{"id":"W4383998603","doi":"10.1007/s10661-023-11468-3","title":"Assessment of pixel-oriented k-NN machine learning algorithm performance for the interannual remote sensing monitoring of eelgrass beds at the mouth of the Romaine","year":2023,"lang":"en","type":"review","venue":"Environmental Monitoring and Assessment","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Collège de Maisonneuve; Hydro-Québec; EnGlobe (Canada)","funders":"Hydro-Québec","keywords":"Environmental monitoring; Remote sensing; Environmental science; Ecotoxicology; Pixel; Algorithm; Computer science; Artificial intelligence; Ecology; Geology; Environmental engineering; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001082352,0.0004718032,0.0009660274,0.00005298716,0.0006547879,0.00003290967,0.0005584948,0.0001452058,0.00002572233],"category_scores_gemma":[0.00001163291,0.0002400969,0.0003998855,0.0002630089,0.0001878068,0.0001147167,0.001266857,0.0005575927,0.000003957563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006456338,"about_ca_system_score_gemma":0.00002912473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004878182,"about_ca_topic_score_gemma":0.00001655274,"domain_scores_codex":[0.9970459,0.0002719795,0.0009833475,0.0004876746,0.0008070102,0.0004041239],"domain_scores_gemma":[0.9975719,0.0005932215,0.001127628,0.0006261164,0.000008936115,0.000072148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001178974,0.00008047035,0.07555491,0.003304471,0.000498392,0.000001626904,0.0004991189,0.001229749,0.0005118657,0.000001516511,0.000005221551,0.9183009],"study_design_scores_gemma":[0.003305012,0.00159607,0.4521533,0.04364338,0.006302615,0.0001266753,0.01208787,0.1429973,0.006319702,0.00003461986,0.3289553,0.002478237],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"review","genre_scores_codex":[0.6390252,0.3533965,0.001173343,0.00006840802,0.002803785,0.002850201,0.0004449725,0.00005117185,0.0001863986],"genre_scores_gemma":[0.3447437,0.6517434,0.002747677,0.000001947734,0.0002778327,0.00004077066,0.00004451519,0.0000797246,0.0003204932],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9158226,"threshold_uncertainty_score":0.9790866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02149662126248878,"score_gpt":0.2988462292434608,"score_spread":0.277349607980972,"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."}}