EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Context-Aware Multi-Agent Architecture for Wildfire Insights

Ashen Sandeep iD, Sithum Jayarathna iD, Sunera Sandaruwan iD, Venura Samarappuli iD, Dulani Meedeniya iD, Charith Perera iD

Sensors · 06.02.2026 · 26 (3) · 1070

DOI: 10.3390/s26031070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 06.02.2026. Verfasst von Ashen Sandeep und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wildfires are environmental hazards with severe ecological, social, and economic impacts. Wildfires devastate ecosystems, communities, and economies worldwide, with rising frequency and intensity driven by climate change, human activity, and environmental shifts. Analyzing wildfire insights such as detection, predictive patterns, and risk assessment enables proactive response and long-term prevention. However, most of the existing approaches have been focused on isolated processing of data, making it challenging to orchestrate cross-modal reasoning and transparency. This study proposed a novel orchestrator-based multi-agent system (MAS), with the aim of transforming multimodal environmental data into actionable intelligence for decision making. We designed a framework to utilize Large Multimodal Models (LMMs) augmented by structured prompt engineering and specialized Retrieval-Augmented Generation (RAG) pipelines to enable transparent and context-aware reasoning, providing a cutting-edge Visual Question Answering (VQA) system. It ingests diverse inputs like satellite imagery, sensor readings, weather data, and ground footage and then answers user queries. Validated by several public datasets, the system achieved a precision of 0.797 and an F1-score of 0.736. Thus, powered by Agentic AI, the proposed, human-centric solution for wildfire management, empowers firefighters, governments, and researchers to mitigate threats effectively.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencedisaster managementmultimodal RAGsustainabilityvisual question answering

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka.
  • School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK.

ORCID-Profile: Ashen Sandeep, Sithum Jayarathna, Sunera Sandaruwan, Venura Samarappuli, Dulani Meedeniya, Charith Perera

Zitieren

APA

Sandeep, A., Jayarathna, S., Sandaruwan, S., Samarappuli, V., Meedeniya, D., & Perera, C. (2026). Context-Aware Multi-Agent Architecture for Wildfire Insights. Sensors, 26(3), 1070. https://doi.org/10.3390/s26031070

Vancouver

Sandeep A, Jayarathna S, Sandaruwan S, Samarappuli V, Meedeniya D, Perera C. Context-Aware Multi-Agent Architecture for Wildfire Insights. Sensors. 2026;26(3):1070. doi:10.3390/s26031070

BibTeX
@article{Sandeep2026,
  author = {Sandeep, Ashen and Jayarathna, Sithum and Sandaruwan, Sunera and Samarappuli, Venura and Meedeniya, Dulani and Perera, Charith},
  title = {Context-Aware Multi-Agent Architecture for Wildfire Insights},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {3},
  pages = {1070},
  doi = {10.3390/s26031070}
}
Kostenlos starten →