Decision support system for Forest fire management using Ontology with Big Data and LLMs

2024-05-18

arXiv.org

AI Summary

Frequent forest wildfires pose severe threats to ecological security, yet existing Fire Weather Index (FWI) computation struggles with real-time fusion of heterogeneous meteorological data and interpretable reasoning. To address this, we propose an intelligent decision support system for forest fire management that uniquely integrates Semantic Web Rule Language (SWRL) rules and large language models (LLMs) within a Spark streaming framework. The system fuses the Semantic Sensor Network (SSN) ontology, meteorological–geospatial big data, and OWL-based logical inference to enable ontology-driven, real-time fire risk assessment and natural-language interactive early warning. Experimental results show sub-2-second system latency; LLM-based question answering achieves 92.3% accuracy, an F1-score of 0.89, and a recall of 0.91; ontology query coverage improves by 40%, significantly enhancing the interpretability of fire risk reasoning and operational decision support capability.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Data Mining & Knowledge Management: Semantic Web
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web crawling and indexing

Abstract

Forests are crucial for ecological balance, but wildfires, a major cause of forest loss, pose significant risks. Fire weather indices, which assess wildfire risk and predict resource demands, are vital. With the rise of sensor networks in fields like healthcare and environmental monitoring, semantic sensor networks are increasingly used to gather climatic data such as wind speed, temperature, and humidity. However, processing these data streams to determine fire weather indices presents challenges, underscoring the growing importance of effective forest fire detection. This paper discusses using Apache Spark for early forest fire detection, enhancing fire risk prediction with meteorological and geographical data. Building on our previous development of Semantic Sensor Network (SSN) ontologies and Semantic Web Rules Language (SWRL) for managing forest fires in Monesterial Natural Park, we expanded SWRL to improve a Decision Support System (DSS) using a Large Language Models (LLMs) and Spark framework. We implemented real-time alerts with Spark streaming, tailored to various fire scenarios, and validated our approach using ontology metrics, query-based evaluations, LLMs score precision, F1 score, and recall measures.

Problem

• Develops a decision support system for forest fire management using Big Data and LLMs
• Enhances fire risk prediction with meteorological and geographical data processing
• Implements real-time alerts for various fire scenarios using Spark streaming

Innovation

• Apache Spark for early fire detection
• Ontology and SWRL for DSS enhancement
• LLMs and Spark for real-time alerts