Engineering topics

Itai Kloog

Publications and source records attributed to Itai Kloog.

3 records

NASA NTRS2021

Impact of environmental attributes on the uncertainty in MAIAC/MODIS AOD retrievals: A comparative analysis

This work examines the impact of different environmental attributes on the uncertainty in satellite-based Aerosol Optical Depth (AOD) retrieval against the benchmark Aerosol Robotic Network (AERONET) AOD measurements at 21 sites across North Africa, California and Germany, in the years 2007–2017. As a first step, we studied the effects of spatial averaging the Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD retrievals, and of temporal averaging the AERONET AOD around the satellite (Aqua) overpass, on the agreement between the two products. AERONET AOD averaging over a time-window of ±15 min around the satellite overpass and the 1 ×1 km2 spatial grid of MAIAC were found to provide the best AOD retrieval performance. Next, MAIAC AOD were stratified according to different co-measured environmental attributes (aerosol loading, dominant particle size, vegetation cover, and prevailing particle type) and analyzed against the AERONET AOD. The envelope of the expected retrieval error varied considerably among different environmental attributes categories, with more accurate AOD retrievals obtained over highly vegetated areas (i.e. less surface reflectance) than over arid areas. Moreover, the retrieval accuracy was found to be sensitive to the aerosol loading and particle size, with a large bias between the MAIAC and AERONET AOD during high aerosol loading of coarse particles. In addition, the retrieval accuracy of MAIAC AOD was found to depend on the aerosol type due to the aerosol model assumptions regarding their optical properties.

AOD RETRIEVAL↗

NASA NTRS2020

Advancing Methodologies for Applying Machine Learning and Evaluating Spatiotemporal Models of Fine Particulate Matter (PM 2.5 ) Using Satellite Data Over Large Regions

Reconstructing the distribution of fine particulate matter (PM 2.5 ) in space and time, even far from ground monitoring sites, is an important exposure science contribution to epidemiologic analyses of PM 2.5 health impacts. Flexible statistical methods for prediction have demonstrated the integration of satellite observations with other predictors, yet these algorithms are susceptible to overfitting the spatiotemporal structure of the training datasets. We present a new approach for predicting PM 2.5 using machine-learning methods and evaluating prediction models for the goal of making predictions where they were not previously available. We apply extreme gradient boosting (XGBoost) modeling to predict daily PM 2.5 on a 1 x 1 km 2 resolution for a 13 state region in the Northeastern USA for the years 2000–2015 using satellite-derived aerosol optical depth and implement a recursive feature selection to develop a parsimonious model. We demonstrate excellent predictions of withheld observations but also contrast an RMSE of 3.11 μg/m 3 in our spatial cross-validation withholding nearby sites versus an overfit RMSE of 2.10 μg/m 3 using a more conventional random ten-fold splitting of the dataset. As the field of exposure science moves forward with the use of advanced machine-learning approaches for spatiotemporal modeling of air pollutants, our results show the importance of addressing data leakage in training, overfitting to spatiotemporal structure, and the impact of the predominance of ground monitoring sites in dense urban sub-networks on model evaluation. The strengths of our resultant modeling approach for exposure in epidemiologic studies of PM 2.5 include improved efficiency, parsimony, and interpretability with robust validation while still accommodating complex spatiotemporal relationships.

air pollution↗

NASA NTRS2015

Spatiotemporal Prediction of Fine Particulate Matter Using High-Resolution Satellite Images in the Southeastern US 2003-2011

Numerous studies have demonstrated that fine particulate matter (PM(sub 2.5), particles smaller than 2.5 micrometers in aerodynamic diameter) is associated with adverse health outcomes. The use of ground monitoring stations of PM(sub 2.5) to assess personal exposure, however, induces measurement error. Land-use regression provides spatially resolved predictions but land-use terms do not vary temporally. Meanwhile, the advent of satellite-retrieved aerosol optical depth (AOD) products have made possible to predict the spatial and temporal patterns of PM(sub 2.5) exposures. In this paper, we used AOD data with other PM(sub 2.5) variables, such as meteorological variables, land-use regression, and spatial smoothing to predict daily concentrations of PM(sub 2.5) at a 1 sq km resolution of the Southeastern United States including the seven states of Georgia, North Carolina, South Carolina, Alabama, Tennessee, Mississippi, and Florida for the years from 2003 to 2011. We divided the study area into three regions and applied separate mixed-effect models to calibrate AOD using ground PM(sub 2.5) measurements and other spatiotemporal predictors. Using 10-fold cross-validation, we obtained out of sample R2 values of 0.77, 0.81, and 0.70 with the square root of the mean squared prediction errors of 2.89, 2.51, and 2.82 cu micrograms for regions 1, 2, and 3, respectively. The slopes of the relationships between predicted PM2.5 and held out measurements were approximately 1 indicating no bias between the observed and modeled PM(sub 2.5) concentrations. Predictions can be used in epidemiological studies investigating the effects of both acute and chronic exposures to PM(sub 2.5). Our model results will also extend the existing studies on PM(sub 2.5) which have mostly focused on urban areas because of the paucity of monitors in rural areas.

PM2.5↗