Indian Journal of Agricultural Research

Indian Journal of Agricultural Research cover
Volume 60 · Issue 6 · 2026/04/29

Modelling Soil Organic Carbon Across a Rugged Altitudinal Gradient in Drylands: A Machine Learning Approach Using Multi-Source Covariates

Tumuzghi Tesfay
Nazih Y. Rebouh
Dmitry E. Kucher
Balwan Singh
Elsayed S. Mohamed
Igor Yu. Savin
169 Views

Submitted

2026/02/17

First Online

2026/04/29

doi

10.18805/IJARe.AF-1030

Cite article - Tumuzghi Tesfay, Nazih Y. Rebouh, Dmitry E. Kucher, Balwan Singh, Elsayed S. Mohamed, Igor Yu. Savin. (2026). Modelling Soil Organic Carbon Across a Rugged Altitudinal Gradient in Drylands: A Machine Learning Approach Using Multi-Source Covariates. Indian Journal of Agricultural Research. 60(6): 926–935. doi: 10.18805/IJARe.AF-1030

Abstract

Background: Soil organic carbon (SOC) is essential for soil health, food security and climate change mitigation. However, reliable data on SOC distribution and its environmental drivers remain limited in data-scarce dryland regions like Eritrea. This hinders effective soil management and restoration planning.

Methods: SOC modelling was conducted across an altitudinal gradient landscape using environmental covariates and machine learning. Three predictor sets (46, 28 and 11 variables) were used selected through three approaches: 1) no selection, 2) removal of highly collinear (r≥0.90) and non-significant variables and 3) boruta algorithm-based selection. The predictive performance of cubist, random forest (RF) and partial least squares (PLS) algorithms were evaluated.

Result: SOC levels across the study area were generally low (mean = 0.71%). Rainfed croplands and communal grazing areas showed particularly depleted SOC, attributed to unsustainable land management, while forest and irrigated systems retained significantly higher SOC, indicating greater carbon sequestration potential. The Cubist model with 46 predictors performed best (R² = 0.7465, RPD = 2.0895), whereas PLS with 11 variables had the lowest accuracy (R² = 0.5930, RPD = 1.6491). Temperature emerged as the strongest predictor, followed by land use, altitude, Soil Organic Carbon Index, Landsat 8 band B10 and rainfall. The dominance of temperature for SOC prediction was supported by the strong negative correlation of SOC with temperature (r = -0.582) and positive with altitude (r = 0.580). These underscore the role of climate on the spatial-temporal dynamics of SOC and highlight for climate-smart strategies. Thus, we conclude that cost-effective assessments and monitoring of SOC that support evidence-based strategies for enhancing soil health, land restoration and climate resilience are possible through the developed Cubist and RF models from the Eritrean Central Highlands to the Western Midlands and similar environments.

