{"id":"W4403066769","doi":"10.1016/j.isprsjprs.2024.09.039","title":"Automated localization of dike leakage outlets using UAV-borne thermography and YOLO-based object detectors","year":2024,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Leakage (economics); Computer vision; Detector; Dike; Artificial intelligence; Remote sensing; Object detection; Thermography; Computer science; Object (grammar); Leak detection; Environmental science; Geology; Leak; Pattern recognition (psychology); Optics; Infrared; Physics; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008308968,0.0003481829,0.0003194194,0.0006079435,0.0001507555,0.0003488791,0.0002291732,0.0002597289,0.0004460546],"category_scores_gemma":[0.0001870222,0.0001317283,0.0001418691,0.0003638493,0.0001114901,0.0003347116,0.0003359349,0.0001680825,0.0003876378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001455293,"about_ca_system_score_gemma":0.0002525501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002245446,"about_ca_topic_score_gemma":0.006946838,"domain_scores_codex":[0.9999256,0.000006100212,0.000002270206,0.00002530798,0.00001907298,0.00002161],"domain_scores_gemma":[0.9999208,0.00001254231,0.00001879566,0.00001110397,0.00002611356,0.00001061613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006928662,0.0002513932,0.1746584,0.0003350686,0.0001049388,0.000460594,0.0006020357,0.02774871,0.486857,0.0008430882,0.003317275,0.3041286],"study_design_scores_gemma":[0.00008100831,0.0002691533,0.4681294,0.0000878322,0.0001269009,0.0003108541,0.0007225565,0.4024015,0.1186141,0.0004859317,0.0087124,0.00005840321],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9462573,0.0003518277,0.04881617,0.00004266587,0.00004812789,0.00002896951,0.0004884425,0.0007985092,0.003167963],"genre_scores_gemma":[0.9828402,0.00009118331,0.01538008,0.00001315131,0.000007042281,0.0000112742,0.0003021779,0.00001898086,0.001335849],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002245446,"threshold_uncertainty_score":0.004464686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006833672581618145,"score_gpt":0.2335048238504636,"score_spread":0.2266711512688455,"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."}}