Articles | Volume 14, issue 12
https://doi.org/10.5194/amt-14-7729-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-14-7729-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
09 Dec 2021
Research article |
| 09 Dec 2021
| 09 Dec 2021
Inpainting radar missing data regions with deep learning
Pacific Northwest National Laboratory, Atmospheric Sciences and Global Change Division, Richland, WA, USA
Joseph C. Hardin
Pacific Northwest National Laboratory, Atmospheric Sciences and Global Change Division, Richland, WA, USA
Related authors
Matthew W. Christensen, Andrew Geiss, Adam C. Varble, and Po-Lun Ma
EGUsphere, https://doi.org/10.5194/egusphere-2025-3850, https://doi.org/10.5194/egusphere-2025-3850, 2025
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Short summary
We used satellite data and machine learning to better understand how tiny particles in the atmosphere affect clouds and their brightness. At higher spatial resolution, we discovered a new “M”-shaped pattern in the relationship between cloud water and droplet concentration unlike the inverted-V shape observed at coarsely gridded scales. Cloud water increases more with droplet concentration when rain is present. These findings support the development of next-generation atmospheric models.
Jianfeng Li, Andrew Geiss, Zhe Feng, L. Ruby Leung, Yun Qian, and Wenjun Cui
Earth Syst. Sci. Data, 17, 3721–3740, https://doi.org/10.5194/essd-17-3721-2025, https://doi.org/10.5194/essd-17-3721-2025, 2025
Short summary
Short summary
We developed a high-resolution (4 km and hourly) observational derecho dataset over the United States east of the Rocky Mountains from 2004 to 2021 by using a mesoscale convective system dataset, bow echoes detected by a machine learning method, hourly gust speeds, and physically based identification criteria.
Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang
EGUsphere, https://doi.org/10.5194/egusphere-2025-1501, https://doi.org/10.5194/egusphere-2025-1501, 2025
Short summary
Short summary
This study leverages machine learning models to classify cloud thermodynamic phases using multi-sensor remote sensing data collected at the Department of Energy Atmospheric Radiation Measurement North Slope of Alaska observatory. We evaluate model performance, feature importance, application of the model to another observatory, and quantify how the models respond to instrument outages.
Andrew Geiss and Po-Lun Ma
Geosci. Model Dev., 18, 1809–1827, https://doi.org/10.5194/gmd-18-1809-2025, https://doi.org/10.5194/gmd-18-1809-2025, 2025
Short summary
Short summary
Particles in the Earth's atmosphere strongly impact the planet's energy budget, and atmosphere simulations require accurate representation of their interaction with light. This work introduces two approaches to represent light scattering by small particles. The first is a scattering simulator based on Mie theory implemented in Python. The second is a neural network emulator that is more accurate than existing methods and is fast enough to be used in climate and weather simulations.
Andrew Geiss, Po-Lun Ma, Balwinder Singh, and Joseph C. Hardin
Geosci. Model Dev., 16, 2355–2370, https://doi.org/10.5194/gmd-16-2355-2023, https://doi.org/10.5194/gmd-16-2355-2023, 2023
Short summary
Short summary
Atmospheric aerosols play a critical role in Earth's climate, but it is too computationally expensive to directly model their interaction with radiation in climate simulations. This work develops a new neural-network-based parameterization of aerosol optical properties for use in the Energy Exascale Earth System Model that is much more accurate than the current one; it also introduces a unique model optimization method that involves randomly generating neural network architectures.
Andrew Geiss, Sam J. Silva, and Joseph C. Hardin
Geosci. Model Dev., 15, 6677–6694, https://doi.org/10.5194/gmd-15-6677-2022, https://doi.org/10.5194/gmd-15-6677-2022, 2022
Short summary
Short summary
This work demonstrates the use of modern machine learning techniques to enhance the resolution of atmospheric chemistry simulations. We evaluate the schemes for an 8 x 10 increase in resolution and find that they perform substantially better than conventional methods. Methods are introduced to target machine learning methods towards this type of problem, most notably by ensuring they do not break known physical constraints.
