correlation between the pregnant disaster environment and the geological disaster is high, which is beneficial to the occurrence of the geological disaster, and the low FR value represents that the correlation between the pregnant disaster environment and the geological disaster is low, which is not beneficial to the occurrence of the geological disaster. When a geological disaster occurs, the geological disaster is not only related to the pregnant disaster environment, but also has a big relation with the inducing factors in the period. And drawing an accumulated rainfall map of a rainfall process in the occurrence time period of each historical geological disaster point, wherein rainfall is a main inducing factor of the pipeline geological disaster. The accumulated rainfall in one rainfall process is up to the day of disaster occurrence, and the one rainfall process is not continuously interrupted for more than two days. The occurrence time of each geological disaster point is different, and the corresponding rainfall is also different, so that each geological disaster point corresponds to one rainfall accumulation graph, and the n rainfall accumulation graphs are drawn at the n geological disaster points.
The long distance of oil and gas pipeline transportation of defeated oil gas of length, pipeline circuit is long, pipeline geological disasters along the line are many, geological environment difference along the line is big, need be by professional technical personnel, the expert carries out pipeline geological disasters investigation along the line, according to geological disasters investigation result, technical personnel according to the geological environment background of pipeline along the line, geological disasters development characteristic, distribution law and main induction condition, according to the principle of "similar in the district, district difference", the easy subregion of division of pipeline geological disasters of marking off to draw pipeline geological disasters easily sends out the subregion map. The easy-to-send subareas are divided into a high easy-to-send area, a medium easy-to-send area, a low easy-to-send area and a non easy-to-send area, the easy-to-send subareas of different levels are generally distributed in a staggered mode, so that the pipeline is divided into a plurality of easy-to-send subareas along the line, and the geological environment in each geological disaster easy-to-send subarea is similar. The high-susceptibility subarea is not subjected to all geological disasters in a certain future time period, and the low-susceptibility subarea is not subjected to no geological disasters in a certain future time period, so that the difference in the same susceptibility subarea needs to be represented. Geological environments in the same geological disaster prone subarea are similar but not completely the same, so an FR (fuzzy r) diagram is superimposed to reflect the refined difference of the pregnant disaster environment in each prone subarea. When negative samples are sampled, the samples cannot be sampled only in a low incidence area, and the samples cannot be sampled only in a high incidence area.
After the general FR diagram and the volatile partitions of the pregnant disaster environment are superposed, the pipeline is divided into a plurality of negative sample acquisition units along the line, the boundary of each negative sample acquisition unit is used as the boundary of negative sample sampling, and independent sampling is carried out in each negative sample acquisition unit. The negative samples avoid selecting potential geological disaster hidden danger points as far as possible, and have regional representativeness as far as possible to avoid extreme negative sample points. The extreme negative sample points are not similar to the extreme ends of the geological disaster points, can only represent specific non-geological disaster areas, and have no regional representativeness. If only a batch of minimum FR values are selected during sampling, the negative sample points can be concentrated in a specific non-geological disaster area, so that the area representativeness is lost, all the total FR value range intervals which need to be counted and the total FR values corresponding to the geological disaster points are analyzed, and then the proper FR values collected by the negative samples are selected. And after analysis, selecting the average between the FR value corresponding to the geological disaster point and the lower bound of the FR value of the negative sample acquisition unit area where the geological disaster point is located as a basis for acquiring the negative sample. In addition, the acquiring process of the negative sample also needs to characterize the influence of the difference of the inducing factors on the geological disaster, and the FR values corresponding to the FR values and the geological disaster point are similar, but the inducing factors have larger difference and are used as another basis for acquiring the negative sample.
And counting the total FR value range interval in each negative sample acquisition unit area, counting the total FR values corresponding to the early warning analysis units where the geological disaster points are located, and calculating the average of the total FR values corresponding to the geological disaster points and the minimum value of the negative sample acquisition unit area where the geological disaster points are located. For example, landslide geological disasters occur in three groups of dam villages at east city offices of the city of li chuan of the emshi soil family of the city of li, north huo in 7/2016, the total FR value corresponding to the landslide disasters is 5.44, and the total FR range of the negative sample acquisition unit area in which the landslide disasters are located is as follows: [2.89,7.11], the average number of the disasters and the minimum value is 4.165, the central point of an early warning analysis unit with the total FR near 4.165 is collected in a negative sample collection unit area where the disasters are located to serve as one negative sample point, and the negative sample point is kept consistent with the accumulated rainfall inducing the landslide in the rainfall process at 2016, 7 and 7 days; collecting a total FR value near 5.44 in the same negative sample collecting unit area, wherein rainfall is obviously less than the position of accumulated rainfall inducing the landslide in the rainfall process, and collecting another negative sample point; the spatial location property and the temporal property of the negative samples are determined through sampling. The method is used for sampling the spatial position attribute and the time attribute of the negative sample points corresponding to all geological disaster points, and the ratio of the positive sample points to the negative sample points after sampling is 1:2. And finally, extracting data of the disaster-pregnant environment and the inducing factors by using the positions of the negative sample points, and endowing the stratum, the rock-soil body type, the elevation, the gradient, the slope direction, the plane curvature, the water system, the fault and the annual average rainfall value as well as the accumulated rainfall value in the rainfall process to each negative sample point to form a complete negative sample set with time, space positions, inducing factors and disaster-pregnant environment numerical values.
