Exploring soil property spatial patterns in a small grazed catchment using machine learning

Simple item page
dc.contributor.authorBarrena-Gonzalez, Jesus
dc.contributor.authorGabourel-Landaverde, V. Anthony
dc.contributor.authorMora, Jorge
dc.contributor.authorContador, J. Francisco Lavado
dc.contributor.authorFernandez, Manuel Pulido
dc.date.accessioned2025-01-20T17:27:46Z
dc.date.available2025-01-20T17:27:46Z
dc.date.issued2023
dc.description.abstractAcquiring comprehensive insights into soil properties at various spatial scales is paramount for effective land management, especially within small catchment areas that often serve as vital pastured landscapes. These regions, characterized by the intricate interplay of agroforestry systems and livestock grazing, face a pressing challenge: mitigating soil degradation while optimizing land productivity. This study aimed to analyze the spatial distribution of eight topsoil (0-5 cm) properties (clay, silt, sand, pH, cation exchange capacity, available potassium, total nitrogen, and soil organic matter) in a small grazed catchment. Four machine learning algorithms-Random Forest (RF), Support Vector Machines (SVM), Cubist, and K-Nearest Neighbors (kNN)-were used. The Boruta algorithm was employed to reduce the dimensionality of environmental covariates. The model's accuracy was assessed using the Concordance Correlation Coefficient (CCC) and Root Mean Square Error (RMSE). Additionally, uncertainty in predicted maps was quantified and assessed. The results revealed variations in predictive model performance for soil properties. Specifically, kNN excelled for clay, silt, and sand content, while RF performed well for soil pH, CEC, and TN. Cubist and SVM achieved accuracy in predicting AK and SOM, respectively. Clay, silt, CEC, and TN yielded favourable predictions, closely aligning with observations. Conversely, sand content, soil pH, AK, and SOM predictions were slightly less accurate, highlighting areas for improvement. Boruta algorithm streamlined covariate selection, reducing 23 covariates to 10 for clay and 4 for soil pH and AK prediction, enhancing model efficiency. Our study revealed spatial uncertainty patterns mirroring property distributions, with higher uncertainty in areas with elevated content. Model accuracy varied by confidence levels, performing best at intermediate levels and showing increased uncertainty at extremes. These findings offer insights into model capabilities and guide future research in soil property prediction. In conclusion, these results urge more research in small watersheds for soil and territorial management.
dc.fuente.origenWOS
dc.identifier.doi10.1007/s12145-023-01125-1
dc.identifier.eissn1865-0481
dc.identifier.issn1865-0473
dc.identifier.urihttps://doi.org/10.1007/s12145-023-01125-1
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/91574
dc.identifier.wosidWOS:001087919700001
dc.issue.numero4
dc.language.isoen
dc.pagina.final3838
dc.pagina.inicio3811
dc.revistaEarth science informatics
dc.rightsacceso restringido
dc.subjectEnvironmental covariate reduction
dc.subjectPredictive modelling
dc.subjectSpatial variability
dc.subjectUncertainty assessment
dc.subject.ods02 Zero Hunger
dc.subject.odspa02 Hambre cero
dc.titleExploring soil property spatial patterns in a small grazed catchment using machine learning
dc.typeartículo
dc.volumen16
sipa.indexWOS
sipa.trazabilidadWOS;2025-01-12
Files
Collections
Artículos de revistas