Arid and semi-arid environments are highly sensitive to climate variability and water scarcity, yet the ecohydrological dynamics of many coastal deserts in southern Peru remain poorly understood. This study characterized the temporal and spatial dynamics of water stress in the district of Inclán (Tacna, Peru) using multitemporal Sentinel-2 and Landsat 8/9 imagery for 2017–2024, with TerraClimate variables as regional hydroclimatic context. Vegetation and moisture were assessed with NDVI, NDMI, NDWI, and SAVI, and land surface temperature (LST) was derived from Landsat thermal products. Standardized anomalies (z-scores) and a composite water stress index (IEHV) were calculated to identify temporal changes and spatial patterns. Vegetation and moisture conditions were persistently low, with consistently low NDVI and NDMI and predominantly negative NDWI. LST showed a clear seasonal contrast, with higher, more homogeneous values in the warm season and more heterogeneous spatial patterns in the cold season. Anomalies suggested a weak tendency toward higher water stress in 2021–2024, which was not significant when the first year was excluded, whereas 2020 showed a temporary anomaly toward lower stress, associated with positive vegetation anomalies and the coolest surface temperatures of the series; its cause could not be established. Spatially, higher vegetation and moisture values appeared, on visual inspection, in drainage corridors, lowlands, and irrigated fields, while more exposed areas appeared drier and thermally more extreme. Integrating spectral and thermal indices allowed characterization of ecohydrological stress and its spatial heterogeneity in this arid coastal system, pending field validation.
The Sierra Minera de Cartagena-La Unión (SE Spain) is a historical mining district where acid mine drainage (AMD) continues to impact soils and water resources. This study, on the one hand, maps three of the secondary iron minerals linked to AMD processes—hematite, goethite, and jarosite—using Sentinel-2 multispectral imagery and, on the other, evaluates how their spatial distribution relates to geomorphological processes and landform configuration. Three spectral techniques were applied: band ratio, minimum wavelength mapper, and a parabola fitting technique. Seventy-four field samples were analysed using X-ray diffraction (XRD) to validate mineral identification. Results indicate that the parabola fitting technique provided the most reliable classification. Sentinel-2 successfully distinguished the three minerals despite its multispectral resolution, due to its red-edge bands capturing diagnostic VNIR features associated with iron-bearing mineral spectral features. Integration of mineral maps with landform units mapped through aerial photointerpretation revealed a strong geomorphological control on AMD mineral deposition: hematite dominates well-drained depositional environments such as alluvial fans, while jarosite and goethite concentrate in colluvial slopes, drainage channels, marshes, and substratum units affected by sulphide oxidation and intermittent moisture conditions
Soil salinization poses a critical threat to agricultural sustainability in arid agroecosystems, limiting food security and economic stability. On the northern coast of Peru, the synergy between inefficient water management and extreme climate variability has accelerated soil degradation, demanding precise spatial monitoring tools. This study proposes a Hybrid Smart Ensemble model to map soil electrical conductivity (EC), integrating optical data (Sentinel-2), dual-polarization SAR texture (Sentinel-1), and thermal imagery (Landsat-9 LST). Three modeling scenarios were evaluated: (1) Random Forest (RF), (2) Deep Neural Network (DNN), and (3) a Hybrid Ensemble. To overcome the typical scarcity of field data in developing regions, a Spatial Data Augmentation strategy based on Tobler's First Law was implemented. The results demonstrated that the hybrid architecture (Scenario 3) achieved superior performance (R² = 0.86; RMSE = 1.70 dS/m), exceeding the baselines of individual classifiers. While the Random Forest provided stability in moderate ranges, the inclusion of Deep Learning proved essential for capturing the nonlinear spectral response of extreme salt crusts (>12 dS/m). Variable importance analysis identified Ground Surface Temperature (LST) and Elevation as dominant predictors, validating the hypothesis that thermal inertia and topographic depressions are the main physical drivers of salinity in hyperarid environments. The resulting map, with a 10 m resolution, reveals "hot spots" in the Chulucanas and Lower Piura sectors, providing valuable information for implementing targeted detection and analysis zones to optimize drainage rehabilitation and soil recovery strategies.While themodel effectively delineates non-saline baselines and severe salt crusts, boundary zones (moderate salinity)remain challenging due to historical sampling limitations. Therefore, the applicability of the model is currentlylimited to hyperarid agroecosystems with edaphic and topographic characteristics similar to those of the LowerPiura Valley; results should be validated with additional field campaigns before implementation in other contexts.
