Physics-informed CNNs (PICNNs with soft PDE penalty and PInteCNNs with hard-coded solver) predict wood thermal responses from multimodal data, claiming better accuracy and interpretability than data-driven models on three wood datasets.
A multimodal physics-informed neural network approach for mean radiant temperature modeling.arXiv preprint arXiv:2503.08482, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physics-Informed Modeling for Wood Thermal Analysis and Prediction
Physics-informed CNNs (PICNNs with soft PDE penalty and PInteCNNs with hard-coded solver) predict wood thermal responses from multimodal data, claiming better accuracy and interpretability than data-driven models on three wood datasets.