Search

Menu
Search
in Ecology

Soil classification in the Sudan Savanna using sentinel products and topographic information with machine learning models

168 Views


Abstract

Accurate soil information is crucial for sustainable agricultural planning and land management, particularly in data-scarce regions, such as the Sudan Savanna, the largest sorghum-producing area in Africa. A recent study reported that soils in this region corresponded well with the topography, having formed primarily through erosion–deposition processes, resulting in systematic variation in soil types along the landscape. Therefore, this study compared the performances of three machine learning models, i.e., Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM), for soil classification based on multisource remote sensing and topographic data. Ground-truth data with four different soil types, Lixisols, Petric Plinthosols, Pisoplinthic Petric Plinthosols, and Gleysols, were used to train and validate the models using 19 remote sensing-derived covariates including Sentinel-1 SAR, Sentinel-2 bands, spectral indices, and Topographic Wetness Index. Machine learning classification was analyzed under different scenarios of remote sensing feature combination. Results showed that the XGBoost with the selected feature combination achieved the highest performance with an overall accuracy of 78.9%, followed by RF (72.3%) and SVM (65.2%). Among the selected features, topographic parameters appeared the most important and provided complementary information for accurate soil classification. This study demonstrates the effectiveness of integrating optical, radar, and topographic information for soil mapping and provides a valuable management tool to support agricultural and environmental strategies in the Sudan Savanna.

Data availability

The datasets generated and analyzed in the current study are available from the corresponding authors upon reasonable request for academic and non-commercial research purposes, subject to project approval and data-sharing agreements.

References

  1. Schoonover, J. E. & Crim, J. F. An introduction to soil concepts and the role of soils in watershed management. Contemp. Water Res. 154, 21–47. https://doi.org/10.1111/j.1936-704x.2015.03186.x (2015).

    Google Scholar 

  2. Dewitte, O. et al. Harmonisation of the soil map of Africa at the continental scale. Geoderma 211–212, 138–153. https://doi.org/10.1016/j.geoderma.2013.07.007 (2013).

    Google Scholar 

  3. Hermans, T. D. G. et al. Combining local knowledge and soil science for integrated soil health assessments in conservation agriculture systems. J. Environ. Manage. 286, 112192. https://doi.org/10.1016/j.jenvman.2021.112192 (2021).

    Google Scholar 

  4. Winklerprins, A. M. G. A. Insights and applications local soil knowledge: A tool for sustainable land management. Soc. Nat. Resour. 12, 151–161. https://doi.org/10.1080/089419299279812 (1999).

    Google Scholar 

  5. Ikazaki, K., Nagumo, F., Simporé, S. & Barro, A. Understanding yield-limiting factors for sorghum in semi-arid sub-Saharan Africa: Beyond soil nutrient deficiency. Soil Sci. Plant Nutr 70, 114–122. https://doi.org/10.1080/00380768.2025.2522832 (2024).

    Google Scholar 

  6. Ikazaki, K., Nagumo, F., Simporé, S., Iseki, K. & Barro, A. Impact of effective soil depth on agronomic recommendations for sorghum and its economic viability in Africa. Soil. Sci. Plant. Nutr. 71, 724–735. https://doi.org/10.1080/00380768.2025.2522832 (2025).

    Google Scholar 

  7. Leenaars, J. G. B., Kempen, B., van Oostrum, A. J. M. & Batjes, N. H. Afr. Soil Profile Database, (2014).

  8. Nenkam, A. M. et al. Applications and challenges of digital soil mapping in Africa. Geoderma 449, 117007. https://doi.org/10.1016/j.geoderma.2024.117007 (2024).

    Google Scholar 

  9. Behrens, T. & Scholten, T. Digital soil mapping in Germany—A review. J. Plant. Nutr. Soil. Sci. 169, 434–443. https://doi.org/10.1002/jpln.200521962 (2006).

    Google Scholar 

  10. Ikazaki, K., Nagumo, F., Simporé, S. & Barro, A. Soil toposequence, productivity, and a simple technique to detect petroplinthites using ground-penetrating radar in the Sudan Savanna. Soil Sci. Plant Nutr. 64, 623–631. https://doi.org/10.1080/00380768.2018.1502604 (2018).

