Machine Learning for Hydrological and Earth Systems
Dr. Shijie Jiang
Mission
In the face of increasing environmental and climatic pressures, understanding the variability and causality of biogeochemical cycles across spatial and temporal scales is essential. The Machine Learning for Hydrological and Earth Systems (ML4HES) group, also part of the ELLIS Unit Jena, explores how environmental and climate sciences can benefit from advances in machine learning integrated with domain science. Our research combines data-driven insights with domain knowledge to investigate feedbacks, interactions, and responses within Earth systems, with a particular focus on advancing our understanding of coupled hydrological, ecological, and climate systems.
Focus areas
Ecohydrological and climate systems
We investigate the interactions between ecohydrological and climatic processes that drive water and energy fluxes across regions and scales. Our research focuses on understanding the role of vegetation and its feedback mechanisms in shaping hydroclimatic dynamics, including extreme events.
Soil-plant hydraulics
We study water transport and regulation within the soil-plant-atmosphere continuum, focusing on how vegetation responds to and influences environmental changes. Our work emphasizes root zone processes and uses diverse datasets to explore plant-water interactions, particularly under drought conditions.
Watershed hydro-biogeochemistry
Our research examines how hydrological and biogeochemical processes operate and interact at the watershed scale. We study the cycling of water, energy, carbon, and nutrients, with an emphasis on watershed responses to both natural and human-induced variability.
Hybrid and explainable machine learning
Methodologically, our group combines advanced data-driven techniques with classical Earth system analysis to improve the modeling and understanding of complex dynamics within interconnected Earth subsystems. We emphasize the integration of machine learning with domain knowledge to develop robust methods for identifying dependencies, interactions, couplings, feedback mechanisms, and causal relationships across biogeochemical processes to address key scientific questions.
News
November 2024
Winter is approaching, but November is full of excitement! This month we welcome two newcomers, Chao Wang and Yao Li. Stay tuned for their exciting work! Our team also participated in the 9th "Long Night of Science" in Jena with the booth of ELLIS Unit Jena, showing how AI is being used to understand climate change and develop solutions.
September 2024
We are excited to have Jialiang Zhou join our group for his PhD journey! Jialiang will explore a new method to understand plant physiological responses. We are also delighted to welcome Shengyue Chen to our group for a one-year visit.
Georgios Blougouras, Feini Huang, and Shijie Jiang attended and presented at EGU24 in Vienna. At the conference, Shijie also convened and chaired a successful and well-attended session on Explainable and Hybrid Machine Learning in Hydrology.
The project funded by Carl Zeiss Stiftung aims for excellent research in AI and will be located at the interface between AI and environmental research. The goal is to integrate expertise into AI approaches and to draw new insights from this, e.g., for climate extremes and their effects ecosystem functions or services.
Publications
2025
Shi, Z.; Zhao, W.; Xiong, Y.; Lian, X.; Fang, J.; Jiang, S.; Yan, C.; Winkler, A.; Qiu, G. Y.: A theoretical framework for critical canopy temperature and its potential to improve remote-sensing-based estimation of evapotranspiration. SSRN Conference Paper Series (2025)
Agathangelidis, I.; Blougouras, G.; Cartalis, C.; Polydoros, A.; Tzanis, C. G.; Philippopoulos, K.: Global climatology of the daytime surface cooling of urban parks using satellite observations. Geophysical Research Letters 52 (2), e2024GL112887 (2025)
Wang, C.; Jiang, S.; Zheng, Y.; Han, F.; Kumar, R.; Rakovec, O.; Li, S.: Distributed hydrological modeling with physics‐encoded deep learning: A general framework and its application in the Amazon. Water Resources Research 60 (4), e2023WR036170 (2024)
