Full Text (PDF)
Abstract
Crop pathogens frequently find alternative hosts and a reservoir in weed species, making it harder to manage the disease and causing major loss of yield. The study discusses the use of smart methods which are machine learning and computer vision to detect the transmission of weed based diseases to farm produce in early stages. We created a predictive system that combines the process of image analysis of weed health with environmental data and agronomic data. This system is based on convolutional neural networks (CNNs) to locate the visual manifestations of the disease on common weed and a random forest classifier to estimate the possibility of further infection of the crop. Field trials on major crops and the weeds associated with them were performed to obtain data on visual symptoms of the weeds, as well as disease incidence in crops. The model that was developed showed prediction accuracy of 88 percent on occurrence of high-risk conditions that result in disease transfer. These results will show that the intelligent systems will be able to issue timely alerts, and proactive and specific disease management methods can be implemented in precision agriculture. The strategy has significantly enhanced the traditional methods of scouting since it automatizes. and facilitates the detection of the threats of disease that arise with the appearance of weeds.
License
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Article Type: Research Article
EUR J SUSTAIN DEV RES, Volume 10, Issue 2, 2026, Article No: em0385
https://doi.org/10.29333/ejosdr/18138
Publication date: 01 Apr 2026
Online publication date: 15 Mar 2026
Article Views: 22
Article Downloads: 8
Open Access References How to cite this article