Modeling of Path Loss for Radio Wave Propagation in Wireless Sensor Networks in Cassava Crops Using Machine Learning

Aug 5, 2026

Modeling radio signal propagation remains central to planning wireless communication systems, particularly wireless sensor networks (WSN) deployed in vegetated agricultural environments such as cassava fields. Although many propagation models exist, accurately characterizing wireless-channel attenuation is still challenging and highly relevant for deployment decisions. This work evaluates ITU-R, FITU-R, and COST-235 vegetation propagation models against path-loss measurements and applies machine learning methods (LR, K-NN, SVM, RF) to improve prediction performance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Precision agriculture and WSN use

Need for propagation modeling

Radio wave propagation models and research scope

Vegetation-based models (ITU-R, FITU-R, COST-235)

Path-loss measurements in cassava fields

Machine learning methods for prediction

Linear regression, K-NN, SVM, random forest

Results and comparison

Error metrics and model performance

agriculture Article Modeling of Path Loss for Radio Wave Propagation in Wireless Sensor Networks in Cassava Crops Using Machine Learning Alexis Barrios-Ulloa 1, Alejandro Cama-Pinto 2, *, Emiro De-la-Hoz-Franco 2, Raól Ram½rez-Velarde 3 and Dora Cama-Pinto 4,5, * Citation: Barrios-Ulloa, A.; Cama-Pinto, A.; De-la-Hoz-Franco, E.; Ramírez-Velarde, R.; Cama-Pinto, D. Modeling of Path Loss for Radio Wave Propagation in Wireless Sensor Networks in Cassava Crops Using Machine Learning. Agriculture 2023, 13, 2046. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)agriculture13112046 Academic Editors: Gniewko Niedbała, Sebastian Kujawa, Magdalena Piekutowska and Tomasz Wojciechowski Received: 15 September 2023 Revised: 10 October 2023 Accepted: 18 October 2023 Published: 25 October 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 Electronic Engineering, Universidad de Sucre, Sincelejo 700001, Colombia; [alexis.barrios@unisucre.edu.co](alexis.barrios@unisucre.edu.co) 2 Department of Computer Science and Electronics, Universidad de la Costa, Barranquilla 080002, Colombia; [edelahoz@cuc.edu.co](edelahoz@cuc.edu.co) 3 School of Engineering and Sciences, Instituto Tecnolâgico y de Estudios Superiores de Monterrey, Monterrey 64849, Mexico; [rramirez@tec.mx](rramirez@tec.mx) 4 Faculty of Industrial Engineering, Universidad Nacional Mayor de San Marcos, Lima 15081, Peru 5 Department of Computer Architecture and Technology, University of Granada, 18071 Granada, Spain * Correspondence: [acama1@cuc.edu.co](acama1@cuc.edu.co) (A.C.-P.); [doracamapinto@correo.ugr.es](doracamapinto@correo.ugr.es) (D.C.-P.) Abstract: Modeling radio signal propagation remains one of the most critical tasks in the planning of wireless communication systems, including wireless sensor networks (WSN) . Despite the existence of a considerable number of propagation models, the studies aimed at characterizing the attenuation in the wireless channel are still numerous and relevant. These studies are used in the design and planning of wireless networks deployed in various environments, including those with abundant vegetation. This paper analyzes the performance of three vegetation propagation models, ITU-R, FITU-R, and COST-235, and compares them with path loss measurements conducted in a cassava ﬁeldin Sincelejo, Colombia. Additionally, we applied four machine learning techniques: linear regression (LR), k-nearest neighbors (K-NN), support vector machine (SVM), and random forest (RF), aiming to enhance prediction accuracy levels. The results show that vegetation models based on traditional approaches are not able to adequately characterize attenuation, while models obtained by machine learning using RF, K-NN, and SVM can predict path loss in cassava with RMSE and MAE values below 5 dB. Keywords: agriculture; cassava crops; machine learning; radio wave propagation models; wireless sensor networks 1. Introduction Agriculture is an activity of great relevance in several countries, and in many of them, it is considered a priority within their national security policies because of its importance in sustaining the population [1] . Like other industrial sectors, agriculture has undergone asigniﬁcant evolution in the last two decades, transitioning from a model based on variable monitoring to one of greater autonomy and automation in cultivation. This evolution can encompass the entire production chain, from planting to the ﬁnal marketing stage [2] . In this regard, precision agriculture (PA) is one of the most signiﬁcant concepts in the modern agricultural industry, owing to the adopt

FAQs

Which vegetation propagation models are analyzed in the study?

The study analyzes ITU-R, FITU-R, and COST-235 vegetation propagation models and compares them with measured path loss in a cassava field.

How does machine learning improve path-loss prediction in cassava crops?

The paper applies linear regression, K-NN, support vector machine, and random forest to predict path loss, showing lower prediction errors than traditional vegetation models.

Why is efficient radio propagation modeling important for wireless sensor networks in agriculture?

Accurate modeling supports proper WSN deployment by accounting for attenuation caused by both path characteristics and the vegetation environment, reducing issues like insufficient coverage or unnecessary node usage.

Aug 5, 2026

Upload by Ava Thompson