{"id":"W4392585445","doi":"10.5194/egusphere-egu24-4737","title":"GreenRoofNet: Integrating High-Resolution Aerial Imagery with Deep Learning for Efficient Green Roof Monitoring","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of Toronto","funders":"","keywords":"Aerial imagery; Remote sensing; Roof; Superresolution; Computer science; Deep learning; Artificial intelligence; High resolution; Computer vision; Environmental science; Geology; Geography; Image (mathematics); Archaeology","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":[0.0006730731,0.001405586,0.0006068,0.001665727,0.0004019421,0.001026711,0.001841101,0.001224738,0.003822742],"category_scores_gemma":[0.001182376,0.000472487,0.0008499475,0.001036308,0.0003769245,0.001486501,0.001213264,0.001139272,0.001878673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001082301,"about_ca_system_score_gemma":0.0008954466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02104979,"about_ca_topic_score_gemma":0.03228934,"domain_scores_codex":[0.9996587,0.00003883128,0.00001513747,0.0001185513,0.00009262707,0.0000762303],"domain_scores_gemma":[0.9997389,0.00005833871,0.00003156492,0.00005091917,0.00009430745,0.00002606368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003700485,0.0005494176,0.006707865,0.0002646093,0.0003369192,0.0002688198,0.0001082803,0.162415,0.01630743,0.001791793,0.07390974,0.7369701],"study_design_scores_gemma":[0.0000198348,0.00005595347,0.001676933,0.00002262713,0.00002197221,0.00004098319,0.00003665796,0.9844428,0.006089128,0.002152263,0.005418632,0.00002224377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1770134,0.004238056,0.683932,0.001928372,0.0008777769,0.000490689,0.01577677,0.1003871,0.01535583],"genre_scores_gemma":[0.5158591,0.001418493,0.4350218,0.001111079,0.000191897,0.0004131374,0.02869547,0.001367577,0.01592147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02104979,"threshold_uncertainty_score":0.04185456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01110610423232322,"score_gpt":0.2411134481646061,"score_spread":0.2300073439322829,"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."}}