Claims (6)
1. The utility model provides a pipeline geological disasters intelligence early warning negative sample sampling method under restraint of partition easily sends out which characterized in that includes following content:
(1) Selecting factors required by early warning of a pipeline geological disaster area, wherein the required factors comprise a pregnant disaster environment and induction factors;
the disaster-pregnant environment comprises stratum, rock and soil body types, elevation, gradient, slope direction, plane curvature, water system, fault and annual average rainfall;
the inducing factors mainly refer to rainfall, which is the accumulated rainfall in the process of one-time rainfall;
(2) Dividing an early warning analysis unit, dividing the area along the pipeline into square early warning analysis units according to grid units with uniform size, and using the square early warning analysis units as the smallest geographical space units in artificial intelligence training to process the pregnant disaster environment and the induction factors into grid files with the same standard by using a GIS technology;
(3) Calculating FR, drawing an FR grid map, calculating the FR of each disaster-prone environment factor by using a geological disaster point and each disaster-prone environment map layer data obtained by checking pipeline geological disasters by using an FR model (probability ratio model), wherein the FR comprises a stratum FR, a rock-soil body type FR, an elevation FR, a slope FR, a plane curvature FR, a water system FR, a fault FR and an annual rainfall FR, solving the total FR of each disaster-prone environment, and drawing a corresponding FR grid map by using a GIS technology;
the FR calculation formula is as follows:
FR is the probability ratio of j factor i class, np (LXI) is the number of i class geological disaster evaluation units of the factor variable X, np (Xj) is the evaluation unit data of the factor variable Xj, m is the number of secondary classification factors of the factor variable Xi, and n represents the number of factors;
(4) The method comprises the steps of manufacturing a pipeline geological disaster easily-occurring subarea, drawing a pipeline geological disaster easily-occurring subarea map by a geological disaster investigation technician, dividing the pipeline geological disaster easily-occurring subarea by the pipeline geological disaster investigation technician according to the principles of similarity in areas and difference between areas according to geological environment background, geological disaster development characteristics, distribution rules and main inducing conditions along the pipeline, namely that the geological environment background conditions, the main inducing conditions and the geological disaster development characteristics are basically similar in the same type of areas, and the areas of different types have obvious differences, and drawing the pipeline geological disaster easily-occurring subarea map;
(5) Counting and drawing an accumulated rainfall map of a rainfall process ending at the occurrence date of each geological disaster point, wherein each geological disaster point corresponds to one accumulated rainfall map, n geological disaster points correspond to n accumulated rainfall maps, the accumulated rainfall of one rainfall process ends at the current day of the occurrence of the disaster, and the one rainfall process refers to a rainfall process which is not continuously interrupted for more than two days;
(6) Superposing the FR image layers and the distribution image layers to define negative sample acquisition unit areas, wherein one negative sample acquisition unit comprises a plurality of early warning analysis units, and negative samples are respectively sampled in each negative sample acquisition unit area;
(7) Counting the total FR value range of each negative sample collection unit, counting the total FR value of the early warning analysis unit where each geological disaster point is located, and solving the average Mi of the total FR value of the early warning analysis unit where each geological disaster point is located and the minimum total FR value of the negative sample collection units;
(8) Collecting the spatial attribute and the time attribute of a negative sample in a negative sample collecting unit; the method comprises the following steps that the occurred geological disaster points are called positive sample points, the positive samples have spatial attributes and time attributes, the negative sample points also have spatial attributes and time attributes, two negative sample points are collected correspondingly to each geological disaster point, one negative sample point is sampled at a position where the total FR value is equal to Mi and rainfall is the same, the other negative sample point is sampled at a position where the total FR value of the geological disaster point is the same but rainfall is less, and the time attributes of the two negative sample points are equal to the occurrence date of the geological disaster point;
(9) Constructing a negative sample set, and sampling negative sample points to form negative sample points 2 times of that of a positive sample, wherein each negative sample point has a spatial attribute and a time attribute, each negative sample point extracts disaster environment factor data of a corresponding spatial geographical position and extracts induction factor data of corresponding time to form the negative sample set, the negative sample set and the positive sample set jointly form a sample set of the pipeline intelligent geological disaster area early warning model, the disaster environment factor comprises stratum, rock and soil type, elevation, gradient, slope, plane curvature, water system, fault and annual average rainfall, and the induction factor is the accumulated rainfall in one rainfall process.