    Google Scholar 

  11. Schlüter, T. Geological atlas of Africa, (2008).

  12. Gosling, W. D., Scerri, E. M. L. & Kaboth-Bahr, S. The climate and vegetation backdrop to hominin evolution in Africa. Philosophical Transactions of the Royal Society B: Biological Sciences https://doi.org/10.1098/rstb.2020.0483 (2022).

    Google Scholar 

  13. Miller, C. S., Gosling, W. D., Kemp, D. B., Coe, A. L. & Gilmour, I. Drivers of ecosystem and climate change in tropical west Africa over the past ∼540 000 years. J. Quat. Sci. 31, 671–677. https://doi.org/10.1002/jqs.2893 (2016).

    Google Scholar 

  14. Abdi, A. M., Brandt, M., Abel, C. & Fensholt, R. Satellite remote sensing of savannas: Current status and emerging opportunities. J. Remote Sens. https://doi.org/10.1016/j.geoderma.2021.115567 (2022).

    Google Scholar 

  15. Chen, S. et al. Digital mapping of GlobalSoilMap soil properties at a broad scale: A review. Geoderma 409, 115567 (2022).

    Google Scholar 

  16. Forkuor, G., Hounkpatin, O. K. L., Welp, G. & Thiel, M. High resolution mapping of soil properties using Remote Sensing variables in South-Western Burkina Faso: A comparison of machine learning and multiple linear regression models. PLoS One 12, e0170478. https://doi.org/10.1371/journal.pone.0170478 (2017).

    Google Scholar 

  17. Mulder, V. L., de Bruin, S., Schaepman, M. E. & Mayr, T. R. The use of remote sensing in soil and terrain mapping—A review. Geoderma 162, 1–19. https://doi.org/10.1016/j.geoderma.2010.12.018 (2011).

    Google Scholar 

  18. Borges, J., Higginbottom, T. P., Symeonakis, E. & Jones, M. Sentinel-1 and sentinel-2 data for savannah land cover mapping: Optimising the combination of sensors and seasons. Remote Sens. 12, 3862. https://doi.org/10.3390/rs12233862 (2020).

    Google Scholar 

  19. David, R. M., Rosser, N. J. & Donoghue, D. N. M. Improving above ground biomass estimates of Southern Africa dryland forests by combining Sentinel-1 SAR and Sentinel-2 multispectral imagery. Remote Sens. Environ. 113232. https://doi.org/10.1016/j.rse.2022.113232 (2022).

    Google Scholar 

  20. Masemola, C., Cho, M. A. & Ramoelo, A. Sentinel-2 time series based optimal features and time window for mapping invasive Australian native Acacia species in KwaZulu Natal, South Africa. Int. J. Appl. Earth Obs. Geoinf. 93, 102207. https://doi.org/10.1016/j.jag.2020.102207 (2020).

    Google Scholar 

  21. Reinermann, S. et al. Detection of grassland mowing events for Germany by combining Sentinel-1 and Sentinel-2 time series. Remote Sens. 14, 1647. https://doi.org/10.3390/rs14071647 (2022).

    Google Scholar 

  22. Symeonakis, E., Higginbottom, T. P., Petroulaki, K. & Rabe, A. Optimisation of savannah land cover characterisation with optical and SAR data. Remote Sensing 10, 499. https://doi.org/10.3390/rs10040499 (2018).

    Google Scholar 

  23. Zhang, W. et al. From woody cover to woody canopies: How Sentinel-1 and Sentinel-2 data advance the mapping of woody plants in savannas. Remote Sens. Environ. 234, 111465. https://doi.org/10.1016/J.RSE.2019.111465 (2019).

    Google Scholar 

  24. Du, L. et al. Spatial extrapolation of topographic models for mapping soil organic carbon using local samples. Geoderma 404, 115290. https://doi.org/10.1016/j.geoderma.2021.115290 (2021).

    Google Scholar 

  25. Simperegui, K. B. D. et al. Digital mapping of Ghana’s soil properties and nutrients: Performance of spline and weighted average approaches. Geoderma 459, 117365. https://doi.org/10.1016/j.geoderma.2025.117365 (2025).

    Google Scholar 

  26. Usta, A. Prediction of soil water contents and erodibility indices based on artificial neural networks: Using topography and remote sensing. Environ. Monit. Assess. 794. https://doi.org/10.1007/s10661-022-10465-2 (2022).

    Google Scholar 

  27. Winzeler, H. E. et al. Topographic wetness index as a proxy for soil moisture in a hillslope Catena: Flow algorithms and map generalization. Land 2018. https://doi.org/10.3390/land11112018 (2022).

