Advanced AI for Earth Science Studies

We develop interpretable AI and causal inference approaches to understand the complex Earth system.

Earth system models driven by domain-knowledge are physically interpretable, but generally exhibit lower accuracy than machine learning models due to limited observational constraints and substantial uncertainties in model structures and parameterizations. Data-driven machine learning models generally have higher accuracy but are black-boxes with high risk of overfitting and low confidence for future climate projections. Therefore, we focus on developing and applying advanced causality inference approaches to understand and reduce uncertainties in Earth system models, and using inferred causal relationships and domain knowledge to inform and improve machine/deep learning models.

Model structure of the causal-ML and the causal relationship findings from our CH4 study. Further details are provided in our AFM paper.

2024

  1. Earth’s Future
    Projecting large fires in the western US with an interpretable and accurate hybrid machine learning method
    F. Li, Q. Zhu, K. Yuan, F. Ji, A. Paul, P. Lee, V. Radeloff, and M. Chen
    Earth’s Future, 2024

2023

  1. US patent
    Predicting climate conditions based on teleconnections
    H. Ma, K. Yuan, F. Li, C. Leroy, and G. Bronevetsky
    Jun 2023
    US Patent 11,668,856

2022

  1. GMD
    Building a machine learning surrogate model for wildfire activities within a global Earth system model
    Q. Zhu, F. Li, W. Riley, L. Xu, L. Zhao, K. Yuan, H. Wu, J. Gong, and J. Randerson
    Geoscientific Model Development, Jun 2022
  2. AFM
    Understanding and reducing the uncertainties of land surface energy flux partitioning within CMIP6 land models
    K. Yuan, Q. Zhu, W. Riley, F. Li, and H. Wu
    Agricultural and Forest Meteorology, Jun 2022
  3. GMD
    AttentionFire_v1. 0: interpretable machine learning fire model for burned area predictions over tropics
    F. Li, Q. Zhu, W. Riley, L. Zhao, L. Xu, K. Yuan, M. Chen, H. Wu, Z. Gui, J. Gong, and others
    Geoscientific Model Development Discussions, Jun 2022
  4. AFM
    Causality guided machine learning model on wetland CH4 emissions across global wetlands
    K. Yuan, Q. Zhu, F. Li, W. Riley, M. Torn, H. Chu, G. McNicol, M. Chen, S. Knox, K. Delwiche, and others
    Agricultural and Forest Meteorology, Jun 2022
  5. GMD
    AttentionFire_v1. 0: interpretable machine learning fire model for burned area predictions over tropics
    F. Li, Q. Zhu, W. Riley, L. Zhao, L. Xu, K. Yuan, M. Chen, H. Wu, Z. Gui, J. Gong, and others
    Geoscientific Model Development Discussions, Jun 2022

2021

  1. ERL
    Deforestation reshapes land-surface energy-flux partitioning
    K. Yuan, Q. Zhu, S. Zheng, L. Zhao, M. Chen, W. Riley, X. Cai, H. Ma, F. Li, H. Wu, and others
    Environmental Research Letters, Jun 2021