Search

Industrial smoke emissions pose a significant concern to human health. Prior works have shown that using Computer Vision (CV) techniques to identify smoke as visual evidence can influence the attitude of regulators and empower citizens to pursue environmental justice. However, existing datasets are not of sufficient quality nor quantity to train the robust CV models needed to support air quality advocacy. We introduce RISE, the first large-scale video dataset for Recognizing Industrial Smoke Emissions. We adopted a citizen science approach to collaborate with local community members to annotate whether a video clip has smoke emissions. Our dataset contains 12,567 clips from 19 distinct views from cameras that monitored three industrial facilities. These daytime clips span 30 days over two years, including all four seasons. We ran experiments using deep neural networks to establish a strong performance baseline and reveal smoke recognition challenges. Our survey study discussed community feedback, and our data analysis displayed opportunities for integrating citizen scientists and crowd workers into the application of Artificial Intelligence for Social Impact., Comment: Accepted by AAAI 2021

Urban air pollution has been linked to various human health concerns, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developed Smell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. We also applied regression analysis to identify statistically significant effects of push notifications on user engagement. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns, and can empower communities to advocate for better air quality. All citizen-contributed smell data are publicly accessible and can be downloaded from https://smellpgh.org., Comment: Accepted by ACM Transactions on Interactive Intelligent Systems on 2020. This is an extended version of the arXiv:1810.11143, which was accepted by the ACM IUI 2019 conference. arXiv admin note: substantial text overlap with arXiv:1810.11143

Urban air pollution has been linked to various human health considerations, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developed Smell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns, and can empower communities to advocate for better air quality., Comment: Accepted by ACM IUI 2019 conference, with error corrections

As sensing technology proliferates and becomes affordable to the general public, there is a growing trend in citizen science where scientists and volunteers form a strong partnership in conducting scientific research including problem finding, data collection, analysis, visualization, and storytelling. Providing easy-to-use computational tools to support citizen science has become an important issue. To raise the public awareness of environmental science and improve the air quality in local areas, we are currently collaborating with a local community in monitoring and documenting fugitive emissions from a coke refinery. We have helped the community members build a live camera system which captures and visualizes high resolution timelapse imagery starting from November 2014. However, searching and documenting smoke emissions manually from all video frames requires manpower and takes an impractical investment of time. This paper describes a software tool which integrates four features: (1) an algorithm based on change detection and texture segmentation for identifying smoke emissions; (2) an interactive timeline visualization providing indicators for seeking to interesting events; (3) an autonomous fast-forwarding mode for skipping uninteresting timelapse frames; and (4) a collection of animated smoke images generated automatically according to the algorithm for documentation, presentation, storytelling, and sharing. With the help of this tool, citizen scientists can now focus on the content of the story instead of time-consuming and laborious works.

Scientists, journalists, and photographers have used advanced camera technology to capture extremely high-resolution timelapse and developed information visualization tools for data exploration and analysis. However, it takes a great deal of effort for professionals to form and tell stories after exploring data, since these tools usually provide little aids in creating visual elements. We present a web-based timelapse editor to support the creation of guided video tours and interactive slideshows from a collection of large-scale spatial and temporal images. Professionals can embed these two visual elements into web pages in conjunction with various forms of digital media to tell multimodal and interactive stories., Comment: Accepted by 2015 IEEE Information Visualization Posters

Developing information technology to democratize scientific knowledge and support citizen empowerment is a challenging task. In our case, a local community suffered from air pollution caused by industrial activity. The residents lacked the technological fluency to gather and curate diverse scientific data to advocate for regulatory change. We collaborated with the community in developing an air quality monitoring system which integrated heterogeneous data over a large spatial and temporal scale. The system afforded strong scientific evidence by using animated smoke images, air quality data, crowdsourced smell reports, and wind data. In our evaluation, we report patterns of sharing smoke images among stakeholders. Our survey study shows that the scientific knowledge provided by the system encourages agonistic discussions with regulators, empowers the community to support policy making, and rebalances the power relationship between stakeholders., Comment: Accepted by 2017 ACM Conference on Human Factors in Computing Systems (CHI 2017)

To assist residents affected by oil and gas development, public health professionals in a non-profit organization have collected community data, including symptoms, air quality, and personal stories. However, the organization was unable to aggregate and visualize these data computationally. We present the Environmental Health Channel, an interactive web-based tool for visualizing environmental sensing and public health data. This tool enables discussing and disseminating scientific evidence to reveal local environmental and health impacts of industrial activities., Comment: Accepted by 2018 ACM Conference Companion Publication on Designing Interactive Systems (DIS 2018)

The increasing size of cosmological simulations has led to the need for new visualization techniques. We focus on Smoothed Particle Hydrodynamical (SPH) simulations run with the GADGET code and describe methods for visually accessing the entire simulation at full resolution. The simulation snapshots are rastered and processed on supercomputers into images that are ready to be accessed through a web interface (GigaPan). This allows any scientist with a web-browser to interactively explore simulation datasets in both in spatial and temporal dimensions, datasets which in their native format can be hundreds of terabytes in size or more. We present two examples, the first a static terapixel image of the MassiveBlack simulation, a P-GADGET SPH simulation with 65 billion particles, and the second an interactively zoomable animation of a different simulation with more than one thousand frames, each a gigapixel in size. Both are available for public access through the GigaPan web interface. We also make our imaging software publicly available., Comment: 9 pages, 6 figures, Link to the Gigapan image: http://gigapan.org/gigapans/76215/ Link to the TimeMachine animation: http://timemachine.gigapan.org/wiki/Evolution_of_the_Universe Link to Gaepsi: http://web.phys.cmu.edu/~yfeng1/gaepsi