Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Co...Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.展开更多
Numerous Quaternary deposits are existed in the mountainous areas of Southwest China,especially in the transition zone between the QinghaiTibet Plateau and the Sichuan Basin,where strong tectonic movements and frequen...Numerous Quaternary deposits are existed in the mountainous areas of Southwest China,especially in the transition zone between the QinghaiTibet Plateau and the Sichuan Basin,where strong tectonic movements and frequent climatic changes increase the potential landslides.The possible deformation and failure process of potential landslides and their impacts on the surrounding environment are important research topics.Field investigation and monitoring indicate that the Qingliu landslide in Xiameng town,Li County,Sichuan Province,China has been continuously deforming since August 2020.The deformation zone has a maximum deformation depth of approximately 18.9m,a total area of 54,628 m2,and a volume of 34.0×104 m3,which seriously threatens infrastructure projects and dwellings.As a result,understanding the Qingliu landslide evolution process,assessing the hazard risk,and planning disaster prevention measures are of great significance for reducing disaster loss.In this study,the mass movement process and hazard risk of the Qingliu landslide are evaluated,and the effects of different prevention measures are compared and discussed.By using the depth-integrated method,the mass movement of the Qingliu landslide is analyzed.The numerical simulation results indicate that the maximum velocity of the Qingliu landslide is approximately 37.5 m/s,and the duration of the landslide is approximately 90s.The simulated landslide can eventually form a deposited mass with a maximum deposit thickness of 19.4 m and an area of approximately 60,168.3 m2,thereby blocking the river and burying dwellings.Furthermore,a risk assessment of the Qingliu landslide under different forms of protection measures is also produced and discussed by considering the hazard level and economic vulnerability level of the affected area.Setting three layers of anti-slide piles on the deformation zone to reduce the hazard risk of the Qingliu landslide is a better choice.Our results may be useful for planning prevention measures and improving disaster emergency response systems.展开更多
In recent years, natural disasters in China have occurred frequently, especially large disasters such as earthquakes, floods and droughts, which have posed a serious threat to local public safety. In addition, the geo...In recent years, natural disasters in China have occurred frequently, especially large disasters such as earthquakes, floods and droughts, which have posed a serious threat to local public safety. In addition, the geological environment of local mountainous areas in China is complex and diverse, and climate change is large. Considering the dynamic coupling effect of rainfall conditions to stimulate geological disasters, this paper takes dynamic risk assessment technology as the guide, constructs a dynamic risk early warning model of geological disasters, establishes a prototype system, realizes dynamic risk assessment and emergency early warning of geological disasters at the regional level, and provides feasible technical support for targeted emergency disaster prevention. At the same time, the investigation and evaluation, mechanism research and monitoring and early warning related to the comprehensive prevention and control of geological disasters are important tasks that cannot be ignored, an important link in the emergency response system for geological disasters, and a key stage process to guide scientific disaster prevention. On the basis of exploring the mechanism and catastrophic effect of rainfall to stimulate landslides and mudslides, we will carry out in-depth research on disaster prevention countermeasures such as systematic engineering disposal, monitoring and early warning.展开更多
This paper had investigated the termite hazard of garden plants in Shanghai Songjiang Central Park with 71 plants of trees destroyed by termites and two control groups as tested varieties. These 71 plants of trees wou...This paper had investigated the termite hazard of garden plants in Shanghai Songjiang Central Park with 71 plants of trees destroyed by termites and two control groups as tested varieties. These 71 plants of trees would be treated by using the treatment of toxicity soil combined with powder, the first control group would be treated by anti-termite powder, and the second group would be given no treatment. After 50 days'treatment, it was found that the treatment rate of toxicity soil combined with powder was 93%, with stable effect and no repeatability; the treatment rate of anti-termite powder was 33.3%, with unstable effect and repeatability, and it was needed to change and add medicament again and again so as to make sure that trees would no longer be damaged by termite; there still existed termite hazard in the second group without treatment. By contrasting different treatment methods, it could be known that treatment of toxicity soil combined with powder had obvious advantage, harmless to human body and environment, and could replace traditional medicaments and methods with strong toxicity.展开更多
For engineering geological investigation, hydrographic surveys are particularly important. By operating the equipment, relevant technicians analyze hydrogeological data around the project. A series of corresponding me...For engineering geological investigation, hydrographic surveys are particularly important. By operating the equipment, relevant technicians analyze hydrogeological data around the project. A series of corresponding measures were taken to ensure the smooth completion of the project. However, due to the inadequate completion of hydrogeological survey work, it has great harm to the later stage of engineering work, and even will lead to the final failure of the project. Based on this, this paper explores the hazards and prevention measures of hydrogeology in engineering surveys.展开更多
基金supported by the projects of the China Geological Survey(DD20221729,DD20190291)Zhuhai Urban Geological Survey(including informatization)(MZCD–2201–008).
