GCL_FCS30: a global coastline dataset with 30-m resolution and a fine classification system from 2010 to 2020

<p><span>A G</span>lobal <span>C</span>oast<span>L</span>ine <span>D</span>ataset (GCL_FCS30) with a detailed classification system, including categories for (0) artificial, (1) biogenic, (2) sandy, (3) muddy, (4) rocky, and (5) estuary coastlines for 2010, 2015, and 2020. The coastline extraction employed a combined algorithm incorporating the Modified Normalized Difference Water Index (MNDWI), an adaptive threshold segmentation method based on the Maximum Between-Class Variance <span>Method </span>(OTSU), and the Canny edge detector. The coastline classification was performed using a hybrid transect classifier that integrates a random forest algorithm with globally stable training samples derived from multi-source geophysical data.</p>