Matthew W. Christensen, Andrew Geiss, Adam C. Varble, and Po-Lun Ma
EGUsphere, https://doi.org/10.5194/egusphere-2025-3850, https://doi.org/10.5194/egusphere-2025-3850, 2025
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Short summary
We used satellite data and machine learning to better understand how tiny particles in the atmosphere affect clouds and their brightness. At higher spatial resolution, we discovered a new “M”-shaped pattern in the relationship between cloud water and droplet concentration unlike the inverted-V shape observed at coarsely gridded scales. Cloud water increases more with droplet concentration when rain is present. These findings support the development of next-generation atmospheric models.
Jianfeng Li, Andrew Geiss, Zhe Feng, L. Ruby Leung, Yun Qian, and Wenjun Cui
Earth Syst. Sci. Data, 17, 3721–3740, https://doi.org/10.5194/essd-17-3721-2025, https://doi.org/10.5194/essd-17-3721-2025, 2025
Short summary
Short summary
We developed a high-resolution (4 km and hourly) observational derecho dataset over the United States east of the Rocky Mountains from 2004 to 2021 by using a mesoscale convective system dataset, bow echoes detected by a machine learning method, hourly gust speeds, and physically based identification criteria.
Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang
EGUsphere, https://doi.org/10.5194/egusphere-2025-1501, https://doi.org/10.5194/egusphere-2025-1501, 2025
Short summary
Short summary
This study leverages machine learning models to classify cloud thermodynamic phases using multi-sensor remote sensing data collected at the Department of Energy Atmospheric Radiation Measurement North Slope of Alaska observatory. We evaluate model performance, feature importance, application of the model to another observatory, and quantify how the models respond to instrument outages.
Andrew Geiss and Po-Lun Ma
Geosci. Model Dev., 18, 1809–1827, https://doi.org/10.5194/gmd-18-1809-2025, https://doi.org/10.5194/gmd-18-1809-2025, 2025
Short summary
Short summary
Particles in the Earth's atmosphere strongly impact the planet's energy budget, and atmosphere simulations require accurate representation of their interaction with light. This work introduces two approaches to represent light scattering by small particles. The first is a scattering simulator based on Mie theory implemented in Python. The second is a neural network emulator that is more accurate than existing methods and is fast enough to be used in climate and weather simulations.
Shuaiqi Tang, Adam C. Varble, Jerome D. Fast, Kai Zhang, Peng Wu, Xiquan Dong, Fan Mei, Mikhail Pekour, Joseph C. Hardin, and Po-Lun Ma
Geosci. Model Dev., 16, 6355–6376, https://doi.org/10.5194/gmd-16-6355-2023, https://doi.org/10.5194/gmd-16-6355-2023, 2023
Short summary
Short summary
To assess the ability of Earth system model (ESM) predictions, we developed a tool called ESMAC Diags to understand how aerosols, clouds, and aerosol–cloud interactions are represented in ESMs. This paper describes its version 2 functionality. We compared the model predictions with measurements taken by planes, ships, satellites, and ground instruments over four regions across the world. Results show that this new tool can help identify model problems and guide future development of ESMs.
Zhe Feng, Joseph Hardin, Hannah C. Barnes, Jianfeng Li, L. Ruby Leung, Adam Varble, and Zhixiao Zhang
Geosci. Model Dev., 16, 2753–2776, https://doi.org/10.5194/gmd-16-2753-2023, https://doi.org/10.5194/gmd-16-2753-2023, 2023
Short summary
Short summary
PyFLEXTRKR is a flexible atmospheric feature tracking framework with specific capabilities to track convective clouds from a variety of observations and model simulations. The package has a collection of multi-object identification algorithms and has been optimized for large datasets. This paper describes the algorithms and demonstrates applications for tracking deep convective cells and mesoscale convective systems from observations and model simulations at a wide range of scales.
Andrew Geiss, Po-Lun Ma, Balwinder Singh, and Joseph C. Hardin
Geosci. Model Dev., 16, 2355–2370, https://doi.org/10.5194/gmd-16-2355-2023, https://doi.org/10.5194/gmd-16-2355-2023, 2023
Short summary
Short summary
Atmospheric aerosols play a critical role in Earth's climate, but it is too computationally expensive to directly model their interaction with radiation in climate simulations. This work develops a new neural-network-based parameterization of aerosol optical properties for use in the Energy Exascale Earth System Model that is much more accurate than the current one; it also introduces a unique model optimization method that involves randomly generating neural network architectures.
