We are interested in applying machine learning algorithms to various problems in climate science and geoscience, such as dimensionality reduction, cluster analysis, forward and inverse modeling, and image recognition. So far we have mostly used relatively simple machine learning algorithms, including principal component analysis/empirical orthogonal function analysis (e.g., Chen et al., 2013), self-organizing maps (e.g., Chen et al., 2016; Lai et al., 2021), and random forests (e.g., Zhong et al., 2023).
People working on this topic

Assistant Professor

We are keen on applying modern deep learning and image recognition techniques, for example to detect emission plumes for greenhouse gas monitoring, or to identify and track atmospheric rivers. Our group is collaborating with other groups that use such techniques, for example for air quality monitoring (e.g., Yan et al., 2023).
Other developments we follow closely include applications of machine learning in numerical weather prediction. Such machine learning-based models could be highly value not only for making deterministic forecasts, but also for generating large ensembles of forecasts that can be used in ensemble-based data assimilation. We are also interested in augmenting traditional data assimilation methods with machine learning-based algorithms, for example to overcome conventional limitations due to linear and Gaussian assumptions.
Related publications
Yan, X., C. Zuo, Z. Li, H. W. Chen, Y. Jiang, Q. Wang, G. Wang, K. Jia, Y. A, Z. Chen, and J. Chen, 2024: Substantial underestimation of fine-mode aerosol loading from wildfires and its radiative effects in current satellite-based retrievals over the United States. Environmental Science & Technology, 58, 15661–15671, https://doi.org/10.1021/acs.est.4c02498.
Yan, X., Z. Zang, Z. Li, H. W. Chen, J. Chen, Y. Jiang, Y. Chen, B. He, C. Zuo, T. Nakajima, and J. Kim, 2024: Deep learning with pretrained framework unleashes the power of satellite-based global fine-mode aerosol retrieval. Environmental Science & Technology, 58, 14260–14270, https://doi.org/10.1021/acs.est.4c02701.
Lai, H.-W., D. Chen, and H. W. Chen, 2024: Precipitation variability related to atmospheric circulation patterns over the Tibetan Plateau. International Journal of Climatology, 44, 1–17, https://doi.org/10.1002/joc.8317.
Zhong, Z., B. He, H. W. Chen, D. Chen, T. Zhou, W. Dong, C. Xiao, L. Guo, R. Ding, L. Zhang, X. Song, L. Huang, W. Yuan, X. Hao, and X. Zhao, 2023: Reversed asymmetric warming of sub-diurnal temperature over land during recent decades. Nature Communications, 14, 7189, https://doi.org/10.1038/s41467-023-43007-6.
Yan, X., C. Zuo, Z. Li, H. W. Chen, Y. Jiang, B. He, H. Liu, J. Chen, and W. Shi, 2023: Cooperative simultaneous inversion of satellite-based real-time PM2.5 and ozone levels using an improved deep learning model with attention mechanism. Environmental Pollution, 327, 121509, https://doi.org/10.1016/j.envpol.2023.121509.
Lai, H.-W., H. W. Chen, J. Kukulies, T. Ou, and D. Chen, 2021: Regionalization of seasonal precipitation over the Tibetan Plateau and associated large-scale atmospheric systems. Journal of Climate, 34, 2635–2651, https://doi.org/10.1175/JCLI-D-20-0521.1.
Chen, H. W., R. B. Alley, and F. Zhang, 2016: Interannual Arctic sea ice variability and associated winter weather patterns: A regional perspective for 1979–2014. Journal of Geophysical Research: Atmospheres, 121, 14433–14455, https://doi.org/10.1002/2016JD024769.
Chen, H. W., F. Zhang, and R. B. Alley, 2016: The robustness of midlatitude weather pattern changes due to Arctic sea ice loss. Journal of Climate, 26, 7831–7849, https://doi.org/10.1175/JCLI-D-16-0167.1.
Chen, H. W., Q. Zhang, H. Körnich, and D. Chen, 2013: A robust mode of climate variability in the Arctic: The Barents Oscillation. Geophysical Research Letters, 40, 2856–2861, https://doi.org/10.1002/grl.50551.