{"id":"W4283590398","doi":"10.3390/rs14133027","title":"Machine-Learning Classification of SAR Remotely-Sensed Sea-Surface Petroleum Signatures—Part 1: Training and Testing Cross Validation","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Oil Spill Detection and Mitigation","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Space Agency; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; National Aeronautics and Space Administration","keywords":"Support vector machine; Random forest; Feature selection; Racing slick; Synthetic aperture radar; Naive Bayes classifier; Remote sensing; Artificial neural network; Environmental science; Computer science; Machine learning; Artificial intelligence; Cross-validation; Petroleum; Satellite; Oil spill; Geology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01135231,0.002033903,0.001394307,0.002146854,0.0006192482,0.0008746564,0.002074131,0.001961553,0.001657165],"category_scores_gemma":[0.01388263,0.0004485855,0.001078451,0.00129827,0.0008961163,0.001048118,0.001045064,0.001321544,0.0009691835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009535372,"about_ca_system_score_gemma":0.001225647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008924153,"about_ca_topic_score_gemma":0.005072834,"domain_scores_codex":[0.9950883,0.002405435,0.0006355346,0.0007802049,0.0007918273,0.0002986675],"domain_scores_gemma":[0.9856089,0.00836295,0.0005175947,0.001503125,0.0037499,0.0002574928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001223566,0.002573188,0.05236093,0.0003767738,0.0006185097,0.0001720458,0.0001474429,0.5528014,0.01053633,0.000610824,0.004355778,0.3742231],"study_design_scores_gemma":[0.00003838592,0.0003112705,0.007162971,0.00002769991,0.00003503433,0.00003872093,0.00004130889,0.983348,0.008405816,0.00019273,0.0003799224,0.00001817692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8440878,0.001554579,0.1466745,0.0001599794,0.0002019346,0.0005881019,0.0008978876,0.002404387,0.003430784],"genre_scores_gemma":[0.9275158,0.0001779909,0.06617545,0.0001478141,0.00003619295,0.0005570446,0.003359688,0.00008913198,0.001940877],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01135231,"threshold_uncertainty_score":0.06003749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0327639883217107,"score_gpt":0.2497078816498476,"score_spread":0.2169438933281369,"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."}}