Zoom RecordingNotes DocOpen-Source Air Quality Analytic Collaborative FrameworksDegraded air quality is the largest environmental health risk factor, leading to several million premature deaths globally per year. The challenge of combating poor air quality is exacerbated by growing urban populations, changing emissions, and a warming climate. While there have been many advances in the collection of observations of atmospheric composition, reflected in the dramatic increase in archived Earth Observations, as well as in forecast modeling, there is no single measurement or method that alone can provide an accurate depiction of the entire atmosphere. Our rapidly growing collections of observational and model data require us to be smarter about what data to include, and how such data is used. The NASA AIST Analytic Collaborative Frameworks (ACF) is designed to facilitate access, integration, and understanding of large amounts of disparate datasets. Its purpose is to harmonize analytics tools, data, visualization, and computing environments to meet the needs of Earth science investigations and applications. This session offers a collection of open-source ACF technologies for air quality analysis, forecasting, and prediction. Recommended ways to Prepare:
Session Organizers: Thomas Huang, Joe Roberts, Daven Henze, Jeanne Holm, Mohammad Pourhomayoun, Chaowei (Phil) Yang, and Steve Young
Invited Presentations: Air Quality Collaborative Framework (AQ ACF)Joe Roberts and Thomas Huang, NASA JPL
Ambient air pollution is the largest environmental health risk factor, leading to several million premature deaths globally per year. The challenge of combating poor air quality is exacerbated by growing urban populations, changing emissions, and a warming climate. While there have been many advances monitoring and modeling of atmospheric composition, reflected in the dramatic increase in archived Earth Observations, there is no single measurement or method that alone can provide an accurate depiction of the entire atmosphere. The rapidly growing collections of observational and modeling data require us to be smarter about what data to include, and how such data is used. In recent years, NASA has invested significantly in advancing the concepts for Analytics Collaborative Framework (ACF) and New Observing Strategies (NOS) to tackle our software infrastructure need for harmonized data management and dynamic acquisition of diverse measurements for on-demand, interactive, multivariate analysis, and access. It is not enough to have a big data, standalone analytics solution; it is critical that we start integrating data from remote sensing, modeling, and in-situ networks in a harmonized manner that enables timely and data-driven decision-making for air quality management. This work presents the design and development of an Air Quality Analytics Collaborative Framework (AQ ACF), as part of NASA’s Advanced Information Systems Technology (AIST) effort, to establish a data, machine-learning, and numerically driven platform for air quality analysis, visualization, and prediction.
Predicting What We BreatheMohammad Pourhomayoun, CSULA and Jeanne Holm, City of Los Angeles
Air pollution is mostly a human-made problem known as the Silent Killer. It is the main environmental risk for human health and responsible for the early deaths of 7 million people every year, around 600,000 of whom are children. The ability to predict air quality, to intervene to mitigate poor air quality activities, and to inform the most vulnerable people and those suffering from respiratory issues is a significant goal for government and health officials worldwide.
The main objective of this work is to develop predictive models based on advanced AI and machine learning to discover patterns in urban air pollution and enable the accurate forecast of main air pollutant levels including PM2.5, PM10, Ozone, CO, and NOx. To build the predictive models, we used a wide range of data including NASA and non-NASA satellite observations for major air pollutants, ground-based sensor data for air quality components, meteorological data, wildfire data, and other earth observations. Our results have shown the accuracy of more than 90% in the prediction of major air pollutant levels including PM2.5 and ozone in the city of Los Angeles with high temporal and spatial resolutions. By applying machine learning to satellite and ground data, this work will immediately help to inform other cities on appropriate measurements, analytics, predictive algorithms, and mitigation strategies that are useful for dealing with air quality variability.
Developing an interactive tool for characterizing the air pollution-related health impacts in Los Angeles, CA associated with different proposed emission scenariosM. Omar Nawaz and Daven K. Henze, University of Colorado
Poor air quality is a global health crisis that is responsible for millions of premature deaths each year. Reduced complexity frameworks can be used to estimate the effectiveness of different policy solutions; however, developing a framework that is scientifically valid but also malleable enough to be applicable to many different proposed scenarios presents a challenge. In this work, we calculate the sensitivity of pollution in Los Angeles, CA to emissions using the adjoint of the chemical transport model GEOS-Chem. We develop an interactive reduced complexity tool for the Air Quality Analytic Center Framework (AQACF) that is capable of assessing the fine particulate matter (PM2.5), Ozone (O3), and Nitrogen Dioxide (NO2¬) health impacts of different emissions actions from the transportation, energy, agriculture, and industry sectors. We consider different spatial scales of implementation including city-, county-, and state-level actions. Using adjoint sensitivities, the tool is capable of identifying the health impacts associated with many different emission scenarios; we present a single case study based on recently enacted legislation in California that would ban the sale of fossil fuel vehicles by 2035.
Developing Spatiotemporal Tools to Improve Resolution of Air Quality DataChaowei (Phil) Yang, George Mason University
Climate change and pollutant emissions continue to worsen our breathing air, causing severe health problems for national and global citizens including millions of deaths each year. High resolution and fidelity data is desperately needed to support decision making to mitigate such health impact. We are developing a set of spatiotemporal tools to improve ground-level air quality resolution by integrating new observation system data and numerical simulation. The project 1) selects, preprocesses, downscales, and fuses air quality data at various resolution and relevant temporal resolution with LA coverage; 2) relevant machine learning and numerical simulation are being developed to improve the data quality and accuracy; 3) alignment with the NASA AIST Air Quality Analytic Collaborative Framework (AQACF) and Apache Science Data Analytics Platform (SDAP) by automating the data transformation, ingestion, and harmonization for cloud-based management and analysis. Research results complements the AIST AQACF effort by streamlining the generation of value-added air quality data products and analysis. Case studies of Ukraine air quality rapid response and LA ship backlog impact are conducted.
