将物理规律融入时序分解的RNN模型，提升空气质量预测精度与效率。
PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNN
- 分季节与趋势成分，嵌入领域方程到递归框架中
- 在多个预测时长上优于当前最优模型，MSE与MAE均更低
- 适合需要高精度且低计算开销的环境监测场景
时间序列预测常面临准确率与效率的权衡。尽管近期的Transformer模型提升了预测能力，但计算成本较高；线性模型虽更高效，但性能仍不理想。本文提出PIAD-SRNN，一种融合物理信息的自适应分解状态空间RNN，通过分离季节与趋势成分，并将领域方程嵌入递归结构中。我们在室内空气质量数据集上评估其表现，重点预测不同预测时长下的二氧化碳浓度。结果表明，该模型在长期与短期预测中均持续优于当前最优模型，包括基于Transformer的架构，在均方误差（MSE）和平均绝对误差（MAE）指标上均有显著提升。此外，本文还提供了四个精心整理的数据集。代码与数据见：https://github.com/ahmad-shirazi/DSSRNN。
原文摘要 · Abstract (English)
Time series forecasting often demands a trade-off between accuracy and efficiency. While recent Transformer models have improved forecasting capabilities, they come with high computational costs. Linear-based models have shown better accuracy than Transformers but still fall short of ideal performance. We propose PIAD-SRNN, a physics-informed adaptive decomposition state-space RNN, that separates seasonal and trend components and embeds domain equations in a recurrent framework. We evaluate PIAD-SRNN's performance on indoor air quality datasets, focusing on CO2 concentration prediction across various forecasting horizons, and results demonstrate that it consistently outperforms SoTA models in both long-term and short-term time series forecasting, including transformer-based architectures, in terms of both MSE and MAE. Besides proposing PIAD-SRNN which balances accuracy with efficiency, this paper also provides four curated datasets. Code and data: https://github.com/ahmad-shirazi/DSSRNN
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。