Tomato Leaf Disease Detection and Risk Prediction Using Deep Learning and IoT-Based Environmental Monitoring
Dandao Xuebao/Journal of Ballistics · 12.06.2026 · 38 (2) · 499-507
DOI: 10.52783/dxjb.v38.367 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dandao Xuebao/Journal of Ballistics, online erschienen am 12.06.2026. Verfasst von Tabassum U. Mujawar.
Abstract (Originalsprache)
Timely identification of crop diseases is essential for maintaining agricultural productivity, especially in sensitive crops such as tomato. Leaf diseases often develop rapidly and may remain unnoticed until significant damage has occurred. Conventional diagnostic approaches depend on manual inspection, which is subjective, labor-intensive, and often inaccessible to small-scale farmers. Furthermore, disease development is strongly influenced by environmental factors that are rarely monitored continuously in traditional farming practices. This work presents an integrated framework for tomato leaf disease detection and risk prediction by combining deep learning, Internet of Things (IoT) sensing, and interpretable machine learning. A Convolutional Neural Network (CNN) is employed to classify leaf images into healthy and diseased categories. In parallel, an ESP32-based sensor module measures temperature, relative humidity, and soil moisture, transmitting the data to a cloud database. A Decision Tree model analyzes environmental conditions to estimate disease risk levels. Additionally, a generative advisory component produces practical recommendations based on system outputs. Experimental observations indicate that the proposed system can accurately detect disease symptoms while also identifying conditions favorable for disease spread. The architecture is designed to be cost-effective and deployable in real agricultural settings, making it suitable for precision farming applications.
Zitieren
APA
Mujawar, T. U. (2026). Tomato Leaf Disease Detection and Risk Prediction Using Deep Learning and IoT-Based Environmental Monitoring. Dandao Xuebao/Journal of Ballistics, 38(2), 499-507. https://doi.org/10.52783/dxjb.v38.367
Vancouver
Mujawar TU. Tomato Leaf Disease Detection and Risk Prediction Using Deep Learning and IoT-Based Environmental Monitoring. Dandao Xuebao/Journal of Ballistics. 2026;38(2):499-507. doi:10.52783/dxjb.v38.367
BibTeX
@article{Mujawar2026,
author = {Mujawar, Tabassum U.},
title = {Tomato Leaf Disease Detection and Risk Prediction Using Deep Learning and IoT-Based Environmental Monitoring},
journal = {Dandao Xuebao/Journal of Ballistics},
year = {2026},
volume = {38},
number = {2},
pages = {499--507},
doi = {10.52783/dxjb.v38.367}
}
EUVIMED