Investigation of Machine Learning using Satellite-Based Advanced Dvorak Technique Analysis Parameters to Estimate Tropical Cyclone Intensity

Abstract

AbstractSeveral simple and computationally inexpensive machine learning models are explored that can use Advanced Dvorak Technique (ADT) retrieved features of tropical cyclones (TCs) from satellite imagery to provide improved maximum sustained surface wind speed (MSW) estimates. ADT (Version 9.0) TC analysis parameters and operational TC forecast center Best Track data sets from 2005-2016 are used to train and validate the various models over all TC basins globally and select the best among them. Two independent test sets of TC cases from 2017 and 2018 are used to evaluate the intensity estimates produced by the final selected model called the “artificial intelligence (AI)” enhanced Advanced Dvorak Technique (AiDT). The 2017 and 2018 MSW results demonstrate a global RMSE of 7.7 and 8.2 kt, respectively. Basin-specific MSW RMSEs of 8.4, 6.8, 7.3, 8.0, and 7.5 kt were obtained with the 2017 data set in the North Atlantic, East/Central Pacific, Northwest Pacific, South Pacific/Indian, and North Indian ocean basins, respectively, with MSW RMSE values of 8.9, 6.7, 7.1, 10.4, and 7.7 obtained with the 2018 data set. These represent a 30% and 23% improvement over the corresponding ADT RMSE for the 2017 and 2018 data sets, respectively, with the AiDT error reduction significant to 99% in both sets. The AiDT model represents a notable improvement over the ADT performance and also compares favorably to more computationally expensive and complex machine learning models that interrogate satellite images directly while still preserving the operational familiarity of the ADT.