融合频域分解与注意力机制的LSTM模型，提升细颗粒物预测精度。
Frequency-Aware Attention-LSTM for PM$_{2.5}$ Time Series Forecasting
- 先用STL和FFT分离趋势、季节和去噪残差，过滤高频噪声
- 堆叠LSTM捕捉长期依赖，注意力机制动态聚焦关键时间点
- 在真实城市数据上优于传统模型，尤其擅长预测污染峰值
为提升细颗粒物（PM₂.₅）浓度预测的准确性和鲁棒性，本文提出FALNet——一种融合频域分解、时序建模与注意力精调的频率感知LSTM网络。模型首先采用STL与FFT提取趋势、季节成分及去噪后的残差项，有效抑制高频噪声干扰。滤波后的残差输入堆叠LSTM以捕获长期依赖关系，随后通过多头注意力机制动态聚焦关键时间步。在真实城市空气质量数据集上的实验表明，FALNet在MAE、RMSE和R²等标准指标上持续优于传统模型，具备强适应性，能有效捕捉污染峰值期间的剧烈波动与非平稳状态。结果验证了FALNet在实时空气污染预测、环境风险评估与决策支持中的有效性与通用性。
原文摘要 · Abstract (English)
To enhance the accuracy and robustness of PM$_{2.5}$ concentration forecasting, this paper introduces FALNet, a Frequency-Aware LSTM Network that integrates frequency-domain decomposition, temporal modeling, and attention-based refinement. The model first applies STL and FFT to extract trend, seasonal, and denoised residual components, effectively filtering out high-frequency noise. The filtered residuals are then fed into a stacked LSTM to capture long-term dependencies, followed by a multi-head attention mechanism that dynamically focuses on key time steps. Experiments conducted on real-world urban air quality datasets demonstrate that FALNet consistently outperforms conventional models across standard metrics such as MAE, RMSE, and $R^2$. The model shows strong adaptability in capturing sharp fluctuations during pollution peaks and non-stationary conditions. These results validate the effectiveness and generalizability of FALNet for real-time air pollution prediction, environmental risk assessment, and decision-making support.
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。