Andrew Geiss, Sam J. Silva, and Joseph C. Hardin
Geosci. Model Dev., 15, 6677–6694, https://doi.org/10.5194/gmd-15-6677-2022, https://doi.org/10.5194/gmd-15-6677-2022, 2022
Short summary
Short summary
This work demonstrates the use of modern machine learning techniques to enhance the resolution of atmospheric chemistry simulations. We evaluate the schemes for an 8 x 10 increase in resolution and find that they perform substantially better than conventional methods. Methods are introduced to target machine learning methods towards this type of problem, most notably by ensuring they do not break known physical constraints.
Shuaiqi Tang, Jerome D. Fast, Kai Zhang, Joseph C. Hardin, Adam C. Varble, John E. Shilling, Fan Mei, Maria A. Zawadowicz, and Po-Lun Ma
Geosci. Model Dev., 15, 4055–4076, https://doi.org/10.5194/gmd-15-4055-2022, https://doi.org/10.5194/gmd-15-4055-2022, 2022
Short summary
Short summary
We developed an Earth system model (ESM) diagnostics package to compare various types of aerosol properties simulated in ESMs with aircraft, ship, and surface measurements from six field campaigns across spatial scales. The diagnostics package is coded and organized to be flexible and modular for future extension to other field campaign datasets and adapted to higher-resolution model simulations. Future releases will include comprehensive cloud and aerosol–cloud interaction diagnostics.
Christopher R. Williams, Karen L. Johnson, Scott E. Giangrande, Joseph C. Hardin, Ruşen Öktem, and David M. Romps
Atmos. Meas. Tech., 14, 4425–4444, https://doi.org/10.5194/amt-14-4425-2021, https://doi.org/10.5194/amt-14-4425-2021, 2021
Short summary
Short summary
In addition to detecting clouds, vertically pointing cloud radars detect individual insects passing over head. If these insects are not identified and removed from raw observations, then radar-derived cloud properties will be contaminated. This work identifies clouds in radar observations due to their continuous and smooth structure in time, height, and velocity. Cloud masks are produced that identify cloud vertical structure that are free of insect contamination.
Sam J. Silva, Po-Lun Ma, Joseph C. Hardin, and Daniel Rothenberg
Geosci. Model Dev., 14, 3067–3077, https://doi.org/10.5194/gmd-14-3067-2021, https://doi.org/10.5194/gmd-14-3067-2021, 2021
Short summary
Short summary
The activation of aerosol into cloud droplets is an important but uncertain process in the Earth system. The physical and chemical interactions that govern this process are too computationally expensive to explicitly resolve in modern Earth system models. Here, we demonstrate how hybrid machine learning approaches can provide a potential path forward, enabling the representation of the more detailed physics and chemistry at a reduced computational cost while still retaining physical information.
Cited articles
Agrawal, S., Barrington, L., Bromberg, C., Burge, J., Gazen, C., and Hickey,
J.: Machine learning for precipitation nowcasting from radar images, arXiv [preprint], arXiv:1912.12132, 11 December 2019. a
Arjovsky, M., Chintala, S., and Bottou, L.: Wasserstein generative adversarial networks, in: International conference on machine learning, PMLR, 70, 214–223, available at: https://proceedings.mlr.press/v70/arjovsky17a.html (last access: 22 March 2020), 2017. a
Bertalmio, M., Sapiro, G., Caselles, V., and Ballester, C.: Image Inpainting,
in: Proceedings of the 27th annual conference on Computer graphics and
interactive techniques, SIGGRAPH '00, Addison-Wesley Publishing Co., USA, 417–424, https://doi.org/10.1145/344779.344972, 2000. a
Bertalmio, M., Bertozzi, A. L., and Sapiro, G.: Navier-stokes, fluid
