Development and Evaluation of an Evolutionary Programming-Based Tropical Cyclone Intensity Model

Abstract

A statistical–dynamical tropical cyclone (TC) intensity model is developed from a large ensemble of algorithms through evolutionary programming (EP). EP mimics the evolutionary principles of genetic information, reproduction, and mutation to develop a population of algorithms with skillful predictor combinations. From this evolutionary process the 100 most skillful algorithms as determined by root-mean square error on validation data are kept and bias corrected. Bayesian model combination is used to assign weights to a subset of 10 skillful yet diverse algorithms from this list. The resulting algorithm combination produces a forecast superior in skill to that from any individual algorithm. Using these methods, two models are developed to give deterministic and probabilistic forecasts for TC intensity every 12 h out to 120 h: one each for the North Atlantic and eastern and central North Pacific basins. Deterministic performance, as defined by MAE, exceeds that of a “no skill” forecast in the North Atlantic to 96 h and is competitive with the operational Statistical Hurricane Intensity Prediction Scheme and Logistic Growth Equation Model at these times. In the eastern and central North Pacific, deterministic skill is comparable to the blended 5-day climatology and persistence (CLP5) track and decay-SHIFOR (DSHF) intensity forecast (OCD5) only to 24 h, after which time it is generally less skillful than OCD5 and all operational guidance. Probabilistic rapid intensification forecasts at the 25–30 kt (24 h)−1 thresholds, particularly in the Atlantic, are skillful relative to climatology and competitive with operational guidance when subjectively calibrated; however, probabilistic rapid weakening forecasts are not skillful relative to climatology at any threshold in either basin. Case studies are analyzed to give more insight into model behavior and performance.

Quantifying tropical cyclone intensity change induced by sea surface temperature

“…Tropical cyclones (TCs) produce disasters that have great impacts on human society; therefore, accurate predictions of TC intensity and track are of great importance. Despite substantial improvement in TC track prediction during the last few decades, intensity forecast skill has increased much less rapidly (DeMaria et al ., 2007; Cangialosi , 2019; Goni et al ., 2017; Schaffer et al ., 2020). To improve intensity forecasts, many scientists have sought to better understand the oceanic impacts on TC intensity (Schade and Emanuel, 1999; Shay, 2010; Halliwell Jr et al ., 2015; Mei et al ., 2015; Sun et al ., 2016; Lavender et al ., 2018; Li and Toumi, 2018; Wu et al ., 2018).…”

An Opposition-Based Learning Black Hole Algorithm for Localization of Mobile Sensor Network

“…Evolutionary algorithms are a class of optimization algorithms based on the principles of biological evolution in nature, which are used to find optimal or near-optimal solutions in the search space. Evolutionary algorithms mainly include evolutionary programming (EP) [19], the genetic algorithm (GA) [20,21], genetic programming (GP) [22], etc. Swarm intelligence algorithms are a class of optimization algorithms based on the behavior of groups in nature, which achieve global search or optimization problem solving by simulating the collaboration and cooperation among individuals in a group.…”

Soil moisture–precipitation feedbacks in pre‐ and post‐monsoon landfalling tropical cyclones in Bay of Bengal

“…The modern numerical weather prediction models, improvements in dynamical models, physical parameterization, data assimilation techniques, and high temporal satellite observation data have significantly improved the accuracy of cyclone prediction in recent years (Elsberry et al, 2013;Singh et al, 2019;DeMaria et al, 2021;Cha et al, 2022). However, accurately predicting rainfall intensity remains challenging (DeMaria et al, 2014;Cheung et al, 2018;Osuri et al, 2020;Rajeswari et al, 2020;Schaffer et al, 2020;Nellipudi et al, 2021). The TCs of the North Indian Ocean have a shorter lifespan and a variable nature in movement compared to those of other oceans, making forecasting challenging (Raghavan and Sen Sarma, 2000).…”