Modelización espacial de propiedades edáficas con Random Forest: aplicación al Parque Natural los Alcornocales (Andalucía, sur de España)

José Antonio Ortega-Pino; José Antonio Sillero-Medina; Paloma Hueso-González; José Damián Ruiz-Sinoga

doi:10.18172/cig.7283

Authors

José Antonio Ortega-Pino Universidad de Málaga
José Antonio Sillero-Medina Universidad de Málaga https://orcid.org/0000-0002-7856-3239
Paloma Hueso-González Universidad de Málaga https://orcid.org/0000-0002-2554-0041
José Damián Ruiz-Sinoga Universidad de Málaga https://orcid.org/0000-0001-5716-3837

DOI:

https://doi.org/10.18172/cig.7283

Keywords:

Soil, Digital soil mapping, modelling, Random Forest , Mediterranean ecosystem

Abstract

Soil is a key component for sustaining life and maintaining ecosystem balance, as it provides nutrients and participates in essential processes such as the water cycle and carbon sequestration. Therefore, assessing its condition and promoting its conservation have become priorities in the context of climate change. One of the main challenges in soil management is its spatial representation, as the heterogeneity of soil properties and environmental variability hinder an accurate characterization of the territory. This challenge is particularly relevant because precise spatial representation enables the identification of distribution patterns, vulnerable areas, and zones of high environmental quality, thereby supporting informed decision-making. In this context, the main objective of this study is to characterize the soils of Los Alcornocales Natural Park (Andalusia, southern Spain) from a physical, organic, and hydrological perspective using advanced spatial modelling techniques. To this end, the Random Forest (RF) algorithm, based on decision trees, was employed. This algorithm allows the integration of multiple environmental variables and enhances the accuracy of the results. The modelling approach was based on the analysis of 461 soil samples (0–10 cm depth), and validation was conducted using a dual approach: external validation with 10% of the data as an independent dataset, and the internal Out-of-Bag (OOB) validation inherent to the RF algorithm. Error and accuracy metrics demonstrated the robustness of the RF model for predictive mapping in a natural park characterized by high eco-geomorphological heterogeneity (CC, R² = 0.937; Factor K, R² 0.935; COS, R² = 0.918). The results indicated that biotic factors, derived from spectral data, play a determining role in the spatial distribution of the analysed soil indicators (organic carbon, water retention capacity, and soil erodibility). This information constitutes a key tool for guiding land-use planning and sustainable management, with high potential for application in other similar Mediterranean contexts.

Downloads

Download data is not yet available.

Author Biographies

José Antonio Ortega-Pino, Universidad de Málaga

Instituto de Hábitat, Territorio y Digitalización. Universidad de Málaga. España

Paloma Hueso-González, Universidad de Málaga

Instituto de Hábitat, Territorio y Digitalización. Departamento de Geografía. Universidad de Málaga. España

José Damián Ruiz-Sinoga, Universidad de Málaga

Instituto de Hábitat, Territorio y Digitalización. Departamento de Geografía. Universidad de Málaga. España

References

AEMET. Agencia Estatal de Meteorología (2024). Mapas climáticos de España (1991–2020) y ETo (1996–2020). Ministerio para la Transición Ecológica y el Reto Demográfico.

Alaminos-Fernández, A. (2022). Árboles de decisión en R con Random Forest. Limencop, 2022. https://hdl.handle.net/10045/133067

Armas, D., Guevara, M., Alcaraz-Segura, D., Vargas, R., Soriano-Luna, M.A., Durante, P., Oyonarte, C. (2017). Mapa digital del perfil del carbono orgánico en los suelos de Andalucía, España. Ecosistemas, 26(3), 80–88. https://doi.org/10.7818/ECOS.2017.26-3.10 DOI: https://doi.org/10.7818/ECOS.2017.26-3.10

Belgiu, M., Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31. https://doi.org/10.1016/j.isprsjprs.2016.01.011 DOI: https://doi.org/10.1016/j.isprsjprs.2016.01.011

Blanco Bernardeau, A., Alonso-Sarria, F., Gomáriz-Castillo, F.G. (2014). Elaboración de un mapa de carbono orgánico del suelo en la Región de Murcia. In: Tecnologías de la información para nuevas formas de ver el territorio: XVI Congreso Nacional de Tecnologías de la Información Geográfica (pp. 284–292). https://doi.org/10.13140/2.1.2817.0568

