The machine learning approach has shown its state-of-the-art ability to handle segmentation and detection tasks. It is increasingly employed to extract patterns and spatiotemporal features from the ever-increasing stream of Earth system data. However, there is still a significant challenge, which is the generalization capability of the model on cloud images in different types and weather conditions. After studying several popular methods, we propose a semantic segmentation neural network for cloud segmentation. It extracts features learned by source and target domains in an end-to-end behavior, which can address the problem of significant lack of labels in the observed cloud image data. It is further evaluated on the Singapore Whole Sky Image Segmentation (SWIMSEG) dataset by using Mean Intersection-over-Union, recall, F-score, and accuracy matrices. The scores of these matrices are 86%, 97%, 92%, and 96%, which prove that it has excellent efficiency and robustness. Most importantly, a new benchmark based on the SWIMSEG dataset for the task of cloud segmentation is introduced. The others, BENCHMARK, Cirrus Cumulus Stratus Nimbus are evaluated through the model trained from the SWIMSEG dataset by way of visualization. Plain Language Summary The machine learning approaches offer a new view about howto effectively and comprehensively understand ground-based cloud datasets. The essential advantage of deep learning methods is that it can extract more critical cloud features automatically than traditional algorithms, such as spatiotemporal features. Therefore, it is worth exploring the possibility of cloud segmentation with the help of deep learning techniques. We first introduce a semantic segmentation neural network for cloud segmentation problems after measuring a few classic neural networks. The results exceed the traditional methods by a large margin with standard evaluation matrices, such as Mean Intersection-over-Union, recall, F-score, and accuracy. The scores achieved here may accomplish as a baseline for competitive development. Second, the trained model is used to produce a few cloud masks in two public datasets: BENCHMARK, Singapore Whole Sky Image Segmentation, and their respective performance is further evaluated. Finally, the segmentation results show the excellent performance and generalization in another untrained dataset, Cirrus Cumulus Stratus Nimbus.
Over recent decades the deterministic and probabilistic NWPs have been improved significantly. It becomes the essential toll for the meteorological operation and applications. It is very often that there are several deterministic NWPs and EPSs with different resolution available for meteorological operation and applications. Those forecasts are with different characteristics of systematic bias and dispersion errors. Many statistical calibration methods have been proposed and been implemented in the operation, for example, ensemble model output statistics (EMOS) and standardized anomaly model output statistics (SAMOS). Further, Artificial intelligence (AI) based method has been used in different way for calibration.  In this study we applied EMOS and SAMOS to calibrate multi-scale deterministic and probabilistic forecasts. In the frame of SAMOS/EMOS we have introduced AI based methods for selecting the important variables and building the non-linearity for calibration. The CMA(China meteorological Administration) NWP model chain, a convection permitting NWP (3km resolution), a regional NWP (9km) and a global NWP (25km), a regional EPS (10km) and a global EPS (50km) have been used for the calibration. Two years observation and NWP data over Beijing region was selected for training the EMOS/SAMOS method.  EMOS and SAMOS, AI based variable selection and Boosting method etc. have been compared. 2m temperature, 10m Wind and precipitation forecasts have been calibrated and verified with statistical scores such as, root mean square error of ensemble mean, continuous ranked probability score(CRPS)and so on. The results of calibrated ensemble mean and ensemble spread are quite encouraging, which will be presented at the conference.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.