HurriCast: Synthetic Tropical Cyclone Track Generation for Hurricane Forecasting

TL;DR

This work tackles the need for synthetic tropical cyclone tracks to support risk assessment under climate variability. It introduces HurriCast, a hybrid pipeline that combines ARIMA-based frequency forecasting, K-Means spatial clustering, and an Autoencoder with latent Gaussian perturbations to generate multi-year TC climatologies conditioned on historical data from $HURDAT2$. Validation against historical records (1851–2021) shows HurriCast reproduces basin-wide and Florida-area frequencies and track geometries with high fidelity, though it tends to produce some land-crossing tracks for lower-intensity storms, indicating a need for improved land-interaction modeling. The approach offers a scalable tool for insurers and policymakers to augment sparse data and evaluate risk, with future enhancements including GANs/LSTMs for real-time prediction and more physically realistic track life cycles.

Abstract

The generation of synthetic tropical cyclone(TC) tracks for risk assessment is a critical application of preparedness for the impacts of climate change and disaster relief, particularly in North America. Insurance companies use these synthetic tracks to estimate the potential risks and financial impacts of future TCs. For governments and policymakers, understanding the potential impacts of TCs helps in developing effective emergency response strategies, updating building codes, and prioritizing investments in resilience and mitigation projects. In this study, many hypothetical but plausible TC scenarios are created based on historical TC data HURDAT2 (HURricane DATA 2nd generation). A hybrid methodology, combining the ARIMA and K-MEANS methods with Autoencoder, is employed to capture better historical TC behaviors and project future trajectories and intensities. It demonstrates an efficient and reliable in the field of climate modeling and risk assessment. By effectively capturing past hurricane patterns and providing detailed future projections, this approach not only validates the reliability of this method but also offers crucial insights for a range of applications, from disaster preparedness and emergency management to insurance risk analysis and policy formulation.

Figures (5)

• Figure 1: Flowchart of the hurricane track simulator
• Figure 2: Hurricane frequency across different years
• Figure 3: Joint probability of hurricane frequency by longitude and latitude (grid size: 5$^\circ$)
• Figure 4: Comparison of the synthetic tracks (i.e., HurriCast) and historical tracks (i.e., the ground-truth) form frequency.
• Figure 5: Comparison of different categories (CAT) for generated and historical hurricane tropical cyclone.