DeepAI AI Chat
Log In Sign Up

Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model

by   Xingjian Shi, et al.
Hong Kong Observatory
The Hong Kong University of Science and Technology

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.


page 1

page 2

page 3

page 4


DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow

Recently, the dense correlation volume method achieves state-of-the-art ...

The World as a Graph: Improving El Niño Forecasts with Graph Neural Networks

Deep learning-based models have recently outperformed state-of-the-art s...

The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction

This paper studies the problem of predicting the distribution over multi...

ProFuzzBench: A Benchmark for Stateful Protocol Fuzzing

We present a new benchmark (ProFuzzBench) for stateful fuzzing of networ...

From handcrafted to deep local invariant features

The aim of this paper is to present a comprehensive overview of the evol...

What Makes RAFT Better Than PWC-Net?

How important are training details and datasets to recent optical flow m...

Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination

Precipitation nowcasting is an important task for weather forecasting. M...