AI, Machine Learning and Deep Learning Advances in the Photothermal, Photoacoustic and Diffusion Wave Sciences and Technologies
Recent advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) are rapidly transforming photothermal, photoacoustic, and diffusion-wave sciences and technologies. These data-driven approaches offer powerful tools to address long-standing challenges in inverse problems, image reconstruction, signal interpretation, and multi-scale modeling, where traditional physics-based methods often face limitations in computational efficiency and robustness. This Special Topic aims to bring together cutting-edge research that integrates AI/ML/DL techniques with photothermal and photoacoustic physics, as well as more generalized diffusion-wave phenomena, spanning both fundamental theory and practical applications. Topics of interest include physics-informed learning, hybrid modeling frameworks, data-driven discovery of transport mechanisms, and intelligent system design for sensing and imaging. By fostering cross-disciplinary collaboration among computational scientists, physicists, and engineers, this collection seeks to accelerate innovation and provide new insights into complex optically induced thermal, acoustic, ultrasonic and generalized wave-based processes across diverse materials and systems.
Topics covered include, but are not limited to:
- Physics-informed neural networks (PINNs) for heat and wave equations
- Deep learning for photothermal, photoacoustic and diffusion-wave image reconstruction
- Machine learning for inverse problems and parameter estimation
- AI-assisted signal processing and denoising/deblurring in photothermal/photoacoustic/diffusion-wave data
- Data-driven modeling of heat transport and diffusion-wave dynamics
- Hybrid physics–AI frameworks for thermal and acoustic systems
- Neural operators and surrogate models for multi-scale heat transfer
- AI-based design and optimization of photothermal, photoacoustic and diffusion-wave systems
- Uncertainty quantification and interpretability in AI-driven transport analysis (thermal, acoustic, diffusion-wave)
- High-dimensional and sparse data learning in photothermal/photoacoustic/diffusion-wave imaging
- AI in non-destructive evaluation, material characterization, and biomedical diagnosis
- Real-time monitoring and control using machine learning in thermal/sound systems
Guest Editors
JunYan Liu (Harbin University)
Hai Zhang (Laval University)
Lilei Hu (Shanghai University
Shanghai Jiao Tong University)
Jun Xia (University of Buffalo)
Pengfei Zhu (Federal Institute for Materials Research and Testing (BAM))