Estimation of Water Coverage in Permanent and Temporary Shallow Lakes and Wetlands by Combining Remote Sensing Techniques and Genetic Programming: Application to the Mediterranean Basin of the Iberian Peninsula

This work aims to validate the wide use of an algorithm developed using genetic programing (GP) techniques allowing discern between water and non-water pixels near infrared band different thresholds. A total 34 wetlands shallow lakes 18 ecological types were used for validation. These include marshes, salt ponds, saline freshwater, temporary permanent lakes. Furthermore, based on spectral matching Landsat Sentinel-2 sensors, this methodology was applied imagery, improving spatial temporal resolution. When compared other techniques, GP showed better accuracy (over 85% in most cases) acceptable kappa values estimation (? ? 0.7) 10 assayed evaluated with Landsat-7 imagery. The improvements especially achieved wetlands, where existing algorithms scarcely reliable. shows that remote sensing satellite imagery can be a valuable tool monitor coverage multiple factors cause low resolution by commonly indices. allows reconstruction hydrological series showing their behaviors during last three decades, being useful predict how pattern may behave under future global change scenarios.