Detecting and monitoring landslides are hot topics in remote sensing community, particularly with the development of remote sensing technologies and the significant progress of computer vision. To the best of our knowledge, no study focused on deep learning-based methods for landslide detection on hyperspectral images. We proposes a deep learning framework with constraints to detect landslides on hyperspectral image. The framework consists of two steps. First, a deep belief network is employed to extract the spectral–spatial features of a landslide. Second, we insert the high-level features and constraints into a logistic regression classifier for verifying the landslide. Experimental results demonstrated that the framework can achieve higher overall accuracy when compared to traditional hyperspectral image classification methods. The precision of the landslide detection on the whole image, obtained by the proposed method, can reach 97.91%, whereas the precision of the linear support vector machine, spectral information divergence, and spectral angle match are 94.36%, 84.50%, and 86.44%, respectively. Also, this article reveals that the high-level feature extraction system has a significant potential for landslide detection, especially in multi-source remote sensing.

Cryospheric responses to climate warming include glacier retreat, altitude‐dependent thermal instability, and abundant meltwater, which increase the frequency of catastrophic glacier hazard chain (CGHC) events. Here we investigated the formation mechanism of a special CGHC event in 2018, in the Sedongpu Glacier, Eastern Himalayas, China. Based on the multi‐source remote sensing, seismic signal analysis, and numerical simulation, we conducted long‐term retrospective analysis and co‐event process reconstruction. The results show that the event could be divided into two phases. First, the hanging glacier with a volume of 8.5 × 10 ⁶ m ³ collapsed onto the downstream trunk glacier. Next, ∼1.17 × 10 ⁸ m ³ eroded materials from the impacted glacier transformed into debris flow and traveled downstream 8 km. During the cascading process, ice‐rock avalanche momentum and glacier velocity are key factors in determining CGHC formation and eventual volume. Our study helps better understand the domino effects of the CGHC disaster.

With increasing glacial hazards due to global climate warming, a promising digital-twin-based platform has been proposed for early warning of cryospheric disasters.