Cloud detection methodologies: variants and development—a review

TLDR

Cloud detection is a critical task in satellite remote sensing, with researchers developing diverse methods—including machine‑learning, classical threshold‑based, and hybrid approaches—to identify clouds, snow, and thin clouds in imagery. The paper reviews cloud‑detection literature from 2004 to 2018. The authors conduct a systematic review of cloud‑detection studies published between 2004 and 2018. The review finds that threshold‑based methods lack universality and many models omit ground‑based validation, recommending hybrid machine‑learning and physical‑parameter approaches for improved accuracy.

Abstract

Abstract 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.