{"id":"W4224942944","doi":"10.5194/esurf-10-349-2022","title":"Convolutional neural networks for image-based sediment detection applied to a large terrestrial and airborne dataset","year":2022,"lang":"en","type":"article","venue":"Earth Surface Dynamics","topic":"Hydrology and Sediment Transport Processes","field":"Environmental Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Pebble; Pixel; Convolutional neural network; Computer science; Artificial intelligence; Remote sensing; Pattern recognition (psychology); Geology; Geomorphology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001028484,0.002491689,0.0008291249,0.002863302,0.0006548401,0.0009199525,0.001838292,0.001435267,0.00197946],"category_scores_gemma":[0.002203787,0.0005194145,0.001401618,0.002334415,0.0003912279,0.0008441966,0.0009366259,0.001703246,0.001969717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001715382,"about_ca_system_score_gemma":0.001342228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06454541,"about_ca_topic_score_gemma":0.09958775,"domain_scores_codex":[0.9991504,0.00008189429,0.00006118106,0.0003548826,0.000208948,0.0001427111],"domain_scores_gemma":[0.9991212,0.0002451981,0.00009111549,0.0001875891,0.0002954964,0.00005939003],"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":[0.001288415,0.002379742,0.05313374,0.001546526,0.001572333,0.001682085,0.0002512631,0.2789205,0.03030283,0.001080301,0.156787,0.4710553],"study_design_scores_gemma":[0.0001184561,0.0002672147,0.03886171,0.0001028218,0.0001447679,0.0002549978,0.0001738159,0.9280897,0.01580556,0.000909308,0.01519507,0.00007656859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7452794,0.004414593,0.04834194,0.0009878644,0.0008532157,0.0007762537,0.1606516,0.03229534,0.006399842],"genre_scores_gemma":[0.5729011,0.0007200228,0.08262813,0.000321753,0.0001054939,0.0004881752,0.3360552,0.0004745815,0.006305524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06454541,"threshold_uncertainty_score":0.1283394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006090419944500024,"score_gpt":0.2103642395574152,"score_spread":0.2042738196129152,"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."}}