GDMI alone beat NHC's track forecast for Chantal at 12 hours

NHC found that only Google DeepMind's ensemble mean beat its official track forecast for Tropical Storm Chantal at 12 hours. Chantal caused 6 direct deaths in North Carolina.

  • 2 an organization

    GDMI's track errors at 12 to 48 hours were lower than NHC's official errors in a homogeneous comparison, though over only two to six forecasts.

  • Not rated society

    NHC does not report that the AI guidance changed warnings or outcomes in the Carolinas.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Only the deployer supports the benefit.

Compared with

NHC official track forecasts (OFCL) for Chantal in the homogeneous comparison. Measured.

Without the system
OFCL errors of 19.5, 41.6, 60.5 and 88.7 n mi at 12, 24, 36 and 48 h
With it
GDMI errors of 15.6, 33.4, 47.4 and 64.2 n mi
The system’s part
NHC verified GDMI's own track forecasts against the best track alongside the official forecast and other models, which isolates the model's skill. NHC gives no account of how forecasters used GDMI for Chantal. NHC is not fully outside the case, since it uses the model and worked with Google DeepMind to develop it.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
Google DeepMind tropical cyclone model, ensemble mean (NHC designation GDMI)
Made by
Google DeepMind
Used by
NOAA National Hurricane Center (experimental guidance), with output supplied by Google DeepMind
Where
South Carolina and North Carolina, United States
Stage
In a pilot
Date
Kind
Aggregate result
Broad benefit
Estimating the Quantifiable Characteristics of Products, Events, or Information
Collections
Cross-border records
Last revised
31 October 2026

Sources

  1. Report, by the organization that used it.

    Papin, P. P. Tropical Storm Chantal (AL032025), 4–7 July 2025. National Hurricane Center Tropical Cyclone Report, 29 June 2026 (original report dated 3 February 2026), p. 7 and Table 5b.

    The only guidance aid that outperformed OFCL in 12 h was the Google DeepMind ensemble mean (GDMI), which was also a superior performer throughout the forecast period.

  2. Press release, by the organization that used it. Context or contrary evidence.

    National Weather Service. AI in Hurricane Forecasting at the National Hurricane Center: A Q&A with NHC's Science Operations Officer. NOAA/NWS, undated.

    NHC has partnered directly with Google DeepMind to develop a new AI hurricane forecast model that was used experimentally during the 2025 season.

Details

AI system

Workflow

NHC included GDMI among the guidance models in its homogeneous comparison for Chantal. NHC measured each model's track errors against Chantal's best track.

Follow-up

Conditions for replication

The sample is small, with six forecasts at 12 hours and two at 48 hours. The official forecast remains NHC's own judgment, and other aids also beat it at some lead times.

Entry details

Sector

Weather forecasting / tropical cyclones.

Purpose

Google DeepMind built the experimental tropical cyclone model to give forecasters ensemble guidance on the track and intensity of storms.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). GDMI alone beat NHC's track forecast for Chantal at 12 hours (AIBD-0750). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0750.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions