Nowcasting Air Quality by Fusing Insights from Meteorological Data, Satellite Imagery and Social Media Images Using Deep Learning

Khaefi, Muhammad Rizal; Pramestri, Zakiya; Amin, Imaduddin; Lee, Jong Gun

doi:10.1109/asonam.2018.8508698

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, several studies using data from Sina Weibo (a popular social media platform in China) have demonstrated feasibility for tracking air pollution in China (Jiang et al, 2015;Wang et al, 2015), where volume of pollution-related messages was highly correlated with particle pollution levels (Wang et al, 2015). Furthermore, one study found that Twitter data appears promising for detecting smoke pollution from wildfires in California, USA (Sachdeva and McCaffrey, 2018), while another study demonstrated that capturing photos posted on social media can supplement existing meteorological data and satellite imagery for monitoring haze events in Indonesia (Khaefi et al, 2018). More recently a systematic review showcased that data from Twitter can provide new opportunities to study health, especially among underrepresented geographic areas and at-risk patient groups (Sinnenberg et al, 2017).…”

Section: Discussionmentioning

confidence: 99%

Feasibility of using social media to monitor outdoor air pollution in London, England

Hswen

Qin

Brownstein

et al. 2019

Preventive Medicine

View full text Add to dashboard Cite

Air pollution is a serious public health concern. Innovative and scalable methods for detecting harmful air pollutants such as PM2.5 are necessary. This study assessed the feasibility of using social media to monitor outdoor air pollution in an urban area by comparing data from Twitter and validating it against established air monitoring stations. Data were collected from London, England from July 29, 2016 to March 17, 2017. Daily mean PM2.5 data was downloaded from the LondonAir platform consisting of 26 air pollution monitoring sites throughout Greater London. Publicly available tweets geo-located to Greater London containing air pollution terms were captured from the Twitter platform. Tweets with media URL links were excluded to minimize influence of news stories. Sentiment of the tweets was examined as negative, positive, or neutral. Cross-correlation analyses were used to compare the relationship between trends of tweets about air pollution and levels of PM2.5 over time. There were 16,448 tweets without a media URL link, with a mean of 498.42 (SD = 491.08) tweets per week. A significant cross-correlation coefficient of 0.803 was observed between PM2.5 data and the non-media air pollution tweets (p < 0.001). The cross-correlation coefficient was highest between PM2.5 data and air pollution tweets with negative sentiment at 0.816 (p < 0.001). Discussions about air pollution on Twitter reflect particle PM2.5 pollution levels in Greater London. This study highlights that social media may offer a supplemental source to support the detection and monitoring of air pollution in a densely populated urban area.

show abstract

Section: Discussionmentioning

confidence: 99%

Feasibility of using social media to monitor outdoor air pollution in London, England

Hswen

Qin

Brownstein

et al. 2019

Preventive Medicine

View full text Add to dashboard Cite

show abstract

“…As indicated above, a combination of industrial and environmental factors was blamed for these catastrophic events (NASA, 2015). Some accounts of this confluence of environmental and industrial risks, and others like it, have detected among them an urgent, unmet need: namely, a need for "automatic data collection and real-time sensing" (Khaefi et al, 2018). So equipped, it is hoped that those charged with understanding, tempering, and mitigating such risks -agencies like Indonesia's National Board of Disaster Management (Badan Nasional Penanggulangan Bencana; BNPB) -might act in a more timely and effective way in the future.…”

Section: Introductionmentioning

confidence: 99%

Data jurisdictions and rival regimes of algorithmic regulation

Johns

Compton

2019

Regulation & Governance

View full text Add to dashboard Cite

This article aims to characterize and compare some approaches to regulation manifest in distinct yet intersecting domains of data assemblage and algorithmic development, and to explore some implications of their operating in concert. We focus on three such types of domain, each oriented towards different purposes: market jurisdictions; public science jurisdictions; and jurisdictions of humanitarianism. These domains we characterize as data jurisdictions because they tend to propagate distinct normative claims and concerns, and authorize particular types of speech and action, through algorithmic operations and data formatting. In this paper, we focus on the intersection of these archetypal data jurisdictions in two, related initiatives of the United Nations (UN): Haze Gazer and This article is protected by copyright. All rights reserved. This is the author manuscript accepted for publication and has undergone full peer review but has not been through the copyediting, typesetting, pagination and proofreading process, which may lead to differences between this version and the Version of Record. Please cite this article as

show abstract