MAGIC: Microlensing Analysis Guided by Intelligent Computation

Abstract

The modeling of binary microlensing light curves via the standard sampling-based method can be challenging, because of the time-consuming light-curve computation and the pathological likelihood landscape in the high-dimensional parameter space. In this work, we present MAGIC, which is a machine-learning framework to efficiently and accurately infer the microlensing parameters of binary events with realistic data quality. In MAGIC, binary microlensing parameters are divided into two groups and inferred separately with different neural networks. The key feature of MAGIC is the introduction of a neural controlled differential equation, which provides the capability to handle light curves with irregular sampling and large data gaps. Based on simulated light curves, we show that MAGIC can achieve fractional uncertainties of a few percent on the binary mass ratio and separation. We also test MAGIC on a real microlensing event. MAGIC is able to locate degenerate solutions even when large data gaps are introduced. As irregular samplings are common in astronomical surveys, our method also has implications for other studies that involve time series.

23 pages, 19 figures, accepted version. Code available at https://github.com/JasonZHM/magic-microlensing . An earlier version of this work is accepted to the ICML 2022 Workshop on Machine Learning for Astrophysics at https://ml4astro.github.io/icml2022/

References in corpus (21)

• Array Programming with NumPy
• U-Net and its variants for medical image segmentation: theory and applications
• Domain-adversarial neural networks to address the appearance variability of histopathology images
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Discovery of a Jupiter/Saturn Analog with Gravitational Microlensing
• No large population of unbound or wide-orbit Jupiter-mass planets
• Exoplanet Statistics and Theoretical Implications
• A recurrent neural network for classification of unevenly sampled variable stars
• On Neural Differential Equations
• Gravitational lens under perturbations: Symmetry of perturbing potentials with invariant caustics
• OGLE-III Microlensing Events and the Structure of the Galactic Bulge
• Predictions for Microlensing Planetary Events from Core Accretion Theory
• deep21: a Deep Learning Method for 21cm Foreground Removal
• Systematic KMTNet Planetary Anomaly Search. IV. Complete Sample of 2019 Prime-Field
• OGLE-2017-BLG-0173Lb: Low Mass-Ratio Planet in a "Hollywood" Microlensing Event
• A Ubiquitous Unifying Degeneracy in Two-Body Microlensing Systems
• Real-Time Likelihood-Free Inference of Roman Binary Microlensing Events with Amortized Neural Posterior Estimation
• A Machine Learning Classifier for Microlensing in Wide-Field Surveys
• Systematic KMTNet Planetary Anomaly Search, Paper III: One Wide-Orbit Planet And Two Stellar Binaries
• KMT-2019-BLG-0371 and the Limits of Bayesian Analysis
• Light Curve Calculations for Triple Microlensing Systems

Cited by in corpus (4)

• Entanglement-induced provable and robust quantum learning advantages
• Numerically studying the degeneracy problem in extreme finite-source microlensing events
• A differentiable binary microlensing model using adaptive contour integration method
• Binary-lens Microlensing Degeneracy: Impact on Planetary Sensitivity and Mass-ratio Function