2. The intelligent early warning negative sample sampling method for the pipeline geological disasters under the constraint of the easily-issued subareas according to claim 1, which is characterized in that: the negative sample sampling method is based on two types of data of a pregnant disaster environment and an induction factor, a GIS technology is used for dividing an early warning analysis unit, an FR model and a GIS technology are used for calculating and drawing a FR grid map of the pregnant disaster environment, a GIS technology is used for drawing an accumulated rainfall map of each geological disaster point in a rainfall process, and each geological disaster point corresponds to one accumulated rainfall map.
3. The intelligent early warning negative sample sampling method for the pipeline geological disasters under the constraint of the easily-issued subareas according to claim 1, which is characterized in that: based on an FR model and volatile partition constraint, the area and the boundary of negative sample sampling are determined, the concept of a negative sample acquisition unit is defined, the sampling method of the specific position of the negative sample in the negative sample acquisition unit area is determined, and the acquisition boundary and the acquisition position of the negative sample are defined.
4. The intelligent early warning negative sample sampling method for the pipeline geological disasters under the constraint of the easily-issued subareas according to claim 1, which is characterized in that: the method comprises the steps that two negative sample points are collected corresponding to each geological disaster point, one negative sample point is sampled at a position where the total FR value is equal to Mi and rainfall is the same, the other negative sample point is sampled at a position where the total FR value of the geological disaster point is similar but rainfall is less, the time attributes of the two negative sample points are equal to the date of the occurrence of the geological disaster point, and the collected negative sample points are provided with space attributes and time attributes.
5. The intelligent early warning negative sample sampling method for the pipeline geological disasters under the constraint of the easily-issued subareas according to claim 1, which is characterized in that: and each negative sample point extracts the pregnant disaster environment factor data of the corresponding space geographic position and the induction factor data of the corresponding time, and the negative sample point positions are used for extracting the pregnant disaster environment and the induction factor data, and stratum, rock and soil body type, elevation, gradient, slope direction, plane curvature, water system, fault, annual average rainfall value and the accumulated rainfall value in the rainfall process are endowed to each negative sample point to form a complete negative sample set with time, space position, induction factor and pregnant disaster environment numerical value.
6. The intelligent early warning negative sample sampling method for the pipeline geological disasters under the constraint of the easily-issued subareas according to claim 1, which is characterized in that: the negative sample collection method fully considers the influence of pregnant disaster environment and induction factors on geological disasters, avoids collecting potential geological disaster hidden danger points, avoids collecting extreme negative sample points, avoids spatial distribution randomness of negative samples, defines sampling positions and sampling proportions, enables the negative samples to have high effectiveness and high representativeness, improves the collection quality of the negative samples, and is beneficial to improving the accuracy of an intelligent pipeline geological disaster area early warning model and reducing the missing report rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211298958.4A CN115830804B (en) | 2022-10-24 | 2022-10-24 | Pipeline geological disaster intelligent early warning negative sample sampling method under constraint of easily-generated partition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211298958.4A CN115830804B (en) | 2022-10-24 | 2022-10-24 | Pipeline geological disaster intelligent early warning negative sample sampling method under constraint of easily-generated partition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115830804A true CN115830804A (en) | 2023-03-21 |
| CN115830804B CN115830804B (en) | 2023-08-22 |
Family
ID=85525225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211298958.4A Active CN115830804B (en) | 2022-10-24 | 2022-10-24 | Pipeline geological disaster intelligent early warning negative sample sampling method under constraint of easily-generated partition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115830804B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101789120B1 (en) * | 2016-06-23 | 2017-11-15 | (주)해동기술개발공사 | Land Disaster Information System and Method by Parcel using Mobile GIS |
