EUVIMEDEUVIMED entdecken
Crossref

Towards Intelligent Agriculture: A Hybrid Data-Driven Model for Predicting Crop Disease and Pest Infestation

F.O. Aranuwa, E.O. Akinselu, T.I. Adagbonyin, J.H. Aranuwa

Advances in Multidisciplinary & Scientific Research Journal Publication · 31.03.2026 · 12 (1) · 31-46

DOI: 10.22624/aims/v12n1p2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Multidisciplinary & Scientific Research Journal Publication, online erschienen am 31.03.2026. Verfasst von F.O. Aranuwa und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Emerging technologies are rapidly transforming agriculture by bridging the gap between traditional farming practices and smart data-driven systems, thereby enhancing productivity and sustainability. This study is focused at developing a hybrid machine learning framework for the early prediction of crop diseases and pest infestation patterns. Conventional disease detection methods rely heavily on manual inspection, which is labour-intensive, time-consuming, and susceptible to human error. However, integrating artificial intelligence and machine learning technology offers scalable, cost-effective, and accurate detective and predictive solutions for modern agriculture. This study utilized multi-source datasets comprising of 3,000 samples across the features considered in this work. These include healthy and diseased image leaves across the three major crops considered, agro-meteorological data collected through IoT sensors from 30 farms, and pest occurrence records obtained from surveys of 30 smallholder farmers in selected agricultural zones in southwestern Nigeria. A mixed-method approach was adopted, employing Convolutional Neural Networks (CNNs) for the leaf image-based disease classification, Long Short-Term Memory (LSTM) networks handling the environmental time series data, and Random Forest (RF) handling the structured farmers survey data and extension agents report for pest occurrence and infestation severity. Model evaluation was conducted using a 70/30 train-test split and cross-validation to ensure robustness. Experimental results show that the hybrid model achieved improved predictive performance, with accuracy, precision, recall, and F1-score values of 94%, 93%, 92%, and 92%, respectively over other models trained in this work. The findings demonstrate the effectiveness of multi-source data fusion for precision agriculture, enabling early warnings, informed decision-making and proactive disease and pest management to reduce yield losses and improve food security. The study recommends the adoption of this intelligent framework for scalable agricultural monitoring and sustainable food production. Keywords: Hybrid model, Agriculture, Machine learning Crop disease, Prediction, Food security Aims Research Journal Reference Format: Aranuwa, F.O., Akinselu E.O,, Adagbonyin, T.I. & Aranuwa J.H. (2026): Towards Intelligent Agriculture: A Hybrid Data-Driven Model for Predicting Crop Disease and Pest Infestation. Advances in Multidisciplinary Research Journal. Vol. 12 No. 1,Pp 31-46. www.isteams.net/aimsjournal. dx.doi.org/10.22624/AIMS/V12N1P2

Zitieren

APA

Aranuwa, F., Akinselu, E., Adagbonyin, T., & Aranuwa, J. (2026). Towards Intelligent Agriculture: A Hybrid Data-Driven Model for Predicting Crop Disease and Pest Infestation. Advances in Multidisciplinary & Scientific Research Journal Publication, 12(1), 31-46. https://doi.org/10.22624/aims/v12n1p2

Vancouver

Aranuwa F, Akinselu E, Adagbonyin T, Aranuwa J. Towards Intelligent Agriculture: A Hybrid Data-Driven Model for Predicting Crop Disease and Pest Infestation. Advances in Multidisciplinary & Scientific Research Journal Publication. 2026;12(1):31-46. doi:10.22624/aims/v12n1p2

BibTeX
@article{Aranuwa2026,
  author = {Aranuwa, F.O. and Akinselu, E.O. and Adagbonyin, T.I. and Aranuwa, J.H.},
  title = {Towards Intelligent Agriculture: A Hybrid Data-Driven Model for Predicting Crop Disease and Pest Infestation},
  journal = {Advances in Multidisciplinary & Scientific Research Journal Publication},
  year = {2026},
  volume = {12},
  number = {1},
  pages = {31--46},
  doi = {10.22624/aims/v12n1p2}
}
Kostenlos starten →