Mapping spatial distribution of particulate matter using Kriging and Inverse Distance Weighting at supersites of megacity Delhi

Air pollution is a global health threat. Except static official air quality stations, mobile sensing systems are deployed for urban air pollution monitoring to achieve larger sensing coverage and greater sampling granularity. However, the data sparsity and irregularity also bring great challenges for pollution map recovery. To address these problems, we propose a deep autoencoder framework based inference algorithm. Under the framework, a partially observed pollution map formed by the irregular samples are input into the model, then an encoder and a decoder work together to recover the entire pollution map. Inside the decoder, we adopt a convolutional long short-term memory (ConvLSTM) model by revealing its physical interpretation with an atmospheric dispersion model, and further present a weather-related ConvLSTM to enable quasi real-time applications. To evaluate our algorithm, a half-year data collection was deployed with a real-world system on a coastal area including the Sino-Singapore Tianjin Eco-city in north China. With the resolution of 500 m x 500 m x 1 h, our offline method is proved to have high robustness against low sampling coverage and accidental sensor errors, obtaining 14.9% performance improvement over existing methods. Our quasi real-time model better captures the spatiotemporal dependencies in the pollution map with unevenly distributed samples than other real-time approaches, obtaining 4.2% error reduction.

Fine-Grained Air Pollution Inference with Mobile Sensing Systems: A Weather-Related Deep Autoencoder Model

Particulate matter (PM2.5) concentrations are a serious human health concern and global models are the common methods for PM2.5 particle estimation disregarding the local changes and factors. In th...

Predicting PM2.5 levels over the north of Iraq using regression analysis and geographical information system (GIS) techniques

In recent years, there is an increasing attention on air quality derived services for the final users. A dense grid of measures is needed to implement services such as conditional routing, alerting on data values for personal usage, data heatmaps for Dashboards in control room for the operators, and for web and mobile applications for the city users. Therefore, the challenge consists of providing high density data and services starting from scattered data and regardless of the number of sensors and their position to a large number of users. To this aim, this paper is focused on providing an integrated solution addressing at the same time multiple aspects: To create and optimize algorithms for data interpolation (creating regular data from scattered), making it possible to cope with the scalability and providing support for on demand services to provide air quality data in any point of the city with dense data. To this end, the accuracy of different interpolation algorithms has been evaluated comparing the results with respect to real values. In addition, the trends of heatmaps interpolation errors have been exploited to detected devices' dysfunctions. Such anomalies may often be useful to request a maintenance action. The solution proposed has been integrated as a Micro Services providing data analytics in a data flow real time process based on Node.JS Node-RED, called in the paper IoT Applications. The specific case presented in this paper refers to the data and the solution of Snap4City for Helsinki. Snap4City, which has been developed as a part of Select4Cities PCP of the European Commission, and it is presently used in a number of cities and areas in Europe.

High Density Real-Time Air Quality Derived Services from IoT Networks.

Air pollution presents a serious health challenge in urban metropolises. While accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models have yet fully captured the complex interactions between the temporal characteristics of air pollution and the spatial characteristics of urban dynamics. Our proposed Deep-AIR fills this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast, by exploiting domain-specific features (including Air Pollution, Weather, Urban Morphology, Transport, and Time-sensitive features), with a hybrid CNN-LSTM structure to capture the spatio-temporal features, and 1x1 convolution layers to enhance the learning of temporal and spatial interaction. Deep-AIR outperforms compatible baselines by a higher accuracy of 1.5%, 2.7%, and 2.3% for Hong Kong and 1.4%, 1.4% and 3.3% for Beijing in fine-grained 1-hr pollution estimation, and 1-hr and 24-hr forecasts, respectively. Saliency analysis reveals that for Hong Kong, spatial features, including street canyon and road density, are the best predictors for NO2, while temporal features, including historical air pollutants and weather, are the best predictors for PM2.5. For Beijing, historical air pollutant data, traffic congestion, wind direction and seasonal indicator are the best predictors for all pollutants. PM10 in Hong Kong is achieving the best estimation and forecast accuracy, whilst CO in Beijing is achieving the best results.

Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-grained Air Pollution Estimation and Forecast in Metropolitan Cities

Air pollution in a city is the major environmental risk to health. Mobile sensing has become a popular solution in recent years. However, it still suffers from problems such as lack of data and high system uncertainty. This is because that the data amount and distribution vary over time. To address the problems, this paper combines two classic data driven models -- Kriging and Inverse Distance Weighting (IDW). We adopt the Random Forest Algorithm (RF) to adaptively choose the more accurate models (Kriging or IDW) according to the features we extracted. The experiment based on real world testbed shows our adaptive method achieves up to 30.6% error reduction.

A Hybrid Air Pollution Reconstruction by Adaptive Interpolation Method

Mobile sensor networks are widely deployed for air quality monitoring. However, fine-grained pollution inference based on these systems is challenging. Specifically, diverse geospatial attributes in urban areas bring great spatial variations of the pollution field. Besides, the preprocessing on raw samples, such as discretization and averaging, leads to the lost of fine-grained information of mobile sensing. In this paper, we propose an inference algorithm with the attention mechanism to better capture high-frequency information in the pollution field. Furthermore, we introduce the sensing gradients in the attention network to utilize the high-granularity information from the mobile sensors. Evaluations on real-world dataset show that our model outperforms the state-of-the-art method by 13.15% ~ 27.04%.

Enhanced air quality inference with mobile sensing attention mechanism: poster abstract

Air pollution is a serious urban problem that threatens human health. Therefore, fine-grained pollution events detection has become a concerned issue for environmental management. Algorithms in previous studies identify pollution events as uptrend intervals at hour level. However, a significant part of pollution events caused by traffic and industry can be brief but frequent, which may be neglected under traditional coarse-grained detection. In this paper, we propose a fine-grained analysis of air pollution pattern based on minute-level event detection. Over the real-world deployment in Foshan, these events are analyzed according to their geographical contexts and temporal features. Results show insightful findings and this case study provides a practical reference for government inspection and pollution control.

Jiayi Huang

Papers

A Hybrid Air Pollution Reconstruction by Adaptive Interpolation Method

Enhanced air quality inference with mobile sensing attention mechanism: poster abstract

Understanding air pollution patterns in city based on minute-level event detection: poster abstract