Predicting hourly PM2.5 concentrations in wildfire-prone areas using a SpatioTemporal Transformer model
Predicting hourly PM2.5 concentrations in wildfire-prone areas using a SpatioTemporal Transformer model
复制标题
使用 SpatioTemporal Transformer 模型预测野火多发地区每小时 PM2.5 浓度
DOI：
10.1016/j.scitotenv.2022.160446
复制
发表时间：
2023
影响因子：
9.8
通讯作者：
Blaszczak-Boxe, Christopher
中科院分区：
文献类型：
--
作者：
Yu, Manzhu;Masrur, Arif;Blaszczak-Boxe, Christopher
在全球范围内，野火变得越来越频繁和破坏性，产生大量的烟雾，可以传输数千英里。因此，改善野火的空气污染预测至关重要，并向公民提供与局部空气污染事件相关的更频繁，准确和可解释的更新。这项研究提出了一种基于多头注意力的深度学习架构，时空（ST）-Transformer，以改善野火多发地区PM2.5浓度的时空预测。ST-Transformer模型采用稀疏注意机制，集中在空间，时间和变量维度上最有用的上下文信息。该模型包括PM2. 5浓度的关键驱动因子作为预测因子，包括野火周长和强度、气象因子、道路交通、PM2. 5以及过去24 h的时间指标。该模型进行训练，在大洛杉矶地区的EPA的空气质量站的PM2.5浓度进行时间序列预测。预测结果与其他现有的时间序列预测方法进行了比较，表现出更好的性能，特别是在捕捉突然变化或峰值的PM2. 5浓度在野火的情况下。所提出的模型学习的注意力矩阵能够解释复杂的空间、时间和变量依赖关系，表明该模型可以区分野火和非野火。ST-Transformer模型的准确预测和解释能力可以帮助有效地监测和预测野火烟雾的影响，并适用于其他复杂的时空预测问题。
Globally, wildfires are becoming more frequent and destructive, generating a significant amount of smoke that can transport thousands of miles. Therefore, improving air pollution forecasts from wildfires is essential and informing citizens of more frequent, accurate, and interpretable updates related to localized air pollution events. This research proposes a multi-head attention-based deep learning architecture, SpatioTemporal (ST)-Transformer, to improve spatiotemporal predictions of PM2.5concentrations in wildfire-prone areas. The ST-Transformer model employed a sparse attention mechanism that concentrates on the most useful contextual information across spatial, temporal, and variable-wise dimensions. The model includes critical driving factors of PM2.5concentrations as predicting factors, including wildfire perimeter and intensity, meteorological factors, road traffic, PM2.5, and temporal indicators from the past 24 h. The model is trained to conduct time series forecasting on PM2.5concentrations at EPA's air quality stations in the greater Los Angeles area. Prediction results were compared with other existing time series forecasting methods and exhibited better performance, especially in capturing abrupt changes or spikes in PM2.5concentrations during wildfire situations. The attention matrix learned by the proposed model enabled interpretation of the complex spatial, temporal, and variable-wise dependencies, indicating that the model can differentiate between wildfires and non-wildfires. The ST-Transformer model's accurate predictability and interpretation capacity can help effectively monitor and predict the impacts of wildfire smoke and be applicable to other complex spatiotemporal prediction problems.