{"id":"W4213091245","doi":"10.23919/oceans44145.2021.9705953","title":"Hyperspectral Imaging System for Marine Litter Detection","year":2021,"lang":"en","type":"article","venue":"OCEANS 2021: San Diego – Porto","topic":"Microplastics and Plastic Pollution","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Air Canada","funders":"Fundação para a Ciência e a Tecnologia; European Space Agency","keywords":"Hyperspectral imaging; Marine debris; Remote sensing; Litter; Environmental science; Convolutional neural network; Computer science; Artificial intelligence; Oceanography; Geology; Ecology; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000146682,0.0001519343,0.0001547601,0.00003037472,0.000166837,0.00005884863,0.00009488681,0.00005031485,0.004662532],"category_scores_gemma":[0.00005640467,0.0001509967,0.00009911291,0.0001741603,0.00004878069,0.0001096785,0.0001232935,0.00009671631,0.000274839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002434028,"about_ca_system_score_gemma":0.00002142565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001270714,"about_ca_topic_score_gemma":0.0006164322,"domain_scores_codex":[0.9988447,0.00002714691,0.0002192752,0.0003851377,0.0001772609,0.0003464249],"domain_scores_gemma":[0.999523,0.00005426139,0.00007108745,0.0002205623,0.00001859882,0.0001124579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002067927,0.0002978481,0.1194132,0.000226717,0.0001301079,0.0006610707,0.0006732098,0.001250666,0.6920382,0.0018378,0.07331676,0.1099477],"study_design_scores_gemma":[0.003562433,0.0003142125,0.2136316,0.0002162217,0.0005090882,0.001432711,0.002900233,0.07496332,0.3271275,0.001439616,0.3717881,0.002114919],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8651595,0.0002021556,0.07881714,0.0003859906,0.002221402,0.0004449491,0.0001835317,0.0001464252,0.05243888],"genre_scores_gemma":[0.9946521,0.00001078286,0.002420226,0.0001125642,0.0002433539,0.00001126827,0.00005560603,0.00002323035,0.002470847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3649106,"threshold_uncertainty_score":0.9962474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005022788837958435,"score_gpt":0.1898848261094287,"score_spread":0.1848620372714703,"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."}}