The schedule and costs below are for half-day courses. Full-day courses cost twice as much as half-day courses. All amounts are in CNY. Tutorial registration is available through the conference registration page and may be completed separately or as part of a complete conference registration.
For additional questions, please get in touch with the Tutorial Chair at jguo@ntu.edu.tw
Tutorial Program Time Table
TUTORIAL DESCRIPTIONS
T1: Differentiable and data-driven ocean acoustic propagation modeling
Duration: Full-Day
Scheduled Date: Monday, May 25th, 2026
Presenter:
Prof. Mandar Chitre
Head, Acoustic Research Laboratory, National University of Singapore
Teaching Assistant:
Dr. Luyuan Peng
Research Fellow, National University of Singapore
Description:
Differentiable and data-driven approaches are reshaping ocean acoustic propagation modeling by enabling end-to-end optimization, uncertainty-aware inference, and seamless integration with machine learning. This full-day, hands-on tutorial introduces participants to the practical use of physics-based propagation models and their modern, differentiable counterparts, followed by data-driven methods that leverage measurements when the environment is only partially known. Using the open-source UnderwaterAcoustics.jl package — which offers a unified interface to a suite of propagation models in Julia (and is accessible from Python as well) — we will focus on the practical aspects of model selection, problem definition, interpretation of output, and performance considerations rather than exhaustive acoustic theory. Several featured models are differentiable, allowing them to serve as components within optimization problems and machine learning pipelines. Through guided exercises, attendees will develop an understanding of applications such as geoacoustic inversion, path planning with acoustic constraints, matched-field processing, etc. We will also explore data-driven modeling strategies that complement physics-based tools, including how to fuse sparse environmental information with acoustic observations to build robust, operationally useful models. The tutorial emphasizes reproducible workflows, code examples in Julia (and some in Python), and practical tips for scaling from toy problems to real-world scenarios. It is intended for students, researchers and practitioners in ocean acoustics with basic familiarity in scientific computing and some exposure to acoustic propagation modeling. No prior experience with Julia is required.
Biography:
Mandar Chitre is currently the Head of the Acoustic Research Laboratory (ARL) at the Tropical Marine Science Institute (TMSI) in Singapore. He is also an Associate Professor at the Department of Electrical & Computer Engineering (ECE) of the National University of Singapore (NUS). Mandar's research interests include underwater acoustic communications & networking, ocean acoustics, signal processing & machine learning, and collaborative underwater robotics. He was awarded the Distinguished Technical Achievement Award by the IEEE Oceanic Engineering Society in 2020 for his work on underwater communications & networking. He served as the Editor-in-Chief for the IEEE Journal of Oceanic Engineering from 2018 to 2023. Apart from his academic interests, Mandar has a strong passion for computing & software development. He currently maintains several open source packages for acoustic propagation modeling, signal processing, underwater communication, agent-based software development, and large scale graphical visualization.
Photo:
T3: Ocean Remote Sensing Using Global Navigation Satellite System Reflectometry
Duration: Half-Day
Scheduled Date: Monday, May 25th, 2026
Presenter:
Prof. Weimin Huang
Department of Electrical and Computer Engineering
Memorial University
St. John's, NL, A1B 3X5, Canada
Description:
In this tutorial, the research on radar ocean remote sensing using Global Navigation Satellite System Reflectometry (GNSS-R) will be introduced. First, the basic principles of GNSS-R will be explained. Next, some representative methods and most recent results for different ocean remote sensing applications of GNSS-R will be illustrated. The focus will be on sea ice sensing, wave information extraction, and wind speed mapping. Finally, some challenges and future directions about ocean remote sensing using GNSS-R will be outlined.
