Deep Distributed Fusion Network for Air Quality Prediction

Yi, Xiuwen; Zhang, Junbo; Wang, Zhaoyuan; Zheng, Yu

doi:10.1145/3219819.3219822

Cited by 252 publications

(157 citation statements)

References 15 publications

Supporting

Mentioning

157

Contrasting

Order By: Relevance

“…Because air quality related time series data have dynamic and nonlinear characteristics, more and more researchers are trying to use data-driven models, especially in the field of urban computing [18]. A large number of air quality forecasting methods based on the big data have been proposed to help air pollution warning and control [37]. Zheng et al developed a semi-supervised learning approach for air quality forecasting which is based on a co-training framework consisting of two separated classifiers (ANN and CRF) [7].…”

Section: Related Workmentioning

confidence: 99%

Deep Air Quality Forecasting Using Hybrid Deep Learning Framework

Yang

et al. 2021

IEEE Trans. Knowl. Data Eng.

Self Cite

277

109

View full text Add to dashboard Cite

Air quality forecasting has been regarded as the key problem of air pollution early warning and control management. In this paper, we propose a novel deep learning model for air quality (mainly PM2.5) forecasting, which learns the spatial-temporal correlation features and interdependence of multivariate air quality related time series data by hybrid deep learning architecture. Due to the nonlinear and dynamic characteristics of multivariate air quality time series data, the base modules of our model include one-dimensional Convolutional Neural Networks (1D-CNNs) and Bi-directional Long Short-term Memory networks (Bi-LSTM). The former is to extract the local trend features and spatial correlation features, and the latter is to learn spatial-temporal dependencies. Then we design a jointly hybrid deep learning framework based on one-dimensional CNNs and Bi-LSTM for shared representation features learning of multivariate air quality related time series data. We conduct extensive experimental evaluations using two real-world datasets, and the results show that our model is capable of dealing with PM2.5 air pollution forecasting with satisfied accuracy.Index Terms-Air quality forecasting, deep learning, convolutional neural networks, long short-term memory networks ---------- ----------

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Air Quality Forecasting Using Hybrid Deep Learning Framework

Yang

et al. 2021

IEEE Trans. Knowl. Data Eng.

Self Cite

277

109

View full text Add to dashboard Cite

show abstract

“…Recently, various deep learning methods have been used to capture complex non-linear spatial-temporal correlations and predict spatial-temporal series, such as stacked fully connected network [24,35], convolutional neural network (CNN) [23,41] and recurrent neural network (RNN) [39]. Several hybrid models have been proposed to model both spatial and temporal information [7,33,34].…”

Section: Spatial-temporal Predictionmentioning

confidence: 99%

Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction

Yao

Liu

Wei

et al. 2019

The World Wide Web Conference

183

View full text Add to dashboard Cite

Spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environment policy making. Due to data collection mechanism, it is common to see data collection with unbalanced spatial distributions. For example, some cities may release taxi data for multiple years while others only release a few days of data; some regions may have constant water quality data monitored by sensors whereas some regions only have a small collection of water samples. In this paper, we tackle the problem of spatialtemporal prediction for the cities with only a short period of data collection. We aim to utilize the long-period data from other cities via transfer learning. Different from previous studies that transfer knowledge from one single source city to a target city, we are the first to leverage information from multiple cities to increase the stability of transfer. Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm. The meta-learning paradigm learns a well-generalized initialization of the spatial-temporal network, which can be effectively adapted to target cities. In addition, a pattern-based spatial-temporal memory is designed to distill long-term temporal information (i.e., periodicity). We conduct extensive experiments on two tasks: traffic (taxi and bike) prediction and water quality prediction. The experiments demonstrate the effectiveness of our proposed model over several competitive baseline models.

show abstract

“…Accurate prediction of air quality is a challenging task as it is affected by multiple factors such as meteorology, traffic, location, time and social events. Taking into consideration different factors, the work in [11] proposed a DNN (deep neural network with fusion components) based approach to predict the Air Quality Index (AQI), which is a widely used metric to indicate how polluted the air is. A spatial transformation component is used to address spatial correlation and a distributed fusion network is used to merge all the influential factors.…”

Section: Air Qualitymentioning

confidence: 99%

“…A CNN based framework was adopted to capture the salient n-gram information by convolution and pooling operations. Results showed that the deep learning based method substantially outperformed the conventional supervised learning methods (e.g., Support Vector Machines, Random Forest, and Reference Application Data Method Remarks Yi et al [11] Air quality Hourly air pollutants, meteorological data and weather forecast data in China DNN Air quality prediction; Hand-crafted spatial transformation component to address spatial correlation; fusion network to fuse different factors. Ong et al [10] Air quality PM2.…”

Section: Disastermentioning

confidence: 99%

“…Data generated by these devices can be preprocessed, integrated, and made available in standard formats through open services [3]. Numerous smart city applications have been developed and deployed, for example intelligent transportation [4], [5], [6], smart healthcare [7], [8], [9], environment monitoring [10], [11], [12], and public safety [13], [14], [15], just to name a few.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on an Emerging Area: Deep Learning for Smart City Data

Chen

Wang

et al. 2019

IEEE Trans. Emerg. Top. Comput. Intell.

124

View full text Add to dashboard Cite

Rapid urbanisation has brought about great challenges to our daily lives, such as traffic congestion, environmental pollution, energy consumption, public safety and so on. Research on smart cities aims to address these issues with various technologies developed for the Internet of Things. Very recently, the research focus has shifted towards processing of massive amount of data continuously generated within a city environment, e.g., physical and participatory sensing data on traffic flow, air quality, and healthcare. Techniques from computational intelligence have been applied to process and analyse such data, and to extract useful knowledge that helps citizens better understand their surroundings and informs city authorities to provide better and more efficient public services. Deep learning, as a relatively new paradigm in computational intelligence, has attracted substantial attention of the research community and demonstrated greater potential over traditional techniques. This paper provides a survey of the latest research on the convergence of deep learning and smart city from two perspectives: while the technique-oriented review pays attention to the popular and extended deep learning models, the application-oriented review emphasises the representative application domains in smart cities. Our study showed that there are still many challenges ahead for this emerging area owing to the complex nature of deep learning and wide coverage of smart city applications. We pointed out a number of future directions related to deep learning efficiency, emergent deep learning paradigms, knowledge fusion and privacy preservation, and hope these would move the relevant research one step further in creating truly distributed intelligence for smart cities.

show abstract

Deep Distributed Fusion Network for Air Quality Prediction

Cited by 252 publications

References 15 publications

Deep Air Quality Forecasting Using Hybrid Deep Learning Framework

Deep Air Quality Forecasting Using Hybrid Deep Learning Framework

Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction

A Survey on an Emerging Area: Deep Learning for Smart City Data

Contact Info

Product

Resources

About