| Gaussian markov random fields versus linear mixed models for satellite-based PM2. 5 assessment: evidence from the northeastern USA R Sarafian, I Kloog, AC Just, JD Rosenblatt Atmospheric environment 205, 30-35, 2019 | 19 | 2019 |
| Gaussian Markov random fields improve ensemble predictions of daily 1 km PM2. 5 and PM10 across France I Hough, R Sarafian, A Shtein, B Zhou, J Lepeule, I Kloog Atmospheric Environment 264, 118693, 2021 | 15 | 2021 |
| A domain adaptation approach for performance estimation of spatial predictions R Sarafian, I Kloog, E Sarafian, I Hough, JD Rosenblatt IEEE Transactions on Geoscience and Remote Sensing 59 (6), 5197-5205, 2020 | 8 | 2020 |
| Six types of dust events in Eastern Mediterranean identified using unsupervised machine-learning classification D Nissenbaum, R Sarafian, Y Rudich, S Raveh-Rubin Atmospheric Environment 309, 119902, 2023 | 3 | 2023 |
| Deep multi-task learning for early warnings of dust events implemented for the Middle East R Sarafian, D Nissenbaum, S Raveh-Rubin, V Agrawal, Y Rudich NPJ climate and atmospheric science 6 (1), 23, 2023 | 2 | 2023 |
| Optimal-design domain-adaptation for exposure prediction in two-stage epidemiological studies R Sarafian, I Kloog, JD Rosenblatt Journal of Exposure Science & Environmental Epidemiology 33 (6), 963-970, 2023 | 1 | 2023 |
| Domain Adaptation Approaches for Exposure Models R Sarafian https://github.com/ronsarafian/DA_for_EXposure_Models/blob/main …, 2020 | | 2020 |
| Gaussian Markov Random Fields for Big-scale Spatio-Temporal Data R Sarafian https://github.com/ronsarafian/GMRF_Big_Data/blob/main/GMRF_Bid_Data.pdf, 2019 | | 2019 |
