4.7 Article

Estimation of daily NO2 with explainable machine learning model in China, 2007-2020

Related references

Note: Only part of the references are listed.
Article Multidisciplinary Sciences

Global fine-scale changes in ambient NO2 during COVID-19 lockdowns

Matthew J. Cooper et al.

Summary: Using satellite observations of NO2 column densities, we derived spatially resolved ground-level NO2 concentrations globally and compared them between cities during the COVID-19 lockdowns in 2020 and 2019. The study found that strict lockdown conditions were associated with a 29% ± 3% decrease in average country-level population-weighted NO2 concentrations compared to countries without lockdowns. The decrease in NO2 during COVID-19 lockdowns exceeded year-to-year decreases from emission controls and was comparable to reductions equivalent to 15 ± 4 years globally.

NATURE (2022)

Article Engineering, Environmental

Revealing Drivers of Haze Pollution by Explainable Machine Learning

Linlu Hou et al.

Summary: This study used machine learning methods to investigate the roles of meteorological factors, emissions, and chemistry in five severe haze episodes that occurred before or during the COVID-19 lockdown in China. The study found that in addition to high levels of primary emissions, meteorological factors played a dominant role in PM2.5 pollution in these episodes, followed by chemistry.

ENVIRONMENTAL SCIENCE & TECHNOLOGY LETTERS (2022)

Article Engineering, Environmental

Flexible Bayesian Ensemble Machine Learning Framework for Predicting Local Ozone Concentrations

Xiang Ren et al.

Summary: In this study, a Bayesian ensemble machine learning framework was developed to downscale CMAQ estimates of ozone concentrations, aiming to accurately assess human exposure and environmental justice disparities. The framework integrates 13 learning algorithms and undergoes hyper-parameter tuning and validation to ensure accuracy and flexibility.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2022)

Article Multidisciplinary Sciences

Using machine learning to assess the livelihood impact of electricity access

Nathan Ratledge et al.

Summary: Advancements in satellite imagery and machine learning can help address data scarcity and inference challenges. Using the example of the expansion of the electrical grid in Uganda, this study demonstrates how satellite imagery and computer vision techniques can be used to develop local-level livelihood measurements and machine learning-based inference techniques provide more reliable estimates of the impact of electrification. The findings show that grid access in rural Uganda improves village-level asset wealth and doubles the growth rate compared to untreated areas.

NATURE (2022)

Article Engineering, Environmental

Ground-Level NO2 Surveillance from Space Across China for High Resolution Using Interpretable Spatiotemporally Weighted Artificial Intelligence

Jing Wei et al.

Summary: This study developed a novel artificial intelligence approach to fill the gaps in satellite data and derive high-resolution daily surface NO2 concentrations over mainland China. The resulting dataset provides valuable information for studying air pollution patterns, holiday effects, and the impact of the COVID-19 pandemic on NO2 concentrations.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2022)

Article Multidisciplinary Sciences

Prevalence and drivers of abrupt vegetation shifts in global drylands

Miguel Berdugo et al.

Summary: The constant provision of plant productivity is crucial for supporting dryland ecosystems and human wellbeing. Studying the prevalence and drivers of abrupt dynamical patterns in drylands can reveal hotspots of current and future instability. Research shows that abrupt changes in plant productivity are common in drylands, especially negative trends, and are influenced by climate variability and aridity thresholds.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2022)

Article Computer Science, Interdisciplinary Applications

Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost

Ziqi Li

Summary: This paper introduces the local interpretation methods of machine learning models and demonstrates how to extract spatial effects using SHAP. Simulation experiments and empirical research show that locally interpreted machine learning models can be a good alternative to spatial statistical models and perform better in certain circumstances.

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS (2022)

Article Environmental Sciences

Estimating the spatial and temporal variability of the ground-level NO2 concentration in China during 2005-2019 based on satellite remote sensing

Jianhui Xu et al.

Summary: The TSCE-NO2 model proposed in this study provides a reliable estimation of ground-level NO2 concentration in China from 2005 to 2019, revealing the seasonal and regional differences in NO2 concentration across different regions in China. Measures such as energy savings and emission reductions have alleviated NO2 pollution in China while ensuring sustained GDP growth.

