Technological Innovations in Soil Science: Digital Soil Mapping, Artificial Intelligence and Precision Agriculture
Authors/Creators
- 1. ICFRE-Tropical Forest Research Institute (Ministry of Environment, Forests & Climate Change, Govt. of India), P.O. RFRC, Mandla Road, Jabalpur, MP-482021, India
- 2. Department of Artificial Intelligence and Data Science, Jabalpur Engineering College, Jabalpur (MP)
- 3. Government Science College, Jabalpur, MP, India- 482 001
Description
Technological innovation—driven by satellite remote sensing, geospatial analytics, machine learning (ML), and Internet-of-Things (IoT) sensor networks—is transforming soil science from descriptive mapping to predictive, near-real-time decision support. Digital Soil Mapping (DSM) integrates the SCORPAN framework with dense covariate stacks (terrain derivatives, spectral indices, climate layers) and modern ML/ensemble models (Random Forest, Gradient Boosting, Convolutional Neural Networks) to produce high-resolution, three-dimensional soil property maps (e.g., Soil Grids). Remote-sensing platforms such as Sentinel and Landsat provide critical spectral and thermal inputs that—when combined with in-situ and hyperspectral laboratory spectroscopy—enable rapid estimation of soil organic carbon (SOC), texture, moisture, pH, and other indicators. Edge AI, autonomous field platforms, and IoT sensor meshes allow continuous soil health monitoring and enable precision interventions (variable-rate fertilization, irrigation scheduling) that improve nutrient-use efficiency (NUE) and reduce environmental losses. Explainable AI (XAI) methods (SHAP, LIME, partial dependence plots) are increasingly critical to translate model outputs into actionable guidance for land managers. Key challenges remain: model transferability across soil-forming contexts, standardization and interoperability of soil observatories (FAIR data), bias from surface cover in remote sensing-derived predictions, and the need for robust validation frameworks. This chapter synthesizes theory, methods, case studies, limitations, and research directions for the DSM→AI→Precision Agriculture pipeline. This chapter presents a comprehensive synthesis of Digital Soil Mapping (DSM), Artificial Intelligence (AI), and Precision Agriculture technologies transforming soil science. The integration of remote sensing platforms, machine learning algorithms, IoT sensor networks, and decision support systems enables predictive soil intelligence at unprecedented spatial and temporal scales. Advances in ensemble modeling, deep learning for spectral soil analysis, uncertainty quantification, and autonomous soil monitoring are discussed. The chapter further examines challenges related to model transferability, sensor calibration, interpretability, and data governance. Emerging research directions including physics-informed machine learning, federated learning, and agroecosystem digital twins are explored.
Files
5. Rajesh Kumar Mishra.pdf
Files
(407.1 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:aae0372cd961184de5b8f7a8952586c0
|
407.1 kB | Preview Download |
Additional details
References
- 1. Arrouays, D., et al. (2017). GlobalSoilMap: Toward a fine-resolution global grid of soil properties. Advances in Agronomy, 125, 93–134. 2. Baghdadi, N., et al. (2017). SAR-based soil moisture retrieval over agricultural areas. Remote Sensing of Environment, 199, 345–357. 3. Baghdadi, N., et al. (2017). SAR-based soil moisture retrieval. Remote Sensing of Environment 199:345–357. 4. Basso, B., Antle, J. (2020). Digital agriculture for climate resilience. Nature Sustainability, 3, 507–515. 5. Basso, B., et al. (2013). Precision nitrogen management. Agricultural Systems, 117, 56–65. 6. Batjes, N.H. (2016). Harmonized soil property databases. Earth System Science Data, 8, 455–471. 7. Bongiovanni, R., Lowenberg-Deboer, J. (2004). Precision agriculture adoption. Precision Agriculture, 5, 359–387. 8. Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. 9. Chen, S., et al. (2022). Broad-scale mapping of soil properties using machine learning. Geoderma, 409, 115632. 10. Dorigo, W., et al. (2017). ESA CCI soil moisture product. Earth System Science Data, 9, 1–26. 11. Drusch, M., et al. (2012). Sentinel-2: ESA's optical high-resolution mission. Remote Sensing of Environment, 120, 25–36. 12. FAO & ITPS (2021). Global Assessment of Soil Pollution. FAO, Rome. 13. FAO (2015). Status of the World's Soil Resources (SWSR). FAO, Rome. 14. Foley, J.A., et al. (2011). Solutions for cultivated planet. Nature, 478, 337–342. 15. Friedman, J.H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29, 1189–1232. 16. Gebbers, R., Adamchuk, V.I. (2010). Precision agriculture and food security. Science, 327, 828–831. 17. Godfray, H.C.J., et al. (2010). Food security challenge. Science, 327, 812–818. 