{"id":"W4411738446","doi":"10.1080/20964471.2025.2518763","title":"Spatial sample weighted machine learning for multitemporal land cover change modeling with imbalanced datasets","year":2025,"lang":"en","type":"article","venue":"Big Earth Data","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Land cover; Sample (material); Change detection; Cover (algebra); Computer science; Artificial intelligence; Pattern recognition (psychology); Remote sensing; Geography; Machine learning; Land use; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001767531,0.0001181877,0.0001482253,0.00002603163,0.0001680127,0.00005734571,0.0003980909,0.00004189262,0.0002317375],"category_scores_gemma":[0.0000191665,0.00008293521,0.00001399687,0.0001167276,0.00000854601,0.0003857298,0.0004430513,0.00007235137,0.00008350716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001061072,"about_ca_system_score_gemma":0.00001027032,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01858875,"about_ca_topic_score_gemma":0.05281052,"domain_scores_codex":[0.9990869,0.00002610258,0.0001363865,0.0003835818,0.0001395902,0.0002274626],"domain_scores_gemma":[0.999294,0.00005044749,0.00005312356,0.0005446489,0.000005051998,0.000052715],"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":[0.0003529965,0.00008103355,0.9760509,0.0001472103,0.00005735286,0.000007326105,0.0001218073,0.006576689,0.0001607613,0.000005184767,0.001059835,0.01537891],"study_design_scores_gemma":[0.0009845252,0.00004398111,0.01169326,0.00005448725,0.00002335774,0.000001047637,0.000005288254,0.8928452,0.00006096504,0.00001583264,0.09414469,0.0001273497],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8982085,0.0002126633,0.08631487,0.0002847342,0.0002454704,0.0007945757,0.01357588,0.00009803079,0.000265297],"genre_scores_gemma":[0.9743301,0.00004035638,0.002949022,0.0002160257,0.0001032434,0.00002629307,0.0222733,0.0000110588,0.00005061252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9643576,"threshold_uncertainty_score":0.9879466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05220717917520037,"score_gpt":0.2617149815049951,"score_spread":0.2095078023297947,"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."}}