AI Paper Atlas

Research map / Time series / Long-term forecasting

SatSolarCast: A Flexible Framework for Multimodal Solar Irradiance Forecasting via Memory-Alignment Learning

Kuai Dai, Hui Su, Chengxing Zhai, Huiwei Lin, Mingliang Bai

AAAI 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 0 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 the recall phase of memory alignment training (ablation)LSTM+Sat · 3-hour forecasting ablationR2: 0.656 -> 0.726Improved
add the recall phase of memory alignment training (ablation)LSTM+Sat · 3-hour forecasting ablationRMSE: 178.21 -> 152.18Improved
add the recall phase of memory alignment training (ablation)PatchTST+Sat · 3-hour forecasting ablationR2: 0.690 -> 0.707Improved
add the global spatial feature extractor (ablation)LSTM+Sat · 3-hour forecasting ablationR2: 0.702 -> 0.726Improved
add the global spatial feature extractor (ablation)PatchTST+Sat · 3-hour forecasting ablationR2: 0.645 -> 0.707Improved
use spatiotemporal attention fusion instead of simple pooled addition (ablation)LSTM+Sat · 3-hour forecasting ablationRMSE: 153.97 -> 152.18Improved
use spatiotemporal attention fusion instead of simple pooled addition (ablation)PatchTST+Sat · 3-hour forecasting ablationR2: 0.703 -> 0.707Improved
add SatSolarCast satellite memory modulePatchTST · SolarCube 3-hour forecasting (4 stations)R2 and RMSE: 24.04% R2 increase and 17.57% RMSE reductionImproved
add SatSolarCast satellite memory modulePatchTST · SolarCube 6-hour forecasting (4 stations)R2 and RMSE: 21.92% R2 and 12.07% RMSEImproved
add SatSolarCast satellite memory moduleTransformer · SolarCube 3-hour forecasting (psu)R2: 0.603 -> 0.716Improved
add SatSolarCast satellite memory moduleLSTM · SolarCube 3-hour forecasting (psu)RMSE: 180.73 -> 147.17Improved
use LSTM-att+Sat instead of the ViT-based CrossVIVIT multimodal modelCrossVIVIT · SolarCube 3-hour forecasting (avg of 4 stations)R2: 0.693 -> 0.727Improved

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