Publications

Gravitational wave signal extraction against non-stationary instrumental noises with deep neural network

Sapce-borne gravitational wave antennas, such as LISA and LISA-like mission (Taiji and Tianqin), will offer novel perspectives for exploring our Universe while introduce new challenges, especially in data analysis. Aside from the known challenges …

Advancing Space-Based Gravitational Wave Astronomy: Rapid Detection and Parameter Estimation Using Normalizing Flows

Gravitational wave (GW) astronomy is witnessing a transformative shift from terrestrial to space-based detection, with missions like Taiji at the forefront. While the transition brings unprecedented opportunities for exploring massive black hole …

Probing the gravitational wave background from cosmic strings with Alternative LISA-TAIJI network

Analysis of LISA-TAIJI network configurations for detecting stochastic gravitational wave background from cosmic strings, finding LISA-TAIJIc offers optimal sensitivity for constraining string tension at G𝜇~10^-17.

Detecting Extreme-Mass-Ratio Inspirals for Space-Borne Detectors with Deep Learning

Deep learning approach for EMRI detection achieving 94.2% TPR at 1% FPR, demonstrating the potential for efficient signal detection in space-based gravitational wave detectors.

Parameter Inference for Coalescing Massive Black Hole Binaries Using Deep Learning

(This article belongs to the [Special Issue Newest Results in Gravitational Waves and Machine Learning](https://www.mdpi.com/journal/universe/special_issues/48U1E55JLC))

Space-based gravitational wave signal detection and extraction with deep neural network

Science-driven multi-stage deep neural network for space-based gravitational wave detection and extraction achieving >99% accuracy and ≥95% signal similarity, with strong generalization and interpretability demonstrated on synthetic LISA data.

Rapid search for massive black hole binary coalescences using deep learning

Deep learning method for rapid detection of massive black hole binary coalescences in LISA data, achieving high sensitivity with no false alarms while processing 1-year data in seconds.

First machine learning gravitational-wave search mock data challenge

First community-wide machine learning gravitational wave search challenge with 6 algorithms tested on progressively realistic data including real O3a noise. Top ML methods achieve 95% of matched filtering sensitivity for Gaussian noise and 70% for real noise.

Ensemble of deep convolutional neural networks for real-time gravitational wave signal recognition

Ensemble deep learning model combining multiple CNNs successfully detects all O1/O2 BBH events (except GW170818) with zero false alarms on one month of O2 data, demonstrating real-time GW analysis capability.

Sampling with prior knowledge for high-dimensional gravitational wave data analysis

Extracting knowledge from high-dimensional data has been notoriously difficult, primarily due to the so-called "curse of dimensionality" and the complex joint distributions of these dimensions. This is a particularly profound issue for …