Deep-learning-based precipitation observation quality control

View More View Less
  • 1 The University of British Columbia, Vancouver, Canada
  • | 2 National Center for Atmospheric Research, Boulder, Colorado
  • | 3 BC Hydro, Burnaby, Canada
  • | 4 The University of British Columbia, Vancouver, Canada
© Get Permissions
Open access

Abstract

We present a novel approach for the automated quality control (QC) of precipitation for a sparse station observation network within the complex terrain of British Columbia, Canada. Our QC approach uses Convolutional Neural Networks (CNNs) to classify bad observation values, incorporating a multi-classifier ensemble to achieve better QC performance. We train CNNs using human QC’d labels from 2016 to 2017 with gridded precipitation and elevation analyses as inputs. Based on the classification evaluation metrics, our QC approach shows reliable and robust performance across different geographical environments (e.g., coastal and inland mountains), with 0.927 Area Under Curve (AUC) and type I/type II error lower than 15%. Based on the saliency-map-based interpretation studies, we explain the success of CNN-based QC by showing that it can capture the precipitation patterns around, and upstream of the station locations. This automated QC approach is an option for eliminating bad observations for various applications, including the pre-processing of training datasets for machine learning. It can be used in conjunction with human QC to improve upon what could be accomplished with either method alone.

Denotes content that is immediately available upon publication as open access.

Corresponding author address: Yingkai Sha, Department of Earth, Ocean and Atmospheric Sciences, University of British Columbia, 2020-2207 Main Mall, Vancouver, Canada, V6T 1Z4. E-mail: yingkai@eoas.ubc.ca

Abstract

We present a novel approach for the automated quality control (QC) of precipitation for a sparse station observation network within the complex terrain of British Columbia, Canada. Our QC approach uses Convolutional Neural Networks (CNNs) to classify bad observation values, incorporating a multi-classifier ensemble to achieve better QC performance. We train CNNs using human QC’d labels from 2016 to 2017 with gridded precipitation and elevation analyses as inputs. Based on the classification evaluation metrics, our QC approach shows reliable and robust performance across different geographical environments (e.g., coastal and inland mountains), with 0.927 Area Under Curve (AUC) and type I/type II error lower than 15%. Based on the saliency-map-based interpretation studies, we explain the success of CNN-based QC by showing that it can capture the precipitation patterns around, and upstream of the station locations. This automated QC approach is an option for eliminating bad observations for various applications, including the pre-processing of training datasets for machine learning. It can be used in conjunction with human QC to improve upon what could be accomplished with either method alone.

Denotes content that is immediately available upon publication as open access.

Corresponding author address: Yingkai Sha, Department of Earth, Ocean and Atmospheric Sciences, University of British Columbia, 2020-2207 Main Mall, Vancouver, Canada, V6T 1Z4. E-mail: yingkai@eoas.ubc.ca
Save