Among natural hazards, landslides are devastating in China. However, little is known regarding potential landslide-prone areas in Maoxian County. The goal of this study was to apply four deep learning algorithms, the convolutional neural network (CNN), deep neural network (DNN), long short-term memory (LSTM) networks, and recurrent neural network (RNN) in evaluating the possibility of landslides throughout Maoxian County, Sichuan, China. A total of 1290 landslide records was developed using historical records, field observations, and remote sensing techniques. The landslide susceptibility maps showed that most susceptible areas were along the Minjiang River and in some parts of the southeastern portion of the study area. Slope, rainfall, and distance to faults were the most influential factors affecting landslide occurrence. Results revealed that proportion of landslide susceptible areas in Maoxian County was as follows: identified landslides (13.65–23.71%) and non-landslides (76.29–86.35%). The resultant maps were tested against known landslide locations using the area under the curve (AUC). This study indicated that the DNN algorithm performed better than LSTM, CNN, and RNN in identifying landslides in Maoxian County, with AUC values (for prediction accuracy) of 87.30%, 86.50%, 85.60%, and 82.90%, respectively. The results of this study are useful for future landslide risk reduction along with devising sustainable land use planning in the study area.

The Third Pole experiences accelerated glacier retreating particularly in the eastern‐Himalaya, coinciding with a decrease of monsoon‐precipitation in the early 21st century. The extent to which the vanishing abundant maritime glaciers buffer the declining precipitation‐runoff remains unclear. Here, with a state‐of‐the‐art enthalpy‐based distributed cryosphere‐hydrology model and first‐hand hydrometeorology observations at Motuo (latest accessible Chinese county), we carefully examine the Yarlung Zangbo basin along Himalayas. We find that during 1998–2019, the rising downstream runoff (lower Nuxia; +6.40 × 10⁸ m³/yr) offsets the dropping upstream runoff (upper Nuxia; −6.89 × 10⁸ m³/yr); however, only the marginal contribution from the vanishing eastern‐Himalaya and Nyainqêntanglha glaciers. During 1998–2019, dry upstream illustrates limited glacier melt (15.7 mm/yr) with dominated snow melt (78.8 mm/yr); while much larger at humid downstream (144.8 mm/yr for glacier melt and 219.1 mm/yr for snow melt). From 1981 to 2019, we observe glacier‐to‐snow melt transition in both upstream and downstream due to glacier degradation and growing nonmonsoon‐season precipitation.

Glacial lake outburst floods (GLOF) evolve into debris flows by erosion and sediment entrainment while propagating down a valley, which highly increases peak discharge and volume and causes destructive damage downstream. This study focuses on GLOF hazard assessment in the Bhote Koshi Basin (BKB), where was highly developed glacial lakes and was intensely affected by the Gorkha earthquake. A new 2016 glacial lake inventory was established, and six unreported GLOF events were identified with geomorphic outburst evidence from GaoFen-1 satellite images and Google Earth. A new method was proposed to assess GLOF hazard, in which large numbers of landslides triggered by earthquake were considered to enter into outburst floods enlarge the discharge and volume of debris flow in the downstream. Four GLOF hazard classes were derived according to glacial lake outburst potential and a flow magnitude assessment matrix, in which 11 glacial lakes were identified to have very high hazard and 24 to have high hazard. The GLOF hazard in BKB increased after the earthquake due to landslide deposits, which increased by 216.03 × 10⁶ m³, and provides abundant deposits for outburst floods to evolve into debris flows. We suggest that in regional GLOF hazard assessment, small glacial lakes should not be overlooked for landslide deposit entrainment along a flood route that would increase the peak discharge, especially in earthquake-affected areas where large numbers of landslides were triggered.

The Kosi River is an important tributary of the Ganges River, which passes through China, Nepal and India. With a basin area of 71 500 km², the Kosi River has the largest elevation drop in the world (from 8848 m of Mt Everest to 60 m of the Ganges Plain) and covers a broad spectrum of climate, soil, vegetation and socioeconomic zones. The basin suffers from multiple water related hazards including glacial lake outburst, debris flow, landslides, flooding, drought, soil erosion and sedimentation. This paper describes the characteristics of water hazards in the basin, based on the literature review and site investigation covering hydrology, meteorology, geology, geomorphology and socio-economics. Glacial lake outbursts are a huge threat to the local population in the region and they usually further trigger landslides and debris flows. Floods are usually a result of interaction between man-made hydraulic structures and the natural environment. Debris flows are widespread and occur in clusters. Droughts tend to last over long periods and affect vast areas. Rapid population increase, the decline of ecosystems and climate change could further exacerbate various hazards in the region. The paper has proposed a set of mitigating strategies and measures. It is an arduous challenge to implement them in practice. More investigations are needed to fill in the knowledge gaps.