Significant resources have been spent in collecting and storing large and heterogeneous radar datasets during expensive Arctic and Antarctic fieldwork. The vast majority of data available is unlabeled, and the labeling process is both time-consuming and expensive. One possible alternative to the labeling process is the use of synthetically generated data with artificial intelligence. Instead of labeling real images, we can generate synthetic data based on arbitrary labels. In this way, training data can be quickly augmented with additional images. In this research, we evaluated the performance of synthetically generated radar images based on modified cycle-consistent adversarial networks. We conducted several experiments to test the quality of the generated radar imagery. We also tested the quality of a state-of-the-art contour detection algorithm on synthetic data and different combinations of real and synthetic data. Our experiments show that synthetic radar images generated by generative adversarial network (GAN) can be used in combination with real images for data augmentation and training of deep neural networks. However, the synthetic images generated by GANs cannot be used solely for training a neural network (training on synthetic and testing on real) as they cannot simulate all of the radar characteristics such as noise or Doppler effects. To the best of our knowledge, this is the first work in creating radar sounder imagery based on generative adversarial network.

No abstract

There is a strong national interest in the observation of ocean surface winds with high spatial and temporal resolution for understanding tropical cyclones and their effects on weather and climate and in forecasting storms making landfall. Current satellite and aircraft based remote sensing capability is limited in wind speed dynamic range and in the ability to retrieve wind information in the presence of rain, or in temporal and spatial coverage, respectively. The Hurricane Imaging Radiometer (HIRAD) is capable to capture all the hurricane features and dynamics from a high altitude aircraft preserving high resolution measurements. A detailed description of the methods used in simulating the HIRAD instrument surface sampling of wind speed, in intense rain, from various aircraft platforms with realistic operational flight patterns through a time evolving hurricane will be provided in this paper. A noise model used to simulate the effects of rain for various observation path lengths over the swath will also be described. Results will demonstrate the extent of spatial and temporal coverage available from currently available aircraft platforms.

The Hurricane Imaging Radiometer (HIRAD) is an airborne passive microwave radiometer designed to provide high resolution, wide swath imagery of surface wind speed in tropical cyclones from a low profile planar antenna with no mechanical scanning. Wind speed and rain rate images from HIRAD's first field campaign (GRIP, 2010) are presented here followed, by a discussion on the performance of the newly installed thermal control system during the 2012 HS3 campaign. The paper ends with a discussion on the next generation dual polarization HIRAD antenna (already designed) for a future system capable of measuring wind direction as well as wind speed.Index Terms-HIRAD, hurricane wind speed, imaging radiometer.

No abstract