    Google Scholar 

  28. Zhu, C. et al. Constructing soil–landscape units based on slope position and land use to improve soil prediction accuracy. Remote Sens. (Basel) 16, 4090. https://doi.org/10.3390/rs16214090 (2024).

    Google Scholar 

  29. Behrens, T., Zhu, A. X., Schmidt, K. & Scholten, T. Multi-scale digital terrain analysis and feature selection for digital soil mapping. Geoderma 155, 175–185. https://doi.org/10.1016/j.geoderma.2009.07.010 (2010).

    Google Scholar 

  30. Brungard, C. W., Boettinger, J. L., Duniway, M. C., Wills, S. A. & Edwards, T. C. Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma 239–240, 68–83. https://doi.org/10.1016/j.geoderma.2014.09.019 (2015).

    Google Scholar 

  31. Dharumarajan, S., Hegde, R., Janani, N. & Singh, S. K. The need for digital soil mapping in India. Geoderma Reg. e00204. https://doi.org/10.1016/j.geodrs.2019.e00204 (2019).

    Google Scholar 

  32. Hamzehpour, N., Shafizadeh-Moghadam, H. & Valavi, R. Exploring the driving forces and digital mapping of soil organic carbon using remote sensing and soil texture. CATENA 182, 104141. https://doi.org/10.1016/j.catena.2019.104141 (2019).

    Google Scholar 

  33. Wadoux, A. M. J. C. Using deep learning for multivariate mapping of soil with quantified uncertainty. Geoderma 351, 59–70. https://doi.org/10.1016/j.geoderma.2019.05.012 (2019).

    Google Scholar 

  34. Wadoux, A. M. J. C., Minasny, B. & McBratney, A. B. Machine learning for digital soil mapping: Applications, challenges and suggested solutions. Earth-Sci. Rev. 210, 103359. https://doi.org/10.1016/J.EARSCIREV.2020.103359 (2020).

    Google Scholar 

  35. Zeraatpisheh, M., Ayoubi, S., Jafari, A., Tajik, S. & Finke, P. 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 (2019).

    Google Scholar 

  36. Dai, F., Zhou, Q., Lv, Z., Wang, X. & Liu, G. Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau. Ecol. Indic. 45, 184–194. https://doi.org/10.1016/j.ecolind.2014.04.003 (2014).

    Google Scholar 

  37. Ge, X. et al. Updated soil salinity with fine spatial resolution and high accuracy: The synergy of Sentinel-2 MSI, environmental covariates and hybrid machine learning approaches. X Han CATENA. 212, 106054. https://doi.org/10.1016/j.catena.2022.106054 (2022).

    Google Scholar 

  38. Gomes, L. C. et al. Modelling and mapping soil organic carbon stocks in Brazil. Geoderma 340, 337–350. https://doi.org/10.1016/j.geoderma.2019.01.007 (2019).

    Google Scholar 

  39. Grimm, R., Behrens, T., Märker, M. & Elsenbeer, H. Soil organic carbon concentrations and stocks on Barro Colorado Island – Digital soil mapping using Random Forests analysis. Geoderma 146, 102–113. https://doi.org/10.1016/j.geoderma.2008.05.008 (2008).

    Google Scholar 

  40. Takenaka, K. et al. Changes in woody vegetation over 31 years in farmed parkland of the central plateau, Burkina Faso. Land 10, 470. https://doi.org/10.3390/land10050470 (2021).

    Google Scholar 

  41. van Reeuwijk, L. P. Procedures for soil analysis (Int. Soil Reference and Information Centre, 2002).

    Google Scholar 

  42. European Space Agency. SENTINEL-2 user handbook. (2015).

  43. Hajduch, G., Bourbigot, M., Johnsen, H. & Piantanida, R. Sentinel-1 product specification, (2021).

  44. Vreugdenhil, M. et al. Sensitivity of Sentinel-1 backscatter to vegetation dynamics: An Austrian case study. Remote Sensing 10, 1396. https://doi.org/10.3390/rs10091396 (2018).

    Google Scholar 

  45. Teillet, P. M., Staenz, K. & Williams, D. J. Effects of spectral, spatial, and radiometric characteristics on remote sensing vegetation indices of forested regions. Remote Sens. Environ. 61, 139–149. https://doi.org/10.1016/S0034-4257(96)00248-9 (1997).

