Abdul Mutholib, International Islamic University, Malaysia; Nadirah Abdul Rahim, International Islamic University, Malaysia; Teddy Surya Gunawan, International Islamic University, Malaysia
Keywords: Artificial Intelligence (AI), Machine Learning (ML), Decision Support System, Satellite anomalies, Space situational awareness (SSA), Trade Space Exploration, Seradata
Abstract:
Satellites are vital for various applications, including communication, navigation, earth observation and any other research.
Satellite reliability is important for mission continuity and space sustainability, as anomalies can cause costly
failures, loss of operational capacity, and loss of sustainability in outer space. It results in crowded orbit and poses a
risk to other active or future missions. Traditional methods of identifying and resolving anomalies are often reactive
and limited in their ability to handle the complexity and volume of satellite data. Hence, this paper proposes a Web
AI-based Decision Support System (DSS) designed to enhance the identification and resolution of satellite anomalies.
The proposed Web AI-based DSS framework integrates Machine Learning (ML) based Trade-Space Exploration
(TSE) as the model base and Generative AI as the knowledge base to offer insights and recommendations for anomaly
prevention and decision making prior to the launch of the satellite into orbit. The system architecture includes a statistical
data module for satellite anomaly identification and a decision support application. The Seradata database is
utilized as the main source data for satellite anomalies which consist of around 4050 data since 1957. This system
aims to identify anomalies to prevent any failures that mostly occur during satellite orbit and provide appropriate recommendations
for counteractive actions. A detailed literature review highlights the current state of satellite anomaly
identification and the application of the Web AI-based DSS in various fields. The review identifies gaps in existing
research, emphasizing the need for a specialized DSS in satellite anomaly identification. The proposed framework
addresses these gaps by incorporating state-of-the-art artificial intelligence (AI) and a decision-making system. This
paper also summarizes the key findings of the case studies and discusses the benefits of using aWeb AI-based DSS for
satellite anomaly identification management. It also addresses potential challenges and limitations, such as the need
for continuous updates to the model and the integration of diverse data sources. The contribution of this paper can be
summarized as (i) outlines Web AI-based DSS for satellite anomaly identification, (ii) present comprehensive taxonomy
of the Web AI-Based DSS methods applied to space situational awareness (SSA), which addresses the insight of
factors leading to the loss of a satellite and its recommendation to prevent satellite failure during their operational. In
a nutshell, the proposed Web AI-based DSS framework provides a robust solution to manage satellite anomalies, improves
operational efficiency, and mitigates the risk of orbital satellite failure. The paper outlines prospective research
directions that include the advancement of more sophisticated anomaly identification algorithms and the incorporation
of additional data sources, such as data cost, to further improve system performance.
Date of Conference: September 16-19, 2025
Track: Space Debris