Study Reveals Alarming Decline of Groundwater Reserves in High Mountain Asia

Groundwater reserves beneath High Mountain Asia (HMA), known as the “Asian Water Tower,” are diminishing at a concerning rate, according to a recent satellite-based study led by Prof. Shudong Wang from the Aerospace Information Research Institute of the Chinese Academy of Sciences (AIRCAS). The region is crucial for farming, urban areas, and ecosystems that support hundreds of millions in over a dozen downstream countries, with researchers estimating a decline in groundwater storage of approximately 24.2 billion tonnes annually.

Satellite Data and AI Analyze Two Decades of Groundwater Changes

The research published in Environmental Research Letters aimed to address challenges related to limited ground data and the complex mountainous terrain of HMA. To achieve this, the researchers developed an artificial intelligence (AI)-powered assessment model that integrates data from various satellites alongside Earth system modeling and explainable AI, reconstructing groundwater storage changes over the past 20 years.

Findings indicate that around two-thirds of HMA has experienced declining groundwater storage from 2003 to 2020, with the largest losses noted in densely populated downstream basins, such as the Ganges-Brahmaputra, Indus, and Amu Darya. Conversely, some higher elevation inland regions showed localized increases in groundwater storage.

Factors Driving Groundwater Depletion

Climate-related factors account for nearly half of the variation in groundwater storage observed, with significant influences arising from cryosphere changes. The study also highlighted that human-driven groundwater withdrawals are increasingly contributing to depletion, particularly in agricultural areas dependent on irrigation—a trend that intensified after 2010.

Researchers anticipate that if ongoing water use patterns persist, groundwater depletion will likely worsen. While increased glacier melt in certain regions might temporarily slow this decline in the 2060s, the phenomenon is expected to be a temporary “buffer effect” that could subsequently lead to accelerated losses. This poses a growing risk to agricultural lands that rely on these water reserves.

An Innovative Framework for Groundwater Analysis

The study utilized a novel analytical framework based on established scientific principles and extensive observational data, drawing from multiple satellite sensors to estimate groundwater storage changes. It incorporated a lightweight Transformer architecture to better understand hydrological memory and delayed effects within mountainous regions. Additionally, explainable machine learning methods were employed to identify the physical factors driving the observed groundwater changes.

To ensure the reliability of their findings, the researchers validated their results against thousands of groundwater well measurements and independent datasets, reinforcing their study’s conclusions. This comprehensive approach helps tackle long-standing challenges in monitoring groundwater resources in HMA due to its rugged terrain and the lack of detailed information on human water consumption.

The research received funding from the National Key R&D Program of China and the Key Program of the National Natural Science Foundation of China (NSFC).