We're pleased to highlight this publication by Minkyeong Seong and colleagues, which presents a hybrid deep learning–numerical modelling framework for improving long-term predictions of groundwater discharge and radionuclide transport. Using HydroGeoSphere (HGS) as the physics-based reference model, the researchers combined process-based numerical modelling with a graph convolutional long short-term memory (GC-LSTM) deep learning model to achieve highly accurate long-term predictions while dramatically reducing computational costs.

Long-term prediction of groundwater flow and radionuclide transport is essential for evaluating the safety of deep geological repositories used to store radioactive waste. While fully integrated numerical models such as HydroGeoSphere provide highly accurate simulations of coupled surface water, groundwater, and contaminant transport processes, these simulations can become computationally demanding for assessments spanning decades or even millions of years. Simpler models offer faster runtimes but often sacrifice accuracy by neglecting important processes such as unsaturated flow. This study addresses that challenge by combining the strengths of physics-based modelling with artificial intelligence to improve both efficiency and predictive performance.

We’re pleased to highlight this publication, co-authored by Shuangshuang Yu and colleagues, which investigates how creek network topology influences storm-surge-driven salinization in coastal marsh systems. This study leverages HydroGeoSphere (HGS) to simulate coupled surface–subsurface flow and salt transport processes under variable-density conditions, addressing long-standing challenges in understanding how geomorphology controls vertical saltwater intrusion and recovery in marsh environments.