FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting

With the highly demand of large-scale and real-time weather service for public, a refinement of short-time cloudage prediction has become an essential part of the weather forecast productions. To provide a weather-service-compliant cloudage nowcasting, in this paper, we propose a novel hierarchical Convolutional Long-Short-Term Memory network based deep learning model, which we term as FORECAST-CLSTM, with a new Forecaster loss function to predict the future satellite cloud images. The model is designed to fuse multi-scale features in the hierarchical network structure to predict the pixel value and the morphological movement of the cloudage simultaneously. We also collect about 40K infrared satellite nephograms and create a large-scale Satellite Cloudage Map Dataset(SCMD). The proposed FORECAST-CLSTM model is shown to achieve better prediction performance compared with the state-of-the-art ConvLSTM model and the proposed Forecaster Loss Function is also demonstrated to retain the uncertainty of the real atmosphere condition better than conventional loss function.

[1]  Dit-Yan Yeung,et al.  Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model , 2017, NIPS.

[2]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[3]  John A. McGinley,et al.  The Local Analysis and Prediction System ( LAPS ) : Analyses of Clouds, Precipitation, and Temperature , 1996 .

[4]  Hidetomo Sakaino,et al.  Spatio-Temporal Image Pattern Prediction Method Based on a Physical Model With Time-Varying Optical Flow , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[5]  S. Uppala,et al.  New prediction method of cloud attenuation , 1991 .

[6]  Jeff Zhang,et al.  Hierarchical Model for Long-term Video Prediction , 2017, ArXiv.

[7]  Ruth J. Muschel,et al.  Extracting 3D Vascular Structures from Microscopy Images using Convolutional Recurrent Networks , 2017, ArXiv.

[8]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[9]  Wei Xu,et al.  Bidirectional LSTM-CRF Models for Sequence Tagging , 2015, ArXiv.

[10]  Shenghua Gao,et al.  Remembering history with convolutional LSTM for anomaly detection , 2017, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[11]  Heinrich Morf,et al.  Sunshine and cloud cover prediction based on Markov processes , 2014 .

[12]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[13]  Sa-Kwang Song,et al.  DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data , 2017, ArXiv.