top of page


References and Links to Papers


Use of machine learning & deep learning in hazard modeling

Lockwood, J. W., T. Loridan, N. Lin, M. Oppenheimer, and N. Hannah, 2024: A Machine Learning Approach to Model Over-Ocean Tropical Cyclone Precipitation. J. Hydrometeor.,  25, 207–221,


Lockwood, J. W.,  Lin, N.,  Oppenheimer, M., &  Lai, C.-Y. (2022).  Using Neural Networks to Predict Hurricane Storm Surge and to Assess the Sensitivity of Surge to Storm Characteristics. Journal of Geophysical Research: Atmospheres,  127, e2022JD037617.


Machine learning and Generative AI

Lockwood, J. W. (working). ”A comparison of Neural Operator, Diffusion, and Generative Adversarial Network Models for Precipitation Super-resolution over the Continental US”

Lockwood, J. W.  (2024). A Physics-Informed Conditional Super-resolution Tropical Cyclone Wind Field Model  

Lockwood, J. W.,  Lin, N.,  Gori, A., &  Oppenheimer, M. (2024).  Increasing flood hazard posed by tropical cyclone rapid intensification in a changing climate. Geophysical Research Letters,  51, e2023GL105624.


Climate Adaptation and Economics

Lockwood, J., Lin, N., Oppenheimer, M. (2024.), Addressing Socio-Economic Inequalities in Adaptation Measures: A
Cost-Benefit Approach in New York City,


Energy modeling 

Lockwood et al., (working) ”Bayesian Network Modelling of Energy Demand and Extreme Weather”


Decarbonization and Energy

Kousky, C. & Lockwood, J., (2024) ”Leveraging Insurance for Decarbonization,” Journal of Catastrophe Risk and Resilience,


Impact of correlations on future hazard

Lockwood, J. W., Oppenheimer, M., Lin, N., Kopp E. R., Vecchi, G. & Gori, A. (2022). Correlation between future sea-level rise and tropical cyclone activity in CMIP6 models, Earth's Future.

bottom of page