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.

In this study, the SWAT (Soil Water Assessment Tool) hydrological model is implemented to determine the effect of climate change on various hydrological components in two basins located in the foothills of the Andes: the Quino and Muco river basins. The water cycle is analyzed by comparing the model results to climatic data observed in the past (1982–2016) to understand its trend behaviors. Then, the variations and geographical distribution of the components of the hydrological cycle were analyzed using the Representative Concentration Pathway (RCP)8.5 climate scenario to model two periods considering the immediate future (2020–2049) and intermediate future (2050–2079). In this way, in the study area, it is predicted that yearly average temperatures will increase up to 1.7 °C and that annual average precipitation will decrease up to 210 mm for the intermediate future. Obtained results show that the analyzed parameters presented the same trend behavior for both periods of time; however, a greater impact can be expected in the intermediate future. According to the spatial distribution, the impact worsens for all the parameters as the elevation increases in both basins. The model depicted that yearly average evapotranspiration would increase around 5.26% and 5.81% for Quino and Muco basins, respectively, due to the large increase in temperature. This may cause, when combined with the precipitation lessening, a decrease around 9.52% and 9.73% of percolation, 2.38% and 1.76% of surface flow, and 7.44% and 8.14% of groundwater for Quino and Muco basins, respectively, with a consequent decrease of the water yield in 5.25% and 4.98% in the aforementioned watersheds, respectively.

In this study, we combined machine learning and remote sensing techniques to estimate the value of chlorophyll-a concentration in a freshwater ecosystem in the South American continent (lake in Southern Chile). In a previous study, nine artificial intelligence (AI) algorithms were tested to predict water quality data from measurements during monitoring campaigns. In this study, in addition to field data (Case A), meteorological variables (Case B) and satellite data (Case C) were used to predict chlorophyll-a in Lake Llanquihue. The models used were SARIMAX, LSTM, and RNN, all of which showed generally good statistics for the prediction of the chlorophyll-a variable. Model validation metrics showed that all three models effectively predicted chlorophyll as an indicator of the presence of algae in water bodies. Coefficient of determination values ranging from 0.64 to 0.93 were obtained, with the LSTM model showing the best statistics in any of the cases tested. The LSTM model generally performed well across most stations, with lower values for MSE (<0.260 (μg/L)²), RMSE (<0.510 ug/L), MaxError (<0.730 μg/L), and MAE (<0.442 μg/L). This model, which combines machine learning and remote sensing techniques, is applicable to other Chilean and world lakes that have similar characteristics. In addition, it is a starting point for decision-makers in the protection and conservation of water resource quality.

Remote sensing was used as an early alert tool for water clarity changes in five Araucanian Lakes in South-Central Chile. Turbidity records are scarce or unavailable over large and remote areas needed to fully understand the factors associated with turbidity, and their spatial-temporal representation remains a limitation. This work aimed to develop and validate empirical models to estimate values of turbidity from Landsat images and determine the spatial distribution of estimated turbidity in the selected Araucanian Lakes. Secchi disk depth measurements were linked with turbidity measurements to obtain a turbidity dataset. This in turn was used to develop and validate a set of empirical models to predict turbidity based on four single bands and 16 combination bands from 15 multispectral Landsat images. The best empirical models predicted turbidity over the range of 0.3–12.3 NTUs with RMSE values around 0.31–1.03 NTU, R² (Index of Agreement IA) around 0.93–0.99 (0.85–0.97) and mean bias error (MBE) around (−0.36–0.44 NTU). Estimation maps to analyze the temporal-spatial turbidity variation in the lakes were constructed. Finally, it was found that the meteorological conditions may affect the variation of turbidity, mainly precipitation and wind speed. The data indicate that the turbidity has slightly increased in winter–spring. These models will be used in the future to reconstruct large datasets that allow analyzing transparency trends in those lakes.