The sea surface temperature climate change initiative: Alternative image classification algorithms for sea-ice affected oceans

We present a Bayesian image classification scheme for discriminating cloud, clear and sea-ice observations at high latitudes to improve identification of areas of clear-sky over ice-free ocean for SST retrieval. We validate the image classification against a manually classified dataset using Advance...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing of environment 2015-06, Vol.162, p.396-407, Article 396
Main Authors: Bulgin, Claire E., Eastwood, Steinar, Embury, Owen, Merchant, Christopher J., Donlon, Craig
Format: Article
Language:English
Subjects:
Bayesian analysis
Classification
Classifiers
Climate change initiative
Clouds
High latitudes
Image classification
Latitude
Marine
Oceans
Retrieval
Sea surface temperature
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a Bayesian image classification scheme for discriminating cloud, clear and sea-ice observations at high latitudes to improve identification of areas of clear-sky over ice-free ocean for SST retrieval. We validate the image classification against a manually classified dataset using Advanced Along Track Scanning Radiometer (AATSR) data. A three-way classification scheme using a near-infrared textural feature improves classifier accuracy by 9.9% over the nadir only version of the cloud clearing used in the ATSR Reprocessing for Climate (ARC) project in high latitude regions. The three-way classification gives similar numbers of cloud and ice scenes misclassified as clear but significantly more clear-sky cases are correctly identified (89.9% compared with 65% for ARC). We also demonstrate the potential of a Bayesian image classifier including information from the 0.6μm channel to be used in sea-ice extent and ice surface temperature retrieval with 77.7% of ice scenes correctly identified and an overall classifier accuracy of 96%. •Classification in marginal ice zones is critical for sea surface temperature records.•We evaluate algorithms for satellite data image classification at high latitudes.•Clear-cloud-ice classifiers show good water-ice discrimination.•Combining visible and infrared data enhances ice detection.
ISSN:0034-4257
1879-0704
DOI:10.1016/j.rse.2013.11.022