Salinity Properties Retrieval from Sentinel-2 Satellite Data and Machine Learning Algorithms - Article

Aug 4, 2026

Upload by Eliana

Accurate monitoring of soil salinization is essential for ecological security and sustainable agriculture in semiarid regions. This study targets improved estimation of electrical conductivity variables from salt-affected soils in a south Mediterranean area using Sentinel-2 multispectral imagery. Electrical conductivity (soil and leaf) was measured in an olive orchard in central Tunisia across two growing seasons under three irrigation treatments. Selected spectral indices and vegetation-related features were evaluated for Sentinel-2 estimation using Google Earth Engine, and machine learning models calibrated with 12 spectral bands were assessed via k-fold cross-validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Soil salinization as an environmental problem

Role of electrical conductivity in salinity monitoring

Remote sensing and Sentinel-2 opportunities

Related work using spectral characteristics

agronomy Article Salinity Properties Retrieval from Sentinel-2 Satellite Data and Machine Learning Algorithms Nada Mzid 1, *,†, Olfa Boussadia 2,†, Rossella Albrizio 3, *, Anna Maria Stellacci 4, Mohamed Braham 2 and Mladen Todorovic 5 Citation: Mzid, N.; Boussadia, O.; Albrizio, R.; Stellacci, A.M.; Braham, M.; Todorovic, M. Salinity Properties Retrieval from Sentinel-2 Satellite Data and Machine Learning Algorithms. Agronomy 2023, 13, 716 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)agronomy13030716 Academic Editor: Karsten Schmidt Received: 31 December 2022 Revised: 5 February 2023 Accepted: 17 February 2023 Published: 27 February 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Agriculture Forestry and Nature (DAFNE), University of Tuscia, 01100 Viterbo, Italy 2 Olive Institute, Avenue Ibn Khaldoun Tafala, Sousse 4000, Tunisia 3 Institute for Mediterranean Agricultural and Forestry Systems, National Research Council of Italy, P. le Enrico Fermi 1, 80055 Portici, Italy 4 Department of Soil Plant and Food Sciences, University of Bari Aldo Moro, Via G. Amendola 165/a, 70126 Bari, Italy 5 CIHEAM—Mediterranean Agronomic Institute of Bari, 70010 Valenzano, Italy * Correspondence: nada.mzid@unitus.it (N.M.); [rossella.albrizio@cnr.it](rossella.albrizio@cnr.it) (R.A.)† These authors contributed equally to this work. Abstract: The accurate monitoring of soil salinization plays a key role in the ecological security and sustainable agricultural development of semiarid regions. The objective of this study was to achieve the best estimation of electrical conductivity variables from salt-affected soils in a south Mediterranean region using Sentinel-2 multispectral imagery. In order to realize this goal, a test was carried out using electrical conductivity (EC) data collected in central Tunisia. Soil electrical conductivity and leaf electrical conductivity were measured in an olive orchard over two growing seasons and under three irrigation treatments. Firstly, selected spectral salinity, chlorophyll, water, and vegetation indices were tested over the experimental area to estimate both soil and leaf EC using Sentinel-2 imagery on the Google Earth Engine platform. Subsequently, estimation models of soil and leaf EC were calibrated by employing machine learning (ML) techniques using 12 spectral bands of Sentinel-2 images. The prediction accuracy of the EC estimation was assessed by using k-fold cross-validation and computing statistical metrics. The results of the study revealed that machine learning algorithms, together with multispectral data, could advance the mapping and monitoring of soil and leaf electrical conductivity. Keywords: Mediterranean region; olive orchard; soil and leaf electrical conductivity; Google Earth Engine; spectral vegetation indices 1. Introduction Soil salinization is a critical environmental problem in arid and semiarid regions since it seriously affects the ecological sustainability of limited land resources. As a form of land degradation, soil salinization greatly impacts on ecosystem services [1] . Thus, soilsalinization is restricting agriculture's global development and affecting the social economy's growth [2,3] . At the same time, soil salinization is one of the most important factors causing direct adverse effects on soil characteristics, as it gravely affects soil resources, decreases both soil fertility and soil microbial activity; all this results in a sharp decline of soil productivity and nutrient availability [4] . Meanwhile, soil salinization can accelerate the desertiﬁcation process and inhi

FAQs

What is the main goal of this study?

To achieve the best estimation of electrical conductivity variables from salt-affected soils using Sentinel-2 multispectral imagery and machine learning.

How were soil and leaf electrical conductivity data collected?

Soil electrical conductivity and leaf electrical conductivity were measured in an olive orchard over two growing seasons under three irrigation treatments in central Tunisia.

Which approach was used to build and evaluate the estimation models?

Spectral salinity-related features and indices were tested for Sentinel-2 estimation on Google Earth Engine, then machine learning models calibrated with 12 spectral bands were evaluated using k-fold cross-validation and statistical metrics.

Aug 4, 2026

Upload by Eliana