Improvements to short-term weather prediction with recurrent-convolutional networks

被引:2
|
作者
Leinonen, Jussi [1 ]
机构
[1] Fed Off Meteorol & Climatol MeteoSwiss, Locarno, Switzerland
关键词
weather forecasting; neural networks; gated recurrent units; optimizers; model ensembling;
D O I
10.1109/BigData52589.2021.9671869
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The Weather4cast 2021 competition gave the participants a task of predicting the time evolution of two-dimensional fields of satellite-based meteorological data. This paper describes the author's efforts, after initial success in the first stage of the competition, to improve the model further in the second stage. The improvements consisted of a shallower model variant that is competitive against the deeper version, adoption of the AdaBelief optimizer, improved handling of one of the predicted variables where the training set was found not to represent the validation set well, and ensembling multiple models to improve the results further. The largest quantitative improvements to the competition metrics can be attributed to the increased amount of training data available in the second stage of the competition, followed by the effects of model ensembling. Qualitative results show that the model can predict the time evolution of the fields, including the motion of the fields over time, starting with sharp predictions for the immediate future and blurring of the outputs in later frames to account for the increased uncertainty.
引用
收藏
页码:5764 / 5769
页数:6
相关论文
共 50 条
  • [1] Spatio-Temporal Recurrent Convolutional Networks for Citywide Short-term Crowd Flows Prediction
    Jin, Wenwei
    Lin, Youfang
    Wu, Zhihao
    Wan, Huaiyu
    PROCEEDINGS OF THE 2018 2ND INTERNATIONAL CONFERENCE ON COMPUTE AND DATA ANALYSIS (ICCDA 2018), 2015, : 28 - 35
  • [2] ARCH: Adaptive recurrent-convolutional hybrid networks for long-term action recognition
    Xin, Miao
    Zhang, Hong
    Wang, Helong
    Sun, Mingui
    Yuan, Ding
    NEUROCOMPUTING, 2016, 178 : 87 - 102
  • [3] Short-term Traffic Flow Prediction Based on Temporal Convolutional Networks
    Yuan H.
    Chen Z.
    Huanan Ligong Daxue Xuebao/Journal of South China University of Technology (Natural Science), 2020, 48 (11): : 107 - 113and122
  • [4] PCNN: Deep Convolutional Networks for Short-Term Traffic Congestion Prediction
    Chen, Meng
    Yu, Xiaohui
    Liu, Yang
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2018, 19 (11) : 3550 - 3559
  • [5] LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks
    Huang, Rongzhou
    Huang, Chuyin
    Liu, Yubao
    Dai, Genan
    Kong, Weiyang
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2355 - 2361
  • [6] A short-term voltage stability online prediction method based on graph convolutional networks and long short-term memory networks
    Wang, Guoteng
    Zhang, Zheren
    Bian, Zhipeng
    Xu, Zheng
    INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2021, 127
  • [7] Short-term weather forecasting with neural networks
    Jaruszewicz, M
    Mandziuk, J
    NEURAL NETWORKS AND SOFT COMPUTING, 2003, : 843 - 848
  • [8] Representation learning and Graph Convolutional Networks for short-term vehicle trajectory prediction
    Xu, Xinpeng
    Yang, Chen
    Wu, Weiguo
    PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2024, 637
  • [9] Temporal Performance Prediction for Deep Convolutional Long Short-Term Memory Networks
    Fieback, Laura
    Dash, Bidya
    Spiegelberg, Jakob
    Gottschalk, Hanno
    ADVANCED ANALYTICS AND LEARNING ON TEMPORAL DATA, AALTD 2023, 2023, 14343 : 145 - 158
  • [10] Short-term Vehicle Speed Prediction Based on Convolutional Bidirectional LSTM Networks
    Han, Shaojian
    Zhang, Fengqi
    Xi, Junqiang
    Ren, Yanfei
    Xu, Shaohang
    2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2019, : 4055 - 4060