Research Interests

Our research focuses on advancing fundamental understanding of the interactions between hydrology and other subsystems (e.g., ecosystem, energy and carbon cycles, sediment and channels). Water scarcity and excess create varied conflicts and competitions in different parts of the world, and drastic changes in the water cycle put stress on natural and societal systems. Importantly, the changes in water states and flows are a significant driver for changes in other systems, e.g., ecosystem, wildfire regimes, carbon and nutrient cycles. We strive to provide sound physical science, produced by data, data-driven and process-based models, to support decision-making across multiple scales, from catchment scales to global-scale analysis. Meanwhile, our fundamental understanding of the hydrologic cycle, after decades of research, still remains much to be improved. We strive to identify commonalities, determining attributes and learn underlying principles.

Our primary methods include (1) high performance physically-based hydrologic models; and (2) state-of-the-art machine learning. The former allows us to conduct experiments, while the latter, through mining land-based and remotely-sensed data, help to efficiently generate hypotheses about how the system functions. Recently, we have focused on deep-learning-based prediction of soil moisture and other variables. Deep learning has been found to be an exceedingly powerful tool for many applications. Please read my argument, review, and opinions for the integration of deep learning in water-related fields.

We are opening sourcing our hydrologic deep learning code.

Besides machine learning, another tool we use intensively is the Process-based Adaptive Watershed Simulator (PAWS), a comprehensive, computationally-efficient parallel hydrologic model designed for large-scale simulation. The model is now coupled to the Community Land Model (CLM), and therefore is able to simulate Carbon/Nitrogen cycling, ecosystem dynamics and their interactions with the water cycle. Due to its comprehensiveness, efficiency, and flexibility, this tool provides a useful platform for the integration of biogeochemistry, fluid mechanics, and human dimensions into a uniform modeling framework, to investigate their mutual interactions, to test hypothesis about causal relationships and to assess future changes.

PAWS is now open to all users. READ repo access will be granted to anyone who
request it by sending an email to cshen@engr.psu.edu.

 

Some headsups of my involvement:

Shen will present a spotlight talk on ICML2019 workshop. More info at Climatechange.ai. If you are there, let's discuss!

CUAHSI hydroinformatics conference keynote, July 29 - 31, 2019

Talk in Catchment Science: Interactions of Hydrology, Biology and Geochemistry, June 27, In Andover, NH 11:45AM

 

Shen's Google scholar profile

Most Recent News

May 7th, 2019. Penn State team led by Shen was selected by Google.org as one of the 20 grantees of the Google AI Impacts Challenge.

Shen has been promoted to the position of Associate Professor with tenure by Penn State. The appointment becomes effective on July 1st, 2019

May 2019, Fang's paper on modeling desert recharge has been accepted. This is a lot of work to get a handle on the amount of recharge in a very difficult problem: a mountainous desert. A lot of thanks to folks who put in instruments in the desert to obtain moisture and meteorological data in the desert. Thanks to Rohit Salve who started this project. I only visited the site once but had quite some interesting memory of the desert basin.

 

Past News

Older news ...