Cover Image

Air quality monitoring and advanced Bayesian modelling /

"Air Quality Monitoring and Advanced Bayesian Modeling introduces recent developments in urban air quality monitoring and forecasting. The book presents concepts, theories, and case studies related to monitoring methods of criteria air pollutants, advanced methods for real-time characterization...

Full description

Bibliographic Details
Corporate Author: ScienceDirect (Online service)
Other Authors: Li, Yongjie
Format: eBook
Language:English
Published: Amsterdam, Netherlands ; Oxford, United Kingdom ; Cambridge MA : Elsevier, [2023]
Subjects:
Air > Pollution > Measurement > Mathematical models.
Air quality > Forecasting > Mathematical models.
Bayesian statistical decision theory.
Air > Pollution > Mesure > Modèles mathématiques.
Air > Qualité > Prévision > Modèles mathématiques.
Théorie de la décision bayésienne.
Air > Pollution > Measurement > Mathematical models
Bayesian statistical decision theory
Electronic books.
Online Access:Connect to the full text of this electronic book
Table of Contents:
  • Intro
  • Air Quality Monitoring and Advanced Bayesian Modeling
  • Copyright
  • Contents
  • Chapter 1: Introduction
  • 1.1. Clean versus polluted air
  • 1.2. Sources and impacts of air pollutants
  • 1.3. Air quality monitoring strategies
  • 1.4. Modeling and forecasting of air pollution
  • 1.5. About this book
  • References
  • Chapter 2: Current air quality monitoring methods
  • 2.1. Methods for criteria air pollutants
  • 2.1.1. Carbon monoxide (CO)
  • 2.1.2. Sulfur dioxide (SO2)
  • 2.1.3. Nitrogen oxides (NO and NO2)
  • 2.1.4. Ozone (O3)
  • 2.1.5. Particulate matters (PM10 and PM2.5)
  • 2.2. Real-time chemical composition monitoring
  • 2.2.1. Particulate matters
  • 2.2.1.1. Mass spectrometry for real-time PM measurement
  • Mass spectrometry based on electron impact (EI)
  • Mass spectrometry based on laser ionization desorption (LDI)
  • 2.2.1.2. Ion chromatography for real-time PM measurement
  • Ion chromatographic systems for particles only
  • Ion chromatographic systems for gases and particles
  • 2.2.1.3. Real-time measurement of trace elements in PM
  • 2.2.2. Volatile organic compounds
  • 2.2.2.1. Gas chromatography for real-time VOC measurement
  • 2.2.2.2. Mass spectrometry for real-time VOC measurement
  • 2.2.3. Other real-time techniques
  • 2.2.3.1. Optical techniques for real-time measurements of gases
  • 2.2.3.2. Thermal and optical techniques for real-time measurements of PM
  • 2.3. Conclusions
  • References
  • Chapter 3: Emerging air quality monitoring methods
  • 3.1. Low-cost sensors
  • 3.1.1. Electrochemical sensors
  • 3.1.2. Metal oxide sensors
  • 3.1.3. Optical sensors for PM
  • 3.1.4. Sensors for VOCs
  • 3.1.5. New considerations for low-cost sensors
  • 3.1.5.1. Analytical merits
  • 3.1.5.2. Potential interferences
  • 3.1.5.3. Lab calibrations and field comparisons
  • 3.1.5.4. Data correction.
  • 3.1.5.5. Data transmission and sensor networks
  • 3.2. Mobile measurement platforms
  • 3.2.1. On-road air quality monitoring
  • 3.2.1.1. Powered and nonfixed-route vehicles
  • 3.2.1.2. Powered and fixed-route vehicles
  • 3.2.1.3. Nonpowered and nonfixed-route platforms
  • 3.2.1.4. Requirements on monitoring method and data analysis
  • 3.2.2. Air-borne air quality monitoring
  • 3.2.2.1. Balloon-borne measurements
  • 3.2.2.2. Manned-aircraft measurements
  • 3.2.2.3. Unmanned-aircraft measurements
  • 3.2.2.4. Other mobile measurement platforms
  • 3.3. Conclusions
  • References
  • Chapter 4: Traditional statistical air quality forecasting methods
  • 4.1. Multiple linear regression (MLR)
  • 4.1.1. Overview
  • 4.1.2. Basics of multiple linear regression
  • 4.1.3. Ridge regression and LASSO
  • 4.1.4. Example: Estimation of AR(2) parameters with the multiple linear regression, the ridge regression, and the LASSO r ...
  • 4.2. Classification and regression tree (CART)
  • 4.2.1. Overview
  • 4.2.2. Regression tree
  • 4.2.3. Classification tree
  • 4.2.4. Bagging and random forests
  • 4.2.5. Example: Estimation of CO2 emissions from vehicle features with random forest
  • 4.3. Multilayer perceptron
  • 4.3.1. Overview
  • 4.3.2. Basics of multilayer perceptron
  • 4.3.3. Training algorithm of MLP
  • 4.3.4. Example: Imputation of missing air quality data based on multilayer perceptron
  • 4.4. Support vector regression (SVR)
  • 4.4.1. Overview
  • 4.4.2. Formulation of support vector regression
  • 4.5. Case study
  • 4.5.1. Overview
  • 4.5.2. Prediction of PM2.5 and ground-level O3 concentrations of Macau
  • References
  • Chapter 5: Advanced Bayesian air quality forecasting methods
  • 5.1. Overview of technique limitations and advanced topics for improvement
  • 5.1.1. Choice of model complexity
  • 5.1.2. Necessity of model adaptiveness.
  • 5.2. Bayesian model class selection of linear regression model
  • 5.2.1. Overview
  • 5.2.2. Basics of Bayesian model class selection in linear regression model
  • 5.2.3. Modeling of Keeling curve
  • 5.3. Kalman filter-based adaptive air quality model
  • 5.3.1. Overview
  • 5.3.2. Basics of Kalman filter-based adaptive air quality model
  • 5.3.3. Selection of perturbation matrix and measurement noise variance
  • 5.3.4. Revisiting example 5.2.3 (modeling of Keeling curve) with the adaptive linear model
  • 5.4. Time-varying multilayer perceptron
  • 5.4.1. Overview
  • 5.4.2. Basics of time-varying multilayer perceptron
  • 5.4.3. Example: Prediction of Mackey-Glass time series by using the TVMLP model
  • 5.5. Adaptive Bayesian model averaging of multiple time-varying regression models
  • 5.5.1. Overview
  • 5.5.2. Basics of dynamic Bayesian model averaging
  • 5.5.3. Modeling of measured PM2.5 concentration of the low-cost sensor
  • 5.6. Case study
  • 5.6.1. Overview
  • 5.6.2. Air quality forecasting in Macau with the adaptive linear models
  • References
  • Index.