    Google Scholar 

  46. McFeeters, S. K. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. Int. J. Remote Sens. 17, 1425–1432. https://doi.org/10.1080/01431169608948714 (1996).

    Google Scholar 

  47. Du, Y. et al. Water bodies’ mapping from Sentinel-2 imagery with Modified Normalized Difference water Index at 10-m spatial resolution produced by sharpening the swir band. Remote Sensing 8, 354. https://doi.org/10.3390/rs8040354 (2016).

    Google Scholar 

  48. Chen, F., Van de Voorde, T., Roberts, D., Zhao, H. & Chen, J. Detection of ground materials using normalized difference indices with a threshold: Risk and ways to improve. Remote Sensing 13, 450. https://doi.org/10.3390/rs13030450 (2021).

    Google Scholar 

  49. Beven, K. J. & Kirkby, M. J. A physically based, variable contributing area model of basin hydrology / Un modèle à base physique de zone d’appel variable de l’hydrologie du bassin versant. Hydrol. Sci. Bull. 24, 43–69. https://doi.org/10.1080/02626667909491834 (1979).

    Google Scholar 

  50. Breiman, L. Random forests. Mach. Learn. 45, 5–32. https://doi.org/10.1023/A:1010933404324 (2001).

    Google Scholar 

  51. Wiesmeier, M., Barthold, F., Blank, B. & Kögel-Knabner, I. Digital mapping of soil organic matter stocks using Random Forest modeling in a semi-arid steppe ecosystem. Plant Soil 340, 7–24 (2011).

    Google Scholar 

  52. Khalaf, H. S., Mustafa, Y. T. & Fayyadh, M. A. Digital mapping of soil organic matter in Northern Iraq: Machine learning approach. Appl. Sci. 13, 10666 (2023).

    Google Scholar 

  53. Tziolas, N., Samarinas, N., Tsividis, I. & Zalidis, G. Evaluating the effectiveness of improved digital soil maps, generated through a hybrid CNN-XGBoost approach, for estimating soil loss due to water erosion. SPIE-Intl Soc. Opt. Eng. https://doi.org/10.1117/12.3037235 (2024).

    Google Scholar 

  54. Kovačević, M., Bajat, B. & Gajić, B. Soil type classification and estimation of soil properties using support vector machines. Geoderma 154, 340–347. https://doi.org/10.1016/j.geoderma.2009.11.005 (2010).

    Google Scholar 

  55. Pereira, G. W., Valente, D. S. M., de Queiroz, D. M., Santos, N. T. & Fernandes-Filho, E. I. Soil mapping for precision agriculture using support vector machines combined with inverse distance weighting. Precis. Agric. 23, 1189–1204. https://doi.org/10.1007/s11119-022-09880-9 (2022).

    Google Scholar 

  56. Rwanga, S. S. & Ndambuki, J. M. Accuracy assessment of land use/land cover classification using remote sensing and GIS. Int. J. Geosci. 8, 611–622. https://doi.org/10.4236/ijg.2017.84033 (2017).

    Google Scholar 

  57. Yacouby, R. & Axman, D. Probabilistic extension of Precision, Recall, and F1 Score for more thorough evaluation of classification models 79–91, (2020). https://doi.org/10.18653/v1/2020.eval4nlp-1.9

  58. Konkan, A. B. S. et al. Use sentinel satellite data for estimation of soil properties: A review. Int. J. Environ. Agric. Res. (IJOEAR). https://doi.org/10.5281/zenodo.14016023 (2024).

    Google Scholar 

  59. Ma, G., Ding, J., Han, L., Zhang, Z. & Ran, S. Digital mapping of soil salinization based on Sentinel-1 and Sentinel-2 data combined with machine learning algorithms. Reg. Sustain. 2, 177–188. https://doi.org/10.1016/j.regsus.2021.06.001 (2021).

    Google Scholar 

  60. Santaga, F. S., Agnelli, A., Leccese, A. & Vizzari, M. Using sentinel-2 for simplifying soil sampling and mapping: Two case studies in Umbria, Italy. Remote Sens. 13, 3379. https://doi.org/10.3390/rs13173379 (2021).

    Google Scholar 

  61. Iizumi, T. et al. Crop choice advisory for the West African Sudan Savanna based on soil type and presowing rainfall forecasts: A machine learning residual model approach. Clim. Serv. 40, 100605. https://doi.org/10.1016/j.cliser.2025.100605 (2025).

