2023年6月27日, 15:00-15:30

量子宇宙理论物理研究中心研讨会

王赫

hewang@ucas.ac.cn

中国科学院大学 · 国际理论物理中心（亚太地区）

Gravitational Wave Detection and AI Technology:
New Methods for Unveiling the Mysteries of the Universe

• Thriving Advancements in AI for GW Astronomy
  • GW Searches
  • Parameter Estimation
  • Noise Characterization
• Challenge in GW Data Processing: Lessons and Future
  • AI: A transformative force driving scientific breakthroughs
• AI for Science: GW Astronomy
  • Interpretability of AI in science
• Key Takeaways

• In 1916, A. Einstein proposed the GR and predicted the existence of GW.

• Gravitational waves (GW) are a strong field effect in the GR.

  • 2015: the first experimental detection of GW from the merger of two black holes was achieved.

  • 2017: the first multi-messenger detection of a BNS signal was achieved, marking the beginning of multi-messenger astronomy.

  • 2017: the Nobel Prize in Physics was awarded for the detection of GW.

  • As of now: more than 90 gravitational wave events have been discovered.

  • O4, which began on May 24th 2023, is currently in progress.

双星并合系统产生的引力波波源

引力波振幅的测量

地面引力波探测器网络

2017 年诺贝尔物理学奖

• Fundamental Physics
  • Existence of gravitational waves
  • To put constraints on the properties of gravitons
• Astrophysics
  • Refine our understanding of stellar evolution
  • and the behavior of matter under extreme conditions.
• Cosmology
  • The measurement of the Hubble constant
  • Dark energy

©Floor Broekgaarden (repo)

• AI for Science \(\rightarrow\) AI for GW
• Artificial Intelligence (AI) has great potential to revolutionize gravitational wave astronomy by improving data analysis, modeling, and detector development.

• GW Data characteristics:

  • ​Noise: non-Gaussian and non-stationary

  • Signal: A low signal-to-noise ratio (SNR) which is typically about 1/100 of the noise amplitude (-60 dB)

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

Matched-filtering Convolutional Neural Network (MFCNN)

PRD 101, 10 (2020) 104003.

• The majority of machine learning algorithms used for testing are highly sensitive to non-Gaussian real noise backgrounds, resulting in high false positive rates.

PRD 107, 2 (2023): 023021.

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

• Expanding the dimension of the output is to call more information to make decisions in improving AI models.

• Ensemble learning leverages statistical approaches to utilize more information for making informed decisions by combining multiple models.

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

Likelihood

• Traditional parameter estimation (PE) techniques rely on Bayesian analysis methods (posteriors + evidence)

• Computing the full 15-dimensional posterior distribution estimate is very time-consuming:
  • Calculating likelihood function
  • Template generation time-consuming
• Machine learning algorithms are expected to speed up! 

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

• A complete 15-dimensional posterior probability distribution, taking about 1 s (<< \(10^4\) s).

Nature Physics 18, 1 (2022) 112–17

An example: Posterior probability distribution of the complete 15-dimensional parameters

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

• Prior Sampling: 50,000 Posterior samples in approximately 8 Seconds.

• DINGO (Deep INference for Gravitational wave Observations)
  • Tested on 42 BBH events from GWTC-3
  • Being deployed for O4, with the potential to become a new gravitational wave signal search pipeline
  • Capable of calculating evidence
  • Processing time: (using 64 CPU cores)
    • less than 1 hour with IMRPhenomXPHM,
    • approximately 10 hours with SEOBNRv4PHM

PRL 127, 24 (2021) 241103.

PRL 130, 17 (2023) 171403.

CQG. 37 (2020) 055002

• Billion-scale transformer-based model (WaveFormer)
  • Suppression on realistic noise, and
  • Recovery of injections / GW events

arXiv:2212.14283

DOI: 10.21203/rs.3.rs-2452860/v1

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

arXiv:2212.14283, DOI: 10.21203/rs.3.rs-2452860/v1

• Billion-scale transformer-based model (WaveFormer)
  • Suppression on realistic noise, and
  • Recovery of injections / GW events

arXiv:2212.14283

DOI: 10.21203/rs.3.rs-2452860/v1

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

• Billion-scale transformer-based model (WaveFormer)
  • Suppression on realistic noise, and
  • Recovery of injections / GW events

arXiv:2212.14283

DOI: 10.21203/rs.3.rs-2452860/v1

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

• Billion-scale transformer-based model (WaveFormer)
  • Suppression on realistic noise, and
  • Recovery of injections / GW events

arXiv:2212.14283

DOI: 10.21203/rs.3.rs-2452860/v1

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

• Billion-scale transformer-based model (WaveFormer)
  • Suppression on realistic noise, and
  • Recovery of injections / GW events

arXiv:2212.14283

DOI: 10.21203/rs.3.rs-2452860/v1

Data quality improvement

Credit: Marco Cavaglià 

LIGO-Virgo data processing

GW searches

Astrophsical interpretation of GW sources

CQG. 37 (2020) 055002

• Space-based GW Observatories (LISA / Taiji / TianQin)

LIGO-G2300554

PRL 130, 17 (2023) 171402.

