Open Access

ARTICLE

Machine Learning for Smart Soil Monitoring

Khaoula Ben Abdellafou¹, Kamel Zidi², Ahamed Aljuhani¹, Okba Taouali^1,*, Mohamed Faouzi Harkat³

1 Faculty of Computers and Information Technology, University of Tabuk, Tabuk, 71491, Saudi Arabia
2 Applied College, University of Tabuk, Tabuk, 71491, Saudi Arabia
3 Department of Electronics, Faculty of Engineering Annaba, Badji Mokhtar BP. 12, Annaba, 23000, Algeria

* Corresponding Author: Okba Taouali. Email:

(This article belongs to the Special Issue: Artificial Intelligence Algorithms and Applications)

Computers, Materials & Continua 2025, 83(2), 3007-3023. https://doi.org/10.32604/cmc.2025.063146

Received 06 January 2025; Accepted 19 March 2025; Issue published 16 April 2025

Abstract

Environmental protection requires identifying, investigating, and raising awareness about safeguarding nature from the harmful effects of both anthropogenic and natural events. This process of environmental protection is essential for maintaining human well-being. In this context, it is critical to monitor and safeguard the personal environment, which includes maintaining a healthy diet and ensuring plant safety. Living in a balanced environment and ensuring the safety of plants for green spaces and a healthy diet require controlling the nature and quality of the soil in our environment. To ensure soil quality, it is imperative to monitor and assess the levels of various soil parameters. Therefore, an Optimized Reduced Kernel Partial Least Squares (ORKPLS) method is proposed to monitor and control soil parameters. This approach is designed to detect increases or deviations in soil parameter quantities. A Tabu search approach was used to select the appropriate kernel parameter. Subsequently, soil analyses were conducted to evaluate the performance of the developed techniques. The simulation results were analyzed and compared. Through this study, deficiencies or exceedances in soil parameter quantities can be identified. The proposed method involves determining whether each soil parameter falls within a normal range. This allows for the assessment of soil parameter conditions based on the principle of fault detection.

---

Keywords

---