    Google Scholar 

  62. Leães, Á., Gontijo, F., Moreno, W. E. G. & Costa, J. F. C. L. Spatial Cross-Validation for Machine Learning Models Estimates. In International Geostatistics Congress 2024. GEOSTATS 2024. Quantitative Geology and Geostatistics Vol. 20 (eds Azevedo, L. et al.) (Springer, 2025). https://doi.org/10.1007/978-3-031-92870-3_21.

    Google Scholar 

  63. Meyer, H. & Pebesma, E. Predicting into unknown space? Estimating the area of applicability of spatial prediction models. Methods Ecol. Evol. 12, 1620–1633. https://doi.org/10.1111/2041-210X.13650 (2021).

    Google Scholar 

  64. Wang, Y., Khodadadzadeh, M. & Zurita-Milla, R. Spatial+: A new cross-validation method to evaluate geospatial machine learning models. Int. J. Appl. Earth Observ. Geoinform. https://doi.org/10.1016/j.jag.2023.103364 (2023).

    Google Scholar 

Download references

Acknowledgements

This study was conducted under the JIRCAS-INERA collaborative project “Development of watershed management model in the Central Plateau, Burkina Faso (2016–2020).” We thank Dr. Adama Kaboré, Dr. Barthélémy Yelemou, and Mr. Simporé Kouka (INERA) for their assistance with this study. We also thank Dr. Naoyuki Yamashita, Dr. Akihiro Imaya (Forestry and Forest Products Research Institute, Japan), and Dr. Yusuke Takata (National Agriculture and Food Research Organization, Japan) for their constructive advice.

Funding

This research was conducted as part of the JIRCAS-INERA collaborative projects, “Development of watershed management model in the Central Plateau, Burkina Faso (2016–2020)” and “Development of soil and crop management technologies to stabilize upland farming systems of African smallholder farmers (2021–2025)” funded by the Ministry of Agriculture, Forestry and Fisheries of Japan.

Author information

Authors and Affiliations

  1. Japan International Research Center for Agricultural Sciences (JIRCAS), Tsukuba, 305-8686, Ibaraki, Japan

    Win Sithu Maung, Ikazaki Kenta & Sakai Toru

  2. Institut de l’Environnement et de Recherches Agricoles (INERA), Ouagadougou, Burkina Faso

    Simporé Saïdou, Zerbo Lamine & Kone Nicolas

Authors

  1. Win Sithu Maung
    View author publications

    Search author on:PubMed Google Scholar

  2. Ikazaki Kenta
    View author publications

    Search author on:PubMed Google Scholar

  3. Sakai Toru
    View author publications

    Search author on:PubMed Google Scholar

  4. Simporé Saïdou
    View author publications

    Search author on:PubMed Google Scholar

  5. Zerbo Lamine
    View author publications

    Search author on:PubMed Google Scholar

  6. Kone Nicolas
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Conceptualization, methodology, W.S.M., I.K., and S.T; Data collection, I.K., S.S., Z.L, and K.N; Formal analysis and writing–original draft preparation, W.S.M; Writing–review and editing, I.K., S.T, S.S., Z.L, and K.N; Supervision and validation, I.K. and S.T.; Project administration and funding acquisition, I.K. All authors have read and agreed to the published version of the manuscript.

Corresponding authors

Correspondence to
Win Sithu Maung or Ikazaki Kenta.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

About this article

Cite this article

Maung, W.S., Kenta, I., Toru, S. et al. Soil classification in the Sudan Savanna using sentinel products and topographic information with machine learning models.
Sci Rep (2026). https://doi.org/10.1038/s41598-026-46259-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41598-026-46259-6

Keywords

  • Soil classification
  • Machine learning
  • Sentinel image
  • Topography feature
  • Sudan Savanna

Source: Ecology - nature.com

Nonlinear dynamics of Nosema ceranae and the fragile resilience of honeybee colonies under environmental strain

A dataset of insect sounds from 459 species for bioacoustic machine learning

This portal is not a newspaper as it is updated without periodicity. It cannot be considered an editorial product pursuant to law n. 62 of 7.03.2001. The author of the portal is not responsible for the content of comments to posts, the content of the linked sites. Some texts or images included in this portal are taken from the internet and, therefore, considered to be in the public domain; if their publication is violated, the copyright will be promptly communicated via e-mail. They will be immediately removed.

Back to Top
Close