提出新评估指标，提升降水预报的可靠性。
Probability calibration for precipitation nowcasting
- 设计新指标ETCE，更好捕捉降水分级预测偏差
- 结合时间条件的筛选缩放，显著降低误差
- 适合需要高可靠概率预报的气象决策者
可靠的短时降水预报对天气敏感决策至关重要，但神经天气模型（NWMs）常产生校准不佳的概率预测。标准校准度量如期望校准误差（ECE）无法捕捉降水阈值处的偏差。本文提出期望阈值校准误差（ETCE），一种更适用于有序类别（如降水强度）的新型度量。将计算机视觉中的后处理技术拓展至预报领域。实验表明，基于预报时效的筛选缩放方法可在不降低预报质量的前提下，有效减少模型偏差。
原文摘要 · Abstract (English)
Reliable precipitation nowcasting is critical for weather-sensitive decision-making, yet neural weather models (NWMs) can produce poorly calibrated probabilistic forecasts. Standard calibration metrics such as the expected calibration error (ECE) fail to capture miscalibration across precipitation thresholds. We introduce the expected thresholded calibration error (ETCE), a new metric that better captures miscalibration in ordered classes like precipitation amounts. We extend post-processing techniques from computer vision to the forecasting domain. Our results show that selective scaling with lead time conditioning reduces model miscalibration without reducing the forecast quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。