A5046168949- earthquake and tectonic studies
- Seismic Waves and Analysis
- Seismic Imaging and Inversion Techniques
- Earthquake Detection and Analysis
- Explainable Artificial Intelligence (XAI)
- Methane Hydrates and Related Phenomena
- Geological and Geophysical Studies
- High-pressure geophysics and materials
- Big Data and Business Intelligence
- Seismology and Earthquake Studies
- Ethics and Social Impacts of AI
- Advanced Malware Detection Techniques
- Reinforcement Learning in Robotics
- Ionic liquids properties and applications
- Evolutionary Algorithms and Applications
- Geoscience and Mining Technology
- Natural Language Processing Techniques
- Adversarial Robustness in Machine Learning
- Network Security and Intrusion Detection
- Music Technology and Sound Studies
- Lubricants and Their Additives
- Photonic and Optical Devices
- Generative Adversarial Networks and Image Synthesis
- Advanced optical system design
- Landslides and related hazards
Chinese University of Hong Kong
2020-2025
Planetary Science Institute
2025
University of California, Berkeley
2025
East China Normal University
2024
Prince of Wales Hospital
2023
University of Science and Technology of China
2018
Abstract To derive high‐resolution fault zone (FZ) structure of the Chenghai in Yunnan, southwestern China, we deployed a linear dense array crossing from January to February 2018. The consisted 158 short‐period (5 s) three‐component instruments and spanned an aperture ~8 km with average station spacing 40–50 m. During 1‐month deployment, 20 teleseismic earthquakes moment magnitudes larger than 5.5 41 local were recorded. We first analyzed travel times P S waves determine boundaries FZ....
Abstract Low‐velocity zones (LVZ) in the shallow crust such as basins infilled with unconsolidated sediments could significantly amplify seismic waves and cause intense ground motions. In this study, we estimate site response Binchuan basin across active Chenghai fault zone northwest Yunnan Province, Southwest China using data from a large‐aperture (∼8 km) dense linear array of 125 three‐component seismometers deployed 2018 for ∼1 month. We observe that local earthquakes larger epicentral...
With the continuous improvement of national economy, development power enterprises is gradually accelerating, and popularity smart grids also increasing. The grid data center contains a large amount user data, analyzing this can help companies predict load plants, thereby improving resource utilization efficiency enterprises. However, current forecasting models still suffer from information leakage inaccurate predictions during transmission, storage, analysis processes. To solve above...
High-resolution imaging of the shallow structure a fault zone contributes valuable information about regional earthquake hazard and tectonic evolution. The Chenghai Fault (CHF), located in eastern margin collision between Indian Eurasia plates, has accumulated significant shear strain hosted several strong earthquakes, but our understanding its remains limited. Therefore, this study, we deploy ~4.3 km ~ 7 long dense linear arrays across Qina Pianjiao segments CHF from October 24 to November...
This book begins with a detailed introduction to the fundamental principles and historical development of GANs, contrasting them traditional generative models elucidating core adversarial mechanisms through illustrative Python examples. The text systematically addresses mathematical theoretical underpinnings including probability theory, statistics, game theory providing solid framework for understanding objectives, loss functions, optimisation challenges inherent GAN training. Subsequent...
Large Language Models (LLMs) have become a cornerstone of modern artificial intelligence (AI), finding applications across various domains such as healthcare, finance, entertainment, and customer service. To understand their ethical social implications, it is essential to first grasp what these models are, how they function, why carry significant impact. This introduction aims provide comprehensive beginner-friendly overview LLMs, introducing basic structure, training process, the types...
Abstract Determining focal mechanisms of abundant small-magnitude (M < 3) earthquakes can better reveal subsurface fault structures and stress features, but it remains challenging due to insufficient records or inefficient methods. In the past decade, seismicity in Weiyuan region southern Sichuan basin has increased dramatically following massive hydraulic fracturing activities. Here, we apply a multitask deep learning model, PhaseNet+, local dense seismic enhance mechanism catalog....