| CN112001435A (en) * | 2020-08-18 | 2020-11-27 | 中国地质环境监测院 | Method and system for constructing training sample set in regional landslide early warning and storage medium |
| CN112735097A (en) * | 2020-12-29 | 2021-04-30 | 中国地质环境监测院 | Regional landslide early warning method and system |
| CN112966722A (en) * | 2021-02-07 | 2021-06-15 | 南昌大学 | Regional landslide susceptibility prediction method based on semi-supervised random forest model |
| CN112991688A (en) * | 2021-03-03 | 2021-06-18 | 中山大学 | Geological disaster space-time combined early warning method and system based on PUL algorithm |
| CN113822522A (en) * | 2021-06-23 | 2021-12-21 | 中国科学院空天信息创新研究院 | Landslide susceptibility assessment method, device and equipment and readable storage medium |
| CN115100464A (en) * | 2022-06-21 | 2022-09-23 | 长安大学 | Landslide susceptibility assessment method and tool based on support vector machine |
-
2022
- 2022-10-24 CN CN202211298958.4A patent/CN115830804B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101789120B1 (en) * | 2016-06-23 | 2017-11-15 | (주)해동기술개발공사 | Land Disaster Information System and Method by Parcel using Mobile GIS |
| CN112001435A (en) * | 2020-08-18 | 2020-11-27 | 中国地质环境监测院 | Method and system for constructing training sample set in regional landslide early warning and storage medium |
| CN112735097A (en) * | 2020-12-29 | 2021-04-30 | 中国地质环境监测院 | Regional landslide early warning method and system |
| CN112966722A (en) * | 2021-02-07 | 2021-06-15 | 南昌大学 | Regional landslide susceptibility prediction method based on semi-supervised random forest model |
| CN112991688A (en) * | 2021-03-03 | 2021-06-18 | 中山大学 | Geological disaster space-time combined early warning method and system based on PUL algorithm |
| CN113822522A (en) * | 2021-06-23 | 2021-12-21 | 中国科学院空天信息创新研究院 | Landslide susceptibility assessment method, device and equipment and readable storage medium |
| CN115100464A (en) * | 2022-06-21 | 2022-09-23 | 长安大学 | Landslide susceptibility assessment method and tool based on support vector machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115830804B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dunn et al. | HadISD: A quality-controlled global synoptic report database for selected variables at long-term stations from 1973–2011 | |
| Mwangi et al. | Forecasting droughts in East Africa | |
| Carrara et al. | GIS techniques and statistical models in evaluating landslide hazard | |
| CN103197299B (en) | Extraction and quantitative analysis system of weather radar radial wind information | |
| Das et al. | Assessment of urban sprawl using landscape metrics and Shannon’s entropy model approach in town level of Barrackpore sub-divisional region, India | |
| Gudmundsson et al. | Observation-based gridded runoff estimates for Europe (E-RUN version 1.1) | |
| CN111242404B (en) | Extreme evaluation method and system for heavy rainfall induced flood incident | |
| CN108875806B (en) | False forest fire hot spot mining method based on space-time data | |
| CN113139760B (en) | Typhoon risk comprehensive evaluation method and system based on wind and rain big data | |
| CN110134907B (en) | Rainfall missing data filling method and system and electronic equipment | |
| CN107730496A (en) | A kind of multi-temporal remote sensing image building change detecting method based on image blocks | |
| Wei et al. | Exploring the spatiotemporal pattern of traffic congestion performance of large cities in China: A real-time data based investigation | |
| CN111144637A (en) | Regional power grid geological disaster forecasting model construction method based on machine learning | |
| CN113240257A (en) | Territorial space partitioning method and device based on minimum cumulative resistance model | |
| Pan et al. | Spatial identification of housing vacancy in China | |
| Pan et al. | Spatiotemporal dynamics of electricity consumption in China | |
| Ghaderi et al. | Detecting shoreline change employing remote sensing images (Case study: Beris Port-east of Chabahar, Iran) | |
| CN113269240A (en) | Rainfall station site selection information output method and device, electronic equipment and medium | |
| CN108828332B (en) | Method for calculating detection efficiency of lightning positioning system | |
| CN115830804A (en) | Intelligent early warning negative sample sampling method for pipeline geological disasters under constraint of easily-issued subareas | |
| CN115600047B (en) | Small watershed surface average rainfall measurement and calculation method and system based on grid analysis | |
| CN113610436B (en) | Method and system for evaluating dynamic vulnerability of disaster-bearing body | |
| CN115271332A (en) | Drought monitoring method | |
| Hu et al. | Methodology and findings for the exposure analysis of the Chinese wastewater sector to flooding and earthquakes hazards | |
| CN102798370B (en) | Method for measuring area of specified flight level action range of radar net |
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 |