{"id":"W4391903940","doi":"10.24251/hicss.2023.610","title":"Using Isolation Forest and Alternative Data Products to Overcome Ground Truth Data Scarcity for Improved Deep Learning-based Agricultural Land Use Classification Models","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Bundesministerium für Bildung und Forschung","keywords":"Computer science; Ground truth; Deep learning; Context (archaeology); Machine learning; Data mining; Fidelity; Artificial intelligence; Data science; Scale (ratio); Data modeling; Database","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":[0.001944015,0.000834794,0.0004107514,0.001377964,0.0002963535,0.001233897,0.001238157,0.0008992622,0.001440028],"category_scores_gemma":[0.005081758,0.0003173369,0.0005558968,0.001502775,0.0006338463,0.002855662,0.00123029,0.001386144,0.0007151748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007501353,"about_ca_system_score_gemma":0.0007971674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009204337,"about_ca_topic_score_gemma":0.01720603,"domain_scores_codex":[0.9993705,0.0001358952,0.00003761424,0.0002163708,0.0001574763,0.00008208837],"domain_scores_gemma":[0.9985191,0.0005552502,0.0001484572,0.0003531684,0.0003740358,0.00005002343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002436668,0.0003677205,0.0235295,0.0001413719,0.000141633,0.0001387031,0.00020125,0.5815853,0.0145382,0.006651071,0.006263039,0.3661985],"study_design_scores_gemma":[0.000008611617,0.00002143109,0.00193587,0.00001592978,0.000009367214,0.00002144451,0.00003589834,0.9878238,0.004814606,0.003753826,0.001548811,0.00001032132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2039362,0.0003305716,0.785083,0.0004836526,0.00007823137,0.00008463541,0.001980961,0.004494923,0.003527692],"genre_scores_gemma":[0.7204124,0.0001218289,0.272722,0.000205125,0.00003080437,0.0001019673,0.004993078,0.0002424515,0.001170223],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009204337,"threshold_uncertainty_score":0.01830149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1670056823564325,"score_gpt":0.32409154206874,"score_spread":0.1570858597123075,"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."}}