 |
|
Shaoxing Mo
Personal ProfileDr. Shaoxing Mo Assistant Professor of Hydrology and Water ResourcesSchool of Earth Sciences and Engineering, Nanjing University, China E-mail: smo@nju.edu.cn Google Scholar: https://scholar.google.com/citations?user=b5m_q4sAAAAJ&hl=en&oi=ao Shaoxing Mo started his Bachelor of Engineering (BE) in Groundwater Science and Engineering at Nanjing University in 2010. He continued his studies as a PhD student in Hydrology and Water Resources at Nanjing University. He focused on developing machine learning/deep learning methods to efficiently address the challenges associated with high-dimensional uncertainty quantification and inverse modeling in groundwater flow and transport modeling. During his PhD, he visited a deep learning group led by Prof. Nicholas Zabaras at University of Notre Dame for two years (August 2017-August 2019), where he worked on developing and applying the state-of-the-art convolutional neural networks for parameterization of complex hydrogeological structures and heterogeneous parameter fields, and for emulation of time-consuming groundwater models with high-dimensional and strongly nonlinear input-output mappings. After his PhD completed in December 2019, he was employed as a postdoctoral researcher at School of Earth Sciences and Engineering of Nanjing University working on research related to the regional hydrologic cycle, (ground-)water storage changes, and hydrological drought by employing remote sensing (e.g., GRACE), deep learning, and hydrological/land surface models. Currently, Shaoxing has a position as assistant professor at School of Earth Sciences and Engineering where he works on topics related to: 1. Surface water-groundwater cycle and hydrological droughts under climate change and anthropogenic stresses 2. Hydrologic forecasting (e.g., groundwater level and hydrological droughts) 3. Integrated modeling of the regional surface water-groundwater interactions 4. Deep learning-assisted calibration/assimilation of multisource data (in-situ observations and remote sensing) into hydrological models He uses a broad range of methods to study these questions, including numerical modeling, deep learning, explainable artificial intelligence, land surface models, field observations, and remote sensing. Educational BackgroundPhD (Sept 2014-Dec 2019)-Hydrology and Water Resources, Nanjing Uninversity, China Visiting Scholar (Aug 2017-Jan 2019)-Deep Learning, University of Notre Dame, USA BE (Sept 2010-Jun 2014)-Groundwater Science and Engineering, Nanjing University, China Work Experience
Academic Service
Research IntersetsTeachingResearch Projects4. National Natural Science Foundation of China (￥500,000), 2025-2028, Principal investigator Exploring the evolution of groundwater cycle in the Mu Us Sandy Land under global change through data- and model-driven approaches 3. Key Science and Technology Project of Inner Mongolia of China (￥800,000), 2021-2024, Principal investigator Numerical modeling of mine water discharge in arid regions with multiple coal mines 2. National Natural Science Foundation of China (￥240,000), 2021-2023, Principal investigator Joint identification of groundwater contaminant source and highly heterogeneous aquifer parameter fields with deep convolutional long short-term memory networks 1. China Postdoctoral Science Foundation (￥80,000), 2020-2022, Principal investigator Deep learning-based groundwater contaminant source identification and remediation strategy optimization PublicationsGoogle Scholar: https://scholar.google.com/citations?user=b5m_q4sAAAAJ&hl=en&oi=ao (*Corresponding authorship) 12. Feng, L., Mo, S.*, Sun, A. Y., …, Wu, J., Shi, X. (2024).Deep learning-based geological parameterization for history matching CO2 plume migration in complex aquifers. Advances in Water Resources, 193, 104833. 11. Feng, L., Mo, S.*, Sun, A. Y., Wu, J., Shi, X. (2024). Uncertainty quantification of CO2 plume migration in highly channelized aquifers using probabilistic convolutional neural networks. Advances in Water Resources, 183, 104607. 10. Hu, Z., Tang, S., Mo, S.*, Shi, X.*, Yin, X., Sun, Y., Liu, X., Duan, L., Miao, P., Liu, T., Wu, J. (2023). Water storage changes (2003–2020) in the Ordos Basin, China, explained by GRACE data and interpretable deep learning. Hydrogeology Journal, 1-14. 9. Mo, S., Zhong, Y., Forootan, E., Shi, X., Feng, W., Yin, X., Wu, J. (2022). Hydrological droughts of 2017-2018 explained by the Bayesian reconstruction of GRACE(-FO) fields. Water Resources Research, 58, e2022WR031997. 8. Mo, S., Zhong, Y., Forootan, E., Mehrnegar, N., Yin, X., Wu, J., Feng, W., Shi, X. (2022). Bayesian convolutional neural networks for predicting the terrestrial water storage anomalies during GRACE and GRACE-FO gap. Journal of Hydrology, 604, 127244. 7. Du, J., Shi, X.*, Mo, S.*, Kang, X., Wu, J., 2022. Deep learning based optimization under uncertainty for surfactant-enhanced DNAPL remediation in highly heterogeneous aquifers. Journal of Hydrology, 608, 127639. 6. Kang, X., Kokkinaki, A., Kitanidis, P. K., Shi, X., Lee, J., Mo, S., Wu, J. (2021). Hydrogeophysical characterization of nonstationary DNAPL source zones by integrating a convolutional variational autoencoder and ensemble smoother. Water Resources Research, e2020WR028538. 5. Mo, S., Zabaras, N., Shi, X., Wu, J. (2020). Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities. Water Resources Research, 56(2), e2019WR026082. 4. Mo, S., Zabaras, N., Shi, X., Wu, J. (2019). Deep autoregressive networks for high-dimensional inverse problems in groundwater contaminant source identification. Water Resources Research, 55(5), 3856-3881. (Top downloaded paper of 2018-2019 in Wiley) 3. Mo, S., Shi, X., Lu, D., Ye, M., Wu, J. (2019). An adaptive Kriging surrogate method for efficient uncertainty quantification with an application to geological carbon sequestration modeling. Computers & Geosciences, 125, 69-77. 2. Mo, S., Zhu, Y., Zabaras, N., Shi, X., Wu, J. (2019). Deep convolutional encoder-ecoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media. Water Resources Research, 55(1), 703-728. (ESI highly cited paper) 1. Mo, S., Lu, D., Shi, X., Zhang, G., Ye, M., Wu, J. F., Wu, J. C. (2017). A Taylor expansion-based adaptive design strategy for global surrogate modeling with applications in groundwater modeling. Water Resources Research, 53(12), 10802-10823. Honors and AwardsGroupLi Feng, PhD student, 2019- Research interests: Deep learning-based efficient inverse modeling of multi-phase flow in highly complex aquifers Zimin Hu, Master student, 2022- Research interests: Remote sensing and integrated hydrological modeling of regional groundwater storage changes Zeceng Peng, Master student, 2022 Research interests: Explainable deep learning-based probabilistic hydrologic forecaseting (groundwater level and hydrological drought) Chijitai Cheng, Master student, 2024- Research interests: Data- and model-driven investigation of regional water cycle |