Research map / Time series / Causal and generative time series
WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction
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 |
|---|---|---|---|
| use UTAE (temporal attention) instead of Res18 U-Net, 5 days, vegetation features | spatio-temporal model · WildfireSpreadTS | average precision: 0.344 -> 0.372 | Helped |
| use ConvLSTM instead of Res18 U-Net | multi-temporal model · WildfireSpreadTS | average precision: 0.344 -> 0.310 | Hurt |
| add more input features (all instead of vegetation only) for UTAE (ablation) | UTAE, 5 days · WildfireSpreadTS | average precision: 0.372 -> 0.321 | Hurt |
| use VIIRS reflectance instead of NDVI as vegetation feature (1 day) (ablation) | Res18 U-Net · WildfireSpreadTS | average precision: 0.298 -> 0.314 | Helped |
| use VIIRS vs NDVI vs EVI2 with 3 to 5 input days (ablation) | Res18 U-Net · WildfireSpreadTS | average precision: 0.319 vs 0.319 (5 days) | No clear effect |
| increase number of input days from 1 to 5 for VIIRS vegetation features (ablation) | Res18 U-Net · WildfireSpreadTS | average precision: 0.314 -> 0.319 | Helped |
| add weather forecast features (with fire mask, 5 days) (ablation) | Res18 U-Net · WildfireSpreadTS | average precision: 0.293 vs 0.317 (topography) | Hurt |
| use all-day multi-temporal input (5 days) for U-Net with multi features | Res18 U-Net · WildfireSpreadTS | average precision: 0.341 -> 0.344 | No clear effect |
| use all detections instead of last detection only for persistence baseline | persistence baseline · WildfireSpreadTS | average precision: 0.135 -> 0.193 | Helped |
| add a learned model (logistic regression) over persistence | baseline · WildfireSpreadTS | average precision: 0.193 -> 0.288 | Helped |
Closest papers by meaning
- FireScope: Wildfire Risk Raster Prediction With a Chain-of-Thought Oracle (CVPR 2026 · similarity 0.87)
- Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire (NeurIPS 2024 · similarity 0.87)
- DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding (NeurIPS 2025 · similarity 0.84)
- Multi-modal Learning for Geospatial Vegetation Forecasting (CVPR 2024 · similarity 0.82)
- FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring (AAAI 2025 · similarity 0.82)
- MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing (NeurIPS 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.