Accurate glacier mapping is crucial for assessing future water security in Andean ecosystems. Traditional accuracy assessment may be biased due to overlooking spatial autocorrelation during map validation. In recent years, spatial cross-validation (CV) strategies have been proposed in environmental and ecological modeling to reduce bias in predictive accuracy. In this study, we demonstrate the influence of spatial autocorrelation on the accuracy assessment of glacier surface predictive models. This is achieved by comparing the performance of several widely used machine learning algorithms including the gradient-boosting machines (GBM), k-nearest neighbors (KNN), random forest (RF), and logistic regression (LR) for mapping nine main Peruvian glacier regions. Spatial and non-spatial cross-validation methods were used to evaluate the model’s classification errors in terms of the Matthews correlation coefficient. Performance differences of up to 18% were found between bias-reduced (spatial) and overoptimistic (non-spatial) cross-validation results. Regarding only spatial CV, the k-nearest neighbors were the overall best model across Huallanca (0.90), Huayhuasha (0.78), Huaytapallana (0.96), Raura (0.93), Urubamba (0.96), Vilcabamba (0.93), and Vilcanota (0.92) regions, consistently demonstrating the highest performance followed by logistic regression at Blanca (0.95) and Central (0.97) regions. Our validation approach, accounting for spatial characteristics, provides valuable insights for glacier mapping studies and future efforts on glacier retreat monitoring. Incorporating this approach improves the reliability of glacier mapping, guiding future national-level initiatives.

Soil moisture content can be used to predict drought impact on agricultural yield better than precipitation. Remote sensing is viable source of soil moisture data in instrument-scarce areas. However, space-based soil moisture estimates lack suitability for daily and high-resolution agricultural, hydrological, and environmental applications. This study aimed to assess the potential of the random forest machine learning technique to enhance the spatial resolution of remote soil moisture products from the SMAP satellite. Models were built using random forest for spatial downscaling of SMAP-L3-E, then visually and statistically evaluated for disaggregation quality. The impact of topography, soil properties, and precipitation on the downscaled soil moisture was examined. The relationship between downscaled soil moisture and in-situ soil moisture was analyzed. The results indicate that the proposed method demonstrated spatial and hydrological coherence, along with a satisfactory downscaling quality. Statistical validation indicated suitable generalization error for scientific and practical use (RMSE < 0.05 cm3 cm-3). Random forest effectively achieved spatial downscaling of SMAP-L3-E in the study area. Principal component and spatial analysis revealed dependence of downscaled soil moisture on elevation, soil organic carbon content, clay content, and saturated hydraulic conductivity, mainly under near-saturation conditions. Regarding validation against in-situ data, downscaled soil moisture explained in-situ soil moisture well under low soil water content ( = 0.624). Downscaling performance deteriorates for water contents between 0.40 to 0.50 cm3 cm-3, suggesting inadequacy under near saturation conditions at a daily temporal frequency. However, coarser temporal aggregations (7 to 10 days) yielded an average 0.98 correlation coefficient, regardless of saturation conditions. These results could potentially be applied in irrigation planning, soil physics studies and hydrology monitoring, to forecasting the occurrence of droughts, leaching of contaminants, surface runoff modeling, carbon cycle studies, soil's capacity to store and provide nutrients.

Accurately glacier mapping is crucial for understanding climate change impacts, but existing efforts may be biased due to overlooking spatial autocorrelation during map validation. To address this, we compared several widely used machine learning algorithms as gradient boosting machines (GBM), k-nearest neighbor (KNN) and random forest (RF) with parametric logistic regression (GLM) and an unsupervised remote sensing-based method (NDSI) for mapping Peru's glacier regions in a thoughtful experimental setup. Spatial and non-spatial cross-validation methods were used to evaluate model’s performance and compared with a fully independent test set. Performance differences of up to 18% were found between bias-reduced (spatial) and overoptimistic (non-spatial) cross-validation results when compared to independent test set, emphasizing the need to consider spatial autocorrelation when using machine learning for glacier mapping. K-nearest neighbors (KNN) was the overall best model across regions consistently demonstrating the highest performance followed by logistic regression (LR) and gradient boosting machines (GBM). Our novel validation approach, accounting for spatial characteristics, provides valuable insights for glacier mapping studies and future efforts on glacier retreat monitoring. Incorporating this approach improves the reliability of glacier mapping, guiding future national-level initiatives.

