Proximal sensor integration for land use classification and soil analysis in a coastal environment

Sabrina Sharmeen Alam; Somsubhra Chakraborty; Fariha Chowdhury Jain; Shovik Deb; Rachna Singh; David C. Weindorf

doi:10.1016/j.cscee.2024.101079

Proximal sensor integration for land use classification and soil analysis in a coastal environment

Sabrina Sharmeen Alam, Somsubhra Chakraborty, Fariha Chowdhury Jain, Shovik Deb, Rachna Singh, David C. Weindorf

Earth, Environment & Sustainability

Research output: Contribution to journal › Article › peer-review

Abstract

Portable X-ray fluorescence (PXRF) and Nix Pro sensors are efficient tools for rapid in-situ soil analysis. This study combined PXRF and Nix Pro to classify land use and characterize soils from Sandwip Island, Bangladesh. Soil samples from agricultural, abandoned, and seashore areas were analyzed for EC, pH, organic carbon, and texture. Random forest model achieved 84 % classification accuracy, outperforming support vector machines (72 %). Significant soil salinity and management variations were noted, particularly in seashore areas. The findings highlight the potential of these sensors for sustainable soil monitoring, with future work needed to expand applicability to diverse regions and soil types.

Original language	English
Article number	101079
Journal	Case Studies in Chemical and Environmental Engineering
Volume	11
DOIs	https://doi.org/10.1016/j.cscee.2024.101079
State	Published - Jun 2025

Scopus Subject Areas

Environmental Engineering
Environmental Chemistry
General Chemical Engineering
Environmental Science (miscellaneous)
Engineering (miscellaneous)

Keywords

Nix Pro
PXRF
Random forest
Sandwip soils
Support vector machine

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.cscee.2024.101079

Cite this

@article{50f96202b02347848951a3786db085ff,

title = "Proximal sensor integration for land use classification and soil analysis in a coastal environment",

abstract = "Portable X-ray fluorescence (PXRF) and Nix Pro sensors are efficient tools for rapid in-situ soil analysis. This study combined PXRF and Nix Pro to classify land use and characterize soils from Sandwip Island, Bangladesh. Soil samples from agricultural, abandoned, and seashore areas were analyzed for EC, pH, organic carbon, and texture. Random forest model achieved 84 % classification accuracy, outperforming support vector machines (72 %). Significant soil salinity and management variations were noted, particularly in seashore areas. The findings highlight the potential of these sensors for sustainable soil monitoring, with future work needed to expand applicability to diverse regions and soil types.",

keywords = "Nix Pro, PXRF, Random forest, Sandwip soils, Support vector machine",

author = "Alam, {Sabrina Sharmeen} and Somsubhra Chakraborty and Jain, {Fariha Chowdhury} and Shovik Deb and Rachna Singh and Weindorf, {David C.}",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors",

year = "2025",

month = jun,

doi = "10.1016/j.cscee.2024.101079",

language = "English",

volume = "11",

journal = "Case Studies in Chemical and Environmental Engineering",

issn = "2666-0164",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Proximal sensor integration for land use classification and soil analysis in a coastal environment

AU - Alam, Sabrina Sharmeen

AU - Chakraborty, Somsubhra

AU - Jain, Fariha Chowdhury

AU - Deb, Shovik

AU - Singh, Rachna

AU - Weindorf, David C.

PY - 2025/6

Y1 - 2025/6

N2 - Portable X-ray fluorescence (PXRF) and Nix Pro sensors are efficient tools for rapid in-situ soil analysis. This study combined PXRF and Nix Pro to classify land use and characterize soils from Sandwip Island, Bangladesh. Soil samples from agricultural, abandoned, and seashore areas were analyzed for EC, pH, organic carbon, and texture. Random forest model achieved 84 % classification accuracy, outperforming support vector machines (72 %). Significant soil salinity and management variations were noted, particularly in seashore areas. The findings highlight the potential of these sensors for sustainable soil monitoring, with future work needed to expand applicability to diverse regions and soil types.

AB - Portable X-ray fluorescence (PXRF) and Nix Pro sensors are efficient tools for rapid in-situ soil analysis. This study combined PXRF and Nix Pro to classify land use and characterize soils from Sandwip Island, Bangladesh. Soil samples from agricultural, abandoned, and seashore areas were analyzed for EC, pH, organic carbon, and texture. Random forest model achieved 84 % classification accuracy, outperforming support vector machines (72 %). Significant soil salinity and management variations were noted, particularly in seashore areas. The findings highlight the potential of these sensors for sustainable soil monitoring, with future work needed to expand applicability to diverse regions and soil types.

KW - Nix Pro

KW - PXRF

KW - Random forest

KW - Sandwip soils

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85212544446&partnerID=8YFLogxK

U2 - 10.1016/j.cscee.2024.101079

DO - 10.1016/j.cscee.2024.101079

M3 - Article

AN - SCOPUS:85212544446

SN - 2666-0164

VL - 11

JO - Case Studies in Chemical and Environmental Engineering

JF - Case Studies in Chemical and Environmental Engineering

M1 - 101079

ER -

Proximal sensor integration for land use classification and soil analysis in a coastal environment

Abstract

Scopus Subject Areas

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this