Biography:
Weimin Huang received the B.S., M.S., and Ph.D. degrees in radio physics from Wuhan University in 1995, 1997, and 2001, respectively, and the M.Eng. degree in electrical engineering from the Memorial University of Newfoundland, Canada. He was a postdoctoral fellow at the Memorial University of Newfoundland during 2004-2007. From 2008 to 2010, he was a Design Engineer with Rutter Technologies, St. John's, NL. Since 2010, he has been with the Faculty of Engineering and Applied Science, Memorial University of Newfoundland, where he is currently a Professor. He has authored or coauthored more than 350 refereed research articles. His research interests include the mapping of oceanic surface parameters (wind, wave, current) via high-frequency ground wave radar, X-band marine radar, global navigation satellite systems reflectometry, and synthetic aperture radar.
He was the recipient of the Discovery Accelerator Supplements Award from the Natural Sciences and Engineering Research Council of Canada in 2017, and the IEEE Geoscience and Remote Sensing Society Letters Prize Paper Award in 2019, as well as some other teaching and research awards. He is an IEEE OES Distinguished Lecturer. He was a member and the co-chair of the Electrical and Computer Engineering Evaluation Group for Natural Sciences and Engineering Research Council of Canada Discovery Grants from 2018 to 2021. He has been an associate editor for eight journals, including IEEE Transactions on Geoscience and Remote Sensing, IEEE Journal of Oceanic Engineering, etc., and a guest editor for seven journals. He has been a reviewer for more than 130 international journals and a reviewer for many international conferences. He is the general chair and the technical program co-chair for the IEEE 20th International Symposium on Antenna Technology and Applied Electromagnetics, and the general co-chair and the technical program co-chair of the IEEE Oceanic Engineering Society (OES) 13th Currents, Waves, and Turbulence Measurement Workshop. He is a Senior Member of IEEE and an Executive Committee member (Treasurer) of IEEE OES.
Photo:
T4: Machine Learning for Ocean Sensing: From Broken Clues to Vivid Scenes
Duration: Half-Day
Scheduled Date: Monday, May 25th, 2026
Presenters:
Prof. Lei Cheng
Department College of Information Science and Electronic Engineering
Zhejiang University
Prof. Haiqiang Niu
Institute of Acoustics, Chinese Academy of Sciences
Description:
Accurate characterization of complex ocean acoustic environments is a prerequisite for reliable underwater detection and communication. Yet over wide-area oceans, data collected by existing observing networks are often sparse, noisy, and incomplete, making it difficult to recover the fine-grained environmental structures most sensitive to sound propagation—such as eddies, turbulence, and internal waves. These limitations, in turn, make environment-adaptive sound field prediction and localization particularly challenging. This lecture series, Machine Learning for Ocean Sensing, presents a coherent machine-learning framework that progresses from environmental field reconstruction and forecasting to acoustic field prediction and passive target localization, bridging ocean physics, signal processing, and modern AI.
The first two classes focus on multidimensional spatiotemporal representation, reconstruction, and generation of ocean environmental fields. To address the common underuse of multiway information in conventional approaches, we build on tensor-based models—a multidimensional extension of matrix modeling—and integrate them with frontier AI techniques, including deep internal learning, self-supervised learning, neural differential equations, and diffusion models. The goal is to reconstruct and forecast fine-scale ocean structures from limited observations, enabling physically meaningful, high-resolution environmental estimates at scale.
Building on these reconstructed and forecasted environments, the lecture then shows how machine learning can drive major advances in underwater sound field prediction and passive acoustic localization. We present a series of studies spanning training datasets derived from both real-world measurements and simulations; localization in uncertain shallow-water environments; robustness to tilt mismatch in deep-water vertical arrays; simultaneous localization of multiple sound sources; and the development of physically interpretable complex-valued neural networks. In parallel, for sound field prediction, we introduce a pre-trained physics-informed neural network (PINN) approach that substantially improves prediction accuracy for high-frequency, rapidly varying sound fields.
Overall, the lecture highlights how modern machine learning can transform sparse, noisy ocean observations into actionable, fine-grained environmental knowledge—and translate that knowledge into robust acoustic prediction and high-resolution localization—opening new opportunities for next-generation ocean sensing under uncertainty.
