{"id":"W4408122617","doi":"10.1007/s12518-025-00607-9","title":"High resolution satellite data and image segmentation produce accurate benthic substrate maps in clear waters of the great lakes","year":2025,"lang":"en","type":"article","venue":"Applied Geomatics","topic":"Aquatic Invertebrate Ecology and Behavior","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Parks Canada; Fisheries and Oceans Canada","funders":"","keywords":"Benthic zone; Remote sensing; Cartography; Geography; Benthic habitat; High resolution; Satellite; Segmentation; Substrate (aquarium); Satellite imagery; Geology; Computer science; Computer vision; Oceanography; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004089975,0.00009589807,0.0001210656,0.00002534156,0.0001014456,0.00001785225,0.0002758601,0.00007076116,0.0001324899],"category_scores_gemma":[0.00001963777,0.00007017924,0.00001010061,0.0002145407,0.0002872966,0.0001544831,0.0003015061,0.0001068338,0.00008483462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004867867,"about_ca_system_score_gemma":0.0000129673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008588323,"about_ca_topic_score_gemma":0.0005484831,"domain_scores_codex":[0.9991443,0.0000580786,0.0002762587,0.0002390123,0.0001228704,0.0001594976],"domain_scores_gemma":[0.9994076,0.00004335676,0.0001099756,0.0004175513,0.000004715342,0.00001682986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003230182,0.0006309471,0.5971566,0.00053075,0.00008944714,0.00001263019,0.007053661,0.002769812,0.3418132,0.008366602,0.00718299,0.03407031],"study_design_scores_gemma":[0.0007807676,0.00003232466,0.9065374,0.00005046645,0.0001050703,0.000002036164,0.001051282,0.006036598,0.07710984,0.007947287,0.0001630578,0.0001838886],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977068,0.00001011224,0.000158172,0.0004888387,0.00008164098,0.0004595483,0.0000204842,0.00001125946,0.001063139],"genre_scores_gemma":[0.9970375,0.00003363633,0.002437446,0.0001317513,0.000005070594,0.00001757544,0.00007549718,0.000005208623,0.0002562955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3093807,"threshold_uncertainty_score":0.2861826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01545389151038704,"score_gpt":0.2398643159227191,"score_spread":0.2244104244123321,"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."}}