Assessing Population Sensitivity to Urban Air Pollution Using Google Trends and Remote Sensing Datasets

Misra, Prakhar; Takeuchi, Wataru

doi:10.5194/isprs-archives-xlii-3-w11-93-2020

Cited by 3 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three articles are multicenter studies, two are surveys performed in seven countries [ 35 , 54 ], and the remaining are surveys performed in six countries [ 74 ]. Six studies were based on a national-level [ 41 , 47 , 49 , 52 , 60 , 67 ], three on multi-province [ 40 , 45 , 57 ], and seven on multiple-city surveys [ 50 , 51 , 59 , 63 , 64 , 71 , 73 ].…”

Section: Resultsmentioning

confidence: 99%

“…Studies using big data from the Internet were typical of Asian countries and we selected five of them: Google trends for seven Asian megacities [ 35 ]; an Internet search engine, Baidu [ 47 , 49 ]; and posts analysed on Weibo (a popular microblogging system) in China [ 64 , 67 ].…”

Section: Resultsmentioning

confidence: 99%

“…Symptoms were a significant additional element in Misra et al [ 35 ], where the circulation of information on the web was examined; in particular, the search for “cough” and “asthma”, together with “air pollution”, related to pollution measurement; Zakaria et al [ 46 ] used a self-administered questionnaire in Selangor, Malaysia and Nikolopoulou et al [ 69 ] employed a questionnaire-guide in San Diego, California to interview university students; Bergstra et al [ 51 ] examined adults and children in an industrial area in the Netherlands; Malecki et al [ 53 ] considered the linkage with low-level exposure in Wisconsin, USA, selecting a number of questions within a wider survey; Dons et al [ 54 ] developed a cross-sectional questionnaire study in seven European cities; and Pantavou et al [ 58 ] undertook a field study in Athens, associating citizen perception, behaviors, and symptoms with air pollution and dust.…”

Section: Resultsmentioning

confidence: 99%

“…This systematic review identified only five articles that studied perceived pollution using big data in the past five years. Three of them investigated perceived pollution using big data from web searches; namely, one of them used Google Trends [ 35 ] and the other two, the Baidu Index [ 47 , 49 ]. Although we found a correlation between the AQ level and perceived pollution in these three articles, we noticed that each study used different search terms, namely, “air pollution”, “cough”, and “asthma” [ 35 ]; “Shanghai air quality” [ 47 ]; and “haze” [ 49 ].…”

Section: Discussionmentioning

confidence: 99%

“…In India, outdoor air pollution was responsible for more than 670,000 deaths in 2016. To deal with these health effects, several countries have launched large-scale policies, such as China [ 33 , 34 ] and India; in other countries like Thailand, there is a growing demand for policies to address the issue of polluted air [ 35 ]. Although in many countries there are no specific laws or protection rules, WHO guidelines are taken into consideration [ 28 ].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Risk Perception of Air Pollution: A Systematic Review Focused on Particulate Matter Exposure

Cori

Donzelli

Gorini

et al. 2020

IJERPH

View full text Add to dashboard Cite

The adverse health effects of exposure to air pollutants, notably to particulate matter (PM), are well-known, as well as the association with measured or estimated concentration levels. The role of perception can be relevant in exploring effects and pollution control actions. The purpose of this study was to explore studies that analyse people’s perception, together with the measurement of air pollution, in order to elucidate the relationship between them. We conducted a systematic review in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. In March 2020, PubMed, EMBASE, and Scopus databases were explored in an attempt to search for studies published from 2000 to 2020. The review included 38 studies, most of which were conducted in China (n = 13) and the United States (n = 11) and published over the last four years (n = 26). Three studies were multicenter investigations, while five articles were based on a national-level survey. The air quality (AQ) was assessed by monitoring stations (n = 24) or dispersion models (n = 7). Many studies were population questionnaire-based, air monitoring and time-series studies, and web-based investigations. A direct association between exposure and perception emerged in 20 studies. This systematic review has shown that most of the studies establish a relationship between risk perception measurement. A broad spectrum of concepts and notions related to perception also emerged, which is undoubtedly an indicator of the wealth of available knowledge and is promising for future research.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Risk Perception of Air Pollution: A Systematic Review Focused on Particulate Matter Exposure

Cori

Donzelli

Gorini

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

Detecting Elevated Air Pollution Levels by Monitoring Web Search Queries: Algorithm Development and Validation

