{"id":"W4317181824","doi":"10.1289/isee.2022.o-op-019","title":"Characterization of urban built and natural environments with high-resolution satellite images and unsupervised deep learning","year":2022,"lang":"en","type":"article","venue":"ISEE Conference Abstracts","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Cluster analysis; Vegetation (pathology); Unsupervised learning; Scale (ratio); Geography; Urban planning; Deep learning; Built environment; Satellite imagery; Cartography; Remote sensing; Population; Satellite; Computer science; Environmental resource management; Environmental science; Artificial intelligence; Ecology; Environmental health","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001313181,0.0001167256,0.0001368981,0.00002823942,0.0002166801,0.0000403674,0.0001010834,0.00002883023,0.0003869818],"category_scores_gemma":[0.000004070107,0.00009715999,0.00001082561,0.00006798463,0.00005353898,0.0003654711,0.0001541213,0.0001334077,0.00001469498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003574785,"about_ca_system_score_gemma":0.000005326117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003670537,"about_ca_topic_score_gemma":0.0001533783,"domain_scores_codex":[0.999116,0.00005604153,0.0001734432,0.0002519597,0.000232213,0.0001703203],"domain_scores_gemma":[0.9996505,0.00002272506,0.000151981,0.0001068706,0.000004642231,0.00006328877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001726825,0.0001045593,0.2611755,0.00008254834,0.00003424905,0.00001982135,0.002491287,0.01346409,0.7087573,0.00003492268,0.000003275899,0.01365982],"study_design_scores_gemma":[0.0003825721,0.0001261538,0.9901107,0.00001866163,0.00001845339,0.0000114461,0.0002260426,0.000984383,0.006811397,0.00002534411,0.001146381,0.0001384969],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9993059,0.0001467215,0.00002711152,0.00008201526,0.00003908715,0.0001466711,0.00001141836,0.00001527586,0.0002258107],"genre_scores_gemma":[0.9994111,0.0002695381,0.00006479407,0.00003775963,0.00001223778,0.00001459519,0.0000821069,0.000009341924,0.00009851468],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7289352,"threshold_uncertainty_score":0.4237179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007022235921736413,"score_gpt":0.181547135607842,"score_spread":0.1745248996861056,"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."}}