Research map / Probabilistic and scientific modeling / Differential equations and PDEs
A Deep Neural Network Model of Particle Thermal Radiation in Packed Bed
Hao Wu, Shuang Hao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace GPU Monte Carlo with DNN view-factor model | view factor computation · packed bed | time per particle (s): 0.64s -> 2.15 × 10−3s | Improved |
| replace serial CPU Monte Carlo with 6 processors | Monte Carlo view factor · packed bed | time per particle (s): 38.8s -> 7.26s | Improved |
| replace CPU Monte Carlo with GPU | Monte Carlo view factor · packed bed | time per particle (s): 7.26s -> 0.64s | Improved |
| increase network size to 25 x 25 x 25 neurons (ablation) | DNN for f6 · view factor f6 | average error: 1.2 × 10−3 -> 2.7 × 10−5 | Improved |
| increase network from 10 x 5 to 10 x 10 neurons (ablation) | DNN for f6 · view factor f6 | average error: 1.2 × 10−3 -> 3.3 × 10−4 | Improved |
| add data preprocessing (translation, scale, rotation, PCA) (ablation) | DNN for f6 · view factor f6 | average error | Improved |
| consider only pairs within 1.5d instead of full 3.0d range (ablation) | short-range radiation model · packed bed | accumulated view factor: 0.9977 vs 0.84 | Hurt |
| use neural network instead of linear/symbolic regression | two-sphere view factor · f2 | prediction error: 8×10−6 | Improved |
Closest papers by meaning
- Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems (ICML 2025 · similarity 0.80)
- PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs (NeurIPS 2024 · similarity 0.79)
- DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering (NeurIPS 2024 · similarity 0.79)
- Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics (ICML 2024 · similarity 0.79)
- Neural Field Thermal Tomography: A Differentiable Physics Framework for Non-Destructive Evaluation (NeurIPS 2026 · similarity 0.78)
- Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics (NeurIPS 2025 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
