A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN

TLDR

Time series data in practical applications often contain missing values caused by sensor malfunctions, network failures, and outliers. The study proposes a spatiotemporal prediction framework that combines missing‑value processing algorithms with a deep recurrent neural network to address missing data and temporal dependencies in time series. The framework uses missing‑tag and missing‑interval representations, applies three missing‑value fixing algorithms within an LSTM‑based deep neural network, and is trained on Jingjinji air‑quality data, with DFNN and GBDT as baselines. Experiments demonstrate that the DRNN framework outperforms DFNN and GBDT, confirming its effectiveness and offering insights into missing‑value handling strategies. Abstract.

Abstract

Abstract. Time series data in practical applications always contain missing values due to sensor malfunction, network failure, outliers etc. In order to handle missing values in time series, as well as the lack of considering temporal properties in machine learning models, we propose a spatiotemporal prediction framework based on missing value processing algorithms and deep recurrent neural network (DRNN). By using missing tag and missing interval to represent time series patterns, we implement three different missing value fixing algorithms, which are further incorporated into deep neural network that consists of LSTM (Long Short-term Memory) layers and fully connected layers. Real-world air quality and meteorological datasets (Jingjinji area, China) are used for model training and testing. Deep feed forward neural networks (DFNN) and gradient boosting decision trees (GBDT) are trained as baseline models against the proposed DRNN. Performances of three missing value fixing algorithms, as well as different machine learning models are evaluated and analysed. Experiments show that the proposed DRNN framework outperforms both DFNN and GBDT, therefore validating the capacity of the proposed framework. Our results also provides useful insights for better understanding of different strategies that handle missing values.