High-resolution imaging of fault zone structure and its temporal changes can not only advance our understanding earthquake physics, but is also critical for better seismic hazard preparation mitigation. In the past a few years, we deployed multi-scale dense arrays across Chenghai system in Binchuan, Yunnan, China. The first array consisted 381 intermediate-period three-component seismometers with an average station spacing ∼2 km. has been field ∼3 months 2017 recorded numerous local...
Abstract The Anninghe fault (ANHF), located in southwest China, was a major block boundary that hosted M 7.5 earthquakes historically. For seismic hazard assessment, it is critical to investigate properties before future earthquakes. To the structure, we deployed three linear dense arrays with an aperture of ∼8–9 km across different segments ANHF from October 2019 March 2020. More importantly, detonated new methane source generate waves, which environmentally friendly and can be used regions...
Artificial Intelligence (AI) has permeated numerous aspects of our daily lives, from predictive text on smartphones to complex decision-making systems in healthcare and finance. While AI shown remarkable accuracy efficiency, it is often criticized for being a 'black box,' particularly when comes models like deep learning large language (LLMs). This where Explainable (XAI) into play.Explainable aims make decisions transparent, understandable, interpretable. The lack interpretability raised...
Explainable Artificial Intelligence (XAI) addresses the growing need for transparency and interpretability in AI systems, enabling trust accountability decision-making processes. This book offers a comprehensive guide to XAI, bridging foundational concepts with advanced methodologies. It explores traditional models such as Decision Trees, Linear Regression, Support Vector Machines, alongside challenges of explaining deep learning architectures like CNNs, RNNs, Large Language Models (LLMs),...
A novel concept on the optical structure of grating spectrometer is introduced to improve wavelength resolution. Having entering from entrance, light transformed into parallel beam by a lens and concave mirror in order compress size image plane spectrometer, which efficiently reduces full width at half maximum spectral lines. been dispersed grating, converged with spectrum range smaller than that only mirror. By using home-developed Charge Coupled Device camera, lines 588.9951nm 589.5924nm...
Abstract Fault activity and structure are important factors for the assessment of seismic hazards. The Anninghe fault is one most active strike‐slip faults in southwestern China but has been experiencing quiescence M > 4 earthquakes since 1970s. To understand better characteristics its highly locked southern segment, we investigate seismicity ground motion variability using recently deployed multi‐scale dense arrays. Assisted by machine learning (ML) phase picking event discrimination...
Advancements in artificial intelligence, machine learning, and deep learning have catalyzed the transformation of big data analytics management into pivotal domains for research application. This work explores theoretical foundations, methodological advancements, practical implementations these technologies, emphasizing their role uncovering actionable insights from massive, high-dimensional datasets. The study presents a systematic overview preprocessing techniques, including cleaning,...
In recent years, the field of artificial intelligence (AI) and machine learning (ML) has undergone a transformative shift, with generative models emerging as one most significant impactful areas research. Generative models, in essence, are that can generate new data instances resemble given set training data. Unlike discriminative which focus on classification tasks, aim to understand replicate underlying structure data, making them capable generating images, text, audio, even 3D objects....
Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms impact on integrity confidentiality. Practical implementations, examples, label flipping, backdoor are explored alongside defenses such as training, differential privacy, federated learning, highlighting strengths limitations. Advanced methods like...
Large Language Models (LLMs) have become a cornerstone of modern artificial intelligence (AI), finding applications across various domains such as healthcare, finance, entertainment, and customer service. To understand their ethical social implications, it is essential to first grasp what these models are, how they function, why carry significant impact. This introduction aims provide comprehensive beginner-friendly overview LLMs, introducing basic structure, training process, the types...
Large Language Models (LLMs) have become a cornerstone of modern artificial intelligence (AI), finding applications across various domains such as healthcare, finance, entertainment, and customer service. To understand their ethical social implications, it is essential to first grasp what these models are, how they function, why carry significant impact. This introduction aims provide comprehensive beginner-friendly overview LLMs, introducing basic structure, training process, the types...