{"id":29135853,"url":"https://github.com/dnerini/startleiter","last_synced_at":"2025-07-22T04:33:03.556Z","repository":{"id":37400889,"uuid":"328435503","full_name":"dnerini/startleiter","owner":"dnerini","description":"A data-driven paragliding buddy.","archived":false,"fork":false,"pushed_at":"2025-07-15T05:21:11.000Z","size":1955856,"stargazers_count":12,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-15T11:51:32.308Z","etag":null,"topics":["machine-learning","paragliding","radiosonde"],"latest_commit_sha":null,"homepage":"https://dnerini.github.io/startleiter/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dnerini.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,"zenodo":null}},"created_at":"2021-01-10T17:07:42.000Z","updated_at":"2025-05-18T11:14:33.000Z","dependencies_parsed_at":"2023-10-15T06:08:54.298Z","dependency_job_id":"873f9099-9177-4720-a2bf-8f4d4dfc8335","html_url":"https://github.com/dnerini/startleiter","commit_stats":{"total_commits":161,"total_committers":1,"mean_commits":161.0,"dds":0.0,"last_synced_commit":"8ad2ae1db3e26da04e215e0c4f81015101a5b201"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dnerini/startleiter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dnerini%2Fstartleiter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dnerini%2Fstartleiter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dnerini%2Fstartleiter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dnerini%2Fstartleiter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dnerini","download_url":"https://codeload.github.com/dnerini/startleiter/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dnerini%2Fstartleiter/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266428049,"owners_count":23926921,"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","status":"online","status_checked_at":"2025-07-22T02:00:09.085Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"robots_txt_url":"https://github.com/robots.txt","online":true,"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":["machine-learning","paragliding","radiosonde"],"created_at":"2025-06-30T10:08:18.170Z","updated_at":"2025-07-22T04:33:03.525Z","avatar_url":"https://github.com/dnerini.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Welcome to Starleiter! In this project, I used data analysis and machine learning techniques\nto explore the relationship between the atmospheric conditions and paragliding.\n\n## Project Overview\n\nStartleiter is a recommendation system for paragliding pilots. Based on the nearest and\nmost recently available radio-sounding, it computes the probability of flying on the\ncurrent day, as well as the expected maximum flying height and distance.\n\nThe prediction model, a one-dimensional convolutional neural network (1D CNN),\nis trained on radio-sounding data from [UWYO](http://weather.uwyo.edu/upperair/sounding.html)\nand flight reports from [XContest](https://www.xcontest.org/world/en/). \nStartleiter also includes an explainability plot based on [SHAP](https://github.com/slundberg/shap)\nto gain insights on the output of the machine learning model, for example:\n\n![](https://user-images.githubusercontent.com/11967971/178354681-50b8b017-b007-4dd0-99e9-1c5f30e789cb.png)\n\n## Project Components\n\nThe project consists of the following components:\n\n- Data extraction.\n- [Data exploration and visualization](https://dnerini.github.io/startleiter/statistics.html).\n- Data preprocessing and feature engineering.\n- Model training and evaluation.\n- [Predictions](https://dnerini.github.io/startleiter/monitoring.html).\n\n## Credits and Sources\n\n- Flight reports: [XContest](https://www.xcontest.org/)\n- Atmospheric soundings: [University of Wyoming](https://weather.uwyo.edu/upperair/sounding.html)\n- GFS forecast data: [NOAA](https://rucsoundings.noaa.gov/)\n- Explainability score: [SHAP](https://github.com/slundberg/shap)\n- SkewT plot: [MetPy](https://unidata.github.io/MetPy/latest/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdnerini%2Fstartleiter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdnerini%2Fstartleiter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdnerini%2Fstartleiter/lists"}