Radar Super Resolution using a Deep Convolutional Neural Network

Journal Article · Tue Dec 01 04:00:00 EST 2020 · Journal of Atmospheric and Oceanic Technology

DOI:https://doi.org/10.1175/JTECH-D-20-0074.1· OSTI ID:1755126

Geiss, Andrew V. ^[1]; Hardin, Joseph C. ^[1]

---

1. BATTELLE (PACIFIC NW LAB)

Super-resolution involves synthetically increasing the resolution of gridded data beyond its native resolution. Typically, this is done using interpolation schemes, which estimate sub-grid scale values from neighboring data, and perform the same operation everywhere regardless of the large-scale context, or by requiring a network of radars with overlapping fields of view. Recently, significant progress has been made in single image super resolution using convolutional neural networks. Conceptually, a neural network may be able to learn relations between large scale precipitation features and the associated sub-pixel scale variability and outperform interpolation schemes. Here, we use a deep convolutional neural network to artificially enhance the resolution of NEXRAD PPI scans. The model is trained on 6-months of reflectivity observations from the Langley Hill WA (KLGX) radar, and we find that it substantially outperforms common interpolation schemes for x4 and x8 resolution increases based on several objective error and perceptual quality metrics.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1755126
• Report Number(s): PNNL-SA-152524
• Journal Information: Journal of Atmospheric and Oceanic Technology, Journal Name: Journal of Atmospheric and Oceanic Technology Journal Issue: 12 Vol. 37
• Country of Publication: United States
• Language: English

Related Subjects

radar
machine learning
super resolution
Remote sensing
Artificial intelligence
NEXRAD
deep learning