ATMOSPHERIC POLLUTION RESEARCH (2021)

Article Environmental Sciences

Estimating the Daily NO2 Concentration with High Spatial Resolution in the Beijing-Tianjin-Hebei Region Using an Ensemble Learning Model

Yanding Pan et al.

Summary: Nitrogen dioxide (NO2) is an important pollutant associated with human activities, with short-term and long-term effects on human health. An ensemble learning model was used to estimate daily NO2 concentrations in the Beijing-Tianjin-Hebei region from 2010 to 2016, showing good performance. The annual NO2 estimation remained stable over the years, with winter having the highest and summer the lowest NO2 concentrations.

REMOTE SENSING (2021)

Article Geography, Physical

Estimating daily full-coverage near surface O3, CO, and NO2 concentrations at a high spatial resolution over China based on S5P-TROPOMI and GEOS-FP

Yuan Wang et al.

Summary: This study aims to estimate the daily full-coverage NSC of O-3, CO, and NO2 over China, achieving high estimation accuracy and spatial resolution. The results show significant variations in the concentrations of O-3, CO, and NO2 during the COVID-19 lockdown in China, possibly due to restrictions in anthropogenic activities.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Article Environmental Sciences

A robust approach to deriving long-term daily surface NO2 levels across China: Correction to substantial estimation bias in back-extrapolation

Yangyang Wu et al.

Summary: This study corrected estimation bias in back-extrapolation through the use of a robust back-extrapolation random forest (RBE-RF) model, providing a dataset of daily surface NO2 levels across China from 2005 to 2018. RBE-RF significantly reduced underestimation compared to the base model (Base-RF) for NO2 levels during 2005-2012, especially in North China. The RBE-RF model also more accurately predicted the trends in national NO2 levels from 2005 to 2011, highlighting the importance of addressing concept drift in model training.

ENVIRONMENT INTERNATIONAL (2021)

Article Multidisciplinary Sciences

Predicting the effect of confinement on the COVID-19 spread using machine learning enriched with satellite air pollution observations

Xiaofan Xing et al.

Summary: Satellite observations are used to monitor the reincreasing economic activity associated with the lifting of control measures and its effect on the acceleration of COVID-19 cases. Near-real-time satellite NO2 observations provide a better prediction of the deceleration of COVID-19 cases compared to other predictors, indicating the driving role of NO2 in economic activity reduction.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

Article Environmental Sciences

Separating emission and meteorological contributions to long-term PM2.5 trends over eastern China during 2000-2018

Qingyang Xiao et al.

Summary: The study by the authors focused on analyzing the contributions of meteorology and emissions to long-term trends in PM2.5 pollution from 2000 to 2018 in China. It was found that while emissions played a dominant role in the long-term trend of PM2.5 concentration, meteorological conditions also had a notable influence, particularly in affecting interannual variabilities in meteorology-associated PM2.5.

ATMOSPHERIC CHEMISTRY AND PHYSICS (2021)

Article Meteorology & Atmospheric Sciences

Ozone Monitoring Instrument (OMI) Aura nitrogen dioxide standard product version 4.0 with improved surface and cloud treatments

Lok N. Lamsal et al.

Summary: The new version V4.0 of the NASA standard nitrogen dioxide (NO2) product from the Ozone Monitoring Instrument (OMI) on the Aura satellite has enhanced the quality of NO2 data through improvements in the retrieval algorithm, providing up to a 50% increase in tropospheric NO2 in highly polluted areas. The new data is publicly available on the NASA website for users to access and is encouraged to be used over previous versions.

ATMOSPHERIC MEASUREMENT TECHNIQUES (2021)

Article Geosciences, Multidisciplinary

Nitrogen Oxide Emissions from US Oil and Gas Production: Recent Trends and Source Attribution

Barbara Dix et al.

GEOPHYSICAL RESEARCH LETTERS (2020)

Article Environmental Sciences

Short- and intermediate-term exposure to NO2 and mortality: A multi-county analysis in China

Mike Z. He et al.

