AI Agent for Source Finding by SoFiA-2 for SKA-SDC2

2025-11-30

AI Summary

Manual tuning of source extraction parameters in SoFiA-2 for next-generation radio surveys (e.g., SKA) is time-consuming, inefficient, and heavily experience-dependent. Method: We propose the first deep reinforcement learning (DRL) framework for automated parameter optimization, integrating the Soft Actor-Critic (SAC) algorithm into the astronomical data processing pipeline. Using the SKA SDC2 dataset, we formulate a reward-driven interactive environment that jointly optimizes preprocessing, source finding, and reliability filtering parameters in an end-to-end manner. Contribution/Results: Our method surpasses the official SoFiA benchmark after only 100 evaluations, simultaneously improving detection completeness and purity while significantly reducing computational overhead. This work constitutes the first empirical validation of DRL’s efficacy in replacing manual hyperparameter tuning for complex scientific data analysis, establishing a novel paradigm for intelligent astronomical software development.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Auto ML and Hyperparameter Tuning
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Source extraction is crucial in analyzing data from next-generation, large-scale sky surveys in radio bands, such as the Square Kilometre Array (SKA). Several source extraction programs, including SoFiA and Aegean, have been developed to address this challenge. However, finding optimal parameter configurations when applying these programs to real observations is non-trivial. For example, the outcomes of SoFiA intensely depend on several key parameters across its preconditioning, source-finding, and reliability-filtering modules. To address this issue, we propose a framework to automatically optimize these parameters using an AI agent based on a state-of-the-art reinforcement learning (RL) algorithm, i.e., Soft Actor-Critic (SAC). The SKA Science Data Challenge 2 (SDC2) dataset is utilized to assess the feasibility and reliability of this framework. The AI agent interacts with the environment by adjusting parameters based on the feedback from the SDC2 score defined by the SDC2 Team, progressively learning to select parameter sets that yield improved performance. After sufficient training, the AI agent can automatically identify an optimal parameter configuration that outperform the benchmark set by Team SoFiA within only 100 evaluation steps and with reduced time consumption. Our approach could address similar problems requiring complex parameter tuning, beyond radio band surveys and source extraction. Yet, high-quality training sets containing representative observations and catalogs of ground truth are essential.

Problem

• Optimizing parameters for radio source extraction algorithms
• Automating parameter tuning using reinforcement learning AI agent
• Enhancing performance and efficiency in astronomical data analysis

Innovation

• AI agent optimizes SoFiA parameters via reinforcement learning
• Soft Actor-Critic algorithm automates parameter tuning for source extraction
• Framework reduces time and improves performance in radio survey analysis