Search

Cloud detection is an essential and important process in satellite remote sensing. Researchers proposed various methods for cloud detection. This paper reviews recent literature (2004–2018) on cloud detection. Literature reported various techniques to detect the cloud using remote-sensing satellite imagery. Researchers explored various forms of Cloud detection like Cloud/No cloud, Snow/Cloud, and Thin Cloud/Thick Cloud using various approaches of machine learning and classical algorithms. Machine learning methods learn from training data and classical algorithm approaches are implemented using a threshold of different image parameters. Threshold-based methods have poor universality as the values change as per the location. Validation on ground-based estimates is not included in many models. The hybrid approach using machine learning, physical parameter retrieval, and ground-based validation is recommended for model improvement.

Clouds classification is essentially required in weather forecasting and climate related study. Detection, removal and classification of cloud are the major challenges to deal with in satellite-based images. In this paper, literature survey on cloud classification techniques published during 2000 to 2018 is presented. In recent years, various approaches are applied for cloud classification such as threshold-based, machine learning, clustering, K-means, k-nearest-neighbour (K-NN) algorithm and hybrid approach. Threshold-based is the easiest approach but it fails to classify cloud in complex sky conditions. It is also unable to classify cloud at night time. Machine learning-based approach gives highest accuracy but it depends on various parameters like day/night time, weather season, types of satellite and geographical region of the cloud. It is recommended to have hybrid model with the use of machine learning, threshold values and physical parameters.