针对数据少的污染预测，用双编码器融合源域知识与本地信息。
Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments
- 设计双编码器框架，分别学习源域通用特征和目标域特有模式。
- 在台湾77个站点测试中，误差比基线降低4%-7%，性能最佳时R²达0.8739。
- 允许源模型自适应调整效果更优，且近期观测和气象因素是主要影响因子。
短时序细颗粒物（PM2.5）预测在目标域数据有限且源域与目标域统计特性差异显著时仍具挑战。仅依赖本地数据训练的模型难以捕捉复杂时间动态，而直接迁移学习可能引发负迁移。本文提出一种感知域偏移的双编码器迁移学习框架，结合源域知识与目标域特定表征学习。源编码器基于美国10个监测点的小时级数据预训练。框架在台湾77个站点连续两年的小时级观测数据上进行适配与评估，采用时间顺序的训练-验证-测试协议。四类主干基线中，冻结源编码器的双编码器模型表现最优，均方误差（MSE）为21.8960，平均绝对误差（MAE）为3.1597，决定系数（R²）为0.8725，较TL-v1降低约7.1%的MSE，较TL-v2降低4.1%。消融实验显示，移除台湾特有分支导致性能下降最显著。允许源编码器自适应后，整体表现最佳，MSE=21.6575，MAE=3.1383，R²=0.8739。SHAP分析表明，预测主要受近期PM2.5观测值及影响污染物传输与扩散的气象变量驱动。结果表明，当保留目标域信息并允许在目标监督下自适应迁移表示时，源域知识最具有效性。
原文摘要 · Abstract (English)
Short-horizon forecasting of fine particulate matter (PM2.5) remains difficult when observations from the target domain are limited and the statistical properties of the source and target domains differ. In these settings, models trained only on local data may not capture complex temporal dynamics, while direct transfer learning can result in negative transfer. This study develops a shift-aware dual-encoder transfer framework that combines source-domain knowledge with target-specific representation learning. The source encoder was pretrained using hourly observations from 10 U.S. monitoring locations. The framework was then adapted and evaluated using two years of hourly observations from 77 stations in Taiwan under a chronological train-validation-test protocol. Among the four principal baselines, the frozen-source dual-encoder model achieved the best performance, with MSE = 21.8960, MAE = 3.1597, and R^2 = 0.8725. This corresponds to an MSE reduction of approximately 7.1% relative to TL-v1 and 4.1% relative to TL-v2. The ablation analysis showed that removing the Taiwan-specific branch caused the largest decline in performance. Allowing the source encoder to adapt produced the best overall result, with MSE = 21.6575, MAE = 3.1383, and R^2 = 0.8739. SHAP analysis indicated that predictions were driven mainly by recent PM2.5 observations and meteorological variables related to pollutant transport and dispersion. These results suggest that source-domain knowledge is most effective when target-specific information is preserved and the transferred representation is allowed to adapt under target supervision.
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。