Snow and Cloud Discrimination Using Convolutional Neural Networks

Abstract

<p><strong>Abstract.</strong> Snow is an important feature on our planet, and measuring its extent has advantages in climate studies. Snow mapping through satellite remote sensing is often affected by cloud cover. This issue can be resolved by using short wave infrared (SWIR) sensors. In order to obtain an effective cloud mask, our study aims to use SWIR data of a ResourceSat-2 satellite. We employ Convolutional Neural Networks (CNN) to discriminate similar pixels of clouds and snow. The technique is expected to give a high accuracy compared to traditional methods such as thresholding. The cloud mask thus produced can also be used for creating the metadata for Indian Remote Sensing products.</p>

Automatic High-Accuracy Sea Ice Mapping in the Arctic Using MODIS Data

“…Thin clouds and broken ice are often confused for each other. Machine learning methods have been applied to cloud and ice detection, but there is no mature technology for sea ice operational map products [36][37][38]. Zhan et al [36] proposed a deep learning system for cloud and snow classification based on pixel-level fully convolutional neural networks.…”

“…Zhan et al [36] proposed a deep learning system for cloud and snow classification based on pixel-level fully convolutional neural networks. Varshney et al [37] used a convolutional neural network to distinguish between clouds and snow pixels from the shortwave infrared sensor data of the ResourceSat-2 satellite. Ghasemian et al [38] proposed two cloud detection methods, Feature Level Fusion Random Forest and Decision Level Fusion Random Forest, based on machine learning and multifeature fusion, respectively.…”