References

  1. Abdellatif, M.A., Hassan, F.O., Rashed, H.S.A., El Baroudy, A.A., Mohamed, E.S. et al . (2023). Assessing soil organic carbon pool for potential climate-change mitigation in agricultural soils: A case study fayoum depression, Egypt. Land . 12(9): 1755. https://doi.org/10.3390/land12091755. Ayala, I.J.E., Márquez, C.O., García, V.J., Jara, S.C.A., Sisti, J.M. et al . (2021). Multi-predictor mapping of soil organic carbon in the alpine tundra: A case study for the central Ecuadorian páramo. Carbon Balance and Management . 16(1): 1-19. https://doi.org/10.1186/s13021-021-00195-2. Chen, D., Yu, M., González, G. and Gao, Q. (2023). Altitudinal Pattern of Soil Organic Carbon and Nutrients in a Tropical Forest in Puerto Rico. In Neotropical Gradients and their Analysis. https://doi.org/10.1007/978-3-031-22848-3_12. Chen, Q., Wang, Y. and Zhu, X. (2024). Soil organic carbon estimation using remote sensing data-driven machine learning. Peer J. 12(8). https://doi.org/10.7717/peerj.17836. Devine, S.M., O’Geen, A.T., Liu, H., Jin, Y., Dahlke, H.E., Larsen, R.E. and Dahlgren, R.A. (2020). Terrain attributes and forage productivity predict catchment-scale soil organic carbon stocks. Geoderma . 368. https://doi.org/10.1016/j.geoderma.2020.114286. FAO. (2021). National Agricultural Innovation System Assessment in Eritrea-Consolidated Report. Rome, Italy https://doi.org/ 10.4060/cb7296en. FAO. (2017). Soil Organic Carbon: The Hidden Potential (A.V.B.R.V.R. Wiese Liesl, Ed.). Food and Agriculture Organization of the United Nations, Rome, Italy. FAO. (2019). Standard Operating Procedure for Soil Organic Carbon: Walkley-Black method: Titration and Colorimetric Method (1 st ed.). Global Soil Laboratory Network GLOSOLAN, Rome, Italy, 2019. Fick, S.E. and Hijmans, R.J. (2017). WorldClim 2: New 1-km spatial resolution climate surfaces for global land areas. International Journal of Climatology . 37(12): 4302-4315. https://doi.org/10.1002/joc.5086. Galluzzi, G., Plaza, C., Priori, S., Giannetta, B. and Zaccone, C. (2024). Soil organic matter dynamics and stability: Climate vs. time. Science of The Total Environment . 929: 172441. https://doi.org/10.1016/j.scitotenv.2024.172441. Ghebrezgabher, M.G., Yang, T., Yang, X. and Wang, C. (2019). Assessment of desertification in Eritrea: Land degradation based on landsat images. Journal of Arid Land . 11(3). https://doi.org/10.1007/s40333-019-0096-4. Haile, B.T., Ramoelo, A., Dougill, A.J. and Qabaqaba, M. (2025). Land use/land cover (LULC) change and irrigated area monitoring in eritrea: Insights into horticultural production and sustainability. Remote Sensing in Earth Systems Sciences . https://doi.org/10.1007/s41976-025-00247-y. Hoang, T.V.H. (2024). Land use practices effects on soil organic carbon and nitrogen in North-central Vietnam. Agricultural Science Digest . doi: 10.18805/ag.DF-623 . Hosseinpour-Zarnaq, M., Moshiri, F., Jamshidi, M., Taghizadeh-Mehrjardi, R., Tehrani, M. et al . (2024). Monitoring changes in soil organic carbon using satellite-based variables and machine learning algorithms in arid and semi-arid regions. Environmental Earth Sciences . 83(20). https://doi.org/10.1007/s12665-024-11876-9. Jendoubi, D., Liniger, H. and Speranza, C.I. (2025). Impacts of Land Use and Topography on Soil Organic Carbon in a Mediterranean Landscape (North-Western Tunisia). https://doi.org/http://dx.doi.org/10.5194/soil-5-239-2019. Malla, R., Neupane, P.R. and Köhl, M. (2022). Modelling soil organic carbon as a function of topography and stand variables. Forests . 13(9). https://doi.org/10.3390/f13091391. Meliho, M., Boulmane, M., Khattabi, A., Dansou, C.E., Orlando, C.A. et al . (2023). Spatial prediction of soil organic carbon stock in the moroccan high atlas using machine learning. Remote Sensing. 15(10). https://doi.org/10.3390/rs15102494. MoA. (2018). National Land Degradation Neutrality Targets, Ministry of Agriculture, (MoA) Asmara, Eritrea. Mohamed, E.S., Saleh, A.M., Belal, A.B. and Gad, A.A. (2018). Application of Near-Infrared Reflectance for Quantitative Assessment of Soil Properties. In Egyptian Journal of Remote Sensing and Space Science . 21(1). https://doi.org/10.1016/j.ejrs.2017.02.001. Nuguse, M.T., Singh, B. and Ogbazghi, W. (2019). Studies on soil organic carbon and some physico-chemical properties as affected by different land uses in Eritrea. Journal of Soil and Water Conservation . 18(3): 213. https://doi.org/10.5958/2455-7145.2019.00030.4. Page, K.L., Dang, Y.P. and Dalal, R.C. (2020). The Ability of Conservation Agriculture to Conserve Soil Organic Carbon and the Subsequent Impact on Soil Physical, Chemical and Biological Properties and Yield. In Frontiers in Sustainable Food Systems . 4. https://doi.org/10.3389/fsufs.2020.00031. Pellikka, P., Luotamo, M., Sädekoski, N., Hietanen, J., Vuorinne, I. et al . (2023). Tropical altitudinal gradient soil organic carbon and nitrogen estimation using Specim IQ portable imaging spectrometer. Science of The Total Environment . 