Unverified50% confidenceBenchmarkExact time
Models including lagged rainfall features achieved a Brier skill score of 0.074 (95% CI 0.064-0.088) relative to climatology for next-day prediction.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA simple station-month climatology baseline achieved 88.4% accuracy and an AUC of 0.950 in classifying high-rainfall months.69% similarUnverifiedWhen station and year inputs were removed, the model's Brier skill score relative to climatology rose to 0.091; when same-day observations from other stations were added, it rose to 0.131.68% similarUnverifiedGenCast的精度超越欧洲中期天气预报中心（ECMWF）的传统数值模型61% similarUnverifiedThe model is well calibrated: mean predicted risk 0.469, actual observed rate 0.471, calibration slope 1.05, and every decile within 5 percentage points of the observed rate.60% similarUnverifiedAs the model scales from 8B to 70B, the predictive power of fixed output vector similarity for behavior actually worsens, with a paired mean correlation change of -0.080 (95% confidence interval [-0.127, -0.035]).60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114807API
curl https://kongchang.com/api/v1/knowledge/claims/1114807MCP
get_claim(id=1114807)