Submit via CMT here.
We invite submissions on topics at the intersection of machine learning and physical sciences, including but not limited to:
- Materials processing, manufacturing, and industrial applications
- Structure-property-performance and multi-scale materials modelling
- Fluid mechanics, thermal modelling, and transport phenomena
- Materials science and discovery for energy applications
- Machine learning surrogates for high-fidelity physical simulations
- Physics-informed and hybrid machine learning models
- Multi-scale and multi-fidelity learning
- Data-efficient learning, active learning, and experimental design
- Uncertainty quantification, robustness, and generalization in scientific ML
- Multi-physics and PDE-based modelling in energy and materials systems
- Power and energy systems (generation, storage, grids, optimisation, forecasting)
- Transportation and mobility systems
- Smart cities and integrated urban energy systems
- Climate science, climate modelling, and earth system emulation
- Interpretability, explainability, and scientific insight extraction in machine learning for scientific and industrial applications
- Closed-loop and autonomous discovery systems integrating simulations and experiments
- Inverse materials design and optimisation
- Generative models for novel materials and molecular systems
- Transfer learning and meta-learning across materials domains
- Learning from heterogeneous, incomplete, and multi-modal scientific datasets
- Self-supervised, weakly supervised, and few-shot learning for scientific and materials data
Submission Tracks
-
Full papers (max 16 pages including references, LNCS format) for oral presentation (~15min + 5min Q&A) and publication in Springer LNCS. Get the template here.
-
Extended abstracts (2 pages including references) for recently published work in top-tier venues (JMLR, JAIR, MLJ, PAMI, IJCAI, NeurIPS, ICLR, AISTATS, ICML, or other SJR Q1 / CORE A* venues). Authors should indicate the original publication venue in the submission form. Accepted abstracts will be presented orally (~10min + 5min Q&A). Get the template here.
Reviewing format
Double-blind review