EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Digital technologies in rice blast disease management: a comprehensive systematic review of artificial intelligence, IoT, blockchain, and emerging digital tools

Sandip Garai, Suryakant Manik, Kanaka K․K․, Sudhir Kumar, Vijai Pal Bhadana, Nishit Malviya

Smart Agricultural Technology · 2026-12 · 15 · 102488

DOI: 10.1016/j.atech.2026.102488 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Smart Agricultural Technology, 2026-12. Verfasst von Sandip Garai und 5 weiteren Autor:innen. Die Arbeit nennt 127 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rice blast, caused by Magnaporthe oryzae (syn. Pyricularia oryzae ), is the most destructive fungal disease of rice, posing a major threat to global food security. Recent advances in artificial intelligence (AI) and digital agriculture have transformed disease detection, monitoring, and management; however, evidence on their effectiveness remains fragmented. This study presents a PRISMA 2020-compliant systematic review of AI-driven and digital technologies for rice blast management. A total of 2,056 records published between January 2021 and May 2026 were retrieved from PubMed, Scopus, Google Scholar, and Semantic Scholar, of which 109 peer-reviewed studies met the eligibility criteria following duplicate removal and multi-stage screening. Deep learning, particularly convolutional neural networks, dominated the literature, with reported detection accuracies reaching 99.75% under controlled conditions. YOLO-family models were the most widely used object detectors, while hyperspectral imaging, UAV-based remote sensing, and IoT-enabled sensing systems showed considerable promise for early and large-scale disease surveillance. Explainable AI was incorporated in only seven studies, and just 7% validated their models under real field conditions, highlighting a substantial gap between laboratory performance and practical deployment. No eligible studies investigated blockchain, digital twins, or federated learning for rice blast management. The review identifies key research priorities, including field-scale validation, pre-symptomatic detection, explainable AI, low-cost IoT platforms, blockchain-enabled traceability, and digital twin frameworks to enable robust, scalable, and trustworthy AI-driven rice blast management.

Zitieren

APA

Garai, S., Manik, S., K․K․, K., Kumar, S., Bhadana, V. P., & Malviya, N. (2026). Digital technologies in rice blast disease management: a comprehensive systematic review of artificial intelligence, IoT, blockchain, and emerging digital tools. Smart Agricultural Technology, 15, 102488. https://doi.org/10.1016/j.atech.2026.102488

Vancouver

Garai S, Manik S, K․K․ K, Kumar S, Bhadana VP, Malviya N. Digital technologies in rice blast disease management: a comprehensive systematic review of artificial intelligence, IoT, blockchain, and emerging digital tools. Smart Agricultural Technology. 2026;15:102488. doi:10.1016/j.atech.2026.102488

BibTeX
@article{Garai2026,
  author = {Garai, Sandip and Manik, Suryakant and K․K․, Kanaka and Kumar, Sudhir and Bhadana, Vijai Pal and Malviya, Nishit},
  title = {Digital technologies in rice blast disease management: a comprehensive systematic review of artificial intelligence, IoT, blockchain, and emerging digital tools},
  journal = {Smart Agricultural Technology},
  year = {2026},
  volume = {15},
  pages = {102488},
  doi = {10.1016/j.atech.2026.102488}
}
Kostenlos starten →