Dapeng Feng is a postdoctoral fellow in the Department of Earth System Science and Stanford Institute for Human-Centered Artificial Intelligence. During his PhD he developed the differentiable hydrologic modeling framework to unify machine learning and physical models for large-scale water cycle simulations and streamflow forecasting. His current research interests focus on systematically integrating AI, physical models, and big earth observations for large-scale geoscientific modeling and knowledge discovery, particularly in characterizing the terrestrial water cycle and its interactions with plant and climate systems.

Institute Affiliations

Honors & Awards

  • HAI Postdoctoral Fellowship, Stanford Institute for Human-Centered Artificial Intelligence (2023)
  • Top Downloaded Article (Feng et al., 2022), Water Resources Research (2024)
  • Editors’ Choice Award (Ma, Feng et al., 2021), Water Resources Research (2023)
  • Top Cited Article 2020-2021 (Feng et al., 2020), Water Resources Research (2022)
  • James E. Marley Graduate Fellowship in Engineering, Penn State University (2020)
  • C. Norwood Wherry Memorial Graduate Fellowship in Engineering, Penn State University (2021)
  • University Graduate Fellowship, Penn State University (2018)

Professional Education

  • Doctor of Philosophy, Pennsylvania State University (2023)
  • Ph.D., Penn State University, Hydrology (2023)
  • M.E., Peking University, Hydrology and Water Resources (2018)
  • B.E., Wuhan University, Hydraulic Engineering (2015)

Stanford Advisors

All Publications

  • Differentiable modelling to unify machine learning and physical models for geosciences NATURE REVIEWS EARTH & ENVIRONMENT Shen, C., Appling, A. P., Gentine, P., Bandai, T., Gupta, H., Tartakovsky, A., Baity-Jesi, M., Fenicia, F., Kifer, D., Li, L., Liu, X., Ren, W., Zheng, Y., Harman, C. J., Clark, M., Farthing, M., Feng, D., Kumar, P., Aboelyazeed, D., Rahmani, F., Song, Y., Beck, H. E., Bindas, T., Dwivedi, D., Fang, K., Hoge, M., Rackauckas, C., Mohanty, B., Roy, T., Xu, C., Lawson, K. 2023
  • The suitability of differentiable, physics-informed machine learninghydrologic models for ungauged regions and climate change impact assessment HYDROLOGY AND EARTH SYSTEM SCIENCES Feng, D., Beck, H., Lawson, K., Shen, C. 2023; 27 (12): 2357-2373
  • Differentiable, Learnable, Regionalized Process-Based Models With Multiphysical Outputs can Approach State-Of-The-Art Hydrologic Prediction Accuracy WATER RESOURCES RESEARCH Feng, D., Liu, J., Lawson, K., Shen, C. 2022; 58 (10)
  • From calibration to parameter learning: Harnessing the scaling effects of big data in geoscientific modeling. Nature communications Tsai, W. P., Feng, D., Pan, M., Beck, H., Lawson, K., Yang, Y., Liu, J., Shen, C. 2021; 12 (1): 5988


    The behaviors and skills of models in many geosciences (e.g., hydrology and ecosystem sciences) strongly depend on spatially-varying parameters that need calibration. A well-calibrated model can reasonably propagate information from observations to unobserved variables via model physics, but traditional calibration is highly inefficient and results in non-unique solutions. Here we propose a novel differentiable parameter learning (dPL) framework that efficiently learns a global mapping between inputs (and optionally responses) and parameters. Crucially, dPL exhibits beneficial scaling curves not previously demonstrated to geoscientists: as training data increases, dPL achieves better performance, more physical coherence, and better generalizability (across space and uncalibrated variables), all with orders-of-magnitude lower computational cost. We demonstrate examples that learned from soil moisture and streamflow, where dPL drastically outperformed existing evolutionary and regionalization methods, or required only ~12.5% of the training data to achieve similar performance. The generic scheme promotes the integration of deep learning and process-based models, without mandating reimplementation.