• AI serves as a valuable tool in gravitational wave astronomy:
  (Big data & Computational Complexity)
  • Enhancing data analysis,
  • Noise reduction, and
  • Parameter estimation.
  • It streamlines the research process and allows scientists to focus on the most relevant information.
• Beyond a Tool: AI transcends its role as a mere tool by enabling scientific discovery in GW astronomy.
  • Characterization of GW signals involves
    • Exploring beyond the scope of GR ,
    • Enabling real-time inference
  • "Curse of Dimensionality" in inference
    • Overlapping signal  (In progress)
    • Hierarchical Bayesian Analysis (In progress)
  • Test of GR
    • Tighter parameter constraints of variance
    • Guaranteed exact coverage
  • ...

PRD 101, 10 (2020) 104003.

(In preparation)

arXiv: 2211.01304

• AI serves as a valuable tool in gravitational wave astronomy:
  (Big data & Computational Complexity)
  • Enhancing data analysis,
  • Noise reduction, and
  • Parameter estimation.
  • It streamlines the research process and allows scientists to focus on the most relevant information.
• Beyond a Tool: AI transcends its role as a mere tool by enabling scientific discovery in GW astronomy.
  • Characterization of GW signals involves
    • Exploring beyond the scope of GR , 
    • Enabling real-time inference
  • "Curse of Dimensionality" in inference
    • Overlapping signal  (In progress)
    • Hierarchical Bayesian Analysis (In progress)
  • Test of GR
    • Tighter parameter constraints of variance
    • Guaranteed exact coverage
  • ...

arXiv:2305.18528

• AI serves as a valuable tool in gravitational wave astronomy:
  (Big data & Computational Complexity)
  • Enhancing data analysis,
  • Noise reduction, and
  • Parameter estimation.
  • It streamlines the research process and allows scientists to focus on the most relevant information.
• Beyond a Tool: AI transcends its role as a mere tool by enabling scientific discovery in GW astronomy.
  • Characterization of GW signals involves
    • Exploring beyond the scope of GR , 
    • Enabling real-time inference
  • "Curse of Dimensionality" in inference
    • Overlapping signal  (In progress)
    • Hierarchical Bayesian Analysis (In progress)
  • Test of GR
    • Tighter parameter constraints of variance
    • Guaranteed exact coverage
  • ...

ICML2023

• Exploring the importance of understanding how AI models make predictions in scientific research.
  • The critical role of generative models (生成模型是关键)
  • Quantifying uncertainty: a key aspect (不确定性量化问题)
  • Fostering controllable and reliable models (模型的可控可信问题)

Bayes

AI

Credit: 李宏毅

Text-to-image

• Exploring the importance of understanding how AI models make predictions in scientific research.
  • The critical role of generative models (生成模型是关键)
  • Quantifying uncertainty: a key aspect (不确定性量化问题)
  • Fostering controllable and reliable models (模型的可控可信问题)

Bayes

AI

Credit: 李宏毅

Text-to-image

• 值得关注的 AI 技术：
  • Large Language Model (LLM)
  • AI generated content (AIGC)

WaveFormer

Transformer: 750x / 2yrs

• 2016年，AlphaGo 第一版发表在了 Nature 杂志上

• 2021年，AI预测蛋白质结构登上 Science、Nature 年度技术突破，潜力无穷

• 2022年，DeepMind团队通过游戏训练AI发现矩阵乘法算法问题​

• 《达摩院2022十大科技趋势》将 AI for Science 列为重要趋势

  • “人工智能成为科学家的新生产工具，催生科研新范式”

• AI for Science：为科学带来了模型与数据双驱动的新的研究范式

  • AI + 数学、AI + 化学、AI + 医药、AI + 物理、AI + 天文 ...

AlphaGo 围棋机器人

AlphaTensor 发现矩阵算法

AlphaFold 蛋白质结构预测