TempNet -- Temporal Super Resolution of Radar Rainfall Products with Residual CNNs

TL;DR

This paper introduces TempNet, a deep learning model using CNNs to enhance the temporal resolution of radar rainfall data, aiding environmental modeling and flood forecasting.

Contribution

It presents a novel CNN-based architecture for super-resolving the temporal resolution of rainfall products, outperforming optical flow and baseline CNN methods.

Findings

TempNet improves temporal resolution of rainfall data.

The model outperforms optical flow-based interpolation.

Enhanced rainfall maps support hydrological and flood forecasting.

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) 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. 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.