Scalable Cosmic AI Inference using Cloud Serverless Computing with FMI

2025-01-08

AI Summary

To address the dual requirements of low hardware barriers and high accuracy for large-scale astronomical image inference, this paper proposes CAI, a cloud-native serverless inference framework. Methodologically, it introduces the first deep synergy paradigm between astronomical AI and serverless computing, integrating pretrained astronomical foundation models with redshift prediction models. We design the Function-as-a-Service Message Interface (FMI) protocol to unify end-to-end orchestration across heterogeneous compute resources, enabling a cloud–edge–device collaborative inference architecture. Experiments demonstrate that CAI reduces inference latency by 47% for thousand-image batches and improves resource utilization by 3.2× across cloud, HPC, and edge devices. The framework exhibits seamless scalability and cross-platform compatibility. The open-source implementation has been widely adopted in the astronomical community.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Hardware-aware ML
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Large-scale astronomical image data processing and prediction is essential for astronomers, providing crucial insights into celestial objects, the universe's history, and its evolution. While modern deep learning models offer high predictive accuracy, they often demand substantial computational resources, making them resource-intensive and limiting accessibility. We introduce the Cloud-based Astronomy Inference (CAI) framework to address these challenges. This scalable solution integrates pre-trained foundation models with serverless cloud infrastructure through a Function-as-a-Service (FaaS) Message Interface (FMI). CAI enables efficient and scalable inference on astronomical images without extensive hardware. Using a foundation model for redshift prediction as a case study, our extensive experiments cover user devices, HPC (High-Performance Computing) servers, and Cloud. CAI's significant scalability improvement on large data sizes provides an accessible and effective tool for the astronomy community. The code is accessible at https://github.com/UVA-MLSys/AI-for-Astronomy.

Problem

• Astronomical Image Processing
• High Precision Prediction
• Low-resource Hardware

Innovation

• Cloud Computing
• FMI (Federal Model Interface)
• Astronomical Image Analysis