TY - JOUR
T1 - Automatic detection and classification of low-level orographic precipitation processes from space-borne radars using machine learning
AU - Arulraj, Malarvizhi
AU - Barros, Ana P.
N1 - The authors are grateful to four Reviewers for their thorough comments and suggestions. The authors wish to thank NOAA for maintaining the NEXRAD network and NOAA's NSSL for maintaining the MRMS operational data. Access to the MRMS 3D reflectivity data was made possible by the GPM Ground Validation Program. The authors are grateful to Dr. Robert (Bob) Meneghini, Dr. Walter Petersen, and Dr. Simone Tanelli for their advice, comments, and suggestions regarding this work. The research was funded in part by NASA Earth System Science Fellowship Grant NNX16AO10H with the first author, and by NASA Grant 80NSSC19K0685 with the second author.
The authors are grateful to four Reviewers for their thorough comments and suggestions. The authors wish to thank NOAA for maintaining the NEXRAD network and NOAA's NSSL for maintaining the MRMS operational data. Access to the MRMS 3D reflectivity data was made possible by the GPM Ground Validation Program. The authors are grateful to Dr. Robert (Bob) Meneghini, Dr. Walter Petersen, and Dr. Simone Tanelli for their advice, comments, and suggestions regarding this work. The research was funded in part by NASA Earth System Science Fellowship Grant NNX16AO10H with the first author, and by NASA Grant 80NSSC19K0685 with the second author.
PY - 2021/5
Y1 - 2021/5
N2 - Ground-clutter is a significant cause of missed-detection and underestimation of precipitation in complex terrain from space-based radars such as the Global Precipitation Measurement Mission (GPM) Dual-frequency Precipitation Radar (DPR). This research proposes an Artificial Intelligence (AI) framework consisting of a precipitation detection model (PDM) and a precipitation regime classification model (PCM) to improve orographic precipitation retrievals from GPM-DPR using machine learning. The PDM is a Random Forest Classifier using GPM Microwave Imager (GMI) calibrated brightness temperatures (Tbs) and low-level precipitation mixing ratios from the High-Resolution Rapid Refresh (HRRR) analysis as inputs. The PCM is a Convolutional Neural Network that predicts the precipitation regime class, defined independently based on quantitative features of ground-based radar reflectivity profiles, using GPM DPR Ku-band (Ku-PR) reflectivity profiles and GMI Tbs. The AI framework is demonstrated for warm-season precipitation in the Southern Appalachian Mountains over three years (2016–2019), achieving large reductions in false alarms (77%) and missed detections (82%) relative to GPM Ku-PR precipitation products. The spatial distribution of predicted precipitation classes within the GPM overpass reflects the complex interactions between storms and topography that determine orographic precipitation regimes. For each GPM pixel, the local precipitation class informs on the vertical structure of rainfall microphysics aiming to capture low-level processes missed in GPM DPR reflectivity profiles contaminated by ground-clutter (i.e., the radar blind-zone).
AB - Ground-clutter is a significant cause of missed-detection and underestimation of precipitation in complex terrain from space-based radars such as the Global Precipitation Measurement Mission (GPM) Dual-frequency Precipitation Radar (DPR). This research proposes an Artificial Intelligence (AI) framework consisting of a precipitation detection model (PDM) and a precipitation regime classification model (PCM) to improve orographic precipitation retrievals from GPM-DPR using machine learning. The PDM is a Random Forest Classifier using GPM Microwave Imager (GMI) calibrated brightness temperatures (Tbs) and low-level precipitation mixing ratios from the High-Resolution Rapid Refresh (HRRR) analysis as inputs. The PCM is a Convolutional Neural Network that predicts the precipitation regime class, defined independently based on quantitative features of ground-based radar reflectivity profiles, using GPM DPR Ku-band (Ku-PR) reflectivity profiles and GMI Tbs. The AI framework is demonstrated for warm-season precipitation in the Southern Appalachian Mountains over three years (2016–2019), achieving large reductions in false alarms (77%) and missed detections (82%) relative to GPM Ku-PR precipitation products. The spatial distribution of predicted precipitation classes within the GPM overpass reflects the complex interactions between storms and topography that determine orographic precipitation regimes. For each GPM pixel, the local precipitation class informs on the vertical structure of rainfall microphysics aiming to capture low-level processes missed in GPM DPR reflectivity profiles contaminated by ground-clutter (i.e., the radar blind-zone).
KW - Convolution neural network
KW - Global precipitation measurement mission
KW - Machine learning
KW - Orographic precipitation
KW - Precipitation detection
KW - Precipitation radar
UR - http://www.scopus.com/inward/record.url?scp=85101315879&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101315879&partnerID=8YFLogxK
U2 - 10.1016/j.rse.2021.112355
DO - 10.1016/j.rse.2021.112355
M3 - Article
AN - SCOPUS:85101315879
SN - 0034-4257
VL - 257
JO - Remote Sensing of Environment
JF - Remote Sensing of Environment
M1 - 112355
ER -