Breiman, L. (2001). Random forests. Machine learning. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 DOI: https://doi.org/10.1023/A:1010933404324

Bünemann, E.K., Bongiorno, G., Bai, Z., Creamer, R.E., De Deyn, G., de Goede, R., Fleskens, L., Geissen, V., Kuyper, T.W., Mäder, P., Pulleman, M., Sukkel, W., van Groenigen, J.W., Brussaard, L. (2018). Soil quality – A critical review. Soil Biology and Biochemistry, 120, 105–125. https://doi.org/10.1016/j.soilbio.2018.01.030 DOI: https://doi.org/10.1016/j.soilbio.2018.01.030

Cassel, D.K., Nielsen, D.R. (1986). Field capacity and available water capacity. In A. Klute (Ed.), Methods of Soil Analysis. Part 1. Physical and Mineralogical Methods (2nd ed., Agronomy Monograph No. 9, pp. 901–926). American Society of Agronomy / Soil Science Society of America. https://doi.org/10.2136/sssabookser5.1.2ed.c36 DOI: https://doi.org/10.2136/sssabookser5.1.2ed.c36

De Caires, S.A., St Martin, C., Atwell, M.A., Kaya, F., Wuddivira, G.A., Wuddivira, M.N. (2025). Advancing soil mapping and management using geostatistics and integrated machine learning and remote sensing techniques: a synoptic review. Discover Soil., 2(1). https://doi.org/10.1007/s44378-025-00082-z DOI: https://doi.org/10.1007/s44378-025-00082-z

Dragović, N., Vulević, T. (2021). Procesos de degradación del suelo, causas y enfoques de evaluación. En: Leal Filho, W., Azul, A.M., Brandli, L., Lange Salvia, A., Wall, T. (eds.) Vida en la tierra. Enciclopedia de los Objetivos de Desarrollo Sostenible de la ONU. Springer, Cham. https://doi.org/10.1007/978-3-319-95981-8_86 DOI: https://doi.org/10.1007/978-3-319-95981-8_86

Durán-Sandoval, D., Uleri, F., Durán-Romero, G., López, A.M. (2023). Food, Climate Change, and the Challenge of Innovation. Encyclopedia, 3(3): 839–852. https://doi.org/10.3390/encyclopedia3030060. DOI: https://doi.org/10.3390/encyclopedia3030060

Esri. (2024). ArcGIS Pro 3.4 [Software]-

Gaitan, J., Navarro, M.F., Tenti, L., Carfagno, P., Pizarro, M.J., Rigo, S. (2017). Estimación de la pérdida de suelo por erosión hídrica en la República Argentina. INTA. https://www.researchgate.net/publication/321758306

Guitián, F., Carballas, T. (1976). Técnicas de análisis de suelos. Pico Sacro, Santiago de Compostela.

Gutiérrez-Mas, J.M., Gracia Prieto, J., Luján Martínez, M., Sánchez Bellón, Á. (2016). Geología del Campo de Gibraltar. En Geología 16: Geolodía Cádiz. Universidad de Cádiz; Ilustre Colegio Oficial de Geólogos de Andalucía.

Helfenstein, A., Mulder, V.L., Hack-ten Broeke, M.J.D., van Doorn, M., Teuling, K., Walvoort, D.J.J., Heuvelink, G.B.M. (2024). BIS-4D: Mapping soil properties and their uncertainties at 25 m resolution in the Netherlands. Earth System Science Data, 16(6), 2941–2970. https://doi.org/10.5194/essd-16-2941-2024 DOI: https://doi.org/10.5194/essd-16-2941-2024

Heung, B., Bulmer, C.E., Schmidt, M.G. (2014). Predictive soil parent material mapping at a regional-scale: A Random Forest approach. Geoderma, 214–215, 141–154. https://doi.org/10.1016/j.geoderma.2013.09.016 DOI: https://doi.org/10.1016/j.geoderma.2013.09.016

IGME. Instituto Geologico y Minero de España (2003). MAGNA 50 - Mapa Geológico de España a escala 1:50.000 (2ª Serie).

