As natural disasters are induced by geodynamic activities or abnormal changes in the environment, geological hazards tend to wreak havoc on environment and human society. Recently, dramatic increase volume of various types Earth observation 'big data' from multiple sources, rapid development deep learning as a state-of-the-art data analysis tool, have enabled novel advances hazard analysis, with ultimate aim mitigate devastation associated these hazards. Motivated numerous applications, this...

Abstract Landslides are one of the most critical categories natural disasters worldwide and induce severely destructive outcomes to human life overall economic system. To reduce its negative effects, landslides prevention has become an urgent task, which includes investigating landslide-related information predicting potential landslides. Machine learning is a state-of-the-art analytics tool that been widely used in prevention. This paper presents comprehensive survey relevant research on...

Geologic hazards (geohazards) are naturally occurring or human-activity-induced geologic conditions capable of causing damage loss property and/or life. geohazards, such as landslides, surface subsidence, and earthquakes, can seriously affect threaten life, property, public safety. geohazards prevention is the application engineering principles existing emerging technologies to reduce, minimize, prevent effects various hazards. Monitoring early warning most common strategies for prevention....

Landslides are a common type of natural disaster in mountainous areas. As result the comprehensive influences geology, geomorphology and climatic conditions, susceptibility to landslide hazards areas shows obvious regionalism. The evaluation regional can help reduce risk lives mountain residents. In this paper, Shannon entropy theory, fuzzy method an analytic hierarchy process (AHP) have been used demonstrate variable weighting for modeling, combining subjective objective weights. Further,...

Easy and efficient acquisition of high-resolution remote sensing images is importance in geographic information systems. Previously, deep neural networks composed convolutional layers have achieved impressive progress super-resolution reconstruction. However, the inherent problems layer, including difficulty modeling long-range dependency, limit performance these on To address above problems, we propose a generative adversarial network (GAN) by combining advantages swin transformer layers,...

Abstract Slope deformation prediction is crucial for early warning of slope failure, which can prevent property damage and save human life. Existing predictive models focus on predicting the displacement a single monitoring point based time series data, without considering spatial correlations among points, makes it difficult to reveal changes in entire system ignores potential threats from nonselected points. To address above problem, this paper presents novel deep learning method...

As a vital research subject in the field of intelligent transportation systems (ITSs), traffic flow prediction using deep learning methods has attracted much attention recent years. However, numerous existing studies mainly focus on short-term predictions and fail to consider influence external factors. Effective long-term become challenging issue. solution these challenges, this paper proposes approach based spatiotemporal graph convolutional network for with multiple In proposed method,...

Groundwater is a valuable water source for drinking and irrigation purposes in semiarid regions. pollution may affect human health if it not pretreated provided use. This study investigated the hydrochemical characteristics driving groundwater quality potential risks Xinzhou Basin, Shanxi Province, North China. More specifically, we first using descriptive statistical analysis method. We then classified types analyzed evolution mechanisms of Piper Gibbs diagrams. Finally, appraised entropy...

Soil consolidation is closely related to seepage, stability, and settlement of geotechnical buildings foundations, directly affects the use safety superstructures. Nowadays, unidirectional theory soils widely used in certain conditions approximate calculations. The multi-directional soil more reasonable than practical applications, but it much complicated terms index determination solution. To address above problem, this paper, we propose a deep learning method using physics-informed neural...

Meteorological conditions have a strong influence on air quality and can play an important role in prediction. However, due to the "black-box" nature of deep learning, it is difficult obtain trustworthy learning models when considering meteorological To address above problem, this paper, we reveal prediction by utilizing explainable learning. In (1) source data from pollutant datasets, including PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML"...

Abstract Data mining and analysis are critical for preventing or mitigating natural hazards. However, data availability in hazard is experiencing unprecedented challenges due to economic, technical, environmental constraints. Recently, generative deep learning has become an increasingly attractive solution these challenges, which can augment, impute, synthesize based on learned complex, high-dimensional probability distributions of data. Over the last several years, much research...

Landslides result in serious damage to economic and land resources. Automated landslide detection over a wide area for the study prevention of geohazards is important. Linzhi located southeastern part Tibetan Plateau, one most landslide-prone regions China. In this paper, we utilize deep learning approach combination with remote sensing images detect landslides City. SHAP-based interpretability analysis exponential Weighted Method Technique Order Preference by Similarity Ideal Solution...