Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations (2023-02-21T00:00:00.000000Z)

TL;DR

This paper presents a new benchmark dataset named Weather2K, which aims to make up for the deficiencies of existing weather forecasting datasets in terms of real-time, reliability, and diversity, as well as the key bottleneck of data quality, and proposes Meteorological Factors based Multi-Graph Convolution Network (MFMGCN), which can effectively construct the intrinsic correlation among geographic locations based on meteorological factors.

Abstract

Weather forecasting is one of the cornerstones of meteorological work. In this paper, we present a new benchmark dataset named Weather2K, which aims to make up for the deficiencies of existing weather forecasting datasets in terms of real-time, reliability, and diversity, as well as the key bottleneck of data quality. To be specific, our Weather2K is featured from the following aspects: 1) Reliable and real-time data. The data is hourly collected from 2,130 ground weather stations covering an area of 6 million square kilometers. 2) Multivariate meteorological variables. 20 meteorological factors and 3 constants for position information are provided with a length of 40,896 time steps. 3) Applicable to diverse tasks. We conduct a set of baseline tests on time series forecasting and spatio-temporal forecasting. To the best of our knowledge, our Weather2K is the first attempt to tackle weather forecasting task by taking full advantage of the strengths of observation data from ground weather stations. Based on Weather2K, we further propose Meteorological Factors based Multi-Graph Convolution Network (MFMGCN), which can effectively construct the intrinsic correlation among geographic locations based on meteorological factors. Sufficient experiments show that MFMGCN improves both the forecasting performance and temporal robustness. We hope our Weather2K can significantly motivate researchers to develop efficient and accurate algorithms to advance the task of weather forecasting. The dataset can be available at https://github.com/bycnfz/weather2k/.

References50 items

FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models

Conditional Local Convolution for Spatio-Temporal Meteorological Forecasting

Transfer Graph Neural Networks for Pandemic Forecasting

CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Crowd Flow Forecasting with Multi-Graph Neural Networks

A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting

The ERA5 global reanalysis

Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

DeepSphere: a graph-based spherical CNN

MetNet: A Neural Weather Model for Precipitation Forecasting

PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting

WeatherBench: A Benchmark Data Set for Data‐Driven Weather Forecasting

The first high-resolution meteorological forcing dataset for land process studies over China

Reformer: The Efficient Transformer

PyTorch: An Imperative Style, High-Performance Deep Learning Library

GMAN: A Graph Multi-Attention Network for Traffic Prediction

Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting

Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Attention is All you Need

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

MSWEP: 3-hourly 0.25° global gridded precipitation (1979–2015) by merging gauge, satellite, and reanalysis data

The Canadian Land Data Assimilation System (CaLDAS): Description and Synthetic Evaluation Study

Adam: A Method for Stochastic Optimization

Massively parallel solvers for elliptic partial differential equations in numerical weather and climate prediction

Ridge Regression

The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains

Wavelets on Graphs via Spectral Graph Theory

THE GLOBAL LAND DATA ASSIMILATION SYSTEM

The status of the tropical rainfall measuring mission (TRMM) after two years in orbit

Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting

Adversarial Sparse Transformer for Time Series Forecasting

Graphs

2017) propose a deep learning framework for traffic prediction, integrating graph convolution and gated

A vision for the development of benchmarks to bridge geo-science and data science

Ex-tremeweather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events

Nasa global precipitation measurement (gpm) integrated multi-satellite retrievals for gpm (imerg)

Kernel Ridge Regression

ben-Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for eﬁts using numerical weather prediction models

Some current problems in numerical weather prediction

Predicting path failure

Electricity demand forecasting over italy: Potential ben-Weather2K

CS 731 Spring 2011 Advanced Artificial Intelligence Linear Regression