ENVIRONMENTAL POLLUTION (2020)

Article Environmental Sciences

Long-term NO2 exposures and cause-specific mortality in American older adults

Ki-Do Eum et al.

ENVIRONMENT INTERNATIONAL (2019)

Review Computer Science, Artificial Intelligence

Hyperparameters and tuning strategies for random forest

Philipp Probst et al.

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY (2019)

Article Engineering, Environmental

Predicting Fine-Scale Daily NO2 for 2005-2016 Incorporating OMI Satellite Data Across Switzerland

Kees de Hoogh et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2019)

Article Environmental Sciences

A hybrid model approach for estimating health burden from NO2 in megacities in China: a case study in Guangzhou

Baihuiqian He et al.

ENVIRONMENTAL RESEARCH LETTERS (2019)

Article Environmental Sciences

A kriging-calibrated machine learning method for estimating daily ground-level NO2 in mainland China

Zhao-Yue Chen et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2019)

Article Environmental Sciences

Trends and trend reversal detection in 2 decades of tropospheric NO2 satellite observations

Aristeidis K. Georgoulias et al.

ATMOSPHERIC CHEMISTRY AND PHYSICS (2019)

Article Engineering, Environmental

Satellite-Based Estimates of Daily NO2 Exposure in China Using Hybrid Random Forest and Spatiotemporal Kriging Model

Yu Zhan et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2018)

Article Cardiac & Cardiovascular Systems

Short-term effects of nitrogen dioxide on hospital admissions for cardiovascular disease in Wallonia, Belgium

Philippe Collart et al.

INTERNATIONAL JOURNAL OF CARDIOLOGY (2018)

Article Engineering, Environmental

An Ensemble Machine-Learning Model To Predict Historical PM2.5 Concentrations in China from Satellite Data

Qingyang Xiao et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2018)

Article Engineering, Environmental

Does Urban Form Affect Urban NO2? Satellite-Based Evidence for More than 1200 Cities

Matthew J. Bechle et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2017)

Article Multidisciplinary Sciences

Impacts and mitigation of excess diesel-related NOx emissions in 11 major vehicle markets

Susan C. Anenberg et al.

NATURE (2017)

Article Environmental Sciences

Long-Term Trends Worldwide in Ambient NO2 Concentrations Inferred from Satellite Observations

Jeffrey A. Geddes et al.

ENVIRONMENTAL HEALTH PERSPECTIVES (2016)

Article Environmental Sciences

Satellite-Based Spatiotemporal Trends in PM2.5 Concentrations: China, 2004-2013

Zongwei Ma et al.

ENVIRONMENTAL HEALTH PERSPECTIVES (2016)

Article Meteorology & Atmospheric Sciences

The GOME-2 instrument on the Metop series of satellites: instrument design, calibration, and level 1 data processing - an overview

Rosemary Munro et al.

ATMOSPHERIC MEASUREMENT TECHNIQUES (2016)

Article Environmental Sciences

Rapid growth in nitrogen dioxide pollution over Western China, 2005-2013

Yuanzheng Cui et al.

ATMOSPHERIC CHEMISTRY AND PHYSICS (2016)

Article Engineering, Environmental

Scaling Relationship for NO2 Pollution and Urban Population Size: A Satellite Perspective

L. N. Lamsal et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2013)

Article Geosciences, Multidisciplinary

Linking NO2 surface concentration and integrated content in the urban developed atmospheric boundary layer

E. Dieudonne et al.

GEOPHYSICAL RESEARCH LETTERS (2013)

Article Meteorology & Atmospheric Sciences

Ground-level nitrogen dioxide concentrations inferred from the satellite-borne Ozone Monitoring Instrument

L. N. Lamsal et al.

JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES (2008)

Article Medicine, General & Internal

Outdoor air pollution: Nitrogen dioxide, sulfur dioxide, and carbon monoxide health effects

Tze-Ming Chen et al.

AMERICAN JOURNAL OF THE MEDICAL SCIENCES (2007)

Article Geochemistry & Geophysics

The Ozone Monitoring Instrument

PF Levelt et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2006)