IUSS Working Group WRB. (2022). World reference base for soil resources. International soil classification system for naming soils and creating legends for soil maps (4th ed.). International Union of Soil Sciences (IUSS).

Jeong, M., Koo, H. (2025). Evaluating Spatio-Temporal Kriging with Machine Learning Considering the Sources of Spatio-Temporal Variation. ISPRS International Journal of Geo-Information, 14(6), 224. https://doi.org/10.3390/ijgi14060224 DOI: https://doi.org/10.3390/ijgi14060224

López-Senespleda, E., Calama Sainz, R.A., Menéndez-Miguélez, M., del Río, M., Montero, G., Ruiz-Peinado, R. (2022). Estimación del carbono acumulado en la capa orgánica del suelo de las masas forestales en la España peninsular y Baleares. In: La Ciencia Forestal y su contribución a los Objetivos de Desarrollo Sostenible, 8ª Congreso Forestal Español. Sociedad Española de Ciencias Forestales. http://hdl.handle.net/10261/279824

Marañés Corbacho, A., Sánchez Garrido, J.A., De Haro Lozaño, S., Sánchez Gomez, S.T., Lozano Cantarero, F.J. (1994). Análisis de suelo, metodología e interpretación. Servicio de Publicaciones de la Universidad de Almería.

McBratney, A., Santos, M.M., Minasny, B. (2003). On digital soil mapping. Geoderma, 117(1-2), 3-52. https://doi.org/10.1016/s0016-7061(03)00223-4 DOI: https://doi.org/10.1016/S0016-7061(03)00223-4

McBratney, A., Field, D.J., Koch, A. (2014). The dimensions of soil security. Geoderma, 213, 203–213. https://doi.org/10.1016/j.geoderma.2013.08.013 DOI: https://doi.org/10.1016/j.geoderma.2013.08.013

Mesele, S.A., Mechri, M., Okon, M.A., Isimikalu, T.O., Wassif, O.M., Asamoah, E., Ahmad, H.A., Moepi, P.I., Gabasawa, A.I., Bello, S.K., Ayamba, B.E., Owonubi, A., Olayiwola, V.A., Soremi, P.A.S., Khurshid, C. (2025). Current Problems Leading to Soil Degradation in Africa: Raising Awareness and Finding Potential Solutions. European Journal Of Soil Science, 76(1). https://doi.org/10.1111/ejss.70069 DOI: https://doi.org/10.1111/ejss.70069

Minasny, B., McBratney, A.B. (2016). Digital soil mapping: A brief history and some lessons. Geoderma, 264(Part B), 301–311. https://doi.org/10.1016/j.geoderma.2015.07.017 DOI: https://doi.org/10.1016/j.geoderma.2015.07.017

Morgan, R.P.C., Nearing, M.A. (Eds.). (2011). Handbook of erosion modelling. Wiley-Blackwell. DOI: https://doi.org/10.1002/9781444328455

Nolet, C., Carranza, C., Pezij, M., van der Ploeg, M. (2021). Root zone soil moisture estimation with Random Forest. Journal of Hydrology, 593, 125840. https://doi.org/10.1016/j.jhydrol.2020.125840 DOI: https://doi.org/10.1016/j.jhydrol.2020.125840

Panagea, I.S., Berti, A., Čermak, P., Diels, J., Elsen, A., Kusá, H., Piccoli, I., Poesen, J., Stoate, C., Tits, M., Toth, Z., Wyseure, G. (2021). Soil water retention as affected by management induced changes of soil organic carbon: Analysis of long-term experiments in Europe. Land, 10(12). https://doi.org/10.3390/land10121362 DOI: https://doi.org/10.3390/land10121362

Pérez-De-Los-Reyes, A.C., Pérez-De-Los-Reyes, M.L., Chocano, D., Sánchez-Ormeño, M., Bravo, S., Ángel, J.A., García, N.F.J. (2018). Estudio de las propiedades de retención de humedad de suelos vitícolas en Castilla-La Mancha (España). E3S Web Of Conferences, 50, 01034. https://doi.org/10.1051/e3sconf/20185001034 DOI: https://doi.org/10.1051/e3sconf/20185001034

