2000 character limit reached
Recurrent Graph Convolutional Networks for Spatiotemporal Prediction of Snow Accumulation Using Airborne Radar (2302.00817v2)
Published 2 Feb 2023 in cs.LG and eess.SP
Abstract: The accurate prediction and estimation of annual snow accumulation has grown in importance as we deal with the effects of climate change and the increase of global atmospheric temperatures. Airborne radar sensors, such as the Snow Radar, are able to measure accumulation rate patterns at a large-scale and monitor the effects of ongoing climate change on Greenland's precipitation and run-off. The Snow Radar's use of an ultra-wide bandwidth enables a fine vertical resolution that helps in capturing internal ice layers. Given the amount of snow accumulation in previous years using the radar data, in this paper, we propose a machine learning model based on recurrent graph convolutional networks to predict the snow accumulation in recent consecutive years at a certain location. We found that the model performs better and with more consistency than equivalent nongeometric and nontemporal models.
- Ultra-wideband radars for remote sensing of snow and ice. In IEEE MTT-S International Microwave and RF Conference, pages 1–4, 2013.
- Deep Multi-Scale Learning for Automatic Tracking of Internal Layers of Ice in Radar Data. Journal of Glaciology, 67(261):39–48, 2021.
- Deep Ice layer Tracking and Thickness Estimation using Fully Convolutional Networks. In 2020 IEEE International Conference on Big Data (Big Data), pages 3943–3952. IEEE, 2020.
- Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet. Remote Sensing, 13(14), 2021.
- Refining Ice Layer Tracking through Wavelet combined Neural Networks. 2021.
- Airborne snow radar data simulation with deep learning and physics-driven methods. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14:12035–12047, 2021.
- Smart Tracking of Internal Layers of Ice in Radar Data via Multi-Scale Learning. In 2019 IEEE International Conference on Big Data (Big Data), pages 5462–5468. IEEE, 2019.
- Multi-Scale and Temporal Transfer Learning for Automatic Tracking of Internal Ice Layers. In IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, pages 6934–6937, 2020.
- Learning snow layer thickness through physics defined labels. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, pages 1233–1236, 2022.
- Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR 2017, 2017.
- Diffusion convolutional recurrent neural network: Data-driven traffic forecasting, 2017.
- Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, 2018.
- Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 922–929, Jul. 2019.
- Multistream graph attention networks for wind speed forecasting. CoRR, abs/2108.07063, 2021.
- Predicting power outages using graph neural networks. pages 743–747, 11 2018.
- Structured sequence modeling with graph convolutional recurrent networks. In Proceedings of ICLR 2017, 2017.
- Annual Greenland accumulation rates (2009–2012) from airborne snow radar. The Cryosphere, 10(4):1739–1752, 2016.
- Automatic ice surface and bottom boundaries estimation in radar imagery based on level-set approach. IEEE Transactions on Geoscience and Remote Sensing, 55(9):5115–5122, 2017.
- Automatic ice thickness estimation in radar imagery based on charged particles concept. In 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pages 3743–3746, 2017.
- Ai radar sensor: Creating radar depth sounder images based on generative adversarial network. Sensors, 19(24):5479, Dec 2019.
- Contour Detection and Hierarchical Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(5):898–916, 2011.
- Scene graph generation by iterative message passing, 2017.
- Graph r-cnn for scene graph generation, 2018.
- Dynamic graph cnn for learning on point clouds, 2018.
- Large-scale point cloud semantic segmentation with superpoint graphs, 2017.
- A low rank weighted graph convolutional approach to weather prediction. In 2018 IEEE International Conference on Data Mining (ICDM), pages 627–636, 2018.
- Long short-term memory. Neural computation, 9:1735–80, 12 1997.
- Searching for mobilenetv3. CoRR, abs/1905.02244, 2019.
- Searching for activation functions, 2017.
- Improving neural networks by preventing co-adaptation of feature detectors, 2012.
- Adam: A method for stochastic optimization, 2014.