Research map / Image generation / Fast diffusion sampling
GenDA: Generative Data Assimilation on Complex Urban Areas via Classifier-Free Diffusion Guidance
Francisco Giral, Álvaro Manzano Sevillano, Ignacio Gomez Perez, Ricardo Vinuesa, Soledad Le Clainche
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 classifier-free guidance with sensor-conditioned and unconditional branches instead of direct observation conditioning (same backbone) | GenDA multiscale graph diffusion · Urban wind reconstruction, 8000 obs | RRMSE: 0.189 -> 0.136 | Improved |
| add the multiscale reduced-mesh hierarchy (ablation) | GenDA · Urban wind reconstruction, 300 obs | RRMSE: 0.399 -> 0.312 | Improved |
| add the multiscale reduced-mesh hierarchy (ablation) | GenDA · Urban wind reconstruction, 3000 obs | RRMSE: 0.254 -> 0.192 | Improved |
| add the multiscale reduced-mesh hierarchy (ablation) | GenDA · Urban wind reconstruction, 8000 obs | RRMSE | No clear effect |
| add multiscale message passing to the supervised MeshGraphNet baseline | MGN · Urban wind reconstruction, 300 obs | RRMSE: 0.426 -> 0.412 | No clear effect |
| raise guidance weight from 1.0 to 2.0 (ablation) | GenDA · Urban wind reconstruction, 300 obs | RRMSE: 0.311 -> 0.298 | Improved |
| raise guidance weight from 2.0 to 3.0 (ablation) | GenDA · Urban wind reconstruction, 8000 obs | RRMSE: 0.145 -> 0.481 | Hurt |
| raise guidance weight from 2.0 to 3.0 (ablation) | GenDA · Urban wind reconstruction, 3000 obs | RRMSE: 0.183 -> 0.291 | Hurt |
| use guidance weight 1 (purely conditional) instead of guided sampling (ablation) | GenDA · Urban wind reconstruction (various obs) | RRMSE | Hurt |
| switch from random to cloud-based sensor placement at test time | GenDA · Sensor sampling strategy (100-4000 obs) | RRMSE: 0.291 -> 0.354 | Hurt |
| switch from random to trajectory-based sensor placement at test time | GenDA · Sensor sampling strategy (100-4000 obs) | RRMSE: 0.291 -> 0.345 | Hurt |
| increase number of assimilated observations | GenDA ensembles · Held-out sensor CRPS | CRPS: 0.058 -> 0.040 | Improved |
Closest papers by meaning
- FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation (NeurIPS 2025 · similarity 0.86)
- DiffDA: a Diffusion model for weather-scale Data Assimilation (ICML 2024 · similarity 0.85)
- Flow Field Reconstruction with Sensor Placement Policy Learning (NeurIPS 2025 · similarity 0.84)
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation (ICLR 2024 · similarity 0.83)
- Mesh-Free Convolution: Learned Spectral Attenuation and Transport (NeurIPS 2026 · similarity 0.83)
- Learning to Solve Generative ODEs Beyond the Linear Span (NeurIPS 2026 · similarity 0.82)
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.
