Top Cited
6
Abstract:
The landslide disaster in China is widespread and serious. Regional landslide risk assessment has always been one of the most important contents of landslide disaster prevention and mitigation. In recent years, with the rapid development of big data and artificial intelligence technology, machine learning technology has gradually been widely used in landslide hazard assessment andachieved good results. Based on a large number of literatures, this paper systematically expounds the research status of landslide risk assessment methods based on machine learning technology. This paper reviews and analyzes the existing research results from three key links: evaluation factor selection and quantization normalization, data cleaning and sample set construction, model selection and training evaluation, and finally puts forward some suggestions on the development trend of machine learning landslide risk evaluation methods.
The landslide disaster in China is widespread and serious. Regional landslide risk assessment has always been one of the most important contents of landslide disaster prevention and mitigation. In recent years, with the rapid development of big data and artificial intelligence technology, machine learning technology has gradually been widely used in landslide hazard assessment andachieved good results. Based on a large number of literatures, this paper systematically expounds the research status of landslide risk assessment methods based on machine learning technology. This paper reviews and analyzes the existing research results from three key links: evaluation factor selection and quantization normalization, data cleaning and sample set construction, model selection and training evaluation, and finally puts forward some suggestions on the development trend of machine learning landslide risk evaluation methods.
12
2020, 31(6): 60-68.
DOI: 10.16031/j.cnki.issn.1003-8035.2020.06.08
Abstract:
In order to explore the practical role of highway slope automatic monitoring system based on GNSS monitoring station, this paper studies the K69 + 080 section of YQTJ5 section of Chongqing Banan Qijiang Expressway. Firstly, based on LZMR02-GNSS receiver and FS-YL rain gauge, Beidou + safety monitoring cloud platform is independently developed, which can manage and analyze the GNSS surface displacement monitoring stations and deep displacement monitoring holes arranged on site in real time. The monitoring results show that the slope has local collapse and cracking and other unstable phenomena, and early warning is sent to relevant departments and units. Then, the residual sliding force of the slope is calculated based on the transfer coefficient method, and the numerical simulation is carried out by using Geo5 finite element software. The results verify the accuracy of the monitoring system. Therefore, the establishment of highway slope automatic monitoring system can not only solve the shortcomings of conventional manual monitoring of slope, but also ensure the timeliness of monitoring data, which provides a certain reference value for future intelligent monitoring of slope.
In order to explore the practical role of highway slope automatic monitoring system based on GNSS monitoring station, this paper studies the K69 + 080 section of YQTJ5 section of Chongqing Banan Qijiang Expressway. Firstly, based on LZMR02-GNSS receiver and FS-YL rain gauge, Beidou + safety monitoring cloud platform is independently developed, which can manage and analyze the GNSS surface displacement monitoring stations and deep displacement monitoring holes arranged on site in real time. The monitoring results show that the slope has local collapse and cracking and other unstable phenomena, and early warning is sent to relevant departments and units. Then, the residual sliding force of the slope is calculated based on the transfer coefficient method, and the numerical simulation is carried out by using Geo5 finite element software. The results verify the accuracy of the monitoring system. Therefore, the establishment of highway slope automatic monitoring system can not only solve the shortcomings of conventional manual monitoring of slope, but also ensure the timeliness of monitoring data, which provides a certain reference value for future intelligent monitoring of slope.
16
Abstract:
In recent years, landslides occurred frequently in mountain and gorge areas, which brought serious threats to people's life and property safety. Most scholars use SAR single-track data for early identification of landslides in alpine and canyon areas, but some landslides cannot be identified due to geometric distortion of SAR imaging, and the identification results are not comprehensive. In order to carry out comprehensive and accurate early identification of landslide hazards in alpine valley area, this paper adopts bas-INSAR technology, takes the deep cut alpine valley area along the Xiaojiang River in Dongchuan as the research area, and adopts the combination of SAR data of lifting and lowering orbit to identify landslide hazards, and introduces high-resolution optical images as auxiliary identification. Finally, 18 landslide disaster bodies were identified, among which 5 were high-risk potential landslides, and three types of typical potential landslides were analyzed. The analysis results show that the use of elevator rail SAR data combined with complementary way, can effectively avoid the SAR single orbital data geometric distortion problem in mountain valley area, at the same time, this method can more accurately comprehensively to early identification of alpine valley area of landslide hazard, the cause of disaster prevention and mitigation and government decision-making provides a effective means.
In recent years, landslides occurred frequently in mountain and gorge areas, which brought serious threats to people's life and property safety. Most scholars use SAR single-track data for early identification of landslides in alpine and canyon areas, but some landslides cannot be identified due to geometric distortion of SAR imaging, and the identification results are not comprehensive. In order to carry out comprehensive and accurate early identification of landslide hazards in alpine valley area, this paper adopts bas-INSAR technology, takes the deep cut alpine valley area along the Xiaojiang River in Dongchuan as the research area, and adopts the combination of SAR data of lifting and lowering orbit to identify landslide hazards, and introduces high-resolution optical images as auxiliary identification. Finally, 18 landslide disaster bodies were identified, among which 5 were high-risk potential landslides, and three types of typical potential landslides were analyzed. The analysis results show that the use of elevator rail SAR data combined with complementary way, can effectively avoid the SAR single orbital data geometric distortion problem in mountain valley area, at the same time, this method can more accurately comprehensively to early identification of alpine valley area of landslide hazard, the cause of disaster prevention and mitigation and government decision-making provides a effective means.
19
2022, 33(2): 96-104.
DOI: 10.16031/j.cnki.issn.1003-8035.2022.02-12
Abstract:
The evaluation of regional geological disaster susceptibility is of great significance to the prevention and control of geological disasters. This paper takes Yanhe County in Guizhou Province as the research area, and considers 9 factors including altitude, slope, aspect, terrain curvature, NDVI, engineering geological rock formations, faults, roads, and water systems as evaluation factors. The CF model and the CF-LR model were used to evaluate the susceptibility of geological disasters in Yanhe County. The results show that the frequency ratio between the CF model and the CF-LR model of geological hazard susceptibility levels increases significantly from low-prone areas to extremely high-prone areas, which effectively evaluates the susceptibility of geological hazards in Yanhe County; the CF-LR model compares The AUC value of the CF model is increased by 0.096, and the CF-LR model has a higher evaluation accuracy.
The evaluation of regional geological disaster susceptibility is of great significance to the prevention and control of geological disasters. This paper takes Yanhe County in Guizhou Province as the research area, and considers 9 factors including altitude, slope, aspect, terrain curvature, NDVI, engineering geological rock formations, faults, roads, and water systems as evaluation factors. The CF model and the CF-LR model were used to evaluate the susceptibility of geological disasters in Yanhe County. The results show that the frequency ratio between the CF model and the CF-LR model of geological hazard susceptibility levels increases significantly from low-prone areas to extremely high-prone areas, which effectively evaluates the susceptibility of geological hazards in Yanhe County; the CF-LR model compares The AUC value of the CF model is increased by 0.096, and the CF-LR model has a higher evaluation accuracy.
- First
- Prev
- 1
- 2
- 3
- 4
- 5
- Next
- Last
- Total 5 Pages
- To
- Go