Peri, P.L., Gaitán, J., Mastrangelo, M., Nosetto, M., Villagra, P.E., Balducci, E., Pinazo, M., Eclesia, R.P., Von Wallis, A., Villarino, S., Alaggia, F., Polo, M.G., Manrique, S., Meglioli, P.A., Rodríguez-Souilla, J., Mónaco, M., Chaves, J.E., Medina, A., Gasparri, I., Pastur, G.M. (2024). Soil organic carbon stocks in native forest of Argentina: a useful surrogate for mitigation and conservation planning under climate variability. Ecological Processes, 13(1), 1. https://doi.org/10.1186/s13717-023-00474-5 DOI: https://doi.org/10.1186/s13717-023-00474-5

Pouladi, N., Møller, A.B., Tabatabai, S., Greve, M.H. (2019). Mapping soil organic matter contents at field level with Cubist, Random Forest and kriging. Geoderma, 342, 85–92. https://doi.org/10.1016/j.geoderma.2019.02.019 DOI: https://doi.org/10.1016/j.geoderma.2019.02.019

Ren, T., Cai, A. (2025). Global patterns and drivers of soil dissolved organic carbon concentrations. Earth Syst. Sci. Data, 17, 2873–2885, https://doi.org/10.5194/essd-17-2873-2025 DOI: https://doi.org/10.5194/essd-17-2873-2025

Rivas-Martínez, S. (1987). Memoria del Mapa de Series de Vegetación de España. Escala 1:400.000. Instituto para la Conservación de la Naturaleza (ICONA), Ministerio de Agricultura.

Rubio, A.M. (2010). La densidad aparente en suelos forestales del Parque Natural Los Alcornocales. Proyecto Fin de Carrera. https://digital.csic.es/handle/10261/57951

Ruiz-Sinoga, J.D., Romero-Diaz, A. (2010). Soil degradation factors along a Mediterranean pluviometric gradient in Southern Spain. Geomorphology, 118(3–4), 359–368. https://doi.org/10.1016/j.geomorph.2010.02.003 DOI: https://doi.org/10.1016/j.geomorph.2010.02.003

Sharpley, N.A., Williams, R.J. (1990). EPIC—Erosion/Productivity Impact Calculator I: Model documentation. U.S. Department of Agriculture, Technical Bulletin. Beltsville, MD, United States.

Sillero-Medina, J.A., Pérez-González, M.E., Martínez-Murillo, J.F., Ruiz-Sinoga, J.D. (2020). Factors affecting eco-geomorphological dynamics in two contrasting Mediterranean environments. Geomorphology, 352, 106996. https://doi.org/10.1016/j.geomorph.2019.106996 DOI: https://doi.org/10.1016/j.geomorph.2019.106996

Sillero-Medina, J.A., Hueso-González, P., Ruiz-Sinoga, J.D. (2020b). Differences in the Soil Quality Index for Two Contrasting Mediterranean Landscapes in Southern Spain. Land, 9(11), 405. https://doi.org/10.3390/land9110405 DOI: https://doi.org/10.3390/land9110405

Sillero-Medina, J.A., Rodrigo-Comino, J. Ruiz-Sinoga, J.D. (2021) Factors determining the soil available water during the last two decades (1997–2019) in southern Spain. Arab J Geosci, 14, 1971. https://doi.org/10.1007/s12517-021-08265-y DOI: https://doi.org/10.1007/s12517-021-08265-y

Sillero-Medina, J.A. (2022). Repercusiones eco-geomorfológicas de la dinámica paisajística reciente, en ambientes mediterráneos contrastados. [Tesis doctoral, Universidad de Málaga]. http://hdl.handle.net/10630/24375

Subburayalu, S.K., Slater, B.K. (2013). Soil Series Mapping by Knowledge Discovery from an Ohio County Soil Map. Soil Science Society of America Journal, 77(4), 1254-1268. https://doi.org/10.2136/sssaj2012.0321 DOI: https://doi.org/10.2136/sssaj2012.0321

Szabó, B., Szatmári, G., Takács, K., Laborczi, A., Makó, A., Rajkai, K., Pásztor, L. (2019). Mapping soil hydraulic properties using random-forest-based pedotransfer functions and geostatistics, Hydrol. Earth Syst. Sci., 23, 2615–2635, https://doi.org/10.5194/hess-23-2615-2019. DOI: https://doi.org/10.5194/hess-23-2615-2019

Tamara Polo, L.A., Ducuara, J. (2016). Capacidad de campo y punto de marchitez permanente. [Informe de prácticas, Universidad de Sucre].

