{"id":15698206,"url":"https://github.com/weiji14/nz_space_challenge","last_synced_at":"2025-05-09T01:11:10.006Z","repository":{"id":96183610,"uuid":"125764923","full_name":"weiji14/nz_space_challenge","owner":"weiji14","description":"A prototype end-to-end deep learning solution to identify and traverse crevasses in Antarctica for safer navigation. Uses supervised classification and reinforcement learning.","archived":false,"fork":false,"pushed_at":"2018-05-18T00:45:10.000Z","size":136738,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-31T20:06:50.215Z","etag":null,"topics":["a3c","antarctica","binder","crevasse","jupyter-notebook","quilt","reinforcement-learning","remote-sensing","supervised-machine-learning","tensorflowjs","u-net"],"latest_commit_sha":null,"homepage":"https://weiji14.github.io/nz_space_challenge/index.html","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"lgpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/weiji14.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}},"created_at":"2018-03-18T20:30:48.000Z","updated_at":"2024-03-22T11:54:21.000Z","dependencies_parsed_at":"2023-09-24T16:57:04.216Z","dependency_job_id":null,"html_url":"https://github.com/weiji14/nz_space_challenge","commit_stats":{"total_commits":43,"total_committers":1,"mean_commits":43.0,"dds":0.0,"last_synced_commit":"d6f274fbbfaf5449b6751d60b6bdca484b40e59d"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weiji14%2Fnz_space_challenge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weiji14%2Fnz_space_challenge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weiji14%2Fnz_space_challenge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weiji14%2Fnz_space_challenge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/weiji14","download_url":"https://codeload.github.com/weiji14/nz_space_challenge/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253171265,"owners_count":21865295,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["a3c","antarctica","binder","crevasse","jupyter-notebook","quilt","reinforcement-learning","remote-sensing","supervised-machine-learning","tensorflowjs","u-net"],"created_at":"2024-10-03T19:23:52.570Z","updated_at":"2025-05-09T01:11:09.977Z","avatar_url":"https://github.com/weiji14.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [New Zealand Space Challenge 2018](https://www.nzspacechallenge.com/)\nDetecting crevasses in Antarctica for safer, more efficient navigation as an analogue for future space missions.\n\nExperimental (alpha) leaflet map demo using tensorflowjs [here](https://weiji14.github.io/nz_space_challenge/).\n\nYoutube video giving a quick overview explanation [here](https://www.youtube.com/watch?v=Vy-f852grFg).\n\n# CrevasseNet model architecture\n\nConsists of a [classifier module](./crevasse_finder.ipynb) seamlessly joined to a [navigator module](./route_finder.ipynb), trained using supervised learning and reinforcement learning respectively.\n\n![model_architecture](https://user-images.githubusercontent.com/23487320/39678382-dd2066bc-51df-11e8-99e0-7d88299a3146.png)\n\nNote that the classifier component is actually much deeper, but has been abbreviated in the above diagram for simplicity.\n\n## Sample predictions\n\n### [Crevasse Classifier](./crevasse_finder.ipynb)\n\nInput image (satellite/aerial)--\u003e Intermediate Output (crevasse map)\n\n![crevasse_prediction](https://user-images.githubusercontent.com/23487320/39678490-e5883350-51e1-11e8-8483-60fbb84865d9.png)\n\n### [Route Navigator](./route_finder.ipynb)\n\nIntermediate output (crevasse map) --\u003e Action quality outputs\n\n![route_navigator.gif](https://user-images.githubusercontent.com/23487320/39678342-fffe1798-51de-11e8-9061-0e7cc94f32e3.gif)\n\n# Getting started\n\n## Quickstart\n\nLaunch Binder, data will be loaded via [Quilt](https://github.com/quiltdata/quilt). Cheers to [data2binder](https://github.com/quiltdata/data2binder)!\n\n[![Binder](https://mybinder.org/badge.svg)](https://mybinder.org/v2/gh/weiji14/nz_space_challenge/master)\n\n## Installation\n\nStart by cloning this [repo-url](/../../)\n\n    git clone \u003crepo-url\u003e\n    cd nz_space_challenge\n    conda env create -f environment.yml\n\n## Running the jupyter notebook\n\n    source activate nz_space_challenge\n    python -m ipykernel install --user  #to install conda env properly\n    jupyter kernelspec list --json      #see if kernel is installed\n    jupyter notebook\n\n\n# [Data used](/data)\n\n| Name                                                                 | Data Source                                      |\n| -------------------------------------------------------------------- | ------------------------------------------------:|\n|MOA-derived Structural Feature Map of the Ronne Ice Shelf, Version 1  | [NSIDC-0497](https://nsidc.org/data/nsidc-0497)  |\n|MODIS Mosaic of Antarctica 2003-2004 (MOA2004) Image Map, Version 1   | [NSIDC-0280](https://nsidc.org/data/nsidc-0280)  |\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweiji14%2Fnz_space_challenge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fweiji14%2Fnz_space_challenge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweiji14%2Fnz_space_challenge/lists"}