线性模型在长时序温度预测中胜过Transformer，DLinear表现最佳。
UrbanAI 2025 Challenge: Linear vs Transformer Models for Long-Horizon Exogenous Temperature Forecasting
- 用线性与Transformer模型对比长时序仅依赖历史温度的预测。
- DLinear在所有划分数据上准确率最高，优于复杂模型。
- 适合关注时间序列基线性能的研究者或实际应用部署者。
我们研究了仅依赖室内温度历史值的长时序外生温度预测——一种具有挑战性的单变量任务。在标准训练、验证和测试划分下，评估了Linear、NLinear、DLinear、Transformer、Informer和Autoformer等模型。结果表明，线性基线模型（Linear、NLinear、DLinear）始终优于更复杂的Transformer类架构，其中DLinear在所有数据划分中取得最优整体精度。这些发现表明，在极具挑战的外生仅依赖设定下，精心设计的线性模型仍是时间序列预测的强大基线。
原文摘要 · Abstract (English)
We study long-horizon exogenous-only temperature forecasting - a challenging univariate setting where only the past values of the indoor temperature are used for prediction - using linear and Transformer-family models. We evaluate Linear, NLinear, DLinear, Transformer, Informer, and Autoformer under standardized train, validation, and test splits. Results show that linear baselines (Linear, NLinear, DLinear) consistently outperform more complex Transformer-family architectures, with DLinear achieving the best overall accuracy across all splits. These findings highlight that carefully designed linear models remain strong baselines for time series forecasting in challenging exogenous-only settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。