RESUMEN
Several recent studies have evidenced the relevance of machine-learning for soil salinity mapping using Sentinel-2 reflectance as input data and field soil salinity measurement (i.e., Electrical Conductivity-EC) as the target. As soil EC monitoring is costly and time consuming, most learning databases used for training/validation rely on a limited number of soil samples, which can affect the model consistency. Based on the low soil salinity variation at the Sentinel-2 pixel resolution, this study proposes to increase the learning database's number of observations by assigning the EC value obtained on the sampled pixel to the eight neighboring pixels. The method allowed extending the original learning database made up of 97 field EC measurements (OD) to an enhanced learning database made up of 691 observations (ED). Two classification machine-learning models (i.e., Random Forest-RF and Support Vector Machine-SVM) were trained with both OD and ED to assess the efficiency of the proposed method by comparing the models' outcomes with EC observations not used in the models´ training. The use of ED led to a significant increase in both models' consistency with the overall accuracy of the RF (SVM) model increasing from 0.25 (0.26) when using the OD to 0.77 (0.55) when using ED. This corresponds to an improvement of approximately 208% and 111%, respectively. Besides the improved accuracy reached with the ED database, the results showed that the RF model provided better soil salinity estimations than the SVM model and that feature selection (i.e., Variance Inflation Factor-VIF and/or Genetic Algorithm-GA) increase both models´ reliability, with GA being the most efficient. This study highlights the potential of machine-learning and Sentinel-2 image combination for soil salinity monitoring in a data-scarce context, and shows the importance of both model and features selection for an optimum machine-learning set-up.
RESUMEN
Elevated concentrations of arsenic in water supplies represent a worldwide health concern. In at least 14 countries of South America, high levels have been detected relative to international standards and guidelines. Within these countries, the high plateau referred to as the "Altiplano-Puna", encompassing areas of Argentina, Bolivia, Chile, and Perú, exhibits high arsenic concentrations that could be affecting 3 million inhabitants. The origins of arsenic in the Altiplano-Puna plateau are diverse and are mainly natural in origin. Of the natural sources, the most important correspond to mineral deposits, brines, hot springs, and volcanic rocks, whereas anthropogenic sources are related to mining activities and the release of acid mine drainage (AMD). Arsenic is found in all water types of the Altiplano-Puna plateau over a wide range of concentrations (0.01â¯mg·L-1â¯<â¯As in waterâ¯>â¯10â¯mg·L-1) which in decreasing order correspond to: AMD, brines, saline waters, hot springs, rivers affected by AMD, rivers and lakes, and groundwater. Despite the few studies which report As speciation, this metalloid appears mostly in its oxidized form (As[V]) and its mobility is highly susceptible to the influence of dry and wet seasons. Once arsenic is released from its natural sources, it also precipitates in secondary minerals where it is generally stable in the form of saline precipitates and Fe oxides. In relation to human health, arsenic adaptation has been detected in some aboriginal communities of the Puna together with an efficient metabolism of this metalloid. Also, the inefficient methylation of inorganic As in women of the Altiplano might lead to adverse health effects such as cancer. Despite the health risks of living in this arsenic-rich environment with limited water resources, not all of the Altiplano-Puna is properly characterized and there exists a lack of information regarding the basic geochemistry of arsenic in the region.