dynamics, and image and video inpainting, in: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA, 8–14 December 2001, IEEE CVPR, 1, https://doi.org/10.1109/CVPR.2001.990497, 2001. a
Bugeau, A., Bertalmío, M., Caselles, V., and Sapiro, G.: A Comprehensive
Framework for Image Inpainting, IEEE T. Image Process., 19,
2634–2645, https://doi.org/10.1109/TIP.2010.2049240, 2010. a
Criminisi, A., Perez, P., and Toyama, K.: Region filling and object
removal by exemplar-based image inpainting, IEEE T. Image Process., 13, 1200–1212, https://doi.org/10.1109/TIP.2004.833105, 2004. a
Efros, A. A. and Leung, T. K.: Texture Synthesis by Non-parametric Sampling,
IEEE I. Conf. Comp. Vis., 2, 1033–1038, https://doi.org/10.1109/ICCV.1999.790383, 1999. a, b
Elharrouss, O., Almaadeed, N., Al-Maadeed, S., and Akbari, Y.: Image
Inpainting: A Review, Neural Process. Lett., 51, 2007–2028,
https://doi.org/10.1007/s11063-019-10163-0, 2020. a
Feng, Z., Leung, L. R., Houze Jr., R. A., Hagos, S., Hardin, J., Yang, Q., Han, B., and Fan, J.: Structure and evolution of mesoscale convective systems: Sensitivity to cloud microphysics in convection-permitting simulations over the United States, J. Adv. Model. Earth Sy., 10, 1470–1494, https://doi.org/10.1029/2018MS001305, 2018. a
Geiss, A. and Hardin, J. C.: avgeiss/radar_inpainting: AMT Supplementary Code, Zenodo [code], https://doi.org/10.5281/zenodo.5643624, 2021a. a
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D.,
Ozair, S., Courville, A., and Bengio, Y.: Generative Adversarial Networks,
arXiv, arXiv:1406.2661, 10 June 2014. a, b, c
Guillemot, C. and Le Meur, O.: Image Inpainting : Overview and Recent
Advances, IEEE Signal Proc. Mag., 31, 127–144,
https://doi.org/10.1109/MSP.2013.2273004, 2014. a
Hardin, J., Hunzinger, A., Schuman, E., Matthews, A., Bharadwaj, N., Varble, A., Johnson, K., and Giangrande, S.: Ka ARM Zenith Radar (KAZRCFRGEQC), Atmospheric Radiation Measurement (ARM) User Facility, ARM [dataset], https://doi.org/10.5439/1615726, 2019a. a, b, c
Hardin, J., Hunzinger, A., Schuman, E., Matthews, A., Bharadwaj, N., Varble, A., Johnson, K., and Giangrande, S: C-Band Scanning ARM Precipitation Radar (CSAPR2CFRPPIQC), Atmospheric Radiation Measurement (ARM) User Facility, ARM [dataset], https://doi.org/10.5439/1615604, 2019b. a
Hardin, J., Hunzinger, A., Schuman, E., Matthews, A., Bharadwaj, N., Varble,
A., Johnson, K., and Giangrande, S.: CACTI Radar b1 Processing: Corrections, Calibrations, and Processing Report, U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research, Technical Report, DOE/SC-ARM-TR-244, 1–55, https://arm.gov/publications/brochures/doe-sc-arm-tr-244.pdf, last access: 19 May 2020. a, b
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q.: Densely Connected Convolutional Networks, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017, IEEE CVPR, 2261–2269, https://doi.org/10.1109/CVPR.2017.243, 2017. a, b, c
Hubbert, J. C., Dixon, M., Ellis, S. M., and Meymaris, G.: Weather Radar Ground Clutter. Part I: Identification, Modeling, and Simulation, J. Atmos. Ocean. Techn., 26, 1165–1180, https://doi.org/10.1175/2009JTECHA1159.1, 2009a. a
Hubbert, J. C., Dixon, M., and Ellis, S. M.: Weather Radar Ground Clutter. Part II: Real-Time Identification and Filtering, J. Atmos. Ocean. Techn., 26, 1181–1197, https://doi.org/10.1175/2009JTECHA1160.1, 2009b. a
Isola, P., Zhu, J., Zhou, T., and Efros, A. A.: Image-to-Image
Translation with Conditional Adversarial Networks, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017, IEEE CVPR, 5967–5976, https://doi.org/10.1109/CVPR.2017.632, 2017. a, b, c, d
Isom, B., Palmer, R., Secrest, G., Rhoton, R., Saxion, D., Allmon, T., Reed,