Soil organic carbon (SOC) is a crucial component related to various processes that ensure soil health and function. Its modeling is vital for assessing and monitoring soil degradation caused by the potential impact of agricultural activities.This study aimed to model SOC in the Northern highlands of Peru, characterized by a high amount of SOC, which is being affected by crop expansion. Crop rotation (CR) history was linked to ground-truthed soil data via a multi-year crop classification model trained on data from 534 fields across 2022–2024. Each cropland field was represented as a polygon delineating its boundaries and indicating its dominant crop cover. Time series of multispectral Sentinel-2 Level-2A Top of Canopy imagery were used to derive phenological features—such as the timing of maximum canopy cover and the length of the growing period—based on Normalized Difference Vegetation Index (NDVI) time series. A Random Forest classifier was used as the baseline model. The cropland classification model demonstrated a strong overall performance, with F ₁ scores ranging from 0.81 to 0.98 across the different classes. The model performed well for lupin and pasture but scored lower for beans and potatoes. Predictions of cropland classes from 2019 to 2022 were created, resulting in frequency layers that represent crop rotations. Four feature configurations were evaluated: (i) including all features as a benchmark, (ii) excluding climatology, (iii) excluding crop rotation history, and (iv) excluding soil properties. Configurations including all features and excluding crop rotation history showed the highest performance ( R ² = 0.63), while those excluding climatology or soil properties performed worse ( R 2 ≈ 0.52 -- 0.53 ). Although soil features were the most important, fallow frequency emerged as the most critical predictor of SOC in crop rotations. When soil data were excluded, fallow frequency, combined with climatic features, explained over half of the SOC variability. The findings emphasize the importance of incorporating remote sensing-derived CR into SOC mapping efforts.

Soil organic carbon (SOC) is a crucial component related to various processes that ensure soil health and function. Its modeling is vital for assessing and monitoring soil degradation caused by the potential impact of agricultural activities. This study aimed to model SOC in the Northern highlands of Peru, characterized by a high amount of SOC, which is being affected by crop expansion. Crop rotation (CR) was incorporated into a modeling exercise using remote sensing data, fieldwork, and farmer surveys. A multi-year classification model with seven cropland classes was developed using data collected from 534 fields across 2022-2024, including 189 soil samples. Each cropland field was represented as a polygon delineating its boundaries and indicating its dominant crop cover. Time series of multispectral Sentinel-2 Level-2A Top of Canopy imagery were used to derive phenological features—such as the timing of maximum canopy cover and the length of the growing period—based on Normalized Difference Vegetation Index (NDVI) time series. A Random Forest classifier was used as the baseline model. The cropland classification model demonstrated strong overall performance, with F1 scores ranging from 0.81 to 0.98 across the different classes. The model performed well for lupin and pasture but scored lower for beans and potatoes. Predictions of cropland classes from 2019 to 2022 were created, resulting in frequency layers that represent crop rotations. Four feature configurations were evaluated: (i) including all features as a benchmark, (ii) excluding climatology, (iii) excluding crop rotation history, and (iv) excluding soil properties. Configurations including all features and excluding crop rotation history showed the highest performance (R ² = 0.63), while those excluding climatology or soil properties performed worse (R ² ≈ 0.52-0.53). Although soil features were the most important, fallow frequency emerged as the most critical predictor of SOC in crop rotations. When soil data were excluded, fallow frequency, combined with climatic features, explained over half of the SOC variability. The findings emphasize the importance of incorporating CR into SOC mapping efforts.