Research map / Label-efficient and robust learning / Recognition and long-tail
Refining Coarse-Grained Spatial Data Using Auxiliary Spatial Data Sets with Various Granularities
Yusuke Tanaka, Tomoharu Iwata, Toshiyuki Tanaka, Takeshi Kurashima, Maya Okawa, Hiroyuki Toda
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 hierarchical Gaussian processes with auxiliary-data uncertainty and spatial aggregation instead of 2-stage SD | Fine-grained spatial data refinement · PM2.5 | MAPE: 0.052 ± 0.007 -> 0.038 ± 0.005 | Improved |
| Use hierarchical Gaussian processes with auxiliary-data uncertainty and spatial aggregation instead of 2-stage SD | Fine-grained spatial data refinement · Ozone | MAPE: 0.035 ± 0.007 -> 0.030 ± 0.005 | Improved |
| Use hierarchical Gaussian processes with auxiliary-data uncertainty and spatial aggregation instead of 2-stage SD | Fine-grained spatial data refinement · Formaldehyde | MAPE: 0.101 ± 0.013 -> 0.078 ± 0.010 | Improved |
| Use hierarchical Gaussian processes with auxiliary-data uncertainty and spatial aggregation instead of 2-stage SD | Fine-grained spatial data refinement · Benzene | MAPE: 0.181 ± 0.032 -> 0.138 ± 0.021 | Improved |
| Use hierarchical Gaussian processes with auxiliary-data uncertainty and spatial aggregation instead of 2-stage SD | Fine-grained spatial data refinement · Elemental carbon | MAPE: 0.123 ± 0.016 -> 0.100 ± 0.012 | Improved |
| Use hierarchical Gaussian processes with auxiliary-data uncertainty and spatial aggregation instead of 2-stage SD | Fine-grained spatial data refinement · Poverty rate | MAPE: 0.228 ± 0.028 -> 0.202 ± 0.024 | Improved |
Closest papers by meaning
- Learning from Summarized Data: Gaussian Process Regression with Sample Quasi-Likelihood (AAAI 2025 · similarity 0.87)
- Consistent Bayesian Spatial Domain Partitioning Using Predictive Spanning Tree Methods (NeurIPS 2026 · similarity 0.85)
- Learning from Highly Sparse Spatio-temporal Data (NeurIPS 2024 · similarity 0.84)
- RDPI: A Refine Diffusion Probability Generation Method for Spatiotemporal Data Imputation (AAAI 2025 · similarity 0.83)
- Discovering Latent Causal Graphs from Spatiotemporal Data (ICML 2025 · similarity 0.82)
- Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach (ICML 2025 · 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.
