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

Abstract

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

Actas del XIX Congreso de Tecnologías de la Información Geográfica. TIG al servicio de los ODS Zaragoza, 12 a 14 de septiembre de 2022

“…Para complementar la información obtenida con el índice NDVI, utilizamos NDWI (Normalized Difference Water Index), y como es sabido, se refiere a un índice diseñado para la detección remota del agua líquida. Ha sido utilizado por numerosos autores en distintas circunstancias (Campos et al, 2012;Doña et al, 2021) y nosotros lo utilizamos para monitorizar los cambios en el contenido de agua de las hojas, utilizando la reflectancia del infrarrojo próximo (NIR) y del infrarrojo medio (SWIR), su rango de reflectancia estaría definido entre 0.9 -1.7 μm (Gao, 1996) Con este índice podemos estimar previamente el estado hídrico de los árboles de cara a soportar periodos de sequía. La combinación del NIR con el SWIR elimina las variaciones inducidas por la estructura interna de la hoja y el contenido de materia seca de la hoja, lo que mejora la precisión a la hora de valorar si se ha iniciado la recuperación del estado de humedad del cultivo.…”

Remote Sensing Temporal Reconstruction of the Flooded Area in “Tablas de Daimiel” Inland Wetland 2000–2021

“…Satellite imagery notoriously improved water bodies monitoring in terms of detecting changes over time and space [11]. The advances in remote sensing technology allowed diverse hydrological applications, such as monitoring fluctuations of lake or dam surface or mapping small water bodies [12][13][14][15][16]. Remote sensing data from Landsat satellites (Landsat 5 (TM), Landsat 7 (ETM+), and Landsat 8 (OLI)) were widely used since the launch of the Landsat thematic mapper (TM) on 1 March 1984).…”

“…This turns into smaller unconnected water bodies than in other climates, and spatial resolution is a key parameter [15]. Additionally, the 16-day temporal resolution of these sensors can be a limiting factor to interpret wetland dynamics [13,15].…”

“…The Sentinel-2 satellite launched by the European Space Agency (ESA) in 2015 includes a constellation of two polar-orbiting satellites with 5-day temporal resolution and a maximum of 10 m spatial resolution [13,15,18]. The higher resolution of Sentinel-2, both spatial and temporal, can significantly improve the monitoring range, especially for small sites that cannot be covered by the Landsat satellite [8,11,13,15,18]. Some studies assessed a multi-sensor approach that takes advantage of Landsat and Sentinel-2 [12,15,16].…”

First Perceptions of Hydroperiod Mapping and Assessment of Shallow Waters in Coastal Landscapes by Drone-Based Monitoring Activities: A Remote-Sensing and GIS Approach

“…While innovative approaches are being tested for the assessment of large, permanent water bodies, similar techniques are lacking for the monitoring of temporary ponds. Indeed, recent studies have successfully used machine-learning methods and satellite remotesensing time series analysis for spatio-temporal monitoring of the water coverage and quality of lakes and aquaculture ponds [32][33][34][35][36]. However, the implementation of such techniques on small temporary ponds has been hampered by the limited extent and dynamism of these ponds due to short water detention.…”