{"id":"W7134125570","doi":"10.14358/pers.25-00112r3","title":"Semantic Change Detection with Constrained Dual-Head Convolutional Neural Network Architecture for Oil/Gas Well Site Monitoring","year":2025,"lang":"en","type":"article","venue":"Photogrammetric Engineering & Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; University of Waterloo","funders":"","keywords":"Change detection; Convolutional neural network; Land cover; Set (abstract data type); Segmentation; Binary number; Semantics (computer science); Pixel; Intersection (aeronautics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0003427086,0.0009628247,0.000534951,0.0008784371,0.0002993268,0.0005019442,0.001173286,0.0007009595,0.0009579883],"category_scores_gemma":[0.0007038739,0.0003162846,0.0005754245,0.0007975324,0.0003361717,0.0009911177,0.0005951469,0.0009024789,0.0003649442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156877,"about_ca_system_score_gemma":0.001124717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05045128,"about_ca_topic_score_gemma":0.06841478,"domain_scores_codex":[0.9997725,0.00002332093,0.000009586036,0.00008292886,0.00005311331,0.00005853244],"domain_scores_gemma":[0.9998684,0.00002622104,0.00001726892,0.00002175356,0.00005237913,0.00001403479],"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":[0.0005856504,0.0004860447,0.01234061,0.0001370384,0.0002556196,0.0002760712,0.0001151234,0.4854975,0.02093709,0.002639834,0.01251795,0.4642114],"study_design_scores_gemma":[0.0000061349,0.00002513455,0.001326943,0.000004255029,0.00002200467,0.00001974275,0.00001517363,0.9945691,0.002633713,0.0007821651,0.0005885061,0.000007119202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5764995,0.00351155,0.3953727,0.0009286278,0.0002531457,0.0001838612,0.002696909,0.0119639,0.008589734],"genre_scores_gemma":[0.929355,0.000516733,0.06047884,0.0002439429,0.0000474663,0.00006811013,0.004199849,0.0001068483,0.004983307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05045128,"threshold_uncertainty_score":0.1003152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01611355089452916,"score_gpt":0.2271313691111521,"score_spread":0.211017818216623,"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."}}