He Wang PRO
Knowledge increases by sharing but not by saving.
2024年1月6日, 9:20-9:45
2023年第五届全球京师青年学者论坛 · 天文学科分论坛 | 广东 · 珠海
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)
中国科学院大学 · 引力波宇宙太极实验室(北京/杭州)
On behalf of the LIGO-VIRGO-KAGRA collaborations
BEFORE
AFTER
LIGO-G2300554
引力波天文学 & 引力波多信使天文学
Chinese Journal of Space Science, 2023, 43(4): 589-599.
LIGO-G2300554
Nat. Astron. 2021, 5(9): 881-889.
空基引力波探测科学数据的分析与地基相比差距很大:
空间引力波观测频段内含有大量的波源和多种波源类型:
空间太极计划
恒星级质量的致密双星 (黑洞、中子星、白矮星以及它们的两两组合) 的旋近
双白矮星的并合、超大质量双黑洞的并合
极端质量比旋进 (通常是一个恒星级致密天体绕着一个超大质量黑洞的旋进)
宇宙中可能存在的中等质量双黑洞以及前面这些源的信号叠加形成的引力波背景
Credit: ESA, K. Holley-Bockelmann
天琴计划
空间引力波探测获得的是什么样的 (科学) 数据?
其他重要的科学数据处理的技术挑战:
随机噪声(Stochastic noise)
仪器瞬变(glitches)
频谱线(Spectral lines)
数据间断(Data gaps)
非平稳性(Non-stationarities)
Baghi et al., Phys. Rev. D (2019)
Analyses cannot treat sources independently and sequentially work through a list of candidate detections.
Nat. Astron. 2022, 6(12): 1356-1363.
Nat. Astron. 2022, 6(12): 1334-1338.
背景与挑战
全局拟合方法 (Global-fit method)
实践应用步骤
局限性
全局拟合
Global-fit
Strub et al., PRD. arXiv:2307.03763
研究现状
UCB
GPU-based
...
Karnesis et al. 2303.02164.
Hoy & Nuttall. 2312.13039.
Weaving et al. CQG 41, (2023)
Littenberg & Cornish, Phys. Rev. D (2023)
技术痛点/局限性
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”
2023年,DeepMind发布AI工具GNoME (Nature),成功预测220万种晶体结构
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 + 量子、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
验证数学猜想
基于 CNN 的开创性研究工作
卷积神经网络 (CNN) 可以用来搜寻双黑洞并合系统所产生的引力波信号
灵敏度:与匹配滤波方法可比拟
执行速度:远胜过匹配滤波方法 (有GPU加持)
PRL, 2018, 120(14): 141103.
PRD, 2018, 97(4): 044039.
AI for Science \(\rightarrow\) AI for GW Astronomy
Exported: Oct, 2023 (in preparation)
Matched-filtering Convolutional Neural Network (MFCNN)
MLGWSC-1
The majority of AI algorithms used for testing are highly sensitive to non-Gaussian real noise backgrounds, resulting in high false positive rates.
(MFCNN group) H.W., et al. PRD (2023)
CL.M., W.W., H.W., et al. PRD (2022)
Ensemble learning
Leverages statistical approaches to utilize more information for making informed decisions by combining multiple models.
Real-time GW searches for GW150914
H.W., et al. PRD (2020)
Expanding the dimension of the output
CL.M., W.W., H.W., et al. PRD (2023)
\(h(\theta):=\sum_i \alpha_i(\theta) e_i \equiv \alpha(\theta) \text {, }\)
where \(\alpha\in\mathbb{C}^{241}\) and reduced basis \(\{e_i\}\) with \(\left\langle e_i \mid e_j\right\rangle=\delta_{i j}\).
