{"id":"W4385507357","doi":"10.1016/j.asr.2023.07.064","title":"Modelling inland Arctic bathymetry from space using cloud-based machine learning and Sentinel-2","year":2023,"lang":"en","type":"article","venue":"Advances in Space Research","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ducks Unlimited Canada","funders":"Naval Air Warfare Center, Aircraft Division; U.S. Fish and Wildlife Service; Ducks Unlimited Canada","keywords":"Bathymetry; Environmental science; Random forest; Remote sensing; Mean squared error; Arctic; Linear regression; Meteorology; Computer science; Statistics; Machine learning; Geology; Mathematics; Geography; Oceanography","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":[0.001260991,0.0001489273,0.000216299,0.0004357695,0.0003213293,0.0001196203,0.0001585845,0.00008088568,0.0007836142],"category_scores_gemma":[0.0001812447,0.0001348798,0.00003129843,0.001313006,0.0001681825,0.0003230165,0.00006096885,0.0006454057,0.0001453624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001713526,"about_ca_system_score_gemma":0.00004324519,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02145585,"about_ca_topic_score_gemma":0.01016782,"domain_scores_codex":[0.997878,0.0002976479,0.0001704474,0.000432296,0.0005286746,0.0006929565],"domain_scores_gemma":[0.9980175,0.00156048,0.00004550367,0.0001630884,0.00005986129,0.0001535666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005016919,0.000006118672,0.7761131,0.00006400041,0.000003180733,0.00006485744,0.0002652057,0.2222914,0.0002096855,0.000009197756,0.00002195925,0.0009011077],"study_design_scores_gemma":[0.0003999097,0.0000388798,0.02205961,0.0001544505,0.000004020214,0.000003379095,0.0009033075,0.9643984,0.00008777766,0.0009472662,0.01083445,0.0001685845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9817883,0.01578163,0.0004150792,0.0005634924,0.0001737531,0.0001526676,0.0002389348,0.00004476923,0.00084132],"genre_scores_gemma":[0.984827,0.01318418,0.0007627754,0.00002745295,0.0002401164,0.000001959711,0.0007211807,0.00001243439,0.0002229313],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7540535,"threshold_uncertainty_score":0.9850603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1076408850020135,"score_gpt":0.3654333023899502,"score_spread":0.2577924173879367,"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."}}