Examinando por Materia "Random Forest"

Mostrando 1 - 4 de 4

Digital soil mapping of metals and metalloids in croplands using multiple geospatial data and machine learning, implemented in GEE, for the Peruvian Mantaro Valley
(Elsevier, 2024-03-29) Pizarro Carcausto, Samuel; Vera Vilchez, Jesús Emilio; Huamani, Joseph; Cruz, Juancarlos; Lastra Paucar, Sphyros Roomel; Solórzano Acosta, Richard Andi; Verástegui Martínez, Patricia
Quality and safety of the soil are essential to ensure social and economic development and provides the supply of contaminant free food. With agriculture intensification, expansion of urban zones, construction of roads, and mining, some agricultural soils sites become polluted increasing environmental risks to ecosystems functions and human health. Hence the need know the spatial distribution of elements in soils, we mapped 25 elements, namely Ca, Mg, Sr, Ba, Be, K, Na, As, Sb, Se, Tl, Cd, Zn, Al, Pb, Hg, Cr, Ni, Cu, Mo, Ag, Fe, Co, Mn and V, using various geospatial datasets, such as remote sensing, climate, topography, soil data, and distance, to establish the spatial estimation models of spatial distribution trained trough machine learning model with a supervised dataset of 109 topsoil samples, into Google earth engine platform. Using R2, RMSE and MAE to assess the prediction accuracy. First Random Forest gave satisfactory results in predicting the distribution of analyzed elements in soil, being improved for some elements when adds more trees. Additionally, each element analyzed has a different combination of environmental covariates as predictor, mainly soil, climate, topographic and distance variables especially croplands close to rivers, with less importance for spectral variables. Our results suggest that is possible to identify polluted soils and improved regulations to minimize harm to environmental health and human health, for short-to-medium-term environmental risk control.
Landsat images and GIS techniques as key tools for historical analysis of landscape change and fragmentation
(Elsevier, 2024-07-28) Gómez Fernández, Darwin; Salas López, Rolando; Zabaleta Santisteban, Jhon Antony; Medina Medina, Angel J.; Goñas Goñas, Malluri; Silva López, Jhonsy O.; Oliva Cruz, Manuel; Rojas Briceño, Nilton B.
Monitoring and evaluation of landscape fragmentation is important in numerous research areas, such as natural resource protection and management, sustainable development, and climate change. One of the main challenges in image classification is the intricate selection of parameters, as the optimal combination significantly affects the accuracy and reliability of the final results. This research aimed to analyze landscape change and fragmentation in northwestern Peru. We utilized accurate land cover and land use (LULC) maps derived from Landsat imagery using Google Earth Engine (GEE) and ArcGIS software. For this, we identified the best dataset based on its highest overall accuracy, and kappa index; then we performed an analysis of variance (ANOVA) to assess the differences in accuracies among the datasets, finally, we obtained the LULC and fragmentation maps and analyzed them. We generated 31 datasets resulting from the combination of spectral bands, indices of vegetation, water, soil and clusters. Our analysis revealed that dataset 19, incorporating spectral bands along with water and soil indices, emerged as the optimal choice. Regarding the number of trees utilized in classification, we determined that using between 10 and 400 decision trees in Random Forest classification doesn't significantly affect overall accuracy or the Kappa index, but we observed a slight cumulative increase in accuracy metrics when using 100 decision trees. Additionally, between 1989 and 2023, the categories Artificial surfaces, Agricultural areas, and Scrub/ Herbaceous vegetation exhibit a positive rate of change, while the categories Forest and Open spaces with little or no vegetation display a decreasing trend. Consequently, the areas of patches and perforated have expanded in terms of area units, contributing to a reduction in forested areas (Core 3) due to fragmentation. As a result, forested areas smaller than 500 acres (Core 1 and 2) have increased. Finally, our research provides a methodological framework for image classification and assessment of landscape change and fragmentation, crucial information for decision makers in a current agricultural zone of northwestern Peru.
Random Forest-based spatial distribution from heavy metals and associated with ecological and health risk assessment in agricultural soils of the Mantaro Valley, Peru
(Elsevier B.V., 2026-07-31) Orellana Mendoza, Edith; Cosme de la Cruz, Roberto Carlos; Quispe Coquil, Violeta; Mendoza Delgado, Katia; Valero Maraví, Sheila; Rojas León, Ángeles; Ccopi Trucios, Dennis; Pizarro Carcausto, Samuel Edwin
Heavy metal (HM) contamination of agricultural soils in Andean valleys poses a critical threat to ecological integrity, food safety, and human health. This study assessed the spatial distribution, contamination levels, ecological and health risk (non-carcinogenic and carcinogenic) associated with Zn, Pb, Cu, Cd, and As in agricultural soils of the Mantaro Valley in the central Andes of Peru. A total of 306 topsoil samples were analyzed. Random Forest (RF) was used to model the spatial distribution of HM concentrations, integrating spectral, climatic, topographic, edaphic, and distance-related covariates. The RF models showed consistent but element-specific predictive performance. The values of R² ranged from 0.76 to 0.89, with the highest values for Pb and As and the lowest for Cu. Spatial predictions should be interpreted with consideration of the irregular sampling design and inherent uncertainties in spatial extrapolation. Mean concentrations of Zn, Pb, Cu, As, and Cd reached 1347.87, 439.91, 201.71, 90.69, and 4.27 mg kg⁻¹, respectively, exceeding both regulatory thresholds and local geochemical background values. Contamination indices revealed marked enrichment, particularly for As and Cd. Ecological risk was primarily driven by Cd and As, with 70.10% and 61.41% of samples classified as very high ecological risk for these elements, respectively. The comprehensive potential ecological risk index indicated a critical scenario with 71.7% of samples exceeding the very high-risk threshold. Human health risk assessment identified As as the main contributor to both non-carcinogenic and carcinogenic risks, with children showing higher vulnerability than adults. These findings delineate priority agricultural areas where ecological risk and arsenic-related carcinogenic risk overlap, underscoring the urgent need for targeted soil monitoring, exposure reduction, and locally adapted risk management strategies in the Mantaro Valley.
Variability in Fruit Production of Carapa Guianensis Associated with Edaphoclimatic Factors in the Amazon
(Preprints.org (MDPI), 2025-12-17) Angulo Villacorta, Carlos Darwin; Silva da Conceição, Denilson; Chuchon Remon, Rodolfo Juan; Manigat, Donald; Antunez Jimenez, Lorena; de Toledo, José Julio
Carapa guianensis Aubl., widely distributed throughout the Amazon, is recognized for its ecological, economic, and social importance, and constitutes a key source of income for numerous extractive communities. However, fruit production exhibits marked spatial variation that may be influenced by soil properties and climatic factors. In this study, we assessed this variability using data from 21 studies conducted in the Brazilian Amazon, incorporating georeferenced information from each site on climate and soil characteristics. Environmental variables were evaluated using Random Forest models. Average fruit productivity showed a broad range (0.34 to 34.6 kg·tree⁻¹·year⁻¹), with higher values in várzea forests (16.5 kg·tree⁻¹·year⁻¹) and lower values in igapó forests (2.5 kg·tree⁻¹·year⁻¹). The model explained 42% of the observed variability (R² = 0.83 in cross-validation), identifying soil organic carbon, mean annual temperature, and clay content as the most influential predictors. These findings demonstrate that fruit production is shaped by the interaction between edaphic and climatic conditions, which determine the species' productivity patterns, and highlight the need to foster adaptive management strategies that ensure the sustainable use of andiroba across Amazonian ecosystems.