{"id":"W4400321359","doi":"10.1080/07038992.2024.2363236","title":"Automated Rooftop Solar Panel Detection Through Convolutional Neural Networks","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Impact of Light on Environment and Health","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Photovoltaic system; Aerial imagery; Renewable energy; Computer science; Satellite imagery; Convolutional neural network; Ground truth; Segmentation; Grid; Deep learning; Aerial image; Fossil fuel; Remote sensing; Artificial intelligence; Cartography; Geography; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0002225084,0.0006855465,0.0002921286,0.0006809884,0.0001772486,0.000425109,0.0006456129,0.0004252037,0.001723321],"category_scores_gemma":[0.0004940401,0.0002752348,0.0003421551,0.0003966792,0.0001534579,0.000493562,0.0003954856,0.0004481022,0.0007092299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005989718,"about_ca_system_score_gemma":0.0003958751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01438698,"about_ca_topic_score_gemma":0.02419096,"domain_scores_codex":[0.9998565,0.00001343888,0.000004227201,0.00005143644,0.00003397161,0.00004050185],"domain_scores_gemma":[0.9998208,0.00005708411,0.000027621,0.00002166999,0.00006190976,0.00001096445],"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":[0.0004662352,0.0002882879,0.008656518,0.0001292423,0.0001428005,0.0001947407,0.00005775457,0.3407836,0.06904905,0.000794904,0.006112815,0.5733241],"study_design_scores_gemma":[0.000003041527,0.00001705348,0.002063474,0.000005463932,0.000008368162,0.0000154906,0.000007968206,0.9903463,0.006965929,0.0002391356,0.0003238446,0.000003941066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5423108,0.0009369131,0.4397044,0.0002995325,0.0001332434,0.00009339972,0.001428623,0.007513795,0.007579329],"genre_scores_gemma":[0.9374517,0.000249208,0.05617365,0.00008266024,0.00003034837,0.0000332633,0.001627781,0.00007159845,0.00427983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01438698,"threshold_uncertainty_score":0.02860647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02286292748929145,"score_gpt":0.2398622650060244,"score_spread":0.2169993375167329,"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."}}