{"id":"W4389657784","doi":"10.5194/isprs-archives-xlviii-1-w2-2023-71-2023","title":"DEEPURBANMODELLER (DUM): A PROCESS-INFORMED NEURAL ARCHITECTURE FOR HIGH-PRECISION URBAN SURFACE TEMPERATURE PREDICTION","year":2023,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Urban Heat Island Mitigation","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Downscaling; Point cloud; Process (computing); Computer science; Urban climate; Grid; Surface (topology); Satellite; Key (lock); Remote sensing; Architecture; Environmental science; Meteorology; Artificial intelligence; Geography; Aerospace engineering; Urban planning; Mathematics; Civil engineering; Engineering; Geometry","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":[0.0003639001,0.0007335074,0.0004398882,0.0002660471,0.0002805015,0.0006349425,0.001621037,0.0007830485,0.002058429],"category_scores_gemma":[0.0008359636,0.0004415479,0.0006015896,0.0002948919,0.0003757807,0.000962037,0.001021156,0.001381045,0.0004833931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007484344,"about_ca_system_score_gemma":0.0009182203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0133192,"about_ca_topic_score_gemma":0.02069488,"domain_scores_codex":[0.9999006,0.00001906179,0.000004167885,0.00004039296,0.00001941122,0.00001631629],"domain_scores_gemma":[0.9998215,0.00006186017,0.00002253834,0.00002769813,0.00004795722,0.00001857537],"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":[0.00003300493,0.0000323416,0.0008802049,0.00002500991,0.00004520981,0.00002674106,0.00002017793,0.9573457,0.001834921,0.001671253,0.0008716892,0.03721365],"study_design_scores_gemma":[0.000001085811,0.000006743837,0.00005075873,0.000001191356,0.00000217414,0.000001875962,0.000001240328,0.999223,0.0002237036,0.000375524,0.000111162,0.000001562281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08892227,0.0006452941,0.9035159,0.0003938685,0.00009258863,0.00004397995,0.0003115912,0.003090401,0.002984019],"genre_scores_gemma":[0.8626603,0.0003027681,0.1310882,0.0002784483,0.00003520875,0.000156311,0.0007462085,0.0001595156,0.004573085],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0133192,"threshold_uncertainty_score":0.02648336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01383130060140647,"score_gpt":0.2473601662873678,"score_spread":0.2335288656859613,"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."}}