A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction

Abstract

The prediction of wind in terms of both wind speed and direction, which has a crucial impact on many real-world applications like aviation and wind power generation, is extremely challenging due to the high stochasticity and complicated correlation in the weather data. Existing methods typically focus on a sub-set of influential factors and thus lack a systematic treatment of the problem. In addition, fine-grained forecasting is essential for efficient industry operations, but has been less attended in the literature. In this work, we propose a novel data-driven model, Multi-Horizon SpatioTemporal Network (MHSTN), generally for accurate and efficient fine-grained wind prediction. MHSTN integrates multiple deep neural networks targeting different factors in a sequence-to-sequence (Seq2Seq) backbone to effectively extract features from various data sources and produce multi-horizon predictions for all sites within a given region. MHSTN is composed of four major modules. First, a temporal module fuses coarse-grained forecasts derived by Numerical Weather Prediction (NWP) and historical on-site observation data at stations so as to leverage both global and local atmospheric information. Second, a spatial module exploits spatial correlation by modeling the joint representation of all stations. Third, an ensemble module weighs the above two modules for final predictions. Furthermore, a covariate selection module automatically choose influential meteorological variables as initial input. MHSTN is already integrated into the scheduling platform of one of the busiest international airports of China. The evaluation results demonstrate that our model outperforms competitors by a significant margin.

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Sequence to Sequence Learning with Neural Networks
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Generative Adversarial Networks: An Overview
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Deep learning for time series classification: a review
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• An Introduction to Variational Autoencoders
• Striving for Simplicity: The All Convolutional Net
• InceptionTime: Finding AlexNet for Time Series Classification
• A Multi-Horizon Quantile Recurrent Forecaster
• Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
• Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification
• A Benchmark Study on Time Series Clustering
• T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling
• Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders
• Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
• Generative adversarial networks in time series: A survey and taxonomy
• COT-GAN: Generating Sequential Data via Causal Optimal Transport
• Adversarial Variational Embedding for Robust Semi-supervised Learning
• Time-series Generation by Contrastive Imitation
• Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network for End-to-end Speech Enhancement