HBCU-Excellence in Research: Estimate of Ground Nitrogen Dioxide (NO2) and Ozone Concentrations by Using Multiple Satellite Data and Machine Learning Techniques

该奖项的全部或部分资金来自《2021年美国救援计划法案》(公法117-2)。该项目的目标是利用机器学习技术在高空间和时间分辨率下改进对美国毗邻地区地面NO2和臭氧浓度的估计。这些数据将用于多个领域，包括公共健康、环境健康、空气质量、农业研究和环境公平/不平等。本项目将解决以下三个科学问题：(1)哪个机器学习模型(S)可以最好地估计特定区域的地面NO2和臭氧值？(2)模型中哪些变量/参数对估计地面NO2和臭氧层值更有意义？(3)地面NO2和臭氧产物的精度有多高？PIS计划使用OMI和Tropomi的臭氧剖面数据和对流层NO2垂直柱密度(TropNO2VCD)数据，以及TEMPO的合成数据，并结合美国环保局(U.S.EPA)的气象数据、土地覆盖和地面测量数据。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2). The goal of this project is to improve estimates of ground NO2 and ozone concentrations over the contiguous U.S. at high spatial and temporal resolution using machine learning techniques. This data will be useful in multiple fields, including public health, environmental health, air quality, agricultural research and environmental justice/inequality.This project will address the following three science questions: (1) Which machine learning model(s) can best estimate the ground NO2 and ozone values in specific regions? (2) Which variables/parameters have more significance to estimate the ground NO2 and ozone values in the model? (3) How accurate are the ground NO2 and ozone products? The PIs plan to use ozone profile data and tropospheric NO2 vertical column density (TropNO2VCD) data from OMI and TROPOMI, and the synthetic data of TEMPO in conjunction of meteorological data, land cover and ground measurements from the U.S. Environmental Agency (U.S. EPA).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.