Research
I am interested in utilizing multiple satellite datasets (e.g., SMAP, MODIS), in-situ observations, and reanalysis products (e.g., ERA5) to investigate how climate variability and human activities affect water resources. My research focuses on developing BERT/GPT-based foundation models that can be fine-tuned for tasks such as streamflow forecasting, soil moisture prediction, and water quality assessment. Additionally, I apply hybrid models that integrate physics-based hydrological approaches with deep learning techniques, ensuring predictions remain both accurate and physically interpretable. Ultimately, my goal is to provide robust, scalable, and transparent modeling frameworks to support decision-making from local watersheds to global scales. My expertise also includes zero-shot forecasting, cross-task transfer learning, and satellite imagery analysis (e.g., detection and segmentation).
Selected Publications
- Liu, J.; Bian, Y.; Lawson, K.; Shen, C. Probing the Limit of Hydrologic Predictability with the Transformer Network. J. Hydrol. 2024, 637, 131389. paper
- Liu, J.; Rahmani, F.; Lawson, K.; Shen, C. A Multiscale Deep Learning Model for Soil Moisture Integrating Satellite and in Situ Data. Geophys. Res. Lett. 2022, 49 (7), e2021GL096847. paper
🏆 News
- [June 2024] Awarded the Vice Provost and Dean of the Graduate School Student Persistence Scholarship at The Pennsylvania State University.
- [May 2025] Invited to serve as a Student Cluster Competition Reviewer (SCC & IndySCC) for SC25 – The International Conference for High Performance Computing, Networking, Storage, and Analysis.
- [May 2025] Joined the ESS Open Archive editorial team as a moderator.
- [April 2025] My first-author and corresponding-author manuscript, titled “From RNNs to Transformers: benchmarking deep learning architectures for hydrologic prediction”, is now available as a preprint at Hydrology and Earth System Sciences (HESS)
- [Nov 2024] Co-authored paper “Increasing phosphorus loss despite widespread concentration decline in US rivers” published in Proceedings of the National Academy of Sciences (PNAS).
- [Sep 2023] Co-authored paper “Widespread deoxygenation in warming rivers” published in Nature Climate Change.
- [Oct 2021] Co-authored paper “From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling” published in Nature Communications.
- 🥇 Top Downloaded: Jiangtao Liu’s GRL paper (2022)
