Using Slow Feature Analysis and a Cloud-Free Auxiliary Image to Remove Thin Clouds in Landsat-5 VINIR Band Data

An algorithm using slow feature analysis and a cloud-free auxiliary image was proposed to remove thin clouds within Landsat-5 visible and near-infrared (VINIR) band data. The study area was near Norwalk, CA, USA. Five
$800\ (\text{rows})\times 800$
(columns) Landsat-5 images acquired on different dates were studied. Image one was cloud-covered. Image two, a cloud-free one acquired 16 days after image one, was used as the reference image. Images 3–5 were three cloud-free auxiliary images. The algorithm without using an auxiliary image was applied to removing thin clouds in image one. Some clouds were removed, but cloud residuals remained. With the reference image,
$R^{2}$
values were computed, ranging from 0.6039 to 0.8750 for four bands. Then, the algorithm using auxiliary image one was employed to remove the clouds in image one. The removal was improved as the residuals decreased and
$R^{2}$
values increased. The algorithm's performance might not be so sensitive to auxiliary images' acquisition dates as the cloud-removal results using images 3–5 were similar.