Home » veljko petkovic

Tag: veljko petkovic

Figure: Precipitation system observed at 0725 UTC 11 Aug 2020, over the U.S. Midwest. MRMS surface precipitation product (observations) on the left and U-Net output on the right.

Optimal Summertime Precipitation Data from GEO and LEO Observations 

ESSIC/CISESS Scientists Veljko Petković, Malarvizhi Arulraj, and CISESS Summer Intern Vesta Gorooh (UCI PhD student) have a new article in the November issue of the Journal of Hydrometeorology. The article describes the use of machine learning techniques to improve the retrieval of surface precipitation from passive meteorological sensors aboard geosynchronous Earth-orbiting (GEO) and low Earth-orbiting (LEO) satellites.

Read More »
Snow falling around some pine trees

Evaluation of Snowfall Retrieval Performance of GPM Constellation Radiometers Relative to Spaceborne Radars

Several current and former ESSIC/CISESS scientists are co-authors on a new paper in Journal of Hydrometeorology titled “Evaluation of Snowfall Retrieval Performance of GPM Constellation Radiometers Relative to Spaceborne Radars”. Former ESSIC scientist Yalei You was first author on the paper. Current ESSIC/CISESS scientists on the paper are Veljko Petkovic, Lisa Milani, John Yang, and Guojun Gu.

Read More »
Figure: (Top panel) Rain-Rate predicted by eTRaP and observed by MRMS. (Bottom panel) Scatter plot and estimation metrics for Tropical Storm Fiona between September 18, 2022 12 UTC to September 19, 2022 12 UTC.

NPreciSe Evaluation of eTRaP during Tropical Storm Fiona

Tropical Storm Fiona struck Puerto Rico on September 17-18, 2022 causing catastrophic floods and leaving most of the island with a major power outage. Fiona is the first Atlantic storm this season to cause a major disaster. NPreciSe (NOAA Satellite Precipitation Validation System) led by the CISESS science team (Malar Arulraj, Veljko Petkovic, Ralph Ferraro, and Huan Meng), evaluated the performance of the Ensemble Tropical Rainfall Potential (eTRaP) forecasts during this event, using a recently added Multi-Radar/Multi-Sensor (MRMS) observation product over Caribbean Islands.

Read More »
Figure: Case study of August 11, 2018. Convective/stratiform split of the raining system observed by GPM-core satellite (orbit: 025293). From left to right: (a) PMW-retrieved (GPROF) – a current operational benchmark; (b) Dual-frequency Precipitation Radar-derived product – the truth; (c) Bayesian model prediction ResNetV2; (d) Entropy for the Bayesian model prediction – uncertainty map.

Using Bayesian Deep Learning to Improve Precipitation Retrievals

ESSIC/CISESS Scientist Veljko Petković co-authored a study on the application of new and emerging field of BDL concepts to mitigate problems associated with the accuracy of precipitation retrievals from satellite-borne passive microwave (PMW) radiometers, which was published in IEEE Geoscience and Remote Sensing Letters.

Read More »