{"id":"W3092922674","doi":"10.48550/arxiv.2010.06497","title":"Satellite Image Classification with Deep Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Convolutional neural network; Satellite imagery; Machine learning; Python (programming language); Automation; Metadata; Contextual image classification; Feature extraction; Artificial neural network; Remote sensing; Image (mathematics); World Wide Web; Operating system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007267711,0.00111817,0.0007013084,0.001510625,0.0003023291,0.001074514,0.001229638,0.001094282,0.004059899],"category_scores_gemma":[0.002389183,0.0004800702,0.001015581,0.002348608,0.0005011946,0.001312971,0.001138899,0.001565114,0.003531341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073951,"about_ca_system_score_gemma":0.0008491967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01094087,"about_ca_topic_score_gemma":0.01081101,"domain_scores_codex":[0.9994832,0.00007439338,0.00003106636,0.0001561426,0.0001949725,0.00006017163],"domain_scores_gemma":[0.9994313,0.0001303361,0.00007597537,0.0001577547,0.0001775863,0.00002697313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001089815,0.0001581825,0.002416126,0.0001831062,0.0001890337,0.00006722526,0.00005098654,0.271917,0.006732002,0.007555579,0.02430083,0.6863209],"study_design_scores_gemma":[0.000005892225,0.00001618316,0.0004856059,0.00001615379,0.0000102179,0.00001621249,0.000009457776,0.9863788,0.002173882,0.0075322,0.003347287,0.000008032644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02217915,0.001684215,0.9569327,0.0008208952,0.0002305755,0.0001353212,0.001792558,0.01056964,0.005654929],"genre_scores_gemma":[0.4558552,0.002229673,0.5153559,0.0006733865,0.0003967028,0.0003401316,0.01095807,0.0004806465,0.01371033],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01094087,"threshold_uncertainty_score":0.02175438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06620866626672732,"score_gpt":0.1726010951384468,"score_spread":0.1063924288717194,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}