Integrative urban AI to expand coverage, access, and equity of urban data.

We consider the use of AI techniques to expand the coverage, access, and equity of urban data. We aim to enable holistic research on city dynamics, steering AI research attention away from profit-oriented, societally harmful applications (e.g., facial recognition) and toward foundational questions in mobility, participatory governance, and justice. By making available high-quality, multi-variate, cross-scale data for research, we aim to link the macrostudy of cities as complex systems with the reductionist view of cities as an assembly of independent prediction tasks. We identify four research areas in AI for cities as key enablers: interpolation and extrapolation of spatiotemporal data, using NLP techniques to model speech- and text-intensive governance activities, exploiting ontology modeling in learning tasks, and understanding the interaction of fairness and interpretability in sensitive contexts.

Freedom from the Station: Spatial Equity in Access to Dockless Bike Share.

BACKGROUND: Bike sharing systems have potential to substantially boost active transportation levels (and consequent physical and mental health) in urban populations. We explored equity of spatial access in a novel 'dockless' bike share system that does not that constrain bike pickup and drop-off locations to docking stations. METHODS: Starting in July 2017, Seattle, Washington piloted a dockless bike share system that made 10,000 bikes available. We merged data on resident sociodemographic and economic characteristics from the American Community Survey about 93 defined neighborhoods with data about bike locations, bike idle time, and which neighborhoods operators rebalanced bikes to. We used mapping and descriptive statistics to compare access between neighborhoods along sociodemographic and economic lines. RESULTS: With many bikes available, no neighborhood was consistently excluded from access. However, the average availability ranged from 3 bikes per day to 341 per day. Neighborhoods with more bikes had more college-educated residents (median 75% college-educated vs. 65%) and local community resources (median opportunity index score of 24 vs. 19), and higher incomes (median 83,202 vs. 71,296). Rebalancing destinations were strongly correlated with neighborhood demand (r=0.61). CONCLUSIONS: The overall scale of the dockless system ensured there was baseline access throughout Seattle. We observed modest inequities in access along sociodemographic lines, similar to prior findings in studies of docked bike share systems. Dockless bike share systems hold promise for offering equitable spatial access to bike sharing.

Formalizing Visualization Design Knowledge as Constraints: Actionable and Extensible Models in Draco.

There exists a gap between visualization design guidelines and their application in visualization tools. While empirical studies can provide design guidance, we lack a formal framework for representing design knowledge, integrating results across studies, and applying this knowledge in automated design tools that promote effective encodings and facilitate visual exploration. We propose modeling visualization design knowledge as a collection of constraints, in conjunction with a method to learn weights for soft constraints from experimental data. Using constraints, we can take theoretical design knowledge and express it in a concrete, extensible, and testable form: the resulting models can recommend visualization designs and can easily be augmented with additional constraints or updated weights. We implement our approach in Draco, a constraint-based system based on Answer Set Programming (ASP). We demonstrate how to construct increasingly sophisticated automated visualization design systems, including systems based on weights learned directly from the results of graphical perception experiments.

The principles of tomorrow's university.

In the 21st Century, research is increasingly data- and computation-driven. Researchers, funders, and the larger community today emphasize the traits of openness and reproducibility. In March 2017, 13 mostly early-career research leaders who are building their careers around these traits came together with ten university leaders (presidents, vice presidents, and vice provosts), representatives from four funding agencies, and eleven organizers and other stakeholders in an NIH- and NSF-funded one-day, invitation-only workshop titled "Imagining Tomorrow's University." Workshop attendees were charged with launching a new dialog around open research - the current status, opportunities for advancement, and challenges that limit sharing. The workshop examined how the internet-enabled research world has changed, and how universities need to change to adapt commensurately, aiming to understand how universities can and should make themselves competitive and attract the best students, staff, and faculty in this new world. During the workshop, the participants re-imagined scholarship, education, and institutions for an open, networked era, to uncover new opportunities for universities to create value and serve society. They expressed the results of these deliberations as a set of 22 principles of tomorrow's university across six areas: credit and attribution, communities, outreach and engagement, education, preservation and reproducibility, and technologies. Activities that follow on from workshop results take one of three forms. First, since the workshop, a number of workshop authors have further developed and published their white papers to make their reflections and recommendations more concrete. These authors are also conducting efforts to implement these ideas, and to make changes in the university system.  Second, we plan to organise a follow-up workshop that focuses on how these principles could be implemented. Third, we believe that the outcomes of this workshop support and are connected with recent theoretical work on the position and future of open knowledge institutions.

Wide-Open: Accelerating public data release by automating detection of overdue datasets.

Open data is a vital pillar of open science and a key enabler for reproducibility, data reuse, and novel discoveries. Enforcement of open-data policies, however, largely relies on manual efforts, which invariably lag behind the increasingly automated generation of biological data. To address this problem, we developed a general approach to automatically identify datasets overdue for public release by applying text mining to identify dataset references in published articles and parse query results from repositories to determine if the datasets remain private. We demonstrate the effectiveness of this approach on 2 popular National Center for Biotechnology Information (NCBI) repositories: Gene Expression Omnibus (GEO) and Sequence Read Archive (SRA). Our Wide-Open system identified a large number of overdue datasets, which spurred administrators to respond directly by releasing 400 datasets in one week.

