{"id":"W3196207475","doi":"10.1289/isee.2021.p-098","title":"Spatiotemporal characterization of urban activity and environment with imagery and deep learning","year":2021,"lang":"en","type":"article","venue":"ISEE Conference Abstracts","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Bespoke; Convolutional neural network; Built environment; Geography; Correlation; Business; Computer science; Cartography; Artificial intelligence; Ecology; Advertising; Biology","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":[0.0002416214,0.0006347459,0.0003138495,0.002216778,0.0001652822,0.000693057,0.0007426767,0.0005617162,0.0009509397],"category_scores_gemma":[0.001024942,0.0002729326,0.0005974307,0.00189698,0.0004182371,0.000845697,0.0007916148,0.0006987769,0.0006937621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006721638,"about_ca_system_score_gemma":0.0004210817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01928126,"about_ca_topic_score_gemma":0.03903944,"domain_scores_codex":[0.9997663,0.00003358462,0.00001531212,0.00008892281,0.00004272105,0.00005326566],"domain_scores_gemma":[0.9996816,0.00006774073,0.00008218474,0.00006237254,0.00007776622,0.00002830556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003723745,0.0005102241,0.1916569,0.0009686749,0.0005785772,0.000716908,0.0006171663,0.2488582,0.02258263,0.002746207,0.037766,0.4926262],"study_design_scores_gemma":[0.00001958814,0.00009414206,0.166012,0.0002220626,0.0001063255,0.0004694797,0.0007435207,0.7947921,0.007714482,0.006883168,0.02287939,0.00006365051],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6471652,0.007825547,0.2688594,0.002699854,0.0004812917,0.0003401088,0.05087467,0.006871353,0.01488259],"genre_scores_gemma":[0.862202,0.001995418,0.09276108,0.0003449074,0.0002381631,0.0001645862,0.0396184,0.0001722495,0.002503209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01928126,"threshold_uncertainty_score":0.03833807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01764277347488803,"score_gpt":0.2411545986265231,"score_spread":0.223511825151635,"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."}}