AI Paper Atlas

Research map / Time series / Long-term forecasting

Generalising Traffic Forecasting to Regions Without Traffic Observations

Xinyu Su, Majid Sarvi, Feng Liu, Egemen Tanin, Jianzhong Qi

AAAI 2026 · Time series › Long-term forecasting · approach: Attention for time series forecasting · 3 citations (OpenAlex)

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 physics (LWR) loss, weather encoder and spatial grouping together to the STSM-style backboneGenCast · PEMS07RMSE: 8.390 -> 8.253Improved
remove physics constraint (w/o-phy) (ablation)GenCast-L · PEMS07 and PEMS-BayRMSEImproved
add physics constraint to GenCast-L with frozen LLM spatial embeddings (ablation)GenCast-L · PEMS07 and PEMS-BayRMSEImproved
add physics constraint to GenCast-H with trainable GeoHash embeddings (ablation)GenCast-H · PEMS07 and PEMS-BayRMSENo clear effect
add spatial grouping module with entropy loss (ablation)GenCast · PEMS07 and PEMS-BayRMSEImproved
add weather cross-attention encoder (ablation)GenCast · PEMS07 and PEMS-BayRMSEImproved
add spatial grouping entropy loss (ablation)GenCast-L · PEMS07entropy of group assignment weightsImproved
use LLM-based spatial embeddings instead of GeoHash-basedGenCast · PEMS-Bay, METR-LA, MelbourneRMSE: Melbourne RMSE 9.009 (H) vs 9.258 (L)Hurt
use LLM-based spatial embeddings instead of GeoHash-basedGenCast · PEMS07 and PEMS08RMSE: PEMS07 8.285 -> 8.253Improved
use GenCast on ring split of PEMS-BayGenCast · PEMS-Bay (ring split)R2: 0.189 -> 0.241Improved
apply GenCast without spatial embeddings or physics constraints to solar power dataGenCast-w/wx · NRELRMSE: 7.733 -> 7.620Improved
add KITS virtual-node training instead of masking subgraphKITS · PEMS07RMSE: 8.390 (STSM) vs 9.574 (KITS)Hurt

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