{"slug": "physics-guided-convolutional-neural-network-for-domain-growth-prediction-in-with", "title": "Physics-guided Convolutional Neural Network for Domain Growth Prediction in Systems with Conserved Kinetics", "summary": "Researchers developed an attention-based, physics-guided convolutional neural network to predict microstructural evolution in binary mixtures governed by the Cahn-Hilliard equation. The surrogate model accurately forecasts phase separation over long time periods, preserves mixture composition, and aligns with the Lifshitz-Slyozov domain-growth law, offering a computationally efficient alternative to traditional numerical solvers.", "body_md": "arXiv:2606.26128v1 Announce Type: new\nAbstract: The spatiotemporal evolution of many physical, chemical, and biological systems is described by nonlinear partial differential equations (PDEs). Recently, deep neural network-based surrogate models have gained increasing interest as efficient alternatives to computationally expensive traditional numerical solvers. In this work, we propose an attention-based, physics-guided convolutional neural network as a surrogate model to learn the microstructural evolution of such systems. We train the model to accurately predict the full time-evolution of phase separation in binary mixtures governed by the Cahn-Hilliard equation. We show that predictions from our trained surrogate model remain stable and accurate over long-time rollouts for both critical and off-critical mixtures and preserve the mixture composition throughout evolution. We also show that our model accurately captures the growth of domain size and is consistent with the Lifshitz-Slyozov domain-growth law. The prediction results demonstrate the effectiveness of the proposed framework for modeling systems with conserved kinetics and can be extended to other complex dynamical systems.", "url": "https://wpnews.pro/news/physics-guided-convolutional-neural-network-for-domain-growth-prediction-in-with", "canonical_source": "https://arxiv.org/abs/2606.26128", "published_at": "2026-06-26 04:00:00+00:00", "updated_at": "2026-06-26 04:16:48.076239+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "computer-vision"], "entities": ["Cahn-Hilliard equation", "Lifshitz-Slyozov domain-growth law"], "alternates": {"html": "https://wpnews.pro/news/physics-guided-convolutional-neural-network-for-domain-growth-prediction-in-with", "markdown": "https://wpnews.pro/news/physics-guided-convolutional-neural-network-for-domain-growth-prediction-in-with.md", "text": "https://wpnews.pro/news/physics-guided-convolutional-neural-network-for-domain-growth-prediction-in-with.txt", "jsonld": "https://wpnews.pro/news/physics-guided-convolutional-neural-network-for-domain-growth-prediction-in-with.jsonld"}}