MAGIC: Microlensing Analysis Guided by Intelligent Computation
This work addresses a specific problem in astronomy for researchers analyzing microlensing data, offering an incremental improvement by applying existing machine-learning techniques to a domain-specific bottleneck.
The authors tackled the challenge of modeling binary microlensing light curves, which is difficult due to slow computations and complex likelihood landscapes, by developing MAGIC, a machine-learning framework that uses neural networks and neural controlled differential equations to handle irregular sampling and data gaps, achieving fractional uncertainties of a few percent on key parameters like mass ratio and separation in simulations and successfully testing it on a real event.
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.