Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model
复制标题
DOI：
--
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
Xingjian Shi;Zhihan Gao;Leonard Lausen;Hao Wang;D. Yeung;W. Wong;W. Woo
中科院分区：
文献类型：
--
作者：
Xingjian Shi;Zhihan Gao;Leonard Lausen;Hao Wang;D. Yeung;W. Wong;W. Woo
以高分辨率的区域降水预报为目标，降水临近预报已成为从暴雨警报到飞行安全等各种公共服务的重要基础技术。最近，卷积LSTM（ConvLSTM）模型在降水临近预报方面的表现优于传统的基于光流的方法，这表明深度学习模型在解决这一问题方面具有巨大的潜力。然而，基于ConvLSTM的模型中的卷积递归结构是位置不变的，而自然运动和变换（例如，旋转）通常是位置可变的。此外，由于基于深度学习的降水临近预报是一个新兴领域，尚未建立明确的评估协议。为了解决这些问题，我们提出了一个新的模式和基准降水临近预报。具体来说，我们超越了ConvLSTM，提出了Trajectory GRU（TrajGRU）模型，该模型可以主动学习递归连接的位置变量结构。此外，我们还提供了一个基准，其中包括来自香港天文台的真实世界大规模数据集，新的训练损失和全面的评估协议，以促进未来的研究和衡量最先进的水平。
With the goal of making high-resolution forecasts of regional rainfall, precipitation nowcasting has become an important and fundamental technology underlying various public services ranging from rainstorm warnings to flight safety. Recently, the Convolutional LSTM (ConvLSTM) model has been shown to outperform traditional optical flow based methods for precipitation nowcasting, suggesting that deep learning models have a huge potential for solving the problem. However, the convolutional recurrence structure in ConvLSTM-based models is location-invariant while natural motion and transformation (e.g., rotation) are location-variant in general. Furthermore, since deep-learning-based precipitation nowcasting is a newly emerging area, clear evaluation protocols have not yet been established. To address these problems, we propose both a new model and a benchmark for precipitation nowcasting. Specifically, we go beyond ConvLSTM and propose the Trajectory GRU (TrajGRU) model that can actively learn the location-variant structure for recurrent connections. Besides, we provide a benchmark that includes a real-world large-scale dataset from the Hong Kong Observatory, a new training loss, and a comprehensive evaluation protocol to facilitate future research and gauge the state of the art.