PSIque: Next Sequence Prediction of Satellite Images using a Convolutional Sequence-to-Sequence Network
arXiv:1711.10644
Abstract
Predicting unseen weather phenomena is an important issue for disaster management. In this paper, we suggest a model for a convolutional sequence-to-sequence autoencoder for predicting undiscovered weather situations from previous satellite images. We also propose a symmetric skip connection between encoder and decoder modules to produce more comprehensive image predictions. To examine our model performance, we conducted experiments for each suggested model to predict future satellite images from historical satellite images. A specific combination of skip connection and sequence-to-sequence autoencoder was able to generate closest prediction from the ground truth image.
arXiv commentWorkshop on Deep Learning for Physical Sciences (DLPS 2017), NIPS 2017, Long Beach, CA, USA
References in corpus (5)
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Spatio-temporal video autoencoder with differentiable memory
- Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
- ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events
- GlobeNet: Convolutional Neural Networks for Typhoon Eye Tracking from Remote Sensing Imagery