18. Goovaerts, P. (1997). Geostatistics for Natural Resources Evaluation. Oxford Univ. Press. 19. Hengl, T., et al. (2014). SoilGrids1km — Global soil information based on automated mapping. PLOS ONE, 9, e105992. 20. Hengl, T., et al. (2017). SoilGrids250m: Global gridded soil information based on machine learning. PLOS ONE, 12, e0169748. 21. Hengl, T., et al. (2021). Soil property prediction improvements. Soil, 7, 217–240. 22. Heuvelink, G.B.M., Webster, R. (2001). Modelling soil variation. Geoderma, 103, 1–12. 23. IPCC (2019). Climate Change and Land. IPCC Special Report. 24. Jones, H.G. (2004). Irrigation scheduling: Advantages of soil moisture sensors. Agricultural Water Management, 66, 1–8. 25. Kamilaris, A., Prenafeta-Boldú, F.X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture 147:70–90. 26. Karpatne, A., et al. (2017). Physics-guided neural networks. IEEE Transactions on Knowledge and Data Engineering, 29, 2318–2331. 27. Karydas, C.G., et al. (2018). Digital soil mapping at continental scale. Geoderma, 311, 125–139. 28. Khosla, R., et al. (2008). Precision agriculture and nitrogen management. Agronomy Journal, 100, S-79–S-87. 29. Kim, Y., et al. (2008). Wireless sensor networks for agriculture. Computers and Electronics in Agriculture, 64, 122–131. 30. Lal, R. (2004). Soil carbon sequestration impacts. Science, 304, 1623–1627. 31. Li, S., et al. (2020). Data fusion for soil moisture retrieval. Remote Sensing, 12, 3120. 32. Liakos, K.G., et al. (2018). Machine learning in agriculture: A review. Sensors, 18, 2674. 33. Lobell, D.B. (2013). Remote sensing of soil properties. Remote Sensing of Environment 132:27–38. 34. Lobell, D.B., Asner, G.P. (2002). Moisture effects on soil reflectance. Remote Sensing of Environment, 81, 317–326. 35. Lundberg, S.M., Lee, S.I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30. 36. McBratney, A.B., Mendonça Santos, M.L., Minasny, B. (2003). On digital soil mapping. Geoderma, 117, 3–52. 37. Meyer, H., et al. (2019). Improving performance of spatial cross-validation. Ecological Modelling, 397, 13–22. 38. Minasny, B., et al. (2017). Soil carbon 4 per mille initiative. Geoderma, 292, 59–86. 39. Minasny, B., et al. (2019). Digital mapping of soil carbon. Advances in Agronomy 158:1–44. 40. Minasny, B., et al. (2020). Global soil information systems review. Geoderma, 375, 114528. 41. Minasny, B., et al. (2023). Artificial intelligence in soil science. Geoderma, 430, 116338. 42. Minasny, B., McBratney, A.B. (2016). Digital soil mapping: A brief history. Geoderma, 264, 301–311. 43. Mulder, V.L., et al. (2011). The use of remote sensing in digital soil mapping. Geoderma, 162, 1–19. 44. O'Shaughnessy, S.A., Evett, S.R. (2010). Canopy temperature sensors for irrigation scheduling. Agricultural Water Management, 98, 1–13. 45. Olden, J.D., et al. (2008). Machine learning methods in ecology. Ecology 89:107–115. 46. Olden, J.D., et al. (2008). Machine learning methods without tears. Quarterly Review of Biology, 83, 171–193. 47. Padarian, J., Minasny, B., McBratney, A.B. (2019). Using deep learning for digital soil mapping. Soil, 5, 79–89. 48. Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python. JMLR 12:2825–2830. 49. Reichle, R.H., et al. (2017). SMAP soil moisture mission. Remote Sensing of Environment, 191, 2–12. 50. Reichstein, M., et al. (2019). Deep learning and process understanding in Earth system science. Nature, 566, 195–204. 51. Robertson, G.P., Vitousek, P.M. (2009). Nitrogen in agriculture: Balancing productivity and environmental protection. Annual Review of Environment and Resources, 34, 97–125. 52. Rossel, R.A.V., et al. (2006). Proximal sensing of soil properties. Geoderma, 131, 59–75. 53. Rossiter, D.G. (2018). Past, present and future of digital soil mapping. Geoderma, 324, 1–10. 54. Shapley, L.S. (1953). A value for n-person games. Contributions to the Theory of Games. 55. Tilman, D., et al. (2002). Agricultural sustainability and food demand. Nature, 418, 671–677. 56. Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer. 57. Vereecken, H., et al. (2016). Modeling soil processes: A review. Vadose Zone Journal, 15. 58. Viscarra Rossel, R.A., et al. (2016). Visible, near infrared, and mid infrared spectroscopy for soil analysis. Advances in Agronomy, 144, 1–45. 59. Wadoux, A.M.J.C., Minasny, B., McBratney, A.B. (2020). Machine learning for digital soil mapping: Applications, challenges and suggested solutions. Earth-Science Reviews, 210, 103359. 60. Wulder, M.A., et al. (2019). Current status of Landsat program. Remote Sensing of Environment, 225, 127–147. 61. Zhang, C., Kovacs, J.M. (2012). Applications of small UAVs for agriculture. Precision Agriculture, 13, 693–712. 62. Zhang, Q., et al. (2002). Precision agriculture technologies. Computers and Electronics in Agriculture, 36, 113–132. 63. Zhang, Y., et al. (2021). Deep learning for SOC prediction. Soil & Tillage Research, 211, 104999.