文摘Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.
基金the support of the National Natural Science Foundation of China(U2240221,41977229)the Sichuan Youth Science and Technology Innovation Research Team Project(2020JDTD0006)the Sichuan Provincial International Science and Technology Collaboration&Innovation Project(2020YFH0092)。
文摘Numerous Quaternary deposits are existed in the mountainous areas of Southwest China,especially in the transition zone between the QinghaiTibet Plateau and the Sichuan Basin,where strong tectonic movements and frequent climatic changes increase the potential landslides.The possible deformation and failure process of potential landslides and their impacts on the surrounding environment are important research topics.Field investigation and monitoring indicate that the Qingliu landslide in Xiameng town,Li County,Sichuan Province,China has been continuously deforming since August 2020.The deformation zone has a maximum deformation depth of approximately 18.9m,a total area of 54,628 m2,and a volume of 34.0×104 m3,which seriously threatens infrastructure projects and dwellings.As a result,understanding the Qingliu landslide evolution process,assessing the hazard risk,and planning disaster prevention measures are of great significance for reducing disaster loss.In this study,the mass movement process and hazard risk of the Qingliu landslide are evaluated,and the effects of different prevention measures are compared and discussed.By using the depth-integrated method,the mass movement of the Qingliu landslide is analyzed.The numerical simulation results indicate that the maximum velocity of the Qingliu landslide is approximately 37.5 m/s,and the duration of the landslide is approximately 90s.The simulated landslide can eventually form a deposited mass with a maximum deposit thickness of 19.4 m and an area of approximately 60,168.3 m2,thereby blocking the river and burying dwellings.Furthermore,a risk assessment of the Qingliu landslide under different forms of protection measures is also produced and discussed by considering the hazard level and economic vulnerability level of the affected area.Setting three layers of anti-slide piles on the deformation zone to reduce the hazard risk of the Qingliu landslide is a better choice.Our results may be useful for planning prevention measures and improving disaster emergency response systems.
文摘In recent years, natural disasters in China have occurred frequently, especially large disasters such as earthquakes, floods and droughts, which have posed a serious threat to local public safety. In addition, the geological environment of local mountainous areas in China is complex and diverse, and climate change is large. Considering the dynamic coupling effect of rainfall conditions to stimulate geological disasters, this paper takes dynamic risk assessment technology as the guide, constructs a dynamic risk early warning model of geological disasters, establishes a prototype system, realizes dynamic risk assessment and emergency early warning of geological disasters at the regional level, and provides feasible technical support for targeted emergency disaster prevention. At the same time, the investigation and evaluation, mechanism research and monitoring and early warning related to the comprehensive prevention and control of geological disasters are important tasks that cannot be ignored, an important link in the emergency response system for geological disasters, and a key stage process to guide scientific disaster prevention. On the basis of exploring the mechanism and catastrophic effect of rainfall to stimulate landslides and mudslides, we will carry out in-depth research on disaster prevention countermeasures such as systematic engineering disposal, monitoring and early warning.
文摘This paper had investigated the termite hazard of garden plants in Shanghai Songjiang Central Park with 71 plants of trees destroyed by termites and two control groups as tested varieties. These 71 plants of trees would be treated by using the treatment of toxicity soil combined with powder, the first control group would be treated by anti-termite powder, and the second group would be given no treatment. After 50 days'treatment, it was found that the treatment rate of toxicity soil combined with powder was 93%, with stable effect and no repeatability; the treatment rate of anti-termite powder was 33.3%, with unstable effect and repeatability, and it was needed to change and add medicament again and again so as to make sure that trees would no longer be damaged by termite; there still existed termite hazard in the second group without treatment. By contrasting different treatment methods, it could be known that treatment of toxicity soil combined with powder had obvious advantage, harmless to human body and environment, and could replace traditional medicaments and methods with strong toxicity.
文摘For engineering geological investigation, hydrographic surveys are particularly important. By operating the equipment, relevant technicians analyze hydrogeological data around the project. A series of corresponding measures were taken to ensure the smooth completion of the project. However, due to the inadequate completion of hydrogeological survey work, it has great harm to the later stage of engineering work, and even will lead to the final failure of the project. Based on this, this paper explores the hazards and prevention measures of hydrogeology in engineering surveys.
