{"id":"W2995256291","doi":"10.1111/gean.12228","title":"Exploring the Use of Computer Vision Metrics for Spatial Pattern Comparison","year":2019,"lang":"en","type":"article","venue":"Geographical Analysis","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Similarity (geometry); Computer science; Artificial intelligence; Spatial analysis; Index (typography); Data mining; Spatial ecology; Change detection; Gaussian; Wavelet; Dimension (graph theory); Markov chain; Pattern recognition (psychology); Machine learning; Statistics; Mathematics; Image (mathematics); Ecology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002144742,0.00008557736,0.0002670092,0.0001449254,0.00007570945,0.00004565122,0.0002132154,0.00003247314,0.0003837743],"category_scores_gemma":[0.00000483549,0.00004837425,0.0003322665,0.001458317,0.00001780792,0.0001992269,0.0001472441,0.00005748886,0.00006009237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007885937,"about_ca_system_score_gemma":7.302365e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004875329,"about_ca_topic_score_gemma":0.005348775,"domain_scores_codex":[0.9990216,0.000045506,0.0002577826,0.0002281002,0.0002808249,0.0001662128],"domain_scores_gemma":[0.9993048,0.0002314718,0.000107457,0.0002939582,0.00001393374,0.00004838584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001256821,0.00005019757,0.9402359,0.00001517338,0.0001901902,2.193469e-7,0.00005171325,0.03817761,0.00002129276,0.000002643301,0.00004841134,0.02119414],"study_design_scores_gemma":[0.00009925168,0.00006967314,0.5567512,0.000004118977,0.0003003484,1.173827e-7,0.000008604305,0.4401513,0.00004509499,0.00001025799,0.002501662,0.00005838653],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9604768,0.000009524108,0.0390465,0.0001972978,0.00009306033,0.000141179,0.00001204282,0.00001145292,0.00001212941],"genre_scores_gemma":[0.9992774,0.00002923712,0.0005105843,0.0001053371,0.00003305651,0.00001335247,0.00002224342,0.000004545466,0.000004274744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4019737,"threshold_uncertainty_score":0.7370072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05188066270736918,"score_gpt":0.2442396906240725,"score_spread":0.1923590279167033,"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."}}