Foundation Models for Forecasting Water Time Series

Type of project

M.Sc.

Contact

Jesper Mariegaard (jem@dhigroup.com)

Topic

Recent breakthroughs in AI have led to large, pre-trained foundation models for time series, such as TimeGPT, Chronos, and Lag-Llama. These models promise robust, general-purpose forecasting capabilities across domains. This project will evaluate how well these models perform on water-related time series problems, such as wastewater inflow, harbour water levels, or urban runoff. The student will apply the models and compare the performance of these models against traditional forecasting methods (e.g., ARIMA).

Relevance to DHI

Accurate time series forecasts are essential for many DHI applications. If foundation models can provide strong performance across multiple hydrological tasks with minimal effort, they may dramatically simplify and improve forecasting pipelines.

What is the student's contribution

Apply multiple foundation models to 3–5 real-world water time series. Evaluate its performance, robustness, and usability compared to baseline models. Deliverables: code, benchmark comparisons, and practical recommendations for forecasting in water systems.