Development of 300-m gridded digital twins of precipitation over Delhi for 1980-2020

Abstract

The impacts of climate change are felt by most critical systems, such as infrastructure, ecological systems, and power plants. However, contemporary Earth System Models (ESM) are run at spatial resolutions too coarse for assessing effects this localized. High-resolution datasets are required for the planning, adaptation and furthering of urban climate science(NEELESH, 2022). Although there has been tremendous growth in climate science and weather forecasting in general, the development of gridded datasets of the order of sub 300 m or less than 500 m gridded scale is still challenging (DAVID, 2019). Deep learning has proven to be a potent tool in deciphering nonlinear mappings. It can be used as a powerful technology to develop high-resolution products from coarse-resolution available datasets (MARKUS, 2019). Here, we use Deep learning models like SRCNN(super-resolution convolutional neural network) and GAN( Generative Adversarial Network to try to find a solution to this problem.