Uncertainty-Driven Ontology for Decision Support System in Air Transport

Abstract

Recent electronics advances for air transport have increased aircraft density, volume, and frequency in the airspace. These advances come with control requirements for precise navigation, coordinated Air Traffic Management (ATM) or Unmanned aircraft system Traffic Management (UTM), and proactive security. The tight tolerances of aircraft control necessitate management of spatial uncertainty, timeliness precision, and confidence assessment, which have, respectively, variance, reliability, and veracity situation awareness and assessment metrics. Meeting such airspace requirements involves the ability to evaluate how those metrics impact ATM/UTM operations, making the complex interrelationships between them a key aspect for coping with the fast worldwide growth of air transport. To support such growth, ontologies have been proposed as a promising technology for making such interrelationships explicit, while facilitating communication between avionics devices. This paper investigates the use of ontologies in support of electronic ATM/UTM operations, highlighting the use of Uncertainty Representation and the Reasoning Evaluation Framework (URREF) in realizing the ability for Air Traffic Controllers (ATCs) to semantically communicate with aircraft operators concerning physical airspace coordination. Using Avionics Analytics Ontology (AAO) endowed with the URREF, application examples based on two airspace situations are presented. Example results for northeast coast of Brazil atmospheric volcanic ash as well as for the Eyjafjallajokull volcano eruption show a 65–80% success in providing warnings to ATCs for airspace control. The paper demonstrates that an ontology-based UTM enhances the capability and accuracy of an ATM to suggest rerouting in the presence of remarkably deteriorated weather conditions.

WITHDRAWN: Probabilistic Ontology based MEBN model for Tuberculosis Treatment in India

“…Insaurralde et al in his paper " Uncertainty-Driven Ontology for Decision Support System in Air Transport " [2] proposes a MEBN model for e cient airspace navigation and management. The developed model eases communication between avionic devices regarding physical air space coordination.…”

Value-based sensor and information fusion

“…For an edge node, such as internet of things (IoT), the user sits at a console monitoring multimedia data from devices each with on-board control actions and then performing DL analytics over all the data. Combined with an ontology, the agents can support decision timeliness and report quality to afford the decision maker situational assessment for situational awareness [28,29].…”

Digital twin meets information fusion: panel summary

“…An LLM, exemplified by ChatGPT, can be queried but the answers from these models lack a measure of consistency and uncertainty analysis [100]. Likewise, a second aspect is that of eliciting ontological relationships from fusing data [101,102,103] to support the BN to enhance output explainability [104]. Two efforts include data-driven deep learning models and a physics-Bayesian network model.…”