{"id":21268794,"url":"https://github.com/carlos-gg/dl4ds","last_synced_at":"2026-03-06T11:03:13.952Z","repository":{"id":53863150,"uuid":"347954905","full_name":"carlos-gg/dl4ds","owner":"carlos-gg","description":"Deep Learning for empirical DownScaling. Python package with state-of-the-art and novel deep learning algorithms for empirical/statistical downscaling of gridded data","archived":false,"fork":false,"pushed_at":"2024-07-30T09:48:34.000Z","size":4502,"stargazers_count":96,"open_issues_count":11,"forks_count":29,"subscribers_count":2,"default_branch":"master","last_synced_at":"2026-01-14T10:11:33.682Z","etag":null,"topics":["deep-learning","downscaling","earth-observation","earth-science","python","super-resolution","tensorflow"],"latest_commit_sha":null,"homepage":"https://carlos-gg.github.io/dl4ds/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/carlos-gg.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-03-15T12:10:47.000Z","updated_at":"2025-12-22T03:17:26.000Z","dependencies_parsed_at":"2024-11-30T05:06:15.599Z","dependency_job_id":"eab78109-e255-4aa1-9b8f-042e81c53c2b","html_url":"https://github.com/carlos-gg/dl4ds","commit_stats":{"total_commits":476,"total_committers":2,"mean_commits":238.0,"dds":"0.012605042016806678","last_synced_commit":"232ae495151a4d3607402b3e7c8afd51d6bfa3de"},"previous_names":["carlgogo/dl4ds"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/carlos-gg/dl4ds","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carlos-gg%2Fdl4ds","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carlos-gg%2Fdl4ds/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carlos-gg%2Fdl4ds/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carlos-gg%2Fdl4ds/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/carlos-gg","download_url":"https://codeload.github.com/carlos-gg/dl4ds/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/carlos-gg%2Fdl4ds/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30173359,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-06T07:56:45.623Z","status":"ssl_error","status_checked_at":"2026-03-06T07:55:55.621Z","response_time":250,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","downscaling","earth-observation","earth-science","python","super-resolution","tensorflow"],"created_at":"2024-11-21T08:06:27.261Z","updated_at":"2026-03-06T11:03:10.470Z","avatar_url":"https://github.com/carlos-gg.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Tensorflow - Version](https://img.shields.io/badge/Tensorflow%2FKeras-2.6+-blue\u0026logo=tensorflow)](https://github.com/carlgogo/dl4ds) \n[![Python - Version](https://img.shields.io/badge/PYTHON-3.6+-red?style=flat\u0026logo=python\u0026logoColor=white)](https://github.com/carlgogo/dl4ds) \n[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/carlos-gg/dl4ds/blob/master/notebooks/DL4DS_tutorial.ipynb)\n\n# Deep Learning for empirical DownScaling\n\n`DL4DS` (Deep Learning for empirical DownScaling) is a Python package that implements state-of-the-art and novel deep learning algorithms for empirical downscaling of gridded Earth science data. \n\nThe general architecture of `DL4DS` is shown on the image below. A low-resolution gridded dataset can be downscaled, with the help of (an arbitrary number of) auxiliary predictor and static variables, and a high-resolution reference dataset. The mapping between the low- and high-resolution data is learned with either a supervised or a conditional generative adversarial DL model.\n\n\u003cimg src=\"https://github.com/carlos-gg/dl4ds/raw/master/docs/img/fig_workflow.png\" alt=\"drawing\" width=\"800\"/\u003e\n\nThe training can be done from explicit pairs of high- and low-resolution samples (MOS-style, e.g., high-res observations and low-res numerical weather prediction model output) or only with a HR dataset (PerfectProg-style, e.g., high-res observations or high-res model output).\n\nA wide variety of network architectures have been implemented in `DL4DS`. The main modelling approaches can be combined into many different architectures:\n\n|Downscaling type               |Training (loss type)         |Sample type     |Backbone section              |Upsampling method   |\n|---                            |---                          |---             |---                          |---|\n|MOS (explicit pairs of HR and LR data)           |Supervised (non-adversarial) |Spatial         |Plain convolutional          |Pre-upsampling via interpolation |\n|PerfectProg (implicit pairs, only HR data)   |Conditional Adversarial    |Spatio-temporal |Residual                     |Post-upsampling via sub-pixel convolution |\n|                               |                             |                |Dense                        |Post-upsampling via resize convolution |\n|                               |                             |                |Unet (PIN, Spatial samples)  |Post-upsampling via deconvolution   |\n|                               |                             |                |Convnext (Spatial samples)   |                                      |\n\nIn `DL4DS`, we implement a channel attention mechanism to exploit inter-channel relationship of features by providing a weight for each channel in order to enhance those that contribute the most to the optimizaiton and learning process. Aditionally, a Localized Convolutional Block (LCB) is located in the output module of the networks in `DL4DS`. With the LCB we learn location-specific information via a locally connected layer with biases. \n\n`DL4DS` is built on top of Tensorflow/Keras and supports distributed GPU training (data parallelism) thanks to Horovod. \n\n# API documentation \n\nCheck out the API documentation [here](https://carlos-gg.github.io/dl4ds/).\n\n# Installation\n\n```\npip install dl4ds\n```\n\n# Example notebooks\n\nA first Colab notebook can be found in the notebooks folder. Click the badge at the top to open the notebook on Google Colab.\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcarlos-gg%2Fdl4ds","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcarlos-gg%2Fdl4ds","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcarlos-gg%2Fdl4ds/lists"}