Details

Autor(en) / Beteiligte

• Lasko, Kristofer
• O'Neill, Francis D.

Titel

Automated Method for Artificial Impervious Surface Area Mapping in Temperate, Tropical, and Arid Environments Using Hyperlocal Training Data With Sentinel-2 Imagery

Ist Teil von

• IEEE journal of selected topics in applied earth observations and remote sensing, 2024, Vol.17, p.298-314

Ort / Verlag

Piscataway: IEEE

Erscheinungsjahr

2024

Quelle

Free E-Journal (出版社公開部分のみ）

Beschreibungen/Notizen

• This study presents an automated methodology to generate training data to map up-to-date artificial impervious surface (AIS) extent maps using two dates (winter and nonwinter) of a Sentinel-2 granule across six international sites (Egypt, India, Qatar, U.K., Eastern USA, and Western USA). It uses a series of spectral, textural, and distance decision functions combined with an outdated AIS layer to create nontarget and target binary masks from which to generate a balanced set of training data applied to a random forest classifier. Two outdated global AIS layers (GMIS-2010 and GISA-2016) were evaluated within the framework to create AIS maps from more recent years (e.g., 2020). For the decision functions, stepwise threshold adjustments applied to normalized difference vegetation index (NDVI) and Euclidean distance layers were evaluated on the binary masks (low-density AIS, high-density AIS, and nontarget land covers) with 729 permutations and 115 permutations for global impervious surface area (GISA) and global manmade impervious surface (GMIS), respectively. The optimal thresholds were determined globally (all six scenes), individually (scene) and grouped by climate for adaptive thresholds. The accuracy assessment found both GMIS-output and GISA-output with global thresholds can accurately map current AIS with 86.9% (±1.7%) (GISA) and 82.7% (±2.3%) (GMIS) accuracy. Adaptive climate thresholds yielded slightly higher accuracies for temperate, tropics, and arid scenes. A novel beach bare ground sampling mask and annual NDVI standard deviation were also evaluated for performance and improved the accuracy in 5/6 sites. Lastly, the global GISA output was compared with a manually labeled deep learning model (Esri) with slightly lower overall accuracy (86.9% vs 88.6%).