In this work, we present the CAS Landslide Dataset, a large-scale and multisensor dataset for deep learning-based landslide detection, developed by the Artificial Intelligence Group at the Institute of Mountain Hazards and Environment, Chinese Academy of Sciences (CAS). The dataset aims to address the challenges encountered in landslide recognition. With the increase in landslide occurrences due to climate change and earthquakes, there is a growing need for a precise and comprehensive dataset to support fast and efficient landslide recognition. In contrast to existing datasets with dataset size, coverage, sensor type and resolution limitations, the CAS Landslide Dataset comprises 20,865 images, integrating satellite and unmanned aerial vehicle data from nine regions. To ensure reliability and applicability, we establish a robust methodology to evaluate the dataset quality. We propose the use of the Landslide Dataset as a benchmark for the construction of landslide identification models and to facilitate the development of deep learning techniques. Researchers can leverage this dataset to obtain enhanced prediction, monitoring, and analysis capabilities, thereby advancing automated landslide detection.

Streamflow and flood forecasting remains one of the long-standing challenges in hydrology. Traditional physically based models are hampered by sparse parameters and complex calibration procedures particularly in ungauged catchments. We propose a novel hybrid deep learning model termed encoder-decoder double-layer long short-term memory (ED-DLSTM) to address streamflow forecasting at global scale for all (gauged and ungauged) catchments. Using historical datasets, ED-DLSTM yields a mean Nash-Sutcliffe efficiency coefficient (NSE) of 0.75 across more than 2,000 catchments from the United States, Canada, Central Europe, and the United Kingdom, highlighting improvements by the state-of-the-art machine learning over traditional hydrologic models. Moreover, ED-DLSTM is applied to 160 ungauged catchments in Chile and 76.9% of catchments obtain NSE >0 in the best situation. The interpretability of cross-region capacities of ED-DLSTM are established through the cell state induced by adding a spatial attribute encoding module, which can spontaneously form hydrological regionalization effects after performing spatial coding for different catchments. The study demonstrates the potential of deep leaning methods to overcome the ubiquitous lack of hydrologic information and deficiencies in physical model structure and parameterization.