{"id":"W4413808613","doi":"10.1016/j.jenvman.2025.126728","title":"Regional mapping of natural gas compressor stations in the United States and Canada using deep learning on satellite imagery","year":2025,"lang":"en","type":"article","venue":"Journal of Environmental Management","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Environmental Defense Fund; U.S. Department of Energy","keywords":"Satellite imagery; Satellite; Natural gas; Compressor station; Remote sensing; Environmental science; Natural (archaeology); Meteorology; Cartography; Geography; Engineering; Archaeology; Waste management","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0001240175,0.0003602252,0.000204851,0.002152586,0.0006120288,0.0007893378,0.0004954769,0.0003346657,0.001734101],"category_scores_gemma":[0.0005755037,0.0001902028,0.0003035829,0.003789756,0.0003616114,0.0002822199,0.0005045959,0.0003144206,0.0002701532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005901648,"about_ca_system_score_gemma":0.009415351,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9857943,"about_ca_topic_score_gemma":0.991273,"domain_scores_codex":[0.9998772,0.000004798878,0.000004011851,0.00002732099,0.00003945231,0.00004710687],"domain_scores_gemma":[0.9996276,0.00002647981,0.00003260603,0.00001188103,0.000252936,0.00004843111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004889239,0.0002791872,0.6876002,0.0003366172,0.000481824,0.0006560071,0.001126772,0.1265592,0.009955236,0.003544546,0.03847396,0.1304976],"study_design_scores_gemma":[0.0000538645,0.00002035785,0.861255,0.0001140355,0.0001278386,0.00009909797,0.002466576,0.116396,0.001979135,0.0005421264,0.01688596,0.00006008412],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9642842,0.0008447169,0.001329987,0.0004293301,0.0000335371,0.00004098508,0.02474515,0.0004129139,0.007879171],"genre_scores_gemma":[0.9870887,0.0004466696,0.002448494,0.00004468428,0.000007486003,0.00001254123,0.006909668,0.00002347539,0.003018064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01420569,"threshold_uncertainty_score":0.04281968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006666181752646053,"score_gpt":0.1988667199507939,"score_spread":0.1922005381981479,"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."}}