TempNet – temporal super-resolution of radar rainfall products with residual CNNs

Abstract

The temporal and spatial resolution of rainfall data is crucial for environmental modeling studies in which its variability in space and time is considered as a primary factor. Rainfall products from different remote sensing instruments (e.g., radar, satellite) have different space-time resolutions because of the differences in their sensing capabilities and post-processing methods. In this study, we developed a deep-learning approach that augments rainfall data with increased time resolutions to complement relatively lower-resolution products. We propose a neural network architecture based on Convolutional Neural Networks (CNNs), namely TempNet, to improve the temporal resolution of radar-based rainfall products and compare the proposed model with an optical flow-based interpolation method and CNN-baseline model. While TempNet achieves a mean absolute error of 0.332 mm/h, comparison methods achieve 0.35 and 0.341, respectively. The methodology presented in this study could be used for enhancing rainfall maps with better temporal resolution and imputation of missing frames in sequences of 2D rainfall maps to support hydrological and flood forecasting studies. HIGHLIGHTS This paper improves the temporal resolution of radar rainfall products from 10 to 5 min.; A residual Convolutional Neural Network architecture, namely TempNet, is proposed for the temporal downscaling of radar rainfall.; Results show that the TempNet outperforms the optical flow-based temporal interpolation method in the study area.;

Keywords

• convolutional neural networks
• deep learning
• radar rainfall
• rainfall maps
• super-resolution
• temporal downscaling