AI Paper Atlas

Research map / Time series / Long-term forecasting

BCWildfire: A Long-term Multi-factor Dataset and Deep Learning Benchmark for Boreal Wildfire Risk Prediction

Zhengsen Xu, Sibo Cheng, Lanying Wang, Hongjie He, Wentao Sun, Jonathan Li, Lincoln Linlin Xu

AAAI 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters

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 changedWhereMeasuredEffect
add spatial position embedding (ablation)Crossformer · BCWildfire next-day riskF1: 88.11 -> 88.70Improved
add spatial position embedding (ablation)FEDformer · BCWildfire next-day riskF1: 86.87 -> 87.43Improved
add spatial position embedding (ablation)S_Mamba · BCWildfire next-day riskF1: 85.31 -> 87.46Improved
add spatial position embedding (ablation)SCINet · BCWildfire next-day riskF1: 86.38 -> 85.90Hurt
add spatial position embedding (ablation)CrossLinear · BCWildfire next-day riskF1: 87.81 -> 87.90No clear effect
add spatial position embedding (ablation)TSMixer · BCWildfire next-day riskF1: 87.97 -> 88.12No clear effect
add spatial position embedding across architectures (ablation)time-series forecasting models · BCWildfire next-day riskPR-AUC: S_Mamba 94.83 -> 95.74; TSMixer 96.24 -> 96.10Mixed
Transformer architectures vs CNN or Mambawildfire risk models · BCWildfire next-day riskrecall and stabilityImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy