AQUAH: Automatic Quantification and Unified Agent in Hydrology

Songkun Yan, Zhi Li, Siyu Zhu, Yixin Wen, Mofan Zhang, Mengye Chen, Jie Cao, Yang Hong; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 2926-2935

We introduce AQUAH, the first end-to-end language-based agent designed specifically for hydrologic modelling. Starting from a simple natural-language prompt (e.g., "simulate floods for the Little Bighorn basin from 2020 to 2022"), AQUAH autonomously retrieves the required terrain, forcing, and gauge data; configures a hydrologic model; runs the simulation; and generates a self-contained PDF report. The workflow is driven by vision-enabled large-language models, which interpret maps and rasters on the fly and steer key decisions such as outlet selection, parameter initialisation, and uncertainty commentary. Initial experiments across a range of U.S. basins show that AQUAH can complete cold-start simulations and produce analyst-ready documentation without manual intervention--results that hydrologists judge as clear, transparent, and physically plausible. While further calibration and validation are still needed for operational deployment, these early outcomes highlight the promise of LLM-centred, vision-grounded agents to streamline complex environmental modelling and lower the barrier between Earth-observation data, physics-based tools, and decision makers.