A decision‐tree approach to seasonal prediction of extreme precipitation in eastern China

• Published in: International journal of climatology 2020-01, Vol.40 (1), p.255-272
• Main Authors: Wei, Wenguang, Yan, Zhongwei, Jones, Phil D.
• Format: Article
• Language: English
• Subjects: Atmospheric precipitations; Climate; Climate models; Climate system; Climatic indexes; Decision making; decision tree; East Asian monsoon; eastern China; El Nino; El Nino phenomena; El Nino-Southern Oscillation event; extreme precipitation; Extreme weather; La Nina; Monsoon rainfall; Precipitation; Predictions; Rainy season; Regression analysis; Regression models; seasonal prediction; Seasons; Southern Oscillation; Summer; Summer monsoon; Wet season; Winter
• ISSN: 0899-8418; 1097-0088
• DOI: 10.1002/joc.6207

Seasonal prediction of extreme precipitation has long been a challenge especially for the East Asian Summer Monsoon region, where extreme rains are often disastrous for the human society and economy. This paper introduces a decision‐tree (DT) method for predicting extreme precipitation in the rainy season over South China in April–June (SC‐AMJ) and the North China Plain in July–August (NCP‐JA). A number of preceding climate indices are adopted as predictors. In both cases, the DT models involving ENSO and NAO indices exhibit the best performance with significant skills among those with other combinations of predictors and are superior to their linear counterpart, the binary logistic regression model. The physical mechanisms for the DT results are demonstrated by composite analyses of the same DT path samples. For SC‐AMJ, an extreme season can be determined mainly via two paths: the first follows a persistent negative NAO phase in February–March; the second goes with decaying El Niño. For NCP‐JA, an extreme season can also be traced via two paths: the first is featured by “non El Niño” and an extremely negative NAO phase in the preceding winter; the second follows a shift from El Niño in the preceding winter to La Niña in the early summer. Most of the mechanisms underlying the decision rules have been documented in previous studies, while some need further studies. The present results suggest that the decision‐tree approach takes advantage of discovering and incorporating various nonlinear relationships in the climate system, hence is of great potential for improving the prediction of seasonal extreme precipitation for given regions with increasing sample observations. Prediction of seasonal extreme precipitation event has long been a great challenge especially for the East Asian Summer Monsoon region. The decision‐tree method is a data mining algorithm which can discover nonlinear relationships between different climate components and use them to improve the prediction skill. An application of this method to the prediction of extreme precipitation event in the rainy season over (a) South China in April–June and (b) North China Plain in July–August demonstrates superior performance to the linear models.