Biographies:
Dr. Lei Cheng is currently a ZJU Young Professor in the College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China. He received the B.Eng. degree from Zhejiang University in 2013 and the Ph.D. degree from The University of Hong Kong in 2018. He was a Research Scientist at the Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, from 2018 to 2021. He is the author of Bayesian Tensor Decomposition for Signal Processing and Machine Learning (Springer, 2023). He served as a Tutorial Speaker at IEEE ICASSP 2023, and as an Invited Speaker at ASA 2024 and IEEE COA 2024.
He is currently an Associate Editor for IEEE Transactions on Signal Processing (IEEE TSP), IEEE Signal Processing Letters (IEEE SPL), and Signal Processing (Elsevier SP), and also serves as a Guest Editor for the Journal of the Acoustical Society of America (JASA). He is an elected member of the IEEE Sensor Array and Multichannel Technical Committee (IEEE SAM-TC). His research interests include Bayesian machine learning for tensor data analytics and interpretable machine learning for information systems. As the first or corresponding author, he has published more than 40 papers in IEEE Signal Processing Magazine (IEEE SPM), IEEE TSP, IEEE TPAMI, NeurIPS, JASA and IEEE JOE.
Dr. Haiqiang Niu is currently a Full Professor and Doctoral Supervisor at the State Key Laboratory of Acoustics and Marine Information, Institute of Acoustics, Chinese Academy of Sciences (CAS). He is a Fellow of the Acoustical Society of America (ASA) and serves as an Associate Editor for the Journal of the Acoustical Society of America (JASA). Additionally, he holds positions as a Joint Youth Editorial Board Member for Chinese Physics Letters (CPL), Chinese Physics B (CPB), Acta Physica Sinica, and Physics, as well as a Youth Editorial Board Member for Chinese Journal of Acoustics. His current research focuses on machine learning and compressive sensing-based passive underwater acoustic localization and detection, parameter inversion, and normal mode estimation. He has authored over 70 academic papers in leading journals such as JASA, IEEE Journal of Oceanic Engineering, and Applied Acoustics, including 22 papers in JASA/JASA Express Letters, with one single paper cited over 200 times. He has frequently served as a Session Chair at major international conferences, including the ASA Annual Meeting. Notably, he delivered a Plenary Speech at the 16th International Congress on Theoretical and Computational Acoustics and has given four invited talks at the ASA Annual Meetings.
Photos:
Dr. Haiqiang Niu
T5: Open-Source Underwater Robotics: Build Your Own Underwater Robots
Duration: Half-Day
Scheduled Date: Monday, May 25th, 2026
Presenter:
Prof. Fumin Zhang
IEEE Fellow
Chair Professor
Department of Mechanical and Aerospace Engineering
Department of Electronic and Computer Engineering
Director of HKUST-BDR Joint Research Institute
Director of HKUST-JD.COM Joint Research Lab
Director of HKUST-Wuxi Joint Laboratory for Robotic Embodied Dexterity and Intelligence
Associate Director of Low Altitude Economy Research Center
The Hong Kong University of Science And Technology
Overview
This tutorial introduces a practical, open-source approach to underwater robotics, covering system design, hardware integration, autonomy stack, and field deployment. Participants will gain hands-on insights into building and operating a modular, low-cost, and extensible underwater robotic platform suitable for research, education, and rapid prototyping.
The session bridges the gap between theory and real-world deployment, emphasizing open source, reproducibility, and community collaboration.
Motivation
For decades, underwater robotics has been constrained by high-cost proprietary platforms, closed software systems, and complex system integration pipelines. These barriers have limited participation to well-funded institutions and slowed innovation across the broader community. A rapidly maturing open-source system now enables researchers, startups, and students to develop their own underwater robots at significantly reduced cost.
This tutorial aims to:
- Lower the entry barrier to underwater robotics
- Demonstrate reproducible open-source workflows
- Share practical lessons from field deployments
- Foster collaboration within the OCEANS community
Learning Objectives
Participants will learn:
- System architecture of an open-source underwater robot (hardware + software stack)
- Mechanical and electrical design considerations for underwater environments
- Perception, navigation, and control of underwater robots
- Field deployment best practices and safety considerations
Target Audience
- Underwater robotics researchers
- Students
- Engineers entering underwater robotics
- Open-source robotics developers
- Industry practitioners
This tutorial will promote innovation and cultivate a collaborative community in underwater robotics. By empowering participants with reproducible tools and practical knowledge, we aim to broaden participation and reduce barriers in underwater robotic development.
