David John Lary, PhD


Home Institution:
University of Texas, Dallas

Atmospheric science

Current Positions: 
University of Texas, Dallas

  • »
    Founding Director, Center for Multi-scale Intelligent Integrated Interactive Sensing
  • »
    Associate Professor, Department of Physics 

How can we make massive data on air quality useful to people who have respiratory ailments and other affected conditions?

Scholar Project


Personalized environmental health on the neighborhood scale & ultra-fine neighborhood scale public health

Numerous studies have associated high levels of airborne particulate matter (PM) with serious health conditions, such as lung cancer and heart disease. The goal of Dr. Lary’s project is to establish an infrastructure to provide a daily global view of fine airborne particles, known as PM2.5.

A daily snapshot of PM2.5 would allow researchers to study the epidemiology of various health conditions and their environmental triggers. Ultimately, it could allow institutions to issue personalized alerts when the density of PM2.5 reaches certain levels so that individuals who may be affected can take necessary precautions.

See more

The first step in Dr. Lary’s approach involved gathering:

Information from satellite-based remote sensing platforms, which can detect PM2.5 in non-cloudy conditions

Information from aerosol sensors, which measure PM2.5 on the ground

A global, high time resolution view of dynamic weather activity

Next, Dr. Lary used machine learning techniques to relate the satellite data to the data collected by ground-level sensors. Machine learning, a form artificial intelligence, filled in data for any areas where sensor and satellite data wasn’t available.



David John Lary, PhD, is an atmospheric scientist whose work focuses on using remote sensing from robotic aerial vehicles and satellites coupled with machine learning to facilitate scientific discovery and decision support.

In 2010, he joined University of Texas, Dallas as associate professor and founding director of the Center for Multi-scale Intelligent Integrated Interactive Sensing.

He is author of AutoChem, NASA release software that constitutes an automatic computer code generator and documenter for chemically reactive systems. It was designed primarily for modeling atmospheric chemistry and, in particular, for chemical data assimilation. AutoChem has won five NASA awards and has been used to perform long-term chemical data assimilation of atmospheric chemistry and in the validation of observations from the NASA Aura satellite. It has been used in numerous peer-reviewed articles.

See more

Dr. Lary completed his education in the United Kingdom. He received a First Class Double Honors BSc in physics and chemistry from King’s College London (1987) with the Sambrooke Exhibition Prize in Natural Science, and a PhD in atmospheric chemistry from the University of Cambridge, Churchill College (1991).

He then held post-doctoral research assistant and associate positions at Cambridge University until receiving a Royal Society University Research Fellowship in 1996 (also at Cambridge).

From 1998 to 2000, Dr. Lary held a joint position at Cambridge and the University of Tel-Aviv as a senior lecturer and Alon fellow, the highest award Israel can give a young scientist.

In 2000, the chief scientific adviser to the British Prime Minister and head of the British Office of Science and Technology, Professor Sir David King, recommended Dr. Lary to be appointed as a Cambridge University lecturer in chemical informatics.

In 2001, David joined UMBC/Goddard Earth Sciences and Technology Center (GEST) as the first distinguished Goddard fellow in earth science. While at GEST, he authored the award-winning AutoChem software and was involved with NASA Aura validation using probability distribution functions and chemical data assimilation, neural networks for accelerating atmospheric models, the use of Earth Observing Data for health and policy applications, and the optimal design of Earth Observing Systems.

Dr. Lary’s achievements have been recognized by his peers through invited contributions to the Royal Society, National Academies, and Centers for Disease Control; three prestigious fellowships; five editorial commendations; several million dollars in research funding; seven NASA awards; and more than 60 publications with more than one thousand citations in peer-reviewed literature.

More information about his work is at davidlary.info.



Education & Training

PhD, photochemical modeling of the atmosphere, University of Cambridge, England

BSc, physics & chemistry, Kings College, London, England


Selected Honors

IEEE Geoscience and Remote Sensing Society Letters Prize Paper Award, 2010

Appointed to NASA GSFC Deputy Director’s Council on Science, 2009, 2008

NASA Group Achievement Honor Award, 2008

Appointed to the NASA GSFC Science Director’s Council, 2007

See more

NASA Space Act awards, 2005, 2004

NASA Inventions and Contributions Board Award, 2005

NASA Tech Brief Award for creative development of a technical innovation, 2004

NASA Data Assimilation Office Special Recognition Award, 2002

Alon Fellowship, 1998-2001

Royal Society Fellowship, 1996-2002

Sambroke Exhibition Prize for Natural Science, 1986


Selected Publications 

Book Chapters

Applications of Remote Sensing in Tracking Airborne Diseases, in Tracking for Public Health Surveillance, October 2012

Artificial Intelligence in Aerospace, in Aerospace Technologies Advancements, January 2010

Artificial Intelligence in Geoscience and Remote Sensing, in Geoscience and Remote Sensing New Achievements, February 2010

Research Papers

Open-Path Greenhouse Gas Sensor for
UAV applications
Quantum Electronics and Laser Science Conference, May 2012

Low Power Greenhouse Gas Sensors for Unmanned Aerial Vehicles.
Remote Sensing, May 2012

High Resolution Identification of Dust Sources Using Machine Learning and Remote Sensing Data.
Fall American Geophysical Union Meeting, January 2011

Cross-Correlation of Ionospheric Parameters Using Machine-Learning Analysis of Data from Multiple DMSP Spacecraft. Fall American Geophysical Union Meeting, January 2011

Assimilation of Real-Time Satellite and Human Sensor Networks for Modeling Natural Disasters.
Fall American Geophysical Union Meeting, January 2011

MODIS Aerosol Optical Depth Bias Adjustment Using Machine Learning Algorithms.
Fall American Geophysical Union Meeting, January 2011

Which Machine-Learning Models Best Predict Online Auction Seller Deception Risk?
American Accounting Association, Strategic and Emerging Technologies, February 2010

See articles & papers on PubMed