Tian, Z., Liu, F., Liang, Y., Zhu, X. (2022). Mapping soil erodibility in southeast China at 250 m resolution: Using environmental variables and random forest regression with limited samples. International Soil and Water Conservation Research, 10(1), 62-74. https://doi.org/10.1016/j.iswcr.2021.06.005 DOI: https://doi.org/10.1016/j.iswcr.2021.06.005

Townend, J., Reeve, M.J., Carter, A. (2001). Water release characteristic. In K. A. Smith and C. E. Mullins (Eds.), Soil and Environmental Analysis: Physical Methods (2nd ed., pp. 107–152). CRC Press / Marcel Dekker. https://doi.org/10.1201/9780203908600-8 DOI: https://doi.org/10.1201/9780203908600.ch3

Trinco, F.D., Zeraatpisheh, M., Turner, H.C., El Mujtar, V., Tittonell, P.A., Galford, G.L. (2025). High-resolution soil organic carbon mapping for enhancing predictive accuracy of environmental drivers in heterogeneous and mountainous landscapes in Patagonia. Catena, 259, 109353. https://doi.org/10.1016/j.catena.2025.109353 DOI: https://doi.org/10.1016/j.catena.2025.109353

Valera, A. (2023). Técnicas de cartografía digital para la evaluación del carbono orgánico del suelo. Digital Mapping Techniques for Soil Organic Carbon Assessment. In: XXIII Congreso Venezolano de la Ciencia del Suelo, pp. 274-282. https://doi.org/10.13141/RG.2.2.36528.02668

Varvaris, I., Pittaki, Z., Themistokleous, G., Koumoulidis, D., Ouerfelli, D., Eliades, M., Themistocleous, K., Hadjimitsis, D. (2025). Remote Sensing-Based Mapping of Soil Health Descriptors Across Cyprus. Environments, 12(8), 283. https://doi.org/10.3390/environments12080283 DOI: https://doi.org/10.3390/environments12080283

Wadoux, A.M., Minasny, B., McBratney, A.B. (2020). Machine learning for digital soil mapping: Applications, challenges and suggested solutions. Earth-Science Reviews, 210, 103359. https://doi.org/10.1016/j.earscirev.2020.103359 DOI: https://doi.org/10.1016/j.earscirev.2020.103359

Wang, B., Waters, C., Orgill, S., Cowie, A., Clark, A., Li Liu, D., Simpson, M., McGowen, I., Sides, T. (2018). Estimating soil organic carbon stocks using different modelling techniques in the semi-arid rangelands of eastern Australia. Ecological Indicators, 88, 425–438. https://doi.org/10.1016/j.ecolind.2018.01.049 DOI: https://doi.org/10.1016/j.ecolind.2018.01.049

Worsham, L., Markewitz, D., Nibbelink, N. (2010). Incorporating Spatial Dependence into Estimates of Soil Carbon Contents under Different Land Covers. Soil Science Society of America Journal, 74(2), 635-646. https://doi.org/10.2136/sssaj2008.0412 DOI: https://doi.org/10.2136/sssaj2008.0412

Yang, R.-M., Zhang, G.-L., Liu, F., Lu, Y.-Y., Yang, F., Yang, F., Yang, M., Zhao, Y.-G., Li, D.-C. (2016). Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem. Ecological Indicators, 60, 870–878. https://doi.org/10.1016/j.ecolind.2015.08.036 DOI: https://doi.org/10.1016/j.ecolind.2015.08.036

Zeraatpisheh, M., Ayoubi, S., Jafari, A., Tajik, S., Finke, P. (2019). Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma, 338, 445–452. https://doi.org/10.1016/j.geoderma.2018.09.006 DOI: https://doi.org/10.1016/j.geoderma.2018.09.006

Zhu, C., Wei, Y., Zhu, F., Lu, W., Fang, Z., Li, Z., Pan, J. (2022). Digital Mapping of Soil Organic Carbon Based on Machine Learning and Regression Kriging. Sensors, 22(22), 8997. https://doi.org/10.3390/s22228997 DOI: https://doi.org/10.3390/s22228997