Biography:
Dr. Fumin ZHANG is Chair Professor at the Hong Kong University of Science and Technology, serving as Director of HKUST-BDR Joint Research Institute, Director of HKUST-JD.COM Joint Research Lab, Director of HKUST-Wuxi Joint Laboratory for Robotic Embodied Dexterity and Intelligence, and Associate Director of Low Altitude Economy Research Center.
He received a PhD degree in 2004 from the University of Maryland (College Park) in Electrical Engineering and held a postdoctoral position in Princeton University from 2004 to 2007. His research interests include mobile sensor networks, maritime robotics, control systems, and theoretical foundations for cyber-physical systems. He received the NSF CAREER Award in September 2009 and the ONR Young Investigator Program Award in April 2010. He is currently serving as the co-chair for the IEEE RAS Technical Committee on Marine Robotics, associate editors for IEEE Transactions on Automatic Control, and IEEE Transactions on Control of Networked Systems, IEEE Journal of Oceanic Engineering, and International Journal of Robotics Research. He is an IEEE and ASME Fellow.
Photo:
T6: Deep Learning based Architectures for End-to-End Underwater Acoustic Communication and Channel Estimation
Duration: Half-Day
Scheduled Date: Monday, May 25th, 2026
Presenter:
Prof. Suleman Mazhar
Professor & TYSP Fellow, College of Underwater Acoustic Engineering, Harbin Engineering University
Email: suleman.mazhar@fulbrightmail.org ; suleman@hrbeu.edu.cn
Web: https://faculty.hrbeu.edu.cn/SulemanMazhar/
Description:
Deep Learning is an important and emerging field that is getting an attention from all application domains. Current interest in deep learning can be considered a second era renaissance of neural networks. Until the late 90s, researchers tried to identify reliable method to train very deep and better neural networks but gained limited success. With the development of simple yet important theoretical and algorithmic developments, the advances in hardware (GPUs), and advent of Big Data, Deep Learning fills the gap required for this transformation in machine learning.
Purpose of this short course is to introduce Deep Learning and its different architectures with applications in underwater communication and channel estimation so that participants can have an idea about how to utilize different deep learning architectures in underwater acoustic communication (UAC). Particular emphasis will be on end to end UAC OFDM approach and channel estimation. The tutorial will start from neural networks and will provide hands-on exercises with commonly known deep learning architectures using a high-level deep learning tool (Keras). The intent is to familiarize interested participants in nuances of different deep architectures.
Biography:
Dr. Suleman did PhD from Tokyo University (Japan) and post-doctorate from Georgetown University(Washington DC, USA). He has a vast portfolio of research projects as principle investigator of the BiSMiL Lab (Laboratory for Bio-inspired Simulation & Modeling of intelligent Life) in Pakistan and is currently working as a professor as Harbin Engineering University and is TYSP fellow. He served as the chair for IEEE-OES TC-Underwater Acoustics for 2023-24 and currently is the chair for IEEE-OES TC-Living Resources (2025-26). He is also IEEE Distinguished Lecturer and has delivered invited lectures on topics related to AI for Underwater Acoustics and Bio-acoustic applications. He is IEEE senior member, member of Acoustical Society of America and World Commission on Protected Area (International Union for Conservation). His research work focuses on design of deep learning based architectures for bio-acoustics based ecological monitoring and endangered species surveys and underwater acoustic communication receiver design.
Examples of previous tutorials/webinars by same presenter:
1. Tutorial Oceans Seattle 2019: https://seattle19.oceansconference.org/program/tutorials-workshops-and-demonstrations/#1568646083669-53a209b3-eb0d
2. ECOP Webinar: https://www.youtube.com/watch?v=cnEkMsGphNw
Photo:
