GPT-4o rainfall forecasts are conservative and close to historical averages; adding expert model inputs does not improve accuracy and often dampens predicted peaks.
DATA AND METHOD In this study, we focused on rainfall prediction at two different time scales: short-term (15-day scale) and long-term (12-month scale)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Large Language Models for Climate Forecasting
GPT-4o rainfall forecasts are conservative and close to historical averages; adding expert model inputs does not improve accuracy and often dampens predicted peaks.