Groundwater (GW) is the primary source of unfrozen freshwater on the planet and in many semi-arid areas, it is the only source of water available during low-water periods. In north-central Chile, there has been GW depletion as a result of semi-arid conditions and high water demand, which has unleashed major social conflicts, some due to drought and others due to agribusiness practices against the backdrop of a private water management model. The Ligua and Petorca watersheds in the Valparaíso Region were studied in order to analyze the influence of climatic and anthropogenic factors on aquifer depletion using an interdisciplinary approach that integrates hydroclimatic variables, remote sensing data techniques, and GW rights data to promote sustainable GW management. The Standardized Precipitation Index (SPI) and Normalized Difference Vegetation Index (NDVI) were calculated and the 2002–2017 land-use change was analyzed. It was shown that GW decreased significantly (in 75% of the wells) and that the hydrological drought was moderate and prolonged (longest drought in the last 36 years). The avocado-growing area in Ligua increased significantly—by 2623 ha—with respect to other agricultural areas (higher GW decrease), while in Petorca, it decreased by 128 ha. In addition, GW-rainfall correlations were low and GW rights were granted continuously despite the drought. The results confirmed that aquifer depletion was mostly influenced by human factors due to overexploitation by agriculture and a lack of water management.

Coastal wetlands areas are heterogeneous, highly dynamic areas with complex interactions between terrestrial and marine ecosystems, making them essential for the biosphere and the development of human activities. Remote sensing offers a robust and cost-efficient mean to monitor coastal landscapes. In this paper, we evaluate the potential of using high resolution satellite imagery to classify land cover in a coastal area in Concepción, Chile, using a machine learning (ML) approach. Two machine learning algorithms, Support Vector Machine (SVM) and Random Forest (RF), were evaluated using four different scenarios: (I) using original spectral bands; (II) incorporating spectral indices; (III) adding texture metrics derived from the grey-level covariance co-occurrence matrix (GLCM); and (IV) including topographic variables derived from a digital terrain model. Both methods stand out for their excellent results, reaching an average overall accuracy of 88% for support vector machine and 90% for random forest. However, it is statistically shown that random forest performs better on this type of landscape. Furthermore, incorporating Digital Terrain Model (DTM)-derived metrics and texture measures was critical for the substantial improvement of SVM and RF. Although DTM did not increase the accuracy in SVM, this study makes a methodological contribution to the monitoring and mapping of water bodies’ landscapes in coastal cities with weak governance and data scarcity in coastal management.