There is an enormous amount of data available on environmental and human health that holds great promise in providing critical insights into factors that adversely influence our world. Furthermore, the amount of information available on human health (i.e. wearable sensors, social media, web based images and text), and the environment (i.e. low-cost air and water pollution sensors, micro-satellites) is experiencing explosive growth. However, the ability to harness the vast amount of information has been hampered by a current lack of collaboration between experts in data analytics, and environmental and health scientists. With this in mind we have developed close collaborations with machine learning experts, and we are at the forefront of developing and applying machine learning approaches to environmental data analytics. Thus far we have developed methodologies to calibrate and conduct surveillance on low-cost air pollution sensor networks (Zheng et al., 2018, 2019), and we have also developed a novel approach to determine surface particulate matter concentrations at extremely high spatial resolution and accuracy using micro-satellite images (Zheng et al., 2020). We are also currently involved in a variety of projects that analyze large data sets to assess both human and environmental health.
Highlighted Peer-Reviewed Publications:
Zheng, T., Bergin, M.H., Johnson, K.K., Tripathi, S.N., Shirodkar, S., Landis, M., Sutaria, R., Carlson, D.E., Field evaluation of low cost particulate matter sensors in high and low concentration environments, Atmos. Meas. Tech., 11, 8, 4823-4846, 2018.
Zheng, T. S.; Bergin, M. H.; Sutaria, R.; Tripathi, S. N.; Caldow, R.; Carlson, D. E., Gaussian process regression model for dynamically calibrating and surveilling a wireless low-cost particulate matter sensor network in Delhi. Atmospheric Measurement Techniques,12 (9), 5161-5181, 2019.
Zheng, T., Bergin, M.H., Hu, S., Miller, J., Carlson, D.E., Estimating ground-level PM2.5 using micro-satellite images by a convulusional neural network and a random forest approach, Atmos. Environ., 230 (1), 117451, 2020.