Chen¹,

Yousefi²,

Kahoro³

et al. 2022

JMIR Form Res

View full text Add to dashboard Cite

Background:Real-time air pollution monitoring is a valuable tool for public health and environmental surveillance. In recent years, there has been a dramatic increase in air pollution forecasting and monitoring research using artificial neural networks (ANNs). Most of the prior work relied on modeling pollutant concentrations collected from ground-based monitors and meteorological data for long-term forecasting of outdoor ozone, oxides of nitrogen, and PM 2.5 . Given that traditional, highly sophisticated air quality monitors are expensive and are not universally available, these models cannot adequately serve those not living near pollutant monitoring sites. Furthermore, because prior models were built on physical measurement data collected from sensors, they may not be suitable for predicting public health effects experienced from pollution exposure. Objective:This study aims to develop and validate models to "nowcast" the observed pollution levels using Web search data, which is publicly available in near real-time from major search engines. Methods:We developed novel machine learning-based models using both traditional supervised classification methods and state-of-the-art deep learning methods to detect elevated air pollution levels at the US city level, by using generally available meteorological data and aggregate Web-based search volume data derived from Google Trends. We validated the performance of these methods by predicting three critical air pollutants (ozone (O 3 ), nitrogen dioxide (NO 2 ), and fine particulate matter (PM 2.5 )), across ten major U.S. metropolitan statistical areas (MSAs) in 2017 and 2018. We also explore different variations of the long-short term memory (LSTM) model and propose a novel search term Dictionary Learner-Long-Short Term Memory (DL-LSTM) model to learn sequential patterns across multiple search terms for prediction. Results:The top-performing model was a deep neural sequence model LSTM, using meteorological and Web search data, and reached an accuracy of 0.82 (F1 score: 0.51) for O 3, 0.74 (F1 score:0.41) for NO 2 , and 0.85 (F1 score: 0.27) for PM 2.5 , when used for detecting elevated pollution levels. Compared with only using meteorological data, the proposed method achieved superior accuracy by incorporating Web search data. Conclusions:

show abstract

Detecting Elevated Air Pollution Levels by Monitoring Web Search Queries (Preprint)

Chen¹,

Yousefi²,

Kahoro³

et al. 2022

Preprint

View full text Add to dashboard Cite

BACKGROUND Real-time air pollution monitoring is a valuable tool for public health and environmental surveillance. In recent years, there has been a dramatic increase in air pollution forecasting and monitoring research using artificial neural networks (ANNs). Most of the prior work relied on modeling pollutant concentrations collected from ground-based monitors and meteorological data for long-term forecasting of outdoor ozone, oxides of nitrogen, and PM2.5. Given that traditional, highly sophisticated air quality monitors are expensive and are not universally available, these models cannot adequately serve those not living near pollutant monitoring sites. Furthermore, because prior models were built on physical measurement data collected from sensors, they may not be suitable for predicting public health effects experienced from pollution exposure. OBJECTIVE This study aims to develop and validate models to “nowcast” the observed pollution levels using Web search data, which is publicly available in near real-time from major search engines. METHODS We developed novel machine learning-based models using both traditional supervised classification methods and state-of-the-art deep learning methods to detect elevated air pollution levels at the US city level, by using generally available meteorological data and aggregate Web-based search volume data derived from Google Trends. We validated the performance of these methods by predicting three critical air pollutants (ozone (O3), nitrogen dioxide (NO2), and fine particulate matter (PM2.5)), across ten major U.S. metropolitan statistical areas (MSAs) in 2017 and 2018. We also explore different variations of the long-short term memory (LSTM) model and propose a novel search term Dictionary Learner-Long-Short Term Memory (DL-LSTM) model to learn sequential patterns across multiple search terms for prediction. RESULTS The top-performing model was a deep neural sequence model LSTM, using meteorological and Web search data, and reached an accuracy of 0.82 (F1 score: 0.51) for O3, 0.74 (F1 score:0.41) for NO2, and 0.85 (F1 score: 0.27) for PM2.5, when used for detecting elevated pollution levels. Compared with only using meteorological data, the proposed method achieved superior accuracy by incorporating Web search data. CONCLUSIONS The results show that incorporating Web search data with meteorological data improves nowcasting performance for all three pollutants and suggest promising novel applications for tracking global physical phenomena using Web search data CLINICALTRIAL Not Applicable

show abstract

Assessing Population Sensitivity to Urban Air Pollution Using Google Trends and Remote Sensing Datasets

Cited by 3 publications

References 29 publications

Risk Perception of Air Pollution: A Systematic Review Focused on Particulate Matter Exposure

Risk Perception of Air Pollution: A Systematic Review Focused on Particulate Matter Exposure

Detecting Elevated Air Pollution Levels by Monitoring Web Search Queries: Algorithm Development and Validation

Detecting Elevated Air Pollution Levels by Monitoring Web Search Queries (Preprint)

Contact Info

Product

Resources

About