深度学习算法的学习目标:
\((\mathcal{M}_c, \eta)\in\Theta\subset\mathbb{R}^2\)
\((\alpha_r, \alpha_i) \in\mathbb{R}^{482} \)
Neural
Network
AAK - FastEMRIWaveforms (FEW)
Katz et al., Phys. Rev. D (2021)
Chua et al., Phys. Rev. Lett., (2021)
~1s (快 ≳\(10^4\) 倍)
MNRAS 488, L94–L98 (2019)
EMRI 波形模板需求量 40 个数量级以上
张雪婷, C. Messenger, N. Korsakova,
ML Chan, 胡一鸣, 张建东, Phys. Rev. D (2022)
赵天宇, 周阅, 施锐俊, 曹周键, 任智祥, arXiv:2308.16422
恽倩芸, 韩文标, 郭意扬, 王赫, 杜明辉, arXiv:2309.06694
Zhang et al. PRD (2022) |
Zhao et al. (2308.16422) |
Yun et al. (2309.06694) |
|
---|---|---|---|
TDI | - | TDI-1.5 | TDI-2.0 |
Duration | 3 months | 1 year | 0.5 year |
Waveform Family (train) | AK | AAK | AAK |
Waveform Family (test) | AK / AAK | AK / AAK | AAK |
GW Project | TianQin | LISA | Taiji |
Acceleration Noise [fm/sqrt(Hz)] | 1 | 3 | 3 |
OMS Noise [pm/sqrt(Hz)] | 1 | 15 | 8 |
Base Model | CNN | CNN | CNN |
Input Feature domain | time | frequency | time-frequency |
sampling rate | 1/30 Hz | 1/15 Hz | 1/10 Hz |
Yun et al. (2311.18640) |
---|
TDI-2.0 |
0.5 year |
AAK |
AAK / EOB |
Taiji |
3 |
8 |
Unet / VGG |
time-frequency |
1/10 Hz |
Zhang et al. PRD (2022) |
Zhao et al. (2308.16422) |
Yun et al. (2309.06694) |
|
---|---|---|---|
TDI | - | TDI-1.5 | TDI-2.0 |
Duration | 3 months | 1 year | 0.5 year |
Waveform Family (train) | AK | AAK | AAK |
Waveform Family (test) | AK / AAK | AK / AAK | AAK |
GW Project | TianQin | LISA | Taiji |
Acceleration Noise [fm/sqrt(Hz)] | 1 | 3 | 3 |
OMS Noise [pm/sqrt(Hz)] | 1 | 15 | 8 |
Base Model | CNN | CNN | CNN |
Input Feature domain | time | frequency | time-frequency |
sampling rate | 1/30 Hz | 1/15 Hz | 1/10 Hz |
赵天宇*, Ruoxi Lyu*, 王赫, 曹周键, 任智祥, Commun. Phys., (2023)
"One Model to Rule Them All":EMRI / MBHB / GBs / SGWB 的信号提取
王赫, 吴仕超, 曹周键, 刘骁麟, 朱建阳,
Phys. Rev. D, (2020)
阮文洪*, 王赫*, 刘畅, 郭宗宽,
Phys. Lett. B, (2023)
LDC 一年数据上对 MBHB (+GBs) 信号的信号探测
杜明辉*, 梁博*, 王赫†, 徐鹏, 罗子人, 吴岳良†, accepted by SCPMA, arXiv:2308.05510
阮文洪, 王赫, 刘畅, 郭宗宽,
Universe (2023)
亮点:
归一化流模型示意图
亮点:
超高维度的波源参数空间特性 (编码波形)
科学数据的动态性 (编码数据)
计算资源的需求与利用 (CPU vs GPU)
F(t) over 1 year
h(t) over 10 min
y(t) over 1 year
Credit: Maude Le Jeune (2021)
Actually, there are more ...
多类型的大量波源混叠问题
for _ in range(num_of_audiences):
print('Thank you for your attention! 🙏')
This slide: https://slides.com/iphysresearch/2024jan_bnu
超高维度的波源参数空间特性 (编码波形)
科学数据的动态性 (编码数据)
计算资源的需求与利用 (CPU vs GPU)
F(t) over 1 year
h(t) over 10 min
y(t) over 1 year
Credit: Maude Le Jeune (2021)
Actually, there are more ...
多类型的大量波源混叠问题
EMRI 波形模板需求量 40 个数量级以上
MNRAS 488, L94–L98 (2019)
Chua et al., Phys. Rev. Lett., (2021)
~1s (快 ≳\(10^4\) 倍)
\(h(\theta):=\sum_i \alpha_i(\theta) e_i \equiv \alpha(\theta) \text {, }\)
where \(\alpha\in\mathbb{C}^{241}\) and reduced basis \(\{e_i\}\) with \(\left\langle e_i \mid e_j\right\rangle=\delta_{i j}\).
深度学习算法的学习目标
\((\mathcal{M}_c, \eta)\in\Theta\subset\mathbb{R}^2\)
\((\alpha_r, \alpha_i) \in\mathbb{R}^{482} \)
Neural
Network
Chua et al., PRL 122, 21 (2019): 211101.
Chua & Vallisneri. PRL 124, 4 (2020): 041102.
Katz et al., PRD 104, 6 (2021): 064047.
AKK - FastEMRIWaveforms (FEW) package
Katz et al., Phys. Rev. D (2021)
时长 1 年且含有信噪比 70的EMRI时域数据
Simulation-Based Inference (SBI)
PRL 127, 24 (2021) 241103.
PRL 130, 17 (2023) 171403.