883: 163677. https://doi.org/10.1016/j.scitotenv.2023.163677. Prabakaran, S., Kaleeswari, R.K., Backiyavathy, M.R., Jagadeeswaran, R., Selvi, R.G. and Bama, K.S. (2023). Soil carbon stock and carbon pool indices under major land use systems of Mayiladuthurai District, Cauvery Delta Zone, India. Agricultural Science Digest . doi: 10.18805/ag.D-5786 . Shen, C., Xiao, W., Chen, J., Hua, L. and Huang, Z. (2023). Climate- sensitive spatial variability of soil organic carbon in multiple forests, Central China. Global Ecology and Conservation . 46: e02555. https://doi.org/10.1016/j.gecco.2023.e02555. Suleymanov, A., Tuktarova, I., Belan, L., Suleymanov, R., Gabbasova, I. and Araslanova, L. (2023). Spatial prediction of soil properties using random forest, k-nearest neighbours and cubist approaches in the foothills of the Ural Mountains, Russia. Modeling Earth Systems and Environment . https://doi.org/10.1007/s40808-023-01723-4. Tesfay, T., Mohamed, E.S., Mehrteab, M., Ghebretnsae, T.W. and Sereke, T.E. (2025b). Soil organic carbon losses following conversion of natural forests into agriculture: Insights from Eritrea. Dokuchaev Soil Bulletin . 123: 100-115. https://doi.org/10.19047/0136-1694-2025-123-100-115. Tesfay, T., Mohamed, E.S., Savin, I.Y., Kucher, D.E., Rebouh, N.Y. and Ogbazghi, W. (2025a). Soil organic carbon modelling with different input variables: The case of the western lowlands of eritrea. Sustainability . 17(21): 9884. https://doi.org/10.3390/su17219884. Tesfay, T., Ogbazghi, W. and Singh, B. (2020). Effects of soil and water conservation interventions on some physico- chemical properties of soil in Hamelmalo and Serejeka Sub-zones of Eritrea. Journal of Soil and Water Conservation . 19(3): 229-234. https://doi.org/10.5958/2455-7145. 2020.00031.4. Tesfay, T., Ogbazghi, W., Singh, B. and Tsegai, T. (2018). Factors influencing soil and water conservation adoption in basheri, gheshnashm and shmangus laelai, eritrea. IRA- International Journal of Applied Sciences . 12(2). https://doi.org/10.21013/jas.v12.n2.p1. Tesfay, T., Mohamed, E.S.S., Ghebretnsae, T.W., Ghebremariam, S.B. and Mehrteab, M. (2024). Soil organic carbon stock assessment for soil fertility improvement, ecosystem restoration and climate-change mitigation. E3S Web of Conferences . 555. https://doi.org/10.1051/e3sconf/202455501015. Tesfay, T., Ghebretnsae, T. and Mohamed, E. (2026). Estimating carbon sequestration potential of dryland enclosures: A comparative assessment assisted by Sentinel 2 time- series and machine learning framework. Eurasian J. Soil Sci . 15(2): 209-227. https://doi.org/10.18393/ejss.1881636. Urgessa, H.T. and Ferede, T.G. (2023). Effect of land use on plant nutrient availability and soil carbon stock of Mokonisa Machi watershed, Dugda Dawa Woreda, West Guji Zone, Southern Ethiopia. Agricultural Science Digest . 43(2): 135-142. doi: 10.18805/ag.RF-232 . Viscarra, R.R.A.V., Taylor, H.J. and McBratney, A.B. (2007). Multivariate calibration of hyperspectral γ-ray energy spectra for proximal soil sensing. European Journal of Soil Science . 58(1). https://doi.org/10.1111/j.1365-2389.2006.00859.x. von Fromm, S.F., Doetterl, S., Butler, B.M., Aynekulu, E., Berhe, A.A. et al . (2024). Controls on timescales of soil organic carbon persistence across sub-Saharan Africa. Global Change Biology. 30(1). https://doi.org/10.1111/gcb.17089. Weldewahid, Y., Habtu, S., Taye, G., Teka, K. and Gessesse, T.A. (2023). Effects of long-term irrigation practice on soil quality, organic carbon and total nitrogen stocks in the drylands of Ethiopia. Journal of Arid Environments . 214: 104982. https://doi.org/10.1016/j.jaridenv.2023.104982. Yami, B. and Swami, S. (2023). Mapping and Monitoring of Soil Organic Carbon using Regression Analysis of Spectral Indices. https://www.researchgate.net/publication/371912246. Zhang, S., Tian, J., Lu, X. and Tian, Q. (2023). Temporal and spatial dynamics distribution of organic carbon content of surface soil in coastal wetlands of Yancheng, China from 2000 to 2022 based on Landsat images. Catena . 223. https://doi.org/10.1016/j.catena.2023.106961. Zhou, T., Lv, Y., Xie, B., Xu, L., Zhou, Y., Mei, T., Li, Y., Yuan, N. and Shi, Y. (2023). Topography and soil organic carbon in subtropical forests of China. Forests . 14(5). https://doi.org/10.3390/f14051023.
EDITORIAL BOARD

Guided by Experienced Academic Leadership

Distinguished scholars and subject experts committed to editorial excellence, scientific integrity and rigorous peer review.

View Full Board
V. Geethalakshmi
Chief Editor

V. Geethalakshmi

Ex-Vice ChancellorTamil Nadu Agricultural University Coimbatore, INDIA

R. Sarada Jaya Lakshmi
Associate chief editor

R. Sarada Jaya Lakshmi

Ex-Vice ChancellorCoordinator, DAATTC Kurnool, Acharya N.G. Ranga Agricultural University, Andhra Pradesh, INDIA

Neetu Sharma
Editor

Neetu Sharma

ProfessorSher-e-Kashmir University of Agricultural Sciences & Technology of Jammu and Kashmir, INDIA

S. Alarmelu
Editor

S. Alarmelu

Principal ScientistICAR-Sugarcane Breeding Institute, Coimbatore, Tamil Nadu, INDIA.