EUVIMEDEUVIMED entdecken
Crossref

Soil Salinity Mapping using Remote Sensing and Machine Learning: A Comprehensive Review of Methods and Applications

Harish Kumar K., Swaroop A.H.L., Pallavi U., Ramana K.V., Sridhar P.

Research Journal of Chemistry and Environment · 31.10.2026 · 190

DOI: 10.25303/3012rjce1900197 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Research Journal of Chemistry and Environment, online erschienen am 31.10.2026. Verfasst von Harish Kumar K. und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soil salinity is a critical environmental issue affecting agricultural productivity and land sustainability, particularly in arid and semi-arid regions. This study aims to assess and map soil salinity using remote sensing-based spectral indices integrated with geospatial techniques. A comprehensive set of salinity and vegetation indices including SI, NDSI, VSSI, NDVI and SAVI, was derived from multispectral satellite data to enhance the detection of saline-affected areas. The analysis was carried out using GIS-based spatial modeling, where different indices were evaluated for their sensitivity to salinity variations. The results indicate that spectral indices incorporating nearinfrared (NIR), red and shortwave infrared (SWIR) bands are highly effective in distinguishing saline and non-saline regions. Among the indices, NDSI and VSSI demonstrated strong performance in identifying high salinity zones while NDVI and SAVI were useful in assessing vegetation stress related to salinity. The integration of multiple indices provided improved accuracy in salinity mapping compared to single-index approaches. This study highlights the effectiveness of remote sensing and GIS techniques in soil salinity assessment and provides a reliable framework for sustainable land management and decision-making. The findings support policymakers and researchers in developing strategies for salinity mitigation and agricultural planning.

Zitieren

APA

K., H. K., A.H.L., S., U., P., K.V., R., & P., S. (2026). Soil Salinity Mapping using Remote Sensing and Machine Learning: A Comprehensive Review of Methods and Applications. Research Journal of Chemistry and Environment, 190. https://doi.org/10.25303/3012rjce1900197

Vancouver

K. HK, A.H.L. S, U. P, K.V. R, P. S. Soil Salinity Mapping using Remote Sensing and Machine Learning: A Comprehensive Review of Methods and Applications. Research Journal of Chemistry and Environment. 2026:190. doi:10.25303/3012rjce1900197

BibTeX
@article{K2026,
  author = {K., Harish Kumar and A.H.L., Swaroop and U., Pallavi and K.V., Ramana and P., Sridhar},
  title = {Soil Salinity Mapping using Remote Sensing and Machine Learning: A Comprehensive Review of Methods and Applications},
  journal = {Research Journal of Chemistry and Environment},
  year = {2026},
  pages = {190},
  doi = {10.25303/3012rjce1900197}
}
Kostenlos starten →