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

TL;DR

This paper introduces FORECAST-CLSTM, a hierarchical convolutional LSTM model with a new loss function for real-time cloudage nowcasting, improving accuracy and uncertainty retention in satellite image predictions.

Contribution

The paper presents a novel hierarchical ConvLSTM architecture with a specialized loss function for enhanced cloudage prediction in weather forecasting.

Findings

Outperforms state-of-the-art ConvLSTM in cloudage prediction accuracy.

The new Forecaster Loss Function better preserves atmospheric uncertainty.

Large-scale dataset SCMD supports model training and evaluation.

Abstract

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.