In this study, we propose a volume‐to‐point framework for quantitative precipitation estimation (QPE) based on the Quantitative Precipitation Estimation and Segregation Using Multiple Sensor (QPESUMS) Mosaic Radar data set. With a data volume consisting of the time series of gridded radar reflectivities over the Taiwan area, we used machine learning algorithms to establish a statistical model for QPE in weather stations. The model extracts spatial and temporal features from the input data volume and then associates these features with the location‐specific precipitations. In contrast to QPE methods based on the Z–R relation, we leverage the machine learning algorithms to automatically detect the evolution and movement of weather systems and associate these patterns to a location with specific topographic attributes. Specifically, we evaluated this framework with the hourly precipitation data of 45 weather stations in Taipei during 2013–2016. In comparison to the operational QPE scheme used by the Central Weather Bureau, the volume‐to‐point framework performed comparably well in general cases and excelled in detecting heavy‐rainfall events. By using the current results as the reference benchmark, the proposed method can integrate the heterogeneous data sources and potentially improve the forecast in extreme precipitation scenarios.

In this study, a novel machine learning approach was used to classify three types of synoptic weather events in Taiwan area from 2001 to 2010. We used reanalysis data with three machine learning algorithms to recognize weather systems and evaluated their performance. Overall, the classifiers successfully identified 52–83% of weather events (hit rate), which is higher than the performance of traditional objective methods.The results showed that the machine learning approach gave low false alarm rate in general, while the support vector machine (SVM) with more principal components of reanalysis data had higher hit rate on all tested weather events. The sensitivity tests of grid data resolution indicated that the differences between the high‐ and low‐resolution datasets are limited, which implied that the proposed method can achieve reasonable performance in weather forecasting with minimal resources.By identifying daily weather systems in historical reanalysis data, this method can be used to study long‐term weather changes, to monitor climatological‐scale variations, and to provide better estimate of climate projections. Furthermore, this method can also serve as an alternative of model output statistics and potentially be used for synoptic weather forecasting.

The Model for Prediction Across Scales (MPAS) is used to simulate the East Asian winter monsoon (EAWM) over the 2011–2020 winter. The 45 day hindcasts are made with 30 km horizontal resolution and constructed to a time-lagged ensemble system. The climatology, the major modes of EAWM variability, and the blocking activities are examined. The evaluation results reveal that MPAS can simulate the climatologic characteristics of EAWM reasonably, with a surface cold bias of 4% and a positive rainfall bias of 9% over East Asia. MPAS can perform skillfully in the forecasts of surface temperature probability of East Asia and is more reliable in detecting below normal and above normal events. The features that influence the EAWM variability are also analyzed. MPAS simulates reasonably in the occurrence frequency of blocking high in both locations and duration time. The empirical orthogonal function analysis also shows that MPAS can capture the two major modes of the surface temperature of EAWM. On the other hand, it is also found that a biased sea surface temperature may modify the circulations over the Western Pacific and affect the simulated occurrence frequency of cold events near Taiwan during winter.

This study analyzed the temporal/spatial distribution of the high‐temperature extremes (HTEs) in Taiwan. Three major weather types for HTEs were identified: the southerly/southwesterly (S/SW) (47.6%), western North Pacific subtropical high (SH) (35.9%), and tropical cyclone (16.5%). The S/SW type features anomalous warm advection in lower atmosphere and anomalous subsidence in all the altitudes around Taiwan. Different from the S/SW type, the SH type warms the surface primarily with increasing downward shortwave radiation. In June, the S/SW type was the most common. In July, both the S/SW and SH types dominated. In August, the tropical cyclone and SH types were more common. The subseasonal variation of extreme hot days (EHDs) for these three weather types is examined. Taipei and Dawu were two HTE hot spots in Taiwan. EHDs in Taipei occurred mostly in July and August, with the SH being the major type. Most EHDs in Dawu occurred in June, with the S/SW being the predominant type. These differences likely resulted from not only the subseasonal monsoon variation but also geographical differences. The interannual variability of the summer EHDs in Taiwan was found to be related to the phase and intensity of the El Niño‐southern oscillation events. The number of EHDs increased in the El Niño decaying summers and decreased in the La Niña decaying summers. The correlation between the number of summer EHDs and the Niño 3.4 SST anomaly reaches its peak in the previous winter (November/December). The associated mechanisms were discussed in the article.

This study aims to propose a strategy to optimize the performance of the Support Vector Machine (SVM) scheme for extreme Meiyu rainfall prediction over southern Taiwan. Variables derived from Climate Forecast System Reanalysis (CFSR) dataset are the candidates for predictor selection. A series of experiments with different combinations of predictors and domains are designed to obtain the optimal strategy for constructing the SVM scheme. The results reveal that the accuracy (ACC), positive predictive values (PPV), probability of detection (POD), and F1-score can exceed 0.6 on average. Choosing the predictors associated with the Meiyu system and determine the domain associated with the correlations between selected predictors and predictand can improve the forecast performance. Our strategy shows the potential to predict extreme Meiyu rainfall in southern Taiwan with lead times from 16 h to 64 h. The F1-score analysis further demonstrates that the forecast performance of our scheme is stable, with slight inter-annual fluctuations from 1990 to 2019. Higher performance would be expected when the north of the South China Sea is characterized by stronger southwesterly flow and abundant low-level moisture for a given year.