{"id":"W2075046504","doi":"10.3390/rs3112440","title":"An Object-Based Classification of Mangroves Using a Hybrid Decision Tree—Support Vector Machine Approach","year":2011,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Coastal wetland ecosystem dynamics","field":"Environmental Science","cited_by":285,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"University of North Carolina at Chapel Hill; National Science Foundation","keywords":"Mangrove; Support vector machine; Remote sensing; Vegetation (pathology); Decision tree; Computer science; Environmental science; Confusion; Object based; Artificial intelligence; Pixel; Pattern recognition (psychology); Geography; Ecology","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":[0.0003223285,0.0001592913,0.0002101434,0.00007815371,0.00009631181,0.00001976215,0.0001451923,0.00005822819,0.00008218713],"category_scores_gemma":[0.00002865561,0.0001485975,0.00007465709,0.0002004681,0.00007340757,0.0001736688,0.00007131779,0.00008936816,0.00003263541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001885742,"about_ca_system_score_gemma":0.00001927523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001708864,"about_ca_topic_score_gemma":0.0006834051,"domain_scores_codex":[0.9986863,0.00007625309,0.0003316175,0.0003658005,0.0002980347,0.0002419914],"domain_scores_gemma":[0.9991668,0.00003373035,0.0002006596,0.0004779297,0.00001441085,0.0001065059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000209756,0.0001788685,0.005673675,0.00006003326,0.00001528178,0.00003255703,0.0006827768,0.004923224,0.4051976,0.00001009153,0.00002592269,0.5829902],"study_design_scores_gemma":[0.0002392538,0.00007815454,0.02350928,0.00003677801,0.00002349363,0.00006889119,0.00009139155,0.9694043,0.006227429,0.0001322176,0.00002428782,0.0001645432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7092288,0.000004189429,0.2853279,0.00000351179,0.00007281046,0.0001431475,0.000007838909,0.00003839918,0.005173431],"genre_scores_gemma":[0.8452996,0.000001096166,0.154586,0.00001733603,0.0000200514,1.69089e-8,0.00003100892,0.00002546922,0.00001940184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9644811,"threshold_uncertainty_score":0.605963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02949860368171094,"score_gpt":0.2396209304309184,"score_spread":0.2101223267492075,"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."}}