Hypothesis testing for performance evaluation of probabilistic seasonal rainfall forecasts
Journal
Geoscience Letters
Journal Volume
11
Journal Issue
1
Date Issued
2024-05
Author(s)
Ke-Sheng Cheng
Gwo‑Hsing Yu
Yuan-Li Tai
Kuo-Chan Huang
Sheng‑Fu Tsai
Dong-Hong Wu
Yun-Ching Lin
Ching-Teng Lee
Tzu-Ting Lo
Abstract
A hypothesis testing approach, based on the theorem of probability integral transformation and the Kolmogorov–Smirnov one-sample test, for performance evaluation of probabilistic seasonal rainfall forecasts is proposed in this study. By considering the probability distribution of monthly rainfalls, the approach transforms the tercile forecast probabilities into a forecast distribution and tests whether the observed data truly come from the forecast distribution. The proposed approach provides not only a quantitative measure for performance evaluation but also a cumulative probability plot for insightful interpretations of forecast characteristics such as overconfident, underconfident, mean-overestimated, and mean-underestimated. The approach has been applied for the performance evaluation of probabilistic season rainfall forecasts in northern Taiwan, and it was found that the forecast performance is seasonal dependent. Probabilistic seasonal rainfall forecasts of the Meiyu season are likely to be overconfident and mean-underestimated, while forecasts of the winter-to-spring season are overconfident. A relatively good forecast performance is observed for the summer season.
Subjects
Probabilistic forecast
Seasonal rainfall
Performance evaluation
Hypothesis test
SDGs
Publisher
Springer
Description
Irrigation Agency, Ministry of Agriculture, Taiwan, R.O.C.
Type
journal article