{"id":"W4392600337","doi":"10.5194/egusphere-egu24-5792","title":"Improving forest disturbance labels through Sentinel-1 change detection validation","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Disturbance (geology); Change detection; Environmental science; Remote sensing; Forestry; Computer science; Geography; Geology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009150636,0.0007270655,0.0005112815,0.001848348,0.000577568,0.001342512,0.001757555,0.000691193,0.0009010981],"category_scores_gemma":[0.01827123,0.0002126492,0.0005530735,0.001222507,0.0006062406,0.001741949,0.001335665,0.001070168,0.0008910567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009237486,"about_ca_system_score_gemma":0.0009041676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01088391,"about_ca_topic_score_gemma":0.01748853,"domain_scores_codex":[0.9958861,0.001068622,0.0004479391,0.0009776781,0.001311071,0.0003085839],"domain_scores_gemma":[0.9875242,0.00356948,0.001986005,0.002761294,0.003879904,0.0002792569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004109525,0.0007244503,0.6183174,0.0004173508,0.0002703141,0.0002937449,0.0009897699,0.09379283,0.01858761,0.003190251,0.03494491,0.2280604],"study_design_scores_gemma":[0.0000729899,0.0003240858,0.2186029,0.0001714371,0.000108124,0.0002438043,0.0007311467,0.7357388,0.02002135,0.003452283,0.0204432,0.00008987273],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.781596,0.0006261935,0.1859244,0.0006696063,0.0006019667,0.0005205655,0.01575299,0.005287824,0.009020374],"genre_scores_gemma":[0.8451265,0.0001269916,0.1159206,0.0003851935,0.00008693654,0.0003362711,0.03660367,0.0002300203,0.001183771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01088391,"threshold_uncertainty_score":0.04839379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02661481174695596,"score_gpt":0.2592971729874919,"score_spread":0.232682361240536,"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."}}