AI D-Day weather forecast falters under pressure
Today's best weather computers would still have struggled to accurately predict the weather for the D-Day landings, University of Reading research shows. The new research, published in the journal Weather ahead of the release of the D-Day film "Pressure," used AI models to produce 50 different forecasts of the storm that famously pushed back the Allies' invasion of Normandy in June 1944.
A new study published in Weather highlights the limitations of AI weather forecasting when it comes to predicting the weather for the 1944 D-Day landings. The researchers used AI models to generate 50 different forecasts of the storm that pushed back the Allied invasion of Normandy. The AI correctly predicted poor conditions over Normandy for the day originally planned, June 5, matching the analysis of Group Captain James Stagg.
However, the AI incorrectly predicted that the storm would move quickly toward Norway on June 6, bringing calmer weather, contrary to the actual, more treacherous conditions faced by the soldiers. Professor Andrew Charlton-Perez, lead author of the study, explained that Stagg had a crucial job, as a wrong forecast could have led to the invasion's failure.
The AI forecast did support a one-day delay for the invasion on June 5, citing dangerous winds. The AI also overstated the calm and clear weather on June 6, despite a 30% probability of unsafe winds. Historical Faroe Islands weather logs suggest the storm may have been stronger than reconstructed. The study emphasizes that while AI can process vast amounts of data quickly, trained meteorologists are still essential for interpreting the forecasts and making informed decisions.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
