Research map / Time series / Foundation models for time series
Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 learned positional embedding with RoPE (ablation) | CrossViViT · CAB 2020-2022 (all) | MAE: 51.11 -> 50.35 | Helped |
| replace learned positional embedding with RoPE (ablation) | CrossViViT · CAB 2020-2022 (hard split) | MAE: 56.84 -> 55.30 | Helped |
| replace learned positional embedding with RoPE (ablation) | CrossViViT · TAM 2017-2019 (all) | MAE: 109.28 -> 49.46 | Helped |
| add satellite spatio-temporal context via cross-attention | time-series transformers · CAB 2020-2022 (all) | MAE: 55.98 -> 50.35 | Helped |
| add satellite context to forecasting | CrossViViT · TAM 2017-2019 (all) | MAE: 32.26 -> 49.46 | Hurt |
| use small multi-quantile model instead of large (ablation) | Multi-Quantile CrossViViT · CAB 2020-2022 (all) | MAE: 74.26 -> 61.80 | Helped |
| use multi-quantile heads in place of single MLP head (ablation) | CrossViViT · CAB 2020-2022 (all) | MAE (median): 50.35 -> 61.80 | Hurt |
| mask time series input during training (ablation) | CrossViViT · CAB | MAE | No clear effect |
Closest papers by meaning
- SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting (NeurIPS 2024 · similarity 0.89)
- Solar Power Generation Forecasting via Multimodal Feature Fusion (Student Abstract) (AAAI 2024 · similarity 0.84)
- Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth (NeurIPS 2024 · similarity 0.82)
- Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting (NeurIPS 2025 · similarity 0.82)
- Multi-modal Learning for Geospatial Vegetation Forecasting (CVPR 2024 · similarity 0.82)
- On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting (NeurIPS 2025 · similarity 0.81)
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.