A Deep Learning Approach for Meter-Scale Air Quality Estimation in Urban Environments Using Very High-Spatial-Resolution Satellite Imagery.

High-spatial-resolution air quality (AQ) mapping is important for identifying pollution sources to facilitate local action. Some of the most populated cities in the world are not equipped with the infrastructure required to monitor AQ levels on the ground and must rely on other sources, like satellite derived estimates, to monitor AQ. Current satellite-data-based models provide AQ mapping on a kilometer scale at best. In this study we focus on producing hundred-meter-scale AQ maps for urban environments in developed cities. We examined the feasibility of an image-based object-detection analysis approach using very high-spatial-resolution (2.5 m) commercial satellite imagery. We fed the satellite imagery to a deep neural network (DNN) to learn the association between visual urban features and air pollutants. The developed model, which solely uses satellite imagery, was tested and evaluated using both ground monitoring observations and land-use regression modeled PM2.5 and NO2 concentrations over London, Vancouver (BC), Los Angeles, and New York City. The results demonstrate a low error with a total RMSE < 2 µg/m3 and highlight the contribution of specific urban features, such as green areas and roads, to continuous hundred-meter-scale AQ estimation. This approach offers promise for scaling to global applications in developed and developing urban environments. Further analysis on domain transferability will enable application of a parsimonious model based merely on satellite images to create hundred-meter-scale AQ maps in developing cities, where current and historical ground data is limited.

What you see is what you breathe? Estimating air pollution spatial variation using street level imagery.

High spatial resolution information on urban air pollution levels is unavailable in many areas globally, partially due to high input data needs of existing estimation approaches. Here we introduce a computer vision method to estimate annual means for air pollution levels from street level images. We used annual mean estimates of NO2 and PM2.5 concentrations from locally calibrated models as labels from London, New York, and Vancouver to allow for compilation of a sufficiently large dataset (~250k images for each city). Our experimental setup is designed to quantify intra and intercity transferability of image-based model estimates. Performances were high and comparable to traditional land-use regression (LUR) and dispersion models when training and testing on images from the same city (R2 values between 0.51 and 0.95 when validated on data from ground monitoring stations). Like LUR models, transferability of models between cities in different geographies is more difficult. Specifically, transferability between the three cities i.e., London, New York, and Vancouver, which have similar pollution source profiles were moderately successful (R2 values between zero and 0.67). Comparatively, performances when transferring models trained on these cities with very different source profiles i.e., Accra in Ghana and Hong Kong were lower (R2 between zero and 0.21) suggesting the need for local calibration with local calibration using additional measurement data from cities that share similar source profiles.

The Fortuitous Discovery of the Olin EILOBI Breathing Techniques: A Case Study.

Exercise-induced laryngeal obstruction (EILO) is the term for the condition previously named vocal cord dysfunction and paradoxical vocal fold motion. It is defined by glottic or supraglottic obstruction during periods of intense exercise. Not all patients respond to conventional therapy with speech-language pathology, behavioral health interventions, and treatment of contributing conditions. In this edition of Journal of Voice, the authors describe a novel series of respiratory retraining techniques, now called Olin EILOBI (EILO biphasic inspiratory) breathing techniques, specifically designed for athletes with EILO. This case presentation describes the discovery of one of these techniques during a session of therapeutic laryngoscopy during exercise. The patient was an adolescent with EILO who demonstrated a positive response to therapy with a variant of these techniques over a few days, having previously struggled with symptoms despite multiple sessions of conventional respiratory retraining over the course of months.

Therapeutic laryngoscopy during exercise: A novel non-surgical therapy for refractory EILO.

BACKGROUND: Exercise-induced laryngeal obstruction (EILO) may affect as many as 6% of the adolescent population, with some patients experiencing symptoms refractory to conservative interventions. OBJECTIVES: This report describes therapeutic laryngoscopy during exercise, a novel, non-surgical intervention that harnesses real-time laryngoscopy video as biofeedback to control laryngeal aperture during high-intensity exercise. Additionally, we quantitate patient-reported perceptions of procedure safety, tolerability, learning value, and effectiveness. METHODS: Clinical EILO patients with symptoms refractory to conventional respiratory retraining and other therapies were referred for the procedure which features laryngoscopy video as biofeedback during serial physician-guided 1-min exercise sprints. We quantify perceptions of procedure safety, tolerability, learning value, and effectiveness through questionnaires offered to all patients as well as observers of the procedure. RESULTS: Forty-one patients and 37 parent observers were approached for feedback; 88% of patients and 95% of observers consented to participation. Patients and observers reported perceptions of safety and tolerability (81% and 86%, respectively), learning value (78% and 91%, respectively), and effectiveness (58% and 80%, respectively) with patient age predicting some responses. Seventy-five percent of patients noted that "Since the procedure, my breathing during exercise has improved," and 85% of this group noted that therapeutic laryngoscopy during exercise was "the most important therapy leading to my breathing improvement." The procedure also provided insight into the psychological experience of patients, a domain not clinically apparent prior to the procedure. CONCLUSIONS: Our data support further study of therapeutic laryngoscopy during exercise as a possible intervention for patients with refractory EILO. Pediatr Pulmonol. 2017;52:813-819. © 2016 Wiley Periodicals, Inc.

Inducible laryngeal obstruction during exercise: moving beyond vocal cords with new insights.

Exercise as an important part of life for the health and wellness of children and adults. Inducible laryngeal obstruction (ILO) is a consensus term used to describe a group of disorders previously called vocal cord dysfunction, paradoxical vocal fold motion, and numerous other terms. Exercise-ILO can impair one's ability to exercise, can be confused with asthma, leading to unnecessary prescription of asthma controller and rescue medication, and results in increased healthcare resource utilization including (rarely) emergency care. It is characterized by episodic shortness of breath and noisy breathing that generally occurs at high work rates. The present diagnostic gold standard for all types of ILO is laryngoscopic visualization of inappropriate glottic or supraglottic movement resulting in airway narrowing during a spontaneous event or provocation challenge. A number of different behavioral techniques, including speech therapy, biofeedback, and cognitive-behavioral psychotherapy, may be appropriate to treat individual patients. A consensus nomenclature, which will allow for better characterization of patients, coupled with new diagnostic techniques, may further define the epidemiology and etiology of ILO as well as enable objective evaluation of therapeutic modalities.