Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities

03/25/2021
by   Yang Han, et al.
9

Air pollution has long been a serious environmental health challenge, especially in metropolitan cities, where air pollutant concentrations are exacerbated by the street canyon effect and high building density. Whilst accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models fail to fully address the complex interaction between air pollution and urban dynamics. Our Deep-AIR, a novel hybrid deep learning framework that combines a convolutional neural network with a long short-term memory network, aims to address this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast. Our proposed framework creates 1x1 convolution layers to strengthen the learning of cross-feature spatial interaction between air pollution and important urban dynamic features, particularly road density, building density/height, and street canyon effect. Using Hong Kong and Beijing as case studies, Deep-AIR achieves a higher accuracy than our baseline models. Our model attains an accuracy of 67.6 and 24-hr air pollution forecast for Hong Kong, and an accuracy of 65.0 75.3 Kong, street canyon and road density are the best estimators for NO2, while meteorology is the best estimator for PM2.5.

READ FULL TEXT

page 7

page 12

page 14

page 18

research
08/16/2021

AIREX: Neural Network-based Approach for Air Quality Inference in Unmonitored Cities

Urban air pollution is a major environmental problem affecting human hea...
research
11/29/2019

Spatiotemporal deep learning model for citywide air pollution interpolation and prediction

Recently, air pollution is one of the most concerns for big cities. Pred...
research
10/30/2017

Measuring the Impact of Urban Street Trees on Air Quality and Respiratory Illness

New streams of data enable us to associate physical objects with rich mu...
research
08/13/2020

A Novel CMAQ-CNN Hybrid Model to Forecast Hourly Surface-Ozone Concentrations Fourteen Days in Advance

Issues regarding air quality and related health concerns have prompted t...
research
03/23/2023

Forecast-Aware Model Driven LSTM

Poor air quality can have a significant impact on human health. The Nati...
research
02/08/2023

Predicting the performance of hybrid ventilation in buildings using a multivariate attention-based biLSTM Encoder-Decoder neural network

Hybrid ventilation (coupling natural and mechanical ventilation) is an e...
research
10/05/2020

Conditional Generative Adversarial Networks to Model Urban Outdoor Air Pollution

This is a relevant problem because the design of most cities prioritizes...

Please sign up or login with your details

Forgot password? Click here to reset