{"id":"W4306970098","doi":"10.1080/07038992.2022.2135497","title":"Toward Targeted Change Detection with Heterogeneous Remote Sensing Images for Forest Mortality Mapping","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Norges Forskningsråd; Universitetet i Tromsø","keywords":"Change detection; Geography; Cartography; Remote sensing; Random forest; Environmental resource management; Forestry; Computer science; Environmental science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006806445,0.0003035603,0.000389326,0.0002387741,0.0009532768,0.0001262938,0.0002183562,0.000099616,0.00003762592],"category_scores_gemma":[0.0001240948,0.0002712455,0.0002114874,0.0006423341,0.0001823122,0.0002454676,0.00006528876,0.0005711933,0.000005136538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001580949,"about_ca_system_score_gemma":0.0001667007,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04177735,"about_ca_topic_score_gemma":0.08281346,"domain_scores_codex":[0.9976587,0.0001915653,0.0004942064,0.0003919891,0.0005360828,0.0007274493],"domain_scores_gemma":[0.9984358,0.00005995089,0.0005754487,0.0003031764,0.0001249647,0.000500682],"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":[0.00005929581,0.00000359589,0.0002965524,0.0000270286,0.00009200187,0.00187052,0.002017062,0.008200322,0.0237664,1.938352e-7,0.0004180642,0.963249],"study_design_scores_gemma":[0.003092604,0.001642473,0.05091565,0.0007279368,0.0005501874,0.06972182,0.005366554,0.5878984,0.04224569,0.002018356,0.2332328,0.002587513],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.789764,0.0002332732,0.2073606,0.000746111,0.00097545,0.0005108446,0.00001953764,0.00003386434,0.0003563275],"genre_scores_gemma":[0.8206913,0.000006831628,0.1783869,0.0004929091,0.0002984009,1.80133e-8,0.000008817772,0.00005242916,0.00006229188],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9606615,"threshold_uncertainty_score":0.999974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02901131523862828,"score_gpt":0.2186673304819338,"score_spread":0.1896560152433056,"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."}}