Research map / Probabilistic and scientific modeling / Dynamical systems
Physics Perception in Sloshing Scenes With Guaranteed Thermodynamic Consistency
Beatriz Moya, Alberto Badías, David González, Francisco Chinesta, Elías Cueto
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 |
|---|---|---|---|
| use sparse autoencoder instead of POD for velocity | latent reduction · Sloshing simulation, velocity | reconstruction MSE: 19 -> 4.1 | Improved |
| use sparse autoencoder instead of POD for shear stress | latent reduction · Sloshing simulation, shear stress | reconstruction MSE: 19 -> 0.798 | Improved |
| use sparse autoencoder instead of POD for normal stress | latent reduction · Sloshing simulation, normal stress | reconstruction MSE: 20 -> 5.1 | Improved |
| use sparse autoencoder instead of kPCA for velocity | latent reduction · Sloshing simulation, velocity | reconstruction MSE: 6.25 -> 4.1 | Improved |
| use sparse autoencoder instead of kPCA for shear stress | latent reduction · Sloshing simulation, shear stress | reconstruction MSE: 3.36 -> 0.798 | Improved |
| use sparse autoencoder instead of kPCA for position | latent reduction · Sloshing simulation, position | reconstruction MSE: 0.141 -> 0.149 | No clear effect |
| use sparse autoencoder instead of kPCA for internal energy | latent reduction · Sloshing simulation, internal energy | reconstruction MSE: 0.342 -> 0.472 | Hurt |
| use sparse autoencoder instead of kPCA for normal stress | latent reduction · Sloshing simulation, normal stress | reconstruction MSE: 3.371 -> 5.1 | Hurt |
| use sparse autoencoder instead of POD for position | latent reduction · Sloshing simulation, position | reconstruction MSE: 0.257 -> 0.149 | Improved |
Closest papers by meaning
- NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields (ICML 2022 · similarity 0.87)
- Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video (ICLR 2024 · similarity 0.85)
- PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling (ICML 2024 · similarity 0.85)
- Space and time continuous physics simulation from partial observations (ICLR 2024 · similarity 0.84)
- A Pioneering Neural Network Method for Efficient and Robust Fuel Sloshing Simulation in Aircraft (AAAI 2025 · similarity 0.83)
- Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems (CVPR 2025 · similarity 0.83)
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.
