{"id":"W4411394495","doi":"10.3389/fsufs.2025.1581252","title":"Detecting forest and linear woody feature change between 1954 and 2019 in Southeastern Canadian agroecosystems for regional biodiversity assessment","year":2025,"lang":"en","type":"article","venue":"Frontiers in Sustainable Food Systems","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Biodiversity; Change detection; Agroecosystem; Ecosystem services; Scale (ratio); Random forest; Remote sensing; Environmental science; Pixel; Feature (linguistics); Ecosystem; Geography; Environmental resource management; Agroforestry; Forestry; Cartography; Agriculture; Computer science; Ecology; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0003530012,0.0003028417,0.0001539087,0.00165883,0.0009226152,0.0006532908,0.0005627925,0.0002007454,0.0008655125],"category_scores_gemma":[0.0008895958,0.000121334,0.0002277015,0.002028993,0.000362512,0.000393167,0.0004991376,0.0003193981,0.000131322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01214214,"about_ca_system_score_gemma":0.006647114,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.989944,"about_ca_topic_score_gemma":0.9974201,"domain_scores_codex":[0.9997757,0.00001020346,0.000008559215,0.00004789392,0.00008376659,0.00007385365],"domain_scores_gemma":[0.999413,0.00003785389,0.00006605255,0.00002498358,0.0003881654,0.00007003865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001340627,0.00006015999,0.9070117,0.00009976394,0.0001185663,0.0002569353,0.0007359374,0.007817228,0.003886244,0.0004251943,0.004640297,0.07481397],"study_design_scores_gemma":[0.00000407235,0.000007669753,0.9872351,0.0000236562,0.00002405299,0.00003089039,0.0007283375,0.008612861,0.0005466401,0.00007432735,0.002699156,0.00001311305],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892439,0.0005041639,0.0009283195,0.0002313978,0.00001130395,0.0000271097,0.005690772,0.00007246681,0.003290573],"genre_scores_gemma":[0.9934759,0.0002147261,0.001840959,0.00003224537,0.000003827676,0.000008260859,0.00344621,0.000008093327,0.0009699058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01214214,"threshold_uncertainty_score":0.08809775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.013192850999331,"score_gpt":0.2220598260399849,"score_spread":0.2088669750406539,"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."}}