The geo-environment is intensively and greatly affected by the increased human activities in nature. One significant consequence is that active human activities caused many damages to the geo-environment and led to a series of geo-hazards including landslides, surface subsidence, and collapse. Those events pose a serious threat and may result in human casualties, property loss, road damage, destruction of farmland and forest, and failures of communication infrastructure. Thus, protecting the geo-environment has become a pressing issue and quantification of the potential geohazards plays a crucial role during the protection process.
In recent years, advanced quantitative methods such as deep learning and AI have attracted an enormous amount of attention across both academia and industry. Emerged from traditional statistical learning methods, AI & deep-learning methods enabled us to learn from advanced representations within the dataset and perform end-to-end optimization. The AI methods have demonstrated superior performance in a wide variety of fields such as biomedical engineering, energy systems, and computer vision. Nevertheless, the applications in geohazards and the geo-environment sector are still limited in relation to the demand. Hence, there is a huge potential to apply AI, deep-learning, and other data science technology to extract information and enhance human understanding of geo-environmental protection and geohazards prevention.
The main aim of this Research Topic is to develop accurate quantitative models to predict and tackle various geo-environmental hazards. We invite researchers and experts from all over the globe to submit high-quality, original research papers or comprehensive reviews. The topics of interest include but are not limited to:
• Deep-learning & AI technologies in landslide, land subsidence, debris flow, and flood
• Numerical simulation of geohazards including landslide, land subsidence, debris flow, and flood
• Geo-environmental hazards quantitative/qualitative assessment and mitigation
• Remote sensing analysis for landslide, collapse, soil loss, and other geohazards
• Time-series analysis of sensor data for geohazards monitoring such as flood, debris flow, and landslide
• Indoor laboratory physical modeling of geohazards including landslide, and debris flow
• Spatial-temporal analysis of geo-environmental hazards with GIS
We would like to invite scholars to submit contributions related to the application of these techniques in various types of geo-environmental hazards including:
• Landslide
• Land subsidence
• Collapse
• Debris flow
• Earthquake
• Groundwater degradation
The geo-environment is intensively and greatly affected by the increased human activities in nature. One significant consequence is that active human activities caused many damages to the geo-environment and led to a series of geo-hazards including landslides, surface subsidence, and collapse. Those events pose a serious threat and may result in human casualties, property loss, road damage, destruction of farmland and forest, and failures of communication infrastructure. Thus, protecting the geo-environment has become a pressing issue and quantification of the potential geohazards plays a crucial role during the protection process.
In recent years, advanced quantitative methods such as deep learning and AI have attracted an enormous amount of attention across both academia and industry. Emerged from traditional statistical learning methods, AI & deep-learning methods enabled us to learn from advanced representations within the dataset and perform end-to-end optimization. The AI methods have demonstrated superior performance in a wide variety of fields such as biomedical engineering, energy systems, and computer vision. Nevertheless, the applications in geohazards and the geo-environment sector are still limited in relation to the demand. Hence, there is a huge potential to apply AI, deep-learning, and other data science technology to extract information and enhance human understanding of geo-environmental protection and geohazards prevention.
The main aim of this Research Topic is to develop accurate quantitative models to predict and tackle various geo-environmental hazards. We invite researchers and experts from all over the globe to submit high-quality, original research papers or comprehensive reviews. The topics of interest include but are not limited to:
• Deep-learning & AI technologies in landslide, land subsidence, debris flow, and flood
• Numerical simulation of geohazards including landslide, land subsidence, debris flow, and flood
• Geo-environmental hazards quantitative/qualitative assessment and mitigation
• Remote sensing analysis for landslide, collapse, soil loss, and other geohazards
• Time-series analysis of sensor data for geohazards monitoring such as flood, debris flow, and landslide
• Indoor laboratory physical modeling of geohazards including landslide, and debris flow
• Spatial-temporal analysis of geo-environmental hazards with GIS
We would like to invite scholars to submit contributions related to the application of these techniques in various types of geo-environmental hazards including:
• Landslide
• Land subsidence
• Collapse
• Debris flow
• Earthquake
• Groundwater degradation