Spectral similarity between built-up surfaces and exposed dry soil significantly constrains built-up area extraction during dry seasons. Although machine-learning techniques can address this challenge by modeling complex spectral relationships, they generally require sufficiently large and representative labeled training datasets. This study therefore investigates a less data-demanding, rule-based multi-index approach for dry-season built-up mapping, aiming to reduce reliance on large labeled training datasets while maintaining effective classification performance. Sentinel-2A imagery acquired in April 2024 was analyzed, and temporal validation was conducted for 2020, 2022, and 2024. Among the tested combinations, the Built-up Area Extraction Index (BAEI), Dry BareSoil Index (DBSI), and Normalized Difference Vegetation Index (NDVI) achieved the highest performance, yielding 95 % overall accuracy and a Kappa coefficient of 0.89. This represents a substantial improvement over singleindex BAEI (80 % overall accuracy; Kappa 0.55), increasing the built-up user’s accuracy from 61 % to 92 %. Multitemporal validation confirmed that the optimized BAEI–DBSI–NDVI decision rules remained stable across the 2020–2024 dry-season images without recalibration, achieving 93–96 % overall accuracy and a built-up F1-score of 84–93 %. Spatial analysis demonstrated robust performance across peripheral and agricultural zones, with moderate variability in dense urban cores due to spectral heterogeneity. To evaluate the operational robustness of the proposed framework, it was benchmarked against machine-learning classifiers, specifically Support Vector Machine and Random Forest (RF). Under the specific conditions of this study, the proposed rule-based method (95 % accuracy) marginally outperformed both SVM (93 %) and RF (92 %), while offering greater transparency and reducing dependency on large, labeled training datasets. Furthermore, feature importance analysis confirmed the critical role of these selected indices in resolving spectral confusion. These findings suggest that the proposed framework offers a transparent and computationally efficient approach for dry-season urban monitoring in tropical coastal environments similar to Visakhapatnam.
La productividad del agua de los cultivos (PA) es un indicador importante del uso del agua agrícola; uno de los grandes retos del sector agrícola es producir una mayor cantidad de alimentos con la menor cantidad de agua aumentando la PA. Los valores de la PA dependen del rendimiento y la evapotranspiración del cultivo, donde la evapotranspiración actual de los cultivos varía entre las diferentes zonas agroclimáticas y es una función de los tipos de híbridos, la fecha de madurez relativa, las prácticas agronómicas y las condiciones ambientales. El presente estudio tuvo como finalidad estimar la evapotranspiración actual (ETa) y la productividad del agua (PA) en el cultivo de maíz forrajero, mediante la integración de sensores remotos, datos climáticos de reanálisis y el modelo de simulación AquaCrop. La ETa observada se determinó usando el modelo AquaCrop, calibrado con datos de campo y parámetros de la cobertura vegetal; mientras que la ETa estimada se obtuvo a partir del modelo SEBAL, implementado en Google Earth Engine (GEESEBAL), utilizando imágenes Landsat 8 y 9 y datos climáticos de reanálisis. Los resultados mostraron que los sensores remotos sobreestimaron la ETa observada, con una sobreestimación promedio del 13 %. Por otro lado, la productividad del agua (PA) estimada con sensores remotos fue ligeramente menor (2.79 y 2.62 kg/m³) que la observada (3.19 y 2.95 kg/m³), con una diferencia promedio del 12 %. Estos resultados indican que los sensores remotos, junto con datos climáticos de reanálisis, pueden adaptarse como una alternativa viable para el monitoreo espacial de la productividad del agua en zonas agrícolas extensas. No obstante, es necesario trabajar en la reducción del error, por ejemplo, incorporando modelos de estimación espacial del rendimiento o utilizando más de un modelo de balance de energía, como METRIC, SSEBop, entre otros.
