{"id":"W4404814680","doi":"10.1016/j.geomat.2024.100039","title":"A depth-based land-use semantic extraction method for landscape images","year":2024,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Extraction (chemistry); Computer science; Land use; Artificial intelligence; Geography; Engineering; Chemistry; Civil 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002918611,0.00009126733,0.0001120176,0.00003066721,0.00008024077,0.0001564687,0.00009049441,0.00004609387,0.001773663],"category_scores_gemma":[0.00002271514,0.00006431842,0.00006603709,0.0001161213,0.00000519264,0.000276692,0.00002623978,0.0000429994,0.001807149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002238218,"about_ca_system_score_gemma":0.000007247829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003176333,"about_ca_topic_score_gemma":0.0008042323,"domain_scores_codex":[0.9992946,0.0000338078,0.0001428461,0.0002130315,0.0001260861,0.0001896668],"domain_scores_gemma":[0.9994271,0.0003274531,0.00002688751,0.0001618417,0.000003891795,0.00005280585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003627476,0.000785378,0.4948132,0.00873186,0.0005156939,0.0003097293,0.002255542,0.03430377,0.03357196,0.0006415261,0.2323686,0.19134],"study_design_scores_gemma":[0.0004047649,0.0000637819,0.03322195,0.0001791039,0.0001362453,0.00003178663,0.00004808181,0.8932069,0.004061528,0.001291254,0.06708709,0.0002675003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7822773,0.0002185016,0.2039275,0.002562573,0.0005981307,0.0007783177,0.00006598492,0.0004547715,0.009116905],"genre_scores_gemma":[0.9778144,0.000007724044,0.02140795,0.0001523883,0.00007545493,0.00007482645,0.00002752892,0.00001683745,0.000422879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8589032,"threshold_uncertainty_score":0.9991388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01446695854573272,"score_gpt":0.2778423599626966,"score_spread":0.2633754014169639,"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."}}