{"id":"W4309852942","doi":"10.3390/ijgi11120587","title":"Mitigating Imbalance of Land Cover Change Data for Deep Learning Models with Temporal and Spatiotemporal Sample Weighting Schemes","year":2022,"lang":"en","type":"article","venue":"ISPRS International Journal of Geo-Information","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weighting; Inverse distance weighting; Sample (material); Computer science; Land cover; A-weighting; Data mining; Artificial intelligence; 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":[0.0005322749,0.00007049547,0.0001224933,0.00006995687,0.0001470467,0.00006309186,0.0003384122,0.00001934232,0.0001331875],"category_scores_gemma":[0.00004459215,0.00005586452,0.00002487308,0.00006287137,0.00001252063,0.004044473,0.0002507542,0.000109563,0.000002185706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006665611,"about_ca_system_score_gemma":0.000015464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005861237,"about_ca_topic_score_gemma":0.00009941527,"domain_scores_codex":[0.9989356,0.00002421274,0.0003903657,0.00006701579,0.0004851818,0.00009756142],"domain_scores_gemma":[0.9989331,0.00007394491,0.0007981007,0.00008047166,0.00007936612,0.00003500495],"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":[0.0004024512,0.00003620742,0.8867479,0.0000885148,0.0001119912,0.000002805355,0.003476051,0.08863479,0.00006383799,0.0001599737,0.0001635912,0.02011191],"study_design_scores_gemma":[0.001618411,0.000285337,0.01644886,0.000107987,0.00002753029,0.00009298836,0.001074413,0.9541677,0.000218957,0.0005614946,0.02524068,0.000155696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9707975,0.00005540066,0.02809147,0.0003298539,0.0001767911,0.0001433672,0.0002050388,0.000006691906,0.0001939038],"genre_scores_gemma":[0.991232,0.00002522715,0.00818377,0.0001403824,0.00008087834,0.000008079723,0.0003223941,0.00000422186,0.000003026437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.870299,"threshold_uncertainty_score":0.2932145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02425871341536426,"score_gpt":0.2413636574900611,"score_spread":0.2171049440746968,"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."}}