Datasets and Models
TC-GEN: Data-driven tropical cyclone downscaling using machine learning-based high-resolution weather model
Jing, Renzhi; Gao, Jianxiong; Cai, Yunuo; Xi, Dazhi; Zhang, Yinda; Fu, Yanwei; Emanuel, Kerry; Diffenbaugh, Noah; Bendavid, Eran
Synthetic downscaling of tropical cyclones (TCs) is critically important to estimate the long-term hazard of rare high-impact storm events. Existing downscaling approaches rely on statistical or statistical-deterministic models that are capable of generating large samples of synthetic storms with characteristics similar to observed storms. However, these models do not capture the complex two-way interactions between a storm and its environment. In addition, these approaches either necessitate a separate TC size model to simulate storm size or involve post-processing to capture the asymmetries in the simulated surface wind. In this study, we present an innovative data-driven approach for TC synthetic downscaling. Using a machine learning-based high-resolution global weather model (ML-GWM), our approach can simulate the full life cycle of a storm with asymmetric surface wind that accounts for the two-way interactions between the storm and its environment. This approach consists of multiple components: a data-driven model for generating synthetic TC seeds, a blending method that seamlessly integrates storm seeds into the surrounding while maintaining the seed structure, and a model based on a recurrent neural network to correct for biases in storm intensity. Compared to observations and synthetic storms simulated using existing statistical-deterministic and statistical downscaling approaches, our method shows the ability to effectively capture many aspects of TC statistics, including track density, landfall frequency, landfall intensity, and outermost wind extent. Leveraging the computational efficiency of ML-GWM, our approach shows substantial potential for TC regional hazard and risk assessment.
September, 2024
Trying-Early Adaptive Multilevel Splitting Algorithm
Justin Finkel, Paul A. O’Gorman
Rare-event algorithms can be used to sample extreme events at a much-reduced cost compared to standard direct simulations by using ensembles of simulations that are selectively cloned or killed. Initial investigation showed that a promising rare-event algorithm known as adaptive multilevel splitting (AMS) did not perform well on daily precipitation extremes because the timescale of the extreme event was comparable to the timescale over which perturbed simulations diverge. Authors then introduced a modified algorithm, Trying-Early AMS (TEAMS), that split trajectories well in advance of the extreme event's onset. In this reporting period, we continued research on TEAMS and demonstrated improved sampling of extreme local events in the Lorenz 96 model by a factor of order 10 relative to direct sampling.
February, 2024
JPoNG
Rahman Khorramfar,Dharik Mallapragada, Saurabh Amin
JPoNG is an optimization model for joint planning of power and NG infrastructure with a resolved representation of spatial, temporal, and technological system operation. The model is implemented as open-source software in Python with Gurobi solver. The associated code and data is available in the following link
December, 2022
Statistical-Physical Adversarial Learning from Data and Models for Extreme Rainfall Downscaling
Anamitra Saha, Sai Ravela
Modeling the risk of extreme weather events in a changing climate is essential for developing effective adaptation and mitigation strategies. Although the available low-resolution climate models capture different scenarios, accurate risk assessment for mitigation and adaption often demands detail that they typically cannot resolve. Here, we develop a dynamic data-driven downscaling (super-resolution) method that incorporates physics and statistics in a generative framework to learn the fine-scale spatial details of rainfall. Our method transforms coarse-resolution (0.25∘×0.25∘) climate model outputs into high-resolution (0.01∘×0.01∘) rainfall fields while efficaciously quantifying uncertainty. Results indicate that the downscaled rainfall fields closely match observed spatial fields and their risk distributions.
Code
June, 2024