Abstract
Assessments of the status of tidal flats, one of the most extensive coastal ecosystems, have been hampered by a lack of data on their global distribution and change. Here we present globally consistent, spatially-explicit data of the occurrence of tidal flats, defined as sand, rock or mud flats that undergo regular tidal inundation. More than 1.3 million Landsat images were processed to 54 composite metrics for twelve 3-year periods, spanning four decades (1984-1986 to 2017-2019). The composite metrics were used as predictor variables in a machine-learning classification trained with more than 10,000 globally distributed training samples. We assessed accuracy of the classification with 1,348 stratified random samples across the mapped area, which indicated overall map accuracies of 82.2% (80.0-84.3%, 95% confidence interval) and 86.1% (84.2-86.8%, 95% CI) for version 1.1 and 1.2 of the data, respectively. We expect these maps will provide a means to measure and monitor a range of processes that are affecting coastal ecosystems, including the impacts of human population growth and sea level rise.