{"id":15159337,"url":"https://github.com/gkar90/usfs-tree-cover-classification","last_synced_at":"2026-01-20T04:32:26.034Z","repository":{"id":167824715,"uuid":"352533187","full_name":"gkar90/USFS-Tree-Cover-Classification","owner":"gkar90","description":"Deep Learning: Create neural networks to classify the type of forest cover based off cartographic variables compiled from the USFS","archived":false,"fork":false,"pushed_at":"2021-03-30T00:43:56.000Z","size":11211,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-13T18:49:38.806Z","etag":null,"topics":["data-science","google-colab","keras-neural-networks","modeling","python3","tensorflow","tensorflow-models"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gkar90.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2021-03-29T06:02:52.000Z","updated_at":"2021-03-30T02:15:04.000Z","dependencies_parsed_at":null,"dependency_job_id":"c433c289-7633-44e5-97cc-09d2e81541ec","html_url":"https://github.com/gkar90/USFS-Tree-Cover-Classification","commit_stats":{"total_commits":5,"total_committers":2,"mean_commits":2.5,"dds":"0.19999999999999996","last_synced_commit":"289fe8838e1b54a3b0485ad8344bd49186dc396f"},"previous_names":["gkar90/usfs-tree-cover-classification"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gkar90%2FUSFS-Tree-Cover-Classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gkar90%2FUSFS-Tree-Cover-Classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gkar90%2FUSFS-Tree-Cover-Classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gkar90%2FUSFS-Tree-Cover-Classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gkar90","download_url":"https://codeload.github.com/gkar90/USFS-Tree-Cover-Classification/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247687301,"owners_count":20979434,"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":["data-science","google-colab","keras-neural-networks","modeling","python3","tensorflow","tensorflow-models"],"created_at":"2024-09-26T21:04:58.181Z","updated_at":"2025-04-07T16:28:52.870Z","avatar_url":"https://github.com/gkar90.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# USFS Tree Cover Classification\n\n## Introduction\n\nAs a way to continue working with Tensorflow/Keras and neural networks, I found this dataset from the US Forest Serivice about forest cover based off cartographic variables. \n\nThe goal of the project is to use neural networks to predict the type of forest cover we can expect based off inputs such as elevation, slope, aspect, etc..\n\n\n## Dataset\n\nUS Forest Service - GeoData - Tree Cover Canopy Dataset\n\nhttps://data.fs.usda.gov/geodata/rastergateway/treecanopycover/\n\nThe datasets include four wilderness areas located in the Roosevelt National Forest of Northern Colorado. The areas represent forests with minimal human-caused disturbances, so existing forest cover types are mainly a result of ecological processes rather than human forest management practices.\n\n## Model\n\nWe used a Sequential model with 4 hidden layers, and used Sparse Categorical Crossentropy to measure our loss.\n\nThe model was kept with around ~5,000 to keep runtime low. \n\n## Conclusion\n\nThe model we created had close to a 90% accuracy, and had a relatively high precision, recall, and F1 score (all in the 80%+ range). Some things to note were:\n- the data *may have been biased* towards certain forest cover types \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgkar90%2Fusfs-tree-cover-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgkar90%2Fusfs-tree-cover-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgkar90%2Fusfs-tree-cover-classification/lists"}