Deciphering ocean carbon in a changing world.

Dissolved organic matter (DOM) in the oceans is one of the largest pools of reduced carbon on Earth, comparable in size to the atmospheric CO2 reservoir. A vast number of compounds are present in DOM, and they play important roles in all major element cycles, contribute to the storage of atmospheric CO2 in the ocean, support marine ecosystems, and facilitate interactions between organisms. At the heart of the DOM cycle lie molecular-level relationships between the individual compounds in DOM and the members of the ocean microbiome that produce and consume them. In the past, these connections have eluded clear definition because of the sheer numerical complexity of both DOM molecules and microorganisms. Emerging tools in analytical chemistry, microbiology, and informatics are breaking down the barriers to a fuller appreciation of these connections. Here we highlight questions being addressed using recent methodological and technological developments in those fields and consider how these advances are transforming our understanding of some of the most important reactions of the marine carbon cycle.

Scalable clustering algorithms for continuous environmental flow cytometry.

MOTIVATION: Recent technological innovations in flow cytometry now allow oceanographers to collect high-frequency flow cytometry data from particles in aquatic environments on a scale far surpassing conventional flow cytometers. The SeaFlow cytometer continuously profiles microbial phytoplankton populations across thousands of kilometers of the surface ocean. The data streams produced by instruments such as SeaFlow challenge the traditional sample-by-sample approach in cytometric analysis and highlight the need for scalable clustering algorithms to extract population information from these large-scale, high-frequency flow cytometers. RESULTS: We explore how available algorithms commonly used for medical applications perform at classification of such a large-scale, environmental flow cytometry data. We apply large-scale Gaussian mixture models to massive datasets using Hadoop. This approach outperforms current state-of-the-art cytometry classification algorithms in accuracy and can be coupled with manual or automatic partitioning of data into homogeneous sections for further classification gains. We propose the Gaussian mixture model with partitioning approach for classification of large-scale, high-frequency flow cytometry data. AVAILABILITY AND IMPLEMENTATION: Source code available for download at https://github.com/jhyrkas/seaflow_cluster, implemented in Java for use with Hadoop. CONTACT: hyrkas@cs.washington.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Screening and Follow-Up Monitoring for Substance Use in Primary Care: An Exploration of Rural-Urban Variations.

BACKGROUND: Rates of substance use in rural areas are close to those of urban areas. While recent efforts have emphasized integrated care as a promising model for addressing workforce shortages in providing behavioral health services to those living in medically underserved regions, little is known on how substance use problems are addressed in rural primary care settings. OBJECTIVE: To examine rural-urban variations in screening and monitoring primary care- based patients for substance use problems in a state-wide mental health integration program. DESIGN: This was an observational study using patient registry. SUBJECTS: The study included adult enrollees (n = 15,843) with a mental disorder from 133 participating community health clinics. MAIN OUTCOMES: We measured whether a standardized substance use instrument was used to screen patients at treatment entry and to monitor symptoms at follow-up visits. KEY RESULTS: While on average 73.6 % of patients were screened for substance use, follow-up on substance use problems after initial screening was low (41.4 %); clinics in small/isolated rural settings appeared to be the lowest (13.6 %). Patients who were treated for a mental disorder or substance abuse in the past and who showed greater psychiatric complexities were more likely to receive a screening, whereas patients of small, isolated rural clinics and those traveling longer distances to the care facility were least likely to receive follow-up monitoring for their substance use problems. CONCLUSIONS: Despite the prevalent substance misuse among patients with mental disorders, opportunities to screen this high-risk population for substance use and provide a timely follow-up for those identified as at risk remained overlooked in both rural and urban areas. Rural residents continue to bear a disproportionate burden of substance use problems, with rural-urban disparities found to be most salient in providing the continuum of services for patients with substance use problems in primary care.

Voyager: Exploratory Analysis via Faceted Browsing of Visualization Recommendations.

General visualization tools typically require manual specification of views: analysts must select data variables and then choose which transformations and visual encodings to apply. These decisions often involve both domain and visualization design expertise, and may impose a tedious specification process that impedes exploration. In this paper, we seek to complement manual chart construction with interactive navigation of a gallery of automatically-generated visualizations. We contribute Voyager, a mixed-initiative system that supports faceted browsing of recommended charts chosen according to statistical and perceptual measures. We describe Voyager's architecture, motivating design principles, and methods for generating and interacting with visualization recommendations. In a study comparing Voyager to a manual visualization specification tool, we find that Voyager facilitates exploration of previously unseen data and leads to increased data variable coverage. We then distill design implications for visualization tools, in particular the need to balance rapid exploration and targeted question-answering.

Bioinformatics and data-intensive scientific discovery in the beginning of the 21st century.

This article is a summary of the bioinformatics issues and challenges of data-intensive science as discussed in the NSF-funded Data-Intensive Science (DIS) workshop in Seattle, September 19-20, 2010.