There are 4 repositories under downscaling topic.
Statistical climate downscaling in Python
Downscaling & bias correction of CMIP6 tasmin, tasmax, and pr for the R/CIL GDPCIR project
Deep Learning for empirical DownScaling. Python package with state-of-the-art and novel deep learning algorithms for empirical/statistical downscaling of gridded data
A project on how to incorporate physics constraints into deep learning architectures for downscaling or other super--resolution tasks.
Python Package for Empirical Statistical Downscaling. pyESD is under active development and all colaborators are welcomed. The purpose of the package is to downscale any climate variables e.g. precipitation and temperature using predictors from reanalysis datasets (eg. ERA5) to point scale. pyESD adopts many ML and AL as the transfer function.
Diffusion for climate downscaling
Scale down / "pause" Kubernetes workload (Deployments, StatefulSets, and/or HorizontalPodAutoscalers and CronJobs too !) during non-work hours.
TopoPyScale: a Python library to perform simplistic climate downscaling at the hillslope scale
A horizontal autoscaler for Kubernetes workloads
Probabilistic Downscaling of Climate Variables Using Denoising Diffusion Probabilistic Models
Python tool for downsizing Microsoft PowerPoint presentations (pptx) files.
Statistical dowscaling of climate data at daily scale using quantile mapping (QPM) technique.
Given a global mean temperature pathway, generate random global climate fields consistent with it and with spatial and temporal correlation derived from an ESM
A project on how to incorporate physics constraints into deep learning architectures for downscaling or other super--resolution tasks.
Generate stocastic Gaussian realization constrained to a coarse scale image.
Awesome-AI4Earth: a curated list of machine learning in Earth System, especially for weather and climate.
Code repository associated with "Statistical treatment of convolutional neural network super-resolution of inland surface wind for subgrid-scale variability quantification" (Getter, Bessac, Rudi, Feng).
Python package to reconstruct and extend observational climate series through empricial downscaling of large-scale models
Cost saving K8s controller to scale down and up of resources during non-business hours
A collection of notebooks and tools for analyzing the LOCA dataset
Weather Generators with Bayesian Networks
This repository contains three packages that assemble codes and scripts to downscale coarse-resolution reanalysis fields to finer resolutions, accounting for subgrid-scale variability and/or topographic effects.
Downscaling spatial resolution of geo-spatial data (TROPOMI SIF) using auxiliary data (MODIS) by application of U-NET and Local Binary Patterns
Multicore! Faster!
Ease the use of the climate4r package to downscale TraCE21ka and CMIP5 climate data in combination with UERRA reanalysis data.
Using Stereo SGM to calculate the disparity map of two images :Stereo Processing by Semiglobal Matching and Mutual Information .
Created algorithm in C to detect and highlight best image match with template (2 px accuracy) using pixelwise brute force. The algorithm is optimized by 16x to take less than 5 seconds per image-template pair on i7 processor by down-sampling.
A high resolution tool for snow cover reconstruction studies
Scale down Kubernetes deployments after work hours