In the United States, satellite data often miss key land features. But could using high-resolution images and machine learning methods help create an accurate land cover map? Dr. Samantha Kahl ’04 set out to answer this question with a paper recently published in the journal Remote Sensing.
In the paper titled “Ensemble Machine Learning on the Fusion of Sentinel Time Series Imagery with High-Resolution Orthoimagery for Improved Land Use/Land Cover Mapping,” Dr. Kahl and her co-authors found that combining high-resolution images and machine learning improved map accuracy, but also revealed additional issues when spatial information was ignored.