A new method for MODIS cloud classification

Bormin Huang; Steven A. Ackerman; W. Paul Menzel

doi:10.1117/12.619885

29 August 2005 A new method for MODIS cloud classification

Bormin Huang, Steven A. Ackerman, W. Paul Menzel

Proceedings Volume 5890, Atmospheric and Environmental Remote Sensing Data Processing and Utilization: Numerical Atmospheric Prediction and Environmental Monitoring; 58900X (2005) https://doi.org/10.1117/12.619885
Event: Optics and Photonics 2005, 2005, San Diego, California, United States

Abstract

A new technique called the local region of influence (LROI) scheme for supervised cloud classification of the Moderate Resolution Imaging Spectroradiometer (MODIS) is proposed. The classification of each observation is performed within the LROI, where the center of each class is calculated as a weighted average of its training class members with respect to each new observation. The probability of each class is assigned to each observation. The proposed LROI scheme is applied to the MODIS radiances observed from the scenes of clear skies, ice clouds, or water clouds. The classification results are compared with those from the maximum likelihood (ML) classification method, the multicategory support vector machine (MSVM) and the operational MODIS cloud mask algorithm. The lowest misclassification error rates show the advantage of the LROI scheme.

Citation Download Citation

Bormin Huang, Steven A. Ackerman, and W. Paul Menzel "A new method for MODIS cloud classification", Proc. SPIE 5890, Atmospheric and Environmental Remote Sensing Data Processing and Utilization: Numerical Atmospheric Prediction and Environmental Monitoring, 58900X (29 August 2005); https://doi.org/10.1117/12.619885

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available