Analysis of the Google WeatherNext Tropical Cyclone Intensity Forecasts

We evaluate the Google WeatherNext Cyclone (WN‐C) ensemble and ensemble mean TC intensity performance for all storms between June 2022 and May 2026 and compare Google's model against select operational models, such as the Hurricane Analysis and Forecast System (HAFS), Statistical Hurricane Intensity Prediction Scheme Rapid Intensification Index (SHIPS‐RII), and Rapid Intensification Prediction Aid (RIPA). Results indicate WN‐C has comparable, if not better, performance metrics. WN‐C's ensemble mean has a lower mean absolute error than the HAFS model at all forecast hours. The model is comparable to the SHIPS‐RII and better than RIPA in terms of reliability of probabilistic rapid intensification (RI) forecasts over the first 24‐hr forecast period. However, the WN‐C ensemble is generally underdispersive and shows a negative bias in intensity change forecasts, including an underprediction of RI, that increases in magnitude with forecast lead time.

Authors

Institutions

Publication Details

Journal
Geophysical Research Letters
Published
2026-11-18
DOI
https://doi.org/10.1029/2026gl123211
Primary Topic
Tropical and Extratropical Cyclones Research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Analysis of the Google WeatherNext Tropical Cyclone Intensity Forecasts

Brian H. Tang, Jacob Vile, Nour Elgalad
1 links
Geophysical Research Letters
Tropical and Extratropical Cyclones Research
article

Analysis of the Google WeatherNext Tropical Cyclone Intensity Forecasts

Brian H. Tang, Jacob Vile, Nour Elgalad
article en

Abstract

We evaluate the Google WeatherNext Cyclone (WN‐C) ensemble and ensemble mean TC intensity performance for all storms between June 2022 and May 2026 and compare Google's model against select operational models, such as the Hurricane Analysis and Forecast System (HAFS), Statistical Hurricane Intensity Prediction Scheme Rapid Intensification Index (SHIPS‐RII), and Rapid Intensification Prediction Aid (RIPA). Results indicate WN‐C has comparable, if not better, performance metrics. WN‐C's ensemble mean has a lower mean absolute error than the HAFS model at all forecast hours. The model is comparable to the SHIPS‐RII and better than RIPA in terms of reliability of probabilistic rapid intensification (RI) forecasts over the first 24‐hr forecast period. However, the WN‐C ensemble is generally underdispersive and shows a negative bias in intensity change forecasts, including an underprediction of RI, that increases in magnitude with forecast lead time.

Geophysical Research LettersVol. 53(22)
State University of New York (US), University at Albany, State University of New York (US)
University at Albany
Climate action
Tropical and Extratropical Cyclones Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon