Open dataset for benchmarking scaling laws of high-energy laser atmospheric propagation
Xusheng Xia, Zhilin Xia

TL;DR
This paper introduces a comprehensive public dataset of high-energy laser atmospheric propagation simulations, enabling reproducible benchmarking, calibration, and development of surrogate models for scaling laws.
Contribution
It provides a large, organized, and validated dataset of 226,500 simulation cases, facilitating research in scaling-law calibration, benchmarking, and surrogate modeling.
Findings
Dataset includes 226,500 cases with diverse parameters.
Organized data supports statistical analysis and model training.
Simulation pipeline validated against established references.
Abstract
Scaling laws are increasingly used as fast surrogate models for high energy laser atmospheric propagation, yet their calibration and comparison still depend on large collections of high-fidelity wave-optics simulations. Existing studies usually rely on privately organized simulation outputs, which makes it difficult to reproduce published fits or evaluate new surrogate formulations on a shared benchmark. We present a public simulation dataset for high energy laser atmospheric propagation with coupled turbulence and thermal blooming. The release contains 226,500 cases spanning target speed, emission geometry, aperture diameter, visibility, aerosol model, beam quality, turbulence strength, and laser power. Data are organized as a case-level main table linked to indexed long-exposure irradiance arrays and centralized metadata, which supports statistical analysis without hiding the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