Real-time gravitational wave science with neural posterior estimation
Sampling with prior knowledge for high-dimensional gravitational wave data analysis
H.W., et al. Big Data Min. Anal. (2021)
PRD 108, 4 (2023): 044029.
Neural Posterior Estimation with Guaranteed Exact Coverage: The Ringdown of GW150914
arXiv:2310.12209
Fast Parameter Inference on Pulsar Timing Arrays with Normalizing Flows
arXiv:2310.13405, LIGO-P2300306
Cosmological Inference using Gravitational Waves and Normalising Flows
PRL 131, 17 (2023): 171403.
Angular Power Spectrum of Gravitational-Wave Transient Sources as a Probe of the Large-Scale Structure
AI or Bayes
Text-to-image
"A running dog"
AI or Bayes
Text-to-image
"A corgi running on the street"
A picture is worth a thousand words.
A fraction of a thousand words.
Credit: 李宏毅
"A running dog"
On-going
Insights
Dynamic training samples in memory.
Nature Physics 18, 1 (2022): 9–11
On-going
Insights
Dynamic training samples in memory.
Nature Physics 18, 1 (2022): 9–11
for _ in range(num_of_audiences):
print('Thank you for your attention! 🙏')
This slide: https://slides.com/iphysresearch/2024jan_bnu
空间引力波探测的典型波源与全局拟合问题
GW sources and the global-fit problem
其他科学数据处理挑战:Glitches, gaps, non-stationarities
空间引力波探测科学数据处理的技术挑战(超高维参数空间(内禀),非稳态,计算资源)
科学数据处理的深度学习技术应用:现状
科学数据处理的深度学习技术应用:现状
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
©Floor Broekgaarden (repo)
GWTC-3
—— Bernard F. Schutz
DOI:10.1063/1.1629411
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
Matched-filtering Convolutional Neural Network (MFCNN)
GW150914 的实时信号搜寻
The majority of machine learning algorithms used for testing are highly sensitive to non-Gaussian real noise backgrounds, resulting in high false positive rates.
LIGO-Virgo data processing
PRD 107, 6 (2023) 063029
Ensemble learning leverages statistical approaches to utilize more information for making informed decisions by combining multiple models.
PRD 101, 10 (2020) 104003.
PRD 105, 8 (2022) 083013
PRD 107, 2 (2023): 023021.
Expanding the dimension of the output is to call more information to make decisions in improving AI models.
Bayesian statistics
Traditional parameter estimation (PE) techniques rely on Bayesian analysis methods (posteriors + evidence)
Data quality improvement
Credit: Marco Cavaglià
LIGO-Virgo data processing
GW searches
Astrophsical interpretation of GW sources
LIGO-Virgo data processing
Nature Physics 18, 1 (2022) 112–17
Big Data Mining and Analytics 5, 1 (2021) 53–63.
PRL 127, 24 (2021) 241103.
PRL 130, 17 (2023) 171403.
arXiv:2212.14283
Data quality improvement
Credit: Marco Cavaglià
LIGO-Virgo data processing
GW searches
Astrophsical interpretation of GW sources
arXiv:2212.14283
LIGO-Virgo data processing
arXiv:2212.14283
LIGO-Virgo data processing
Taiji
恒星级质量的致密双星 (黑洞、中子星、白矮星以及它们的两两组合) 的旋近
双白矮星的并合、超大质量双黑洞的并合
极端质量比旋进 (通常是一个恒星级致密天体绕着一个超大质量黑洞的旋进)
宇宙中可能存在的中等质量双黑洞以及前面这些源的信号叠加形成的引力波背景
LIGO-G2300554
Credit: ESA, K. Holley-Bockelmann
PLB 841 (2023) 137904.
Communications Physics, 2023, 6(1): 212.
arXiv:2308.05510
Universe, 2023, 9(9): 407.
Schematic view of the global fit approach.
GW170817
GW190412
GW190814
Bayes factor (MCMC)
PRD 101, 10 (2020) 104003.
(In preparation)
arXiv:2305.18528
ICML2023
Bayes
AI
Credit: 李宏毅
Text-to-image
Bayes
AI
Credit: 李宏毅
Text-to-image
for _ in range(num_of_audiences):
print('Thank you for your attention! 🙏')
This slide: https://slides.com/iphysresearch/2023ml_astromoy
Smith, Rory. Nature Physics 18, 1 (2022): 9–11
“国际理论物理中心(亚太地区)” 经联合国教科文组织第38届大会审议通过。由中国科学院、基金委和国际理论物理中心共同建设,是进行基础科学前沿与相关交叉科学领域高水平科研、教育和培训的非营利性组织,是联合国教科文组织基础科学方面的在国内的第一个二类中心。
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
By He Wang
第五届全球京师青年学者论坛-天文学科分论坛