Low-latency Forecasts of Kilonova Light Curves for Rubin and ZTF

TL;DR

This paper presents a machine learning tool that predicts kilonova light curves in real-time using simulated gravitational-wave alert data, aiding electromagnetic follow-up efforts for gravitational-wave events.

Contribution

It introduces a bidirectional LSTM model for low-latency kilonova light curve forecasting from gravitational-wave alerts, incorporating physical constraints and skymap data.

Findings

Achieves low mean squared error of 0.19 (ZTF) and 0.22 (Rubin) in light curve predictions.

Improved performance to an MSE of 0.1 when including ejecta mass information.

Model performance slightly decreases when full skymap data is used.

Abstract

Follow-up of gravitational-wave events by wide-field surveys is a crucial tool for the discovery of electromagnetic counterparts to gravitational wave sources, such as kilonovae. Machine learning tools can play an important role in aiding search efforts. We have developed a public tool to predict kilonova light curves using simulated low-latency alert data from the International Gravitational Wave Network during observing runs 4 (O4) and 5 (O5). It uses a bidirectional long-short-term memory (LSTM) model to forecast kilonova light curves from binary neutron star and neutron star-black hole mergers in the Zwicky Transient Facility (ZTF) and Rubin Observatory's Legacy Survey of Space and Time filters. The model achieves a test mean squared error (MSE) of 0.19 for ZTF filters and 0.22 for Rubin filters, calculated by averaging the squared error over all time steps, filters, and light curves in the test set. We verify the performance of the model against merger events followed-up by the ZTF partnership during O4a and O4b. We also analyze the effect of incorporating skymaps and constraints on physical features such as ejecta mass through a hybrid convolutional neural network and LSTM model. Using ejecta mass, the performance of the model improves to an MSE of 0.1. However, using full skymap information results in slightly lower model performance. Our models are publicly available and can help to add important information to help plan follow-up of candidate events discovered by current and next-generation public surveys.