Precipitation type is a key parameter used for better retrieval of precipitation characteristics as well as to understand the cloud–convection–precipitation coupling processes. Ice crystals and water droplets inherently exhibit different characteristics in different precipitation regimes (e.g., convection, stratiform), which reflect on satellite remote sensing measurements that help us distinguish them. The Global Precipitation Measurement (GPM) Core Observatory’s microwave imager (GMI) and dual-frequency precipitation radar (DPR) together provide ample information on global precipitation characteristics. As an active sensor, the DPR provides an accurate precipitation type assignment, while passive sensors such as the GMI are traditionally only used for empirical understanding of precipitation regimes. Using collocated precipitation type flags from the DPR as the “truth”, this paper employs machine learning (ML) models to train and test the predictability and accuracy of using passive GMI-only observations together with ancillary information from a reanalysis and GMI surface emissivity retrieval products. Out of six ML models, four simple ones (support vector machine, neural network, random forest, and gradient boosting) and the 1-D convolutional neural network (CNN) model are identified to produce 90–94% prediction accuracy globally for five types of precipitation (convective, stratiform, mixture, no precipitation, and other precipitation), which is much more robust than previous similar effort. One novelty of this work is to introduce data augmentation (subsampling and bootstrapping) to handle extremely unbalanced samples in each category. A careful evaluation of the impact matrices demonstrates that the polarization difference (PD), brightness temperature (Tc) and surface emissivity at high-frequency channels dominate the decision process, which is consistent with the physical understanding of polarized microwave radiative transfer over different surface types, as well as in snow and liquid clouds with different microphysical properties. Furthermore, the view-angle dependency artifact that the DPR’s precipitation flag bears with does not propagate into the conical-viewing GMI retrievals. This work provides a new and promising way for future physics-based ML retrieval algorithm development.
This paper introduces novel methodologies for the Natural Language Inference for Clinical Trials (NLI4CT) task. We present TLDR (T5-generated clinical-Language summaries for DeBERTa Report Analysis) which incorporates T5-model generated premise summaries for improved entailment and contradiction analysis in clinical NLI tasks. This approach overcomes the challenges posed by small context windows and lengthy premises, leading to a substantial improvement in Macro F1 scores: a 0.184 increase over truncated premises. Our comprehensive experimental evaluation, including detailed error analysis and ablations, confirms the superiority of TLDR in achieving consistency and faithfulness in predictions against semantically altered inputs.
Precipitation flag (precipitating or not; stratiform or convective) is a key parameter for us to make betterretrieval of precipitation characteristics as well as to understand the cloud-precipitation physicalprocesses. The Global Precipitation Measurement (GPM) Core Observatory’s Microwave Imager (GMI)and Dual-Frequency Precipitation Radar (DPR) together provide ample information on globalprecipitation characteristics. As an active sensor in particular, DPR provides an accurate precipitationflag assignment, while passive sensors like GMI were traditionally believed not to be able to tell apartprecipitation types. Using collocated precipitation flag assignment from DPR as the “truth”, this project employs machinelearning models to train and test the predictability and accuracy of using passive GMI-only observationstogether with ancillary atmosphere information from reanalysis. Precipitation types are classified intothe following classes: convective, stratiform, convective-stratiform mixed, no precipitation, and otherprecipitation. Sub-sampling with different probabilities is employed to construct a balanced trainingdataset. A variety of classification algorithms are tested, including Support Vector Machines, NaiveBayes, Random Forests, Gradient Boosting, and Neural Networks (Multilayer Perceptron Network), andtheir results are evaluated and compared. The trained model has ~ 85% of prediction accuracy for everytype of precipitation. High-frequency channels (166 GHz and 183 GHz channels) and 166 GHzpolarization difference are found among the most important factors that contribute to the modelperformance, which shed light on future instrument channel selection.