J., Crum, T., and Vogt, R.: Detailed observations of wind turbine clutter
with scanning weather radars, J. Atmos. Ocean. Techn., 26, 894–910, https://doi.org/10.1175/2008JTECHA1136.1, 2009. a
Jain, V. and Seung, H.: Natural Image Denoising with Convolutional Networks,
in: Advances in Neural Information Processing Systems 21–Proceedings of the 2008 Conference, NIPS'08, Curran Associates Inc., Red Hook, NY, USA, 769–776, https://dl.acm.org/doi/10.5555/2981780.2981876 (last access: 22 March 2020), 2008. a
Jam, J., Kendrick, C., Walker, K., Drouard, V., Hsu, J. G.-S., and Yap, M. H.: A comprehensive review of past and present image inpainting methods, Computer Vision and Image Understanding, 203, 103147, https://doi.org/10.1016/j.cviu.2020.103147, 2021. a, b
Johnson, K., Fairless, T., and Giangrande, S.: Ka-Band ARM Zenith Radar
Corrections (KAZRCOR, KAZRCFRCOR) Value-Added Products, Technical Report, U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research, 18 pp., available at:
https://www.arm.gov/publications/tech_reports/doe-sc-arm-tr-203.pdf (last access: 22 March 2021), 2020. a
Lang, T. J., Nesbitt, S. W., and Carey, L. D.: On the Correction of Partial
Beam Blockage in Polarimetric Radar Data, J. Atmos. Ocean. Techn., 26, 943–957, https://doi.org/10.1175/2008JTECHA1133.1, 2009. a
Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A.,
Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., and Shi, W.: Photo-Realistic Single Image Super-Resolution Using a Generative
Adversarial Network, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition, IEEE CVPR, Honolulu, HI, USA, 21–26 July 2017, 105–114, https://doi.org/10.1109/CVPR.2017.19, 2017. a
Liu, S., DiMego, G., Guan, S., Kumar, V. K., Keyser, D., Xu, Q., Nai, K.,
Zhang, P., Liu, L., Zhang, J., Howard, K., and Ator, J.: WSR-88D Radar Data
Processing at NCEP, Weather Forecast., 31, 2047–2055,
https://doi.org/10.1175/WAF-D-16-0003.1, 2016. a
Manabe, T. and Ihara, T.: A feasibility study of rain radar for the tropical rainfall measuring mission, 5. Effects of surface clutter on rain
measurements from satellite, J. Radio Res. Lab., 35, 163–181, http://www.nict.go.jp/publication/journal/35/145/Journal_Vol35_No145_pp163-181.pdf (last access: 22 March 2021), 1988. a
Moszkowicz, S., Ciach, G. J., and Krajewski, W. F.: Statistical Detection of
Anomalous Propagation in Radar Reflectivity Patterns, J. Atmos. Ocean. Techn., 11, 1026–1034,
https://doi.org/10.1175/1520-0426(1994)011<1026:SDOAPI>2.0.CO;2, 1994. a
Odena, A., Dumoulin, V., and Olah, C.: Deconvolution and Checkerboard
Artifacts, Distill, https://doi.org/10.23915/distill.00003, 2016. a
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A. A.: Context Encoders: Feature Learning by Inpainting, in: 2016 IEEE Conference on
Computer Vision and Pattern Recognition, IEEE CVPR, Las Vegas, NV, USA, 27–30 June 2016, 2536–2544, https://doi.org/10.1109/CVPR.2016.278, 2016. a
Prudden, R., Adams, S., Kangin, D., Robinson, N., Ravuri, S., Mohamed, S., and Arribas, A.: A review of radar-based nowcasting of precipitation and
applicable machine learning techniques, arXiv [preprint], arXiv:2005.04988, 11 May 2020. a
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for
Biomedical Image Segmentation, in: Medical Image Computing and
Computer-Assisted Intervention, MICCAI, 9351, 234–241,
https://doi.org/10.1007/978-3-319-24574-4_28, 2015. a, b
Shih, T. K., Liang-Chen Lu, Ying-Hong Wang, and Rong-Chi Chang:
Multi-resolution image inpainting, in: 2003 International Conference on
Multimedia and Expo, ICME'03, Proceedings, Baltimore, MD, USA, 6–9 July 2003, 485, https://doi.org/10.1109/ICME.2003.1220960, 2003. a
