GlobeNet: Convolutional Neural Networks for Typhoon Eye Tracking from Remote Sensing Imagery
arXiv:1708.03417
Abstract
Advances in remote sensing technologies have made it possible to use high-resolution visual data for weather observation and forecasting tasks. We propose the use of multi-layer neural networks for understanding complex atmospheric dynamics based on multichannel satellite images. The capability of our model was evaluated by using a linear regression task for single typhoon coordinates prediction. A specific combination of models and different activation policies enabled us to obtain an interesting prediction result in the northeastern hemisphere (ENH).
Under review as a workshop paper at CI 2017
References in corpus (4)
- Adam: A Method for Stochastic Optimization
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
- ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
Cited by in corpus (4)
- PSIque: Next Sequence Prediction of Satellite Images using a Convolutional Sequence-to-Sequence Network
- Typhoon track prediction using satellite images in a Generative Adversarial Network
- Prediction of typhoon tracks using a generative adversarial network with observational and meteorological data
- HPC AI500: A Benchmark Suite for HPC AI Systems