In this proof-of-concept study, we conduct multivariate timeseries forecasting for the concentrations of nitrogen dioxide (NO2), ozone (O3), and (fine) particulate matter (PM10 & PM2.5) with meteorological covariates between two locations using various deep learning models, with a focus on long short-term memory (LSTM) and gated recurrent unit (GRU) architectures. In particular, we propose an integrated, hierarchical model architecture inspired by air pollution dynamics and atmospheric science that employs multi-task learning and is benchmarked by unidirectional and fully-connected models. Results demonstrate that, above all, the hierarchical GRU proves itself as a competitive and efficient method for forecasting the concentration of smog-related pollutants.

翻译：在这项概念验证研究中，我们利用多种深度学习模型，对两个地点之间包含气象协变量的二氧化氮（NO2）、臭氧（O3）以及（细）颗粒物（PM10 和 PM2.5）浓度进行了多元时间序列预测，重点关注长短期记忆（LSTM）和门控循环单元（GRU）架构。特别地，我们受空气污染动力学和大气科学的启发，提出了一种集成的、层次化的模型架构，该架构采用多任务学习，并以单向和全连接模型作为基准。结果表明，最重要的是，层次化GRU被证明是预测雾霾相关污染物浓度的一种具有竞争力且高效的方法。