    View details for DOI 10.1038/s41467-021-26107-z

    View details for PubMedID 34645796

    View details for PubMedCentralID PMC8514470

  • Mitigating Prediction Error of Deep Learning Streamflow Models in Large Data-Sparse Regions With Ensemble Modeling and Soft Data GEOPHYSICAL RESEARCH LETTERS Feng, D., Lawson, K., Shen, C. 2021; 48 (14)
  • Enhancing Streamflow Forecast and Extracting Insights Using Long-Short Term Memory Networks With Data Integration at Continental Scales WATER RESOURCES RESEARCH Feng, D., Fang, K., Shen, C. 2020; 56 (9)
  • Improving River Routing Using a Differentiable Muskingum-Cunge Model and Physics-Informed Machine Learning WATER RESOURCES RESEARCH Bindas, T., Tsai, W., Liu, J., Rahmani, F., Feng, D., Bian, Y., Lawson, K., Shen, C. 2024; 60 (1)
  • Identifying Structural Priors in a Hybrid Differentiable Model for Stream Water Temperature Modeling WATER RESOURCES RESEARCH Rahmani, F., Appling, A., Feng, D., Lawson, K., Shen, C. 2023; 59 (12)
  • The Data Synergy Effects of Time-Series Deep Learning Models in Hydrology WATER RESOURCES RESEARCH Fang, K., Kifer, D., Lawson, K., Feng, D., Shen, C. 2022; 58 (4)
  • Continental-scale streamflow modeling of basins with reservoirs: Towards a coherent deep-learning-based strategy JOURNAL OF HYDROLOGY Ouyang, W., Lawson, K., Feng, D., Ye, L., Zhang, C., Shen, C. 2021; 599
  • Transferring Hydrologic Data Across Continents - Leveraging Data-Rich Regions to Improve Hydrologic Prediction in Data-Sparse Regions WATER RESOURCES RESEARCH Ma, K., Feng, D., Lawson, K., Tsai, W., Liang, C., Huang, X., Sharma, A., Shen, C. 2021; 57 (5)
  • From Hydrometeorology to River Water Quality: Can a Deep Learning Model Predict Dissolved Oxygen at the Continental Scale? Environmental science & technology Zhi, W., Feng, D., Tsai, W. P., Sterle, G., Harpold, A., Shen, C., Li, L. 2021; 55 (4): 2357-2368


    Dissolved oxygen (DO) reflects river metabolic pulses and is an essential water quality measure. Our capabilities of forecasting DO however remain elusive. Water quality data, specifically DO data here, often have large gaps and sparse areal and temporal coverage. Earth surface and hydrometeorology data, on the other hand, have become largely available. Here we ask: can a Long Short-Term Memory (LSTM) model learn about river DO dynamics from sparse DO and intensive (daily) hydrometeorology data? We used CAMELS-chem, a new data set with DO concentrations from 236 minimally disturbed watersheds across the U.S. The model generally learns the theory of DO solubility and captures its decreasing trend with increasing water temperature. It exhibits the potential of predicting DO in "chemically ungauged basins", defined as basins without any measurements of DO and broadly water quality in general. The model however misses some DO peaks and troughs when in-stream biogeochemical processes become important. Surprisingly, the model does not perform better where more data are available. Instead, it performs better in basins with low variations of streamflow and DO, high runoff-ratio (>0.45), and winter precipitation peaks. Results here suggest that more data collections at DO peaks and troughs and in sparsely monitored areas are essential to overcome the issue of data scarcity, an outstanding challenge in the water quality community.

    View details for DOI 10.1021/acs.est.0c06783

    View details for PubMedID 33533608

  • An integrated hydrological modeling approach for detection and attribution of climatic and human impacts on coastal water resources JOURNAL OF HYDROLOGY Feng, D., Zheng, Y., Mao, Y., Zhang, A., Wu, B., Li, J., Tian, Y., Wu, X. 2018; 557: 305-320