Tagawa, T. and Okamoto, K.: Calculations of surface clutter interference
with precipitation measurement from space by 35.5 GHz radar for Global
Precipitation Measurement Mission, in: 2003 IEEE International
Geoscience and Remote Sensing Symposium, IGARSS, Proceedings, Toulouse, France, Int. Geosci. Remote. Se., 21–25 July 2003, 5, 3172–3174, https://doi.org/10.1109/IGARSS.2003.1294719, 2003. a, b
Telea, A.: An Image Inpainting Technique Based on the Fast Marching Method,
Journal of Graphics Tools, 9, 23–24, https://doi.org/10.1080/10867651.2004.10487596, 2004. a
Varble, A., Nesbitt, S., Salio, P., Zipser, E., van den Heever, S., MdFarquhar, G., Kollias, P., Kreidenweis, S., DeMott, P., Jensen, M., Houze, Jr, R., Rasmussen, K., Leung, R., Romps, D., Gochis, D., Avila, E., Williams, C. R., and Borque, P.: Cloud, Aerosol, and Complex Terrain Interactions (CACTI), Science Plan, DOE Technical Report, DOE/SC-ARM-17-004, https://www.arm.gov/publications/programdocs/doe-sc-arm-17-004.pdf (last access: 15 May 2020), 2018. a
Veillette, M. S., Hassey, E. P., Mattioli, C. J., Iskenderian, H., and Lamey,
P. M.: Creating Synthetic Radar Imagery Using Convolutional Neural Networks, J. Atmos. Ocean. Techn., 35, 2323–2338, https://doi.org/10.1175/JTECH-D-18-0010.1, 2018. a, b
Westrick, K. J., Mass, C. F., and Colle, B. A.: The Limitations of the WSR-88D Radar Network for Quantitative Precipitation Measurement over the Coastal Western United States, B. Am. Meteorol. Soc., 80, 2289–2298, https://doi.org/10.1175/1520-0477(1999)080<2289:TLOTWR>2.0.CO;2, 1999. a
Widener, K., Bharadwaj, N., and Johnson, K.: Ka-Band ARM Zenith Radar (KAZR)
Instrument Handbook, DOE Office of Science Atmospheric Radiation Measurement (ARM) Program, United States, Technical Report, DOE/SC-ARM/TR-106, https://doi.org/10.2172/1035855, 2012. a, b, c
Yang, C., Lu, X., Lin, Z., Shechtman, E., Wang, O., and Li, H.:
High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis,
in: 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017, IEEE CVPR, 4076–4084, https://doi.org/10.1109/CVPR.2017.434, 2017. a
Young, C. B., Nelson, B. R., Bradley, A. A., Smith, J. A., Peters-Lidard,
C. D., Kruger, A., and Baeck, M. L.: An evaluation of NEXRAD precipitation
estimates in complex terrain, J. Geophys. Res.-Atmos., 104, 19691–19703, https://doi.org/10.1029/1999JD900123, 1999. a, b
Zhang, J., Howard, K., Langston, C., Vasiloff, S., Kaney, B., Arthur, A.,
Cooten, S. V., Kelleher, K., Kitzmiller, D., Ding, F., Seo, D.-J., Wells, E., and Dempsey, C.: National Mosaic and Multi-Sensor QPE (NMQ) System:
Description, Results, and Future Plans, B. Am. Meteorol. Soc., 92, 1321–1338, https://doi.org/10.1175/2011BAMS-D-11-00047.1, 2011.
a
Zhang, P., Zrnic, D., and Ryzhkov, A.: Partial Beam Blockage Correction Using
Polarimetric Radar Measurements, J. Atmos. Ocean. Techn., 30, 861–872, https://doi.org/10.1175/JTECH-D-12-00075.1, 2013. a
Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., and Liang, J.: UNet++: A Nested
U-Net Architecture for Medical Image Segmentation, in: Deep Learning in
Medical Image Analysis and Multimodal Learning for Clinical Decision Support, DLMIA, 11045, 3–1, https://doi.org/10.1007/978-3-030-00889-5_1, 2018. a, b
Short summary
Radars can suffer from missing or poor-quality data regions for several reasons: beam blockage, instrument failure, and near-ground blind zones, etc. Here, we demonstrate how deep convolutional neural networks can be used for filling in radar-missing data regions and that they can significantly outperform conventional approaches in terms of realism and accuracy.
Radars can suffer from missing or poor-quality data regions for several reasons: beam blockage,...
