Abstract
Satellites detect the distribution of meteorological data worldwide. However, due to the orbital constraints, the satellite can only reach the same area again after one orbiting cycle. The interval between two detections in the same area is long, and the variation of meteorological data between the two detections is unknown. Moreover, meteorological satellite data are only located near the orbit in one cycle, while the global distribution of meteorological data is unknown. Our method allows to train a regression model with only few meteorological satellite data by taking advantage of the recent advances in deep learning. In detail, we train a model-agnostic meta-learning (MAML) model with data from ground stations instead of meteorological satellites and get the initial network parameters. Based on the initial network parameters trained by MAML, we train the regression models again for different areas. We sample the regression curves of all areas by time and get a time series of global meteorological data distribution. Through case studies conducted together with domain experts, we validate the effectiveness of our method.
Graphic abstract










Similar content being viewed by others
References
Antoniou A, Edwards H, Storkey A (2018) How to train your MAML. arXiv e-prints, p. arXiv:1810.09502
Bai W, Sun Y, Du Q, Yang G, Yang Z, Zhang P, Bi Y, Wang X, Cheng C, Han Y (2014) An introduction to the fy3 gnos instrument and mountain-top tests. Atmos Meas Tech 7:1817–1823. https://doi.org/10.5194/amt-7-1817-2014
Cheng S, Shan G, Liu J, Gao Y, Wei P, Bai W, Zhao D (2019) Occvis: a visual analytics system for occultation data. J Vis 22:01. https://doi.org/10.1007/s12650-018-00545-2
Finn C, Abbeel P, Levine S (2017) Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. arXiv e-prints, p. arXiv:1703.03400
Hong F, Chen S, Guo H, Yuan X, Huang J, Zhang Y (2017) Visual exploration of ionosphere disturbances for earthquake research. pp. 1–8, 11. https://doi.org/10.1145/3139295.3139301
Kahng M, Andrews P, Kalro A, Chau DH (2017) Activis: Visual exploration of industry-scale deep neural network models. IEEE Trans Vis Comput Gr. https://doi.org/10.1109/TVCG.2017.2744718
Kahng M, Thorat N, Chau DH, Viegas F, Wattenberg M (2018) Gan lab: Understanding complex deep generative models using interactive visual experimentation. IEEE Trans Vis Comput Gr. https://doi.org/10.1109/TVCG.2018.2864500
Liu M, Shi J, Cao K, Zhu J, Liu S (2017) Analyzing the training processes of deep generative models. IEEE Trans Vis Comput Gr. https://doi.org/10.1109/TVCG.2017.2744938
Liu M, Shi J, Li Z, Li C, Zhu J, Liu S (2016) Towards better analysis of deep convolutional neural networks. IEEE Trans Vis Comput Gr 23:04. https://doi.org/10.1109/TVCG.2016.2598831
Nichol A, Achiam J, Schulman J (2018) On First-Order Meta-Learning Algorithms. arXiv e-prints, p. arXiv:1803.02999
Noll C (2010) The crustal dynamics data information system: a resource to support scientific analysis using space geodesy. Adv Space Res 45:1421–1440. https://doi.org/10.1016/j.asr.2010.01.018
Pezzotti N, Höllt T, Gemert J, Lelieveldt B, Eisemann E, Vilanova A (2018) Deepeyes: progressive visual analytics for designing deep neural networks. IEEE Trans Vis Comput Gr 24:01. https://doi.org/10.1109/TVCG.2017.2744358
Wang J, Gou L, Shen H-W, Yang H (2018) Dqnviz: a visual analytics approach to understand deep q-networks. IEEE Trans Vis Comput Gr. https://doi.org/10.1109/TVCG.2018.2864504
Wang J, Gou L, Yang H, Shen H-W (2018) Ganviz: a visual analytics approach to understand the adversarial game. IEEE Trans Vis Comput Gr. https://doi.org/10.1109/TVCG.2018.2816223
Wang J, Liu X, Shen H-W, Lin G (2016) Multi-resolution climate ensemble parameter analysis with nested parallel coordinates plots. IEEE Trans Vis Comput Gr. https://doi.org/10.1109/TVCG.2016.2598830
Wongsuphasawat K, Smilkov D, Wexler J, Wilson J, Mane D, Fritz D, Krishnan D, Viegas F, Wattenberg M (2017) Visualizing dataflow graphs of deep learning models in tensorflow. IEEE Trans Vis Comput Gr. https://doi.org/10.1109/TVCG.2017.2744878
Acknowledgements
This work was supported by the Strategic Priority Research Program of the Chinese Academy of Sciences, Grant No. XDA19080102.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Cheng, S., Shen, H., Shan, G. et al. Visual analysis of meteorological satellite data via model-agnostic meta-learning. J Vis 24, 301–315 (2021). https://doi.org/10.1007/s12650-020-00704-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12650-020-00704-4