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.

This study conducted a cluster analysis on the fine particulate matter (PM_2.5) data over Taiwan from 2006 to 2015 and diagnosed their association with the synoptic weather patterns. Five clusters are identified via a hierarchical clustering algorithm; three of them correspond to severe events, each with a distinct pattern of temporal evolution within the 240-h window. The occurrence of the different clusters exhibits strong seasonal variation. Two of the polluted clusters are more frequently associated with weak synoptic weather, while the other one is related to northeasterly winds and fronts. Detailed case studies show that the weather patterns’ temporal evolutions clearly modulate the transition among various pollution clusters by influencing the changes in local circulation and atmospheric stability. In winter, the clusters characterizing severe PM_2.5 pollution events occur when Taiwan is influenced by persistent weak synoptic condition, while in autumn, the long-range transport by strong northerly winds leads to the occurrence of severe PM_2.5 pollution. The current results shed light on the potential of combining the data-driven approach and the numerical weather forecasting model to provide extended range forecasts of local air pollution forecasts.

We constructed the A-Train co-located aerosol and marine warm cloud data from 2006 to 2010 winter and spring over East Asia and investigated the sensitivities of single-layer warm cloud properties to aerosols under different precipitation statuses and environmental regimes. The near-surface stability (NSS), modulated by cold air on top of a warm surface, and the estimated inversion strength (EIS) controlled by the subsidence are critical environmental parameters affecting the marine warm cloud structure over East Asia and, thus, the aerosols–cloud interactions. Based on our analysis, precipitating clouds revealed higher cloud susceptibility to aerosols as compared to non-precipitating clouds. The cloud liquid water path (LWP) increased with aerosols for precipitating clouds, yet decreased with aerosols for non-precipitating clouds, consistent with previous studies. For precipitating clouds, the cloud LWP and albedo increased more under higher NSS as unstable air promotes more moisture flux from the ocean. Under stronger EIS, the cloud albedo response to aerosols was lower than that under weaker EIS, indicating that stronger subsidence weakens the cloud susceptibility due to more entrainment drying. Our study suggests that the critical environmental factors governing the aerosol–cloud interactions may vary for different oceanic regions, depending on the thermodynamic conditions.

In this study, we proposed a volume-to-point framework for quantitative precipitation estimation (QPE) based on the QPESUMS (Quantitative Precipitation Estimation and Segregation Using Multiple Sensor) Mosaic Radar dataset. 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 (CWB), 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 QPF in extreme precipitation scenarios.

This study applied representation learning algorithms to satellite images and evaluated the learned latent spaces with classifications of various weather events. The algorithms investigated include the classical linear transformation, i.e., principal component analysis (PCA), state-of-the-art deep learning method, i.e., convolutional autoencoder (CAE), and a residual network pre-trained with large image datasets (PT). The experiment results indicated that the latent space learned by CAE consistently showed higher threat scores for all classification tasks. The classifications with PCA yielded high hit rates but also high false-alarm rates. In addition, the PT performed exceptionally well at recognizing tropical cyclones but was inferior in other tasks. Further experiments suggested that representations learned from higher-resolution datasets are superior in all classification tasks for deep-learning algorithms, i.e., CAE and PT. We also found that smaller latent space sizes had little impact on the classification task’s hit rate. Still, a latent space dimension smaller than 128 caused a significantly higher false-alarm rate. Though the CAE can learn latent spaces effectively and efficiently, the interpretation of the learned representation lacks direct connections to physical attributions. Therefore, developing a physics-informed version of CAE can be a promising outlook for the current work.

In this study, we proposed a volume-to-point framework for quantitative precipitation estimation (QPE) based on the QPESUMS (Quantitative Precipitation Estimation and Segregation Using Multiple Sen...