Colombian soil texture: building a spatial ensemble model

Abstract

Abstract. Texture is a fundamental soil property for multiple applications in environmental and earth sciences. Knowing its spatial distribution allows a better understanding of the response of soil conditions to changes in the environment, such as land use. This paper describes the technical development of Colombia's first texture maps, obtained via a spatial ensemble of national and global digital soil mapping products. This work compiles a new database with 4203 soil profiles, which were harmonized at five standard depths (0–5, 5–15, 15–30, 30–60, and 60–100 cm) and standardized with additive log ratio (ALR) transformation. A compilation of 83 covariates was developed and harmonized at 1 km2 of spatial resolution. Ensemble machine learning (EML) algorithms (MACHISPLIN and landmap) were trained to predict the distribution of soil particle size fractions (PSFs) (clay, sand, and silt), and a comparison with SoilGrids (SG) products was performed. Finally, a spatial ensemble function was created to identify the smallest prediction errors between EML and SG. Our results are the first effort to build a national texture map (clay, sand, and silt fractions) based on digital soil mapping in Colombia. The results of EML algorithms showed that their accuracies were very similar at each standard depth, and were more accurate than SG. The largest improvement with the spatial ensemble was found at the first layer (0–5 cm). EML predictions were frequently selected for each PSF and depth in the total area; however, SG predictions were better when increasing soil depth in some specific regions. The final error distribution in the study area showed that sand presented higher absolute error values than clay and silt fractions, specifically in eastern Colombia. The spatial distribution of soil texture in Colombia is a potential tool to provide information for water-related applications, ecosystem services, and agricultural and crop modeling. However, future efforts need to improve aspects such as treating abrupt changes in the texture between depths and unbalanced data. Our results and the compiled database (https://doi.org/10.6073/pasta/3f91778c2f6ad46c3cc70b61f02532db, Varón-Ramírez and Araujo-Carrillo, 2022, https://doi.org/10.6073/pasta/d6c0bf5847aa40836b42dcc3e0ea874e, Varón-Ramírez et al., 2022) provide new insights to solve some of the aforementioned issues.

Índice de calidad nutricional en suelos cacaoteros de la subregión cordillera de Nariño

“…Predecir el estado actual de los parámetros químicos del suelo, en áreas sin datos disponibles, permite obtener mapas de distribución espacial e identificar áreas con mayor y menor aptitud nutricional para diferentes cultivos (Chinea-Horta y Rodríguez-Izquierdo, 2021). El mapeo digital del suelo [MDS] utiliza covariables ambientales asociadas a factores formadores del suelo, como la precipitación, temperatura, radiación solar, relieve, cobertura del suelo, entre otras, para predecir la distribución de propiedades del suelo (Food and Agriculture Organization [FAO], 2022;Varón-Ramírez et al, 2022). Estas covariables están asociadas a los factores de formación de los suelos y pueden provenir de sensores remotos, análisis digital del terreno, clima o mapas temáticos (Grunwald et al, 2011).…”

Improving the Latin America and Caribbean Soil Information System (SISLAC) database enhances its usability and scalability

“…Soil data are an essential starting point to reach an adequate level of knowledge about soil status, raise awareness about its importance, and preserve this valuable resource (Bouma et al, 2012). Digital soil data (such as soil profiles) are in great demand as inputs to, for example, estimate the potential of agricultural land (Amirinejad et al, 2011;Bini et al, 2013;Owusu et al, 2020); in addition, their availability is key to assessing soil functions such as water and climate regulation, energy supply, and biodiversity (Greiner et al, 2017;Varón-Ramírez et al, 2022). Greater diffusion of soil information has substantial benefits in disciplines such as agricultural sciences because it allows for better estimation of current and future crop productivity or the identification of constraints and risks of land degradation (FAO and IIASA, 2009;Hopmans et al, 2021;Paterson et al, 2015).…”

BIS-4D: Mapping soil properties and their uncertainties at 25 m resolution in the Netherlands

“…In order to achieve this, soil texture can be spatially interpolated as a compositional variable using geostatistical models(Odeh et al, 2003;Lark and Bishop, 2007;Wang and Shi, 2017), e.g. compositional kriging(de Gruijter et al, 1997;Walvoort and de Gruijter, 2001), machine learning(Akpa et al, 2014;Amirian-Chakan et al, 2019;Poggio and Gimona, 2017;Poggio et al, 2021;Malone et al, 2021;Varón-Ramírez et al, 2022), and other techniques(Buchanan et al, 2012;Román Dobarco et al, 2017). Most commonly, these studies used the additive log-ratio transforma-…”