KATHMANDU, August 1: Glacier-fed lakes across Nepal and its transboundary river basins continued to expand in both number and size between 2017 and 2024, with the Koshi basin witnessing the most rapid growth, according to the first automated annual inventory of Himalayan glacial lakes developed by scientists.
The dataset, published in the peer-reviewed journal Earth System Science Data, is expected to significantly improve the monitoring of potentially dangerous glacial lakes and strengthen early warning efforts against glacial lake outburst floods (GLOFs), one of the fastest-growing climate-related hazards in the Himalayas.
Researchers from the University of Leeds, Kathmandu University, the Wadia Institute of Himalayan Geology and the Chinese Academy of Sciences developed the new Glacial Lake Observatory (GLO), which combines satellite imagery and artificial intelligence to automatically detect and monitor glacial lakes every year.
Unlike previous inventories that relied heavily on manual mapping and were updated only every several years, the new system uses deep-learning algorithms trained on thousands of satellite images from the European Space Agency’s Sentinel-1 and Sentinel-2 missions. The approach allows researchers to monitor changes more frequently and consistently, even in remote mountain regions where cloud cover often limits optical observations.
“Fully automated and systematic monitoring of lake area changes has been lacking,” the researchers wrote, adding that continuous observation is essential for identifying unusually rapid lake expansion, estimating water storage and understanding glacier-lake interactions under a warming climate.
Nearly 4,200 unique glacial lakes mapped
The study identified 4,150 unique glacial lakes using Sentinel-2 imagery and 2,967 lakes using Sentinel-1 radar observations across Nepal and adjacent catchments in India and China.
Overall, researchers mapped more than 22,000 individual lake outlines from Sentinel-2 imagery and more than 18,000 outlines from Sentinel-1 data collected between 2017 and 2024.
The combined dataset shows that glacial lakes occupied an average annual area of about 169 square kilometres, with both the number of lakes and their total area increasing during the eight-year study period.
47 potentially dangerous glacial lakes identified within Koshi,...
Most of the growth occurred in the Koshi River basin, which alone contains approximately 61 percent of all mapped glacial lakes. Nine of the 10 fastest-expanding lakes identified in the study are located within this basin, underscoring its growing vulnerability.
The researchers found that expansion was concentrated mainly in high-elevation, glacier-fed lakes that receive meltwater directly from retreating glaciers.
Climate change accelerating glacier retreat
The findings come as scientists warn that glaciers across the Hindu Kush Himalaya are melting at unprecedented rates as temperatures in the region rise much faster than the global average.
The paper notes that High Mountain Asia—often called the “Third Pole” because it contains the world’s largest concentration of ice outside the Arctic and Antarctic—is warming at approximately twice the global average.
As glaciers lose mass, meltwater accumulates behind unstable moraine dams, creating and enlarging glacial lakes. While these lakes temporarily store freshwater, they can also fail catastrophically when triggered by avalanches, landslides or collapsing ice, releasing millions of cubic metres of water downstream within hours.
Such glacial lake outburst floods have repeatedly damaged settlements, hydropower plants, roads and bridges in Nepal and neighbouring Himalayan countries.
The researchers warn that continued glacier retreat could increase both the number and size of hazardous lakes unless they are monitored systematically.
Artificial intelligence improves monitoring
To build the observatory, the research team trained a deep-learning model known as DeepLabV3 using manually mapped glacial lakes before applying it to satellite imagery spanning 2017–2024.
The system analyses radar and optical satellite images separately before combining the results.
Radar imagery from Sentinel-1 enables monitoring even under cloudy conditions, while Sentinel-2’s higher-resolution optical imagery captures smaller lakes more accurately.
Validation showed that the automated mapping achieved strong performance, with F1 scores ranging from 0.80 to 0.92, while Sentinel-2 consistently detected small lakes better than radar imagery. Researchers say the complementary use of both satellites overcomes one of the biggest challenges of Himalayan monitoring—persistent monsoon cloud cover.
Open data for governments and researchers
The newly published dataset has been made openly available and will form the basis of a continuously updated Glacial Lake Observatory portal currently under development.
Scientists expect the database to support a wide range of applications, including disaster risk reduction, glacier research, climate studies, hydropower planning and water resource management.
Because the system is fully automated, future updates can be produced regularly without requiring large teams to manually digitise thousands of lake boundaries.
“This provides the foundation for systematic glacial lake monitoring that does not require manual intervention,” the authors said.
Importance for Nepal
Nepal has witnessed several destructive glacial lake outburst floods over recent decades, while dozens of potentially dangerous glacial lakes have already been identified by previous studies.
With climate change accelerating glacier retreat across the Himalayas, scientists say continuous monitoring has become increasingly important for protecting downstream communities and critical infrastructure.
The new observatory also enables authorities to detect unusual lake expansion at an earlier stage, allowing more timely field investigations and risk assessments before catastrophic failures occur.
Researchers say the annual dataset represents only the first phase of the Glacial Lake Observatory, with future releases expected to continue tracking changes in Himalayan glacial lakes as climate warming reshapes one of the world’s most sensitive mountain environments.
