LSCIDMR: Large-Scale Satellite Cloud Image Database for Meteorological Research

People can infer the weather from clouds. Various weather phenomena are linked inextricably to clouds, which can be observed by meteorological satellites. Thus, cloud images obtained by meteorological satellites can be used to identify different weather phenomena to provide meteorological status and future projections. How to classify and recognize cloud images automatically, especially with deep learning, is an interesting topic. Generally speaking, large-scale training data are essential for deep learning. However, there is no such cloud images database to date. Thus, we propose a large-scale cloud image database for meteorological research (LSCIDMR). To the best of our knowledge, it is the first publicly available satellite cloud image benchmark database for meteorological research, in which weather systems are linked directly with the cloud images. LSCIDMR contains 104 390 high-resolution images, covering 11 classes with two different annotation methods: 1) single-label annotation and 2) multiple-label annotation, called LSCIDMR-S and LSCIDMR-M, respectively. The labels are annotated manually, and we obtain a total of 414 221 multiple labels and 40 625 single labels. Several representative deep learning methods are evaluated on the proposed LSCIDMR, and the results can serve as useful baselines for future research. Furthermore, experimental results demonstrate that it is possible to learn effective deep learning models from a sufficiently large image database for the cloud image classification.

I. Introduction

A better understanding of weather systems is extremely important for peoples’ dailly lives. Weather prediction is more accurate today than in the last century due to great improvements in prediction tools, theory development, computational power, and observation systems [1]. These days, we can accurately predict weather changes in a time interval of days. However, forecasting extreme weather, such as typhoons and dust storms remains challenging. At the same time, the rapid development of artificial intelligence, especially deep learning, has attracted more attention from different research communities [2], [3]. The successful applications of deep learning in computer vision, including tasks of image retrieval [4], face detection [5], semantic segmentation [6], and saliency detection [7], as well as remote sensing (RS) image processing (including hyperspectral image classification [8]–[10], scene classification [11], and image prediction [12]), provide insight for deep-learning-based weather prediction.