Detecting Plant Diseases Using Machine Learning Models

Aug 3, 2026

Uploaded by Riley

Sustainable agriculture is pivotal to global food security and economic stability, with plant disease detection as a key barrier to maintaining healthy crop production. Early and accurate identification helps improve farming decisions, reduce crop losses, and limit environmental impacts. The study proposes a machine learning-based detection framework targeting tomato crops and evaluates YOLOv8 (nano and minor variants), Roboflow 3.0 (Fast), EfficientDetV2 (EfficientNetB0 backbone), and Faster R-CNN (ResNet50 backbone) for precision and suitability in mobile and field scenarios. YOLOv8 nano achieves the best balance, reaching 98.6% mAP with low computation for real-time farmer support.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Introduction

Tomato cultivation and disease risks

Importance of early detection on leaves

Environmental factors and disease dynamics

Machine Learning Approach

Evaluated object detection models

Model performance for mobile and field use

Results and Discussion

YOLOv8 nano as the optimal option

Integration prospects for real-world systems

Future Work

Article Detecting Plant Diseases Using Machine Learning Models Nazar Kohut 1, Oleh Basystiuk 1, Nataliya Shakhovska 1,2 and Nataliia Melnykova 1, * Academic Editors: Olexander Barmak, Iurii Krak, Eduard Manziuk and Pavlo Radiuk Received: 28 November 2024 Revised: 23 December 2024 Accepted: 24 December 2024 Published: 27 December 2024 Citation: Kohut, N.; Basystiuk, O.; Shakhovska, N.; Melnykova, N. Detecting Plant Diseases Using Machine Learning Models. Sustainability 2025, 17, 132 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)su17010132 Copyright: © 2024 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://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) . 1 Department of Artificial Intelligence, Lviv Polytechnic National University, 79013 Lviv, Ukraine; [nazar.kohut.mknssh.2024@lpnu.ua](nazar.kohut.mknssh.2024@lpnu.ua) (N.K.); [oleh.a.basystiuk@lpnu.ua](oleh.a.basystiuk@lpnu.ua) (O.B.); [nataliya.b.shakhovska@lpnu.ua](nataliya.b.shakhovska@lpnu.ua) (N.S.) 2 Department of Civil and Environmental Engineering, Brunel University of London, Uxbridge UB8 3PH, UK * [Correspondence: nataliia.i.melnykova@lpnu.ua](Correspondence: nataliia.i.melnykova@lpnu.ua) Abstract: Sustainable agriculture is pivotal to global food security and economic stability, with plant disease detection being a key challenge to ensuring healthy crop production. The early and accurate identification of plant diseases can significantly enhance agricultural practices, minimize crop losses, and reduce the environmental impacts. This paper presentsan innovative approach to sustainable development by leveraging machine learning models to detect plant diseases, focusing on tomato crops—a vital and globally significant agricultural product. Advanced object detection models including YOLOv8 (minor and nano variants), Roboflow 3.0 (Fast), EfficientDetV2 (with EfficientNetB0 backbone), and Faster R-CNN (with ResNet50 backbone) were evaluated for their precision, efficiency, and suitability for mobile and field applications. YOLOv8 nano emerged as the optimal choice, offering a mean average precision (MAP) of 98.6% with minimal computational requirements, facilitating its integration into mobile applications for real-time support to farmers. This research underscores the potential of machine learning in advancing sustainable agriculture and highlights future opportunities to integrate these models with drone technology, Internet of Things (IoT)-based irrigation, and disease management systems. Expanding datasets and exploring alternative models could enhance this technology’s efficacy and adaptability to diverse agricultural contexts. Keywords: object detection; computer vision; YOLO; YOLOv8; EfficientDet; Faster R-CNN; CNN; agriculture; diseases 1. Introduction Tomatoes are among the most widely grown and economically significant crops worldwide, and ensuring their health is crucial for optimal crop yields and high-quality produce. Tomatoes are one of the foremost cultivated crops globally, with far-reaching economic significance and indispensable contributions to global food security. The cultivation of tomatoes spans diverse agro-climatic zones, reflecting their adaptability and popularity among growers and consumers. However, this widespread cultivation has challenges, and maintaining tomato plant health is critical to ensure optimal yields and the production of high-quality fruits [1] . Disease detection and management have emerged as paramount considerations in safeguarding the health and productivity of tomato plants. The early detection of potential health issues represents a cornerstone in effectively managing diseases as it allows for timely intervention strategies to mitigate t

FAQs

Why is early plant disease detection critical for tomato crops?

Early symptoms on leaves enable timely interventions that reduce disease spread and protect crop yield and quality.

Which machine learning models were evaluated for tomato disease detection?

The study evaluated YOLOv8 (minor and nano variants), Roboflow 3.0 (Fast), EfficientDetV2 with an EfficientNetB0 backbone, and Faster R-CNN with a ResNet50 backbone.

What model performed best and what makes it practical?

YOLOv8 nano achieved 98.6% mean average precision (mAP) while using minimal computation, supporting real-time use in mobile applications for farmers.

Aug 3, 2026

Uploaded by Riley