Examinando por Materia "Digital soil mapping"

Mostrando 1 - 3 de 3

Ensemble machine learning for digital mapping of soil pH and electrical conductivity in the Andean agroecosystem of Peru
(Frontiers Media S.A., 2025-11-06) Carbajal Llosa, Carlos Miguel; Barja , Antony; Pizarro Carcausto, Samuel Edwin
In agricultural systems, soil pH and electrical conductivity (EC) are crucial chemical properties that directly affect nutrient availability and microbial activity, but the challenging environment of the Peruvian Andes has limited research on their estimation. This study aimed to develop an ensemble learning method to predict soil pH and EC in Andean agroecosystems using environmental predictors. By using simple and weighted averaging, we developed a heterogeneous ensemble learning approach that integrates machine learning (ML) algorithms, including Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The weighted ensemble assigns weights to models based on their predictive accuracy, measured by R² from spatial cross-validation. Spatial patterns are noticeable, and pH displays greater spatial clustering than EC. Elevation was the most important predictor in ML models for both parameters. Ensemble models significantly outperformed individual models, with the weighted ensemble achieving R² >0.93 and reducing RMSE by approximately 72%. Among standalone models, RF and XGBoost performed best for pH, while SVM performed the best for EC. ANN models were the least effective. Uncertainty analysis indicated high confidence in pH predictions but moderate to high uncertainty in EC predictions, suggesting that EC is more challenging to predict. Ensemble models with optimized weighting provide robust and accurate mapping of spatially autocorrelated soil properties. The high-confidence pH maps are reliable for soil management decisions, while EC predictions, though more uncertain, effectively identify priority areas for future sampling and investigation.
Soil organic carbon content mapping along the coast of northern Peru: an ensemble machine learning approach
(Frontiers Media SA, 2026-03-26) Salazar Coronel, Wilian; Carbajal Llosa, Carlos Miguel; Chuchon Remon, Rodolfo Juan
Introduction: Soil organic carbon (SOC) content plays a fundamental role in regulating the global carbon cycle and mitigating climate change. It is also a key marker of soil health and a vital plant component. Its distribution in space varies in dry ecosystems, where climate and land use affect it. This study aimed to estimate and map SOC in the Motupe River Basin, northern Peru, by applying machine learning algorithms and ensemble methods. Methods: Four predictive models were evaluated: Support Vector Regression (SVR), Random Forest (RF), Artificial Neural Network (ANN), and Extreme Gradient Boosting (XGBoost), together with two ensemble approaches—simple averaging and weighted — integrating topographic, climatic, edaphic, and vegetation indices variables. Spatial autocorrelation was minimized by spatial block cross-validation. Uncertainty was measured with bootstrapping and the Prediction Interval Ratio (PIR) derived from 90% prediction intervals. Results and discussion: Best performance was achieved by XGBoost (R² = 0.83), weighted ensemble (R² = 0.70), and RF (R² = 0.63). The most influential predictors were EVI, GNDVI, temperature, TRI, and pH. SOC contents showed relatively higher concentrations (>0.7%) in areas with greater vegetation density, within a semi-arid context where SOC levels are generally low. In contrast, lower areas exhibited reduced SOC contents (< 0.6%). The uncertainty analysis indicated that SOC predictions had high to moderate confidence (PIR < 0.2) in the middle-and upper zones of the basin, and moderate confidence (0.1–0.2) in the lower areas. The results suggest that machine learning and ensemble methods improve SOC prediction, benefiting the sustainable management of soil fertility and quality in arid and semi-arid ecosystems of northern Peru.
Spatial prediction of soil organic carbon stocks across contrasting Andean basins, Peru
(Elsevier B.V., 2025-11-06) Carbajal Llosa, Carlos Miguel; Tumbalobos Dextre, Merely; Condori Ataupillco, Levi Tatiana; Cuellar Condori, Nestor Edwin; Gavilan, Carla
Soil organic carbon stocks (SOCS) are critical components of the global carbon cycling and play a central role in climate change mitigation. However, their dynamics in high‐altitude Andean ecosystems remain poorly understood despite their importance for carbon sequestration. The significant spatial heterogeneity of SOCS in mountainous terrain makes accurate quantification and mapping challenging. This study evaluated the performance of geospatial regression and machine learning (ML) approaches for predicting SOCS in two Peruvian Andean basins: Torobamba and Coata. We compared Geographically Weighted Regression (GWR), GWR with collinearity analysis (GWRC), their kriging‐adjusted variants, and ML models (Random Forest, Gradient Boosting). Models were built using key SOCS covariates for each basin and validated through 5‐fold cross‐validation with Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R²). In Torobamba, GWRC markedly improved performance, reducing the RMSE by 79–90% and achieving R² up to 0.99. In contrast, Coata, showed only modest improvements (RMSE reductions of 7.8–9.8%, R² = 0.30–0.39). ML models performed poorly (negative R²), likely due to feature selection, parameter tuning, or limited sample size. Overall, locally weighted regression approaches (GWRK/GWRCK) outperformed conventional ML methods for SOCS prediction in complex mountain environments, particularly with small to medium sample sizes. These results highlight the importance of accounting for spatial non‐stationarity in SOCS and provide methodological guidance for SOCS mapping in Andean ecosystems.