{"id":"W4385065509","doi":"10.1080/10106049.2023.2240283","title":"A landscape metrics-based sample weighting approach for forecasting land cover change with deep learning models","year":2023,"lang":"en","type":"article","venue":"Geocarto International","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Weighting; Geospatial analysis; Sample (material); Land cover; Baseline (sea); Geography; Computer science; Artificial intelligence; Data mining; Cartography; Land use; Engineering; Geology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001171847,0.0005672303,0.0004713651,0.0008931141,0.0001829197,0.0006522705,0.0008817973,0.0004790277,0.0008379028],"category_scores_gemma":[0.003193866,0.0002290983,0.0003608908,0.0007440308,0.0002832216,0.001078502,0.00075827,0.0006863778,0.0001251056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009053908,"about_ca_system_score_gemma":0.000505726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008405685,"about_ca_topic_score_gemma":0.01110031,"domain_scores_codex":[0.9997382,0.00007917317,0.0000239268,0.00006322344,0.00006584237,0.00002972518],"domain_scores_gemma":[0.9993088,0.0002795615,0.00008642557,0.00008152697,0.0002034948,0.00004019749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008906093,0.00007971046,0.006366959,0.0000277043,0.0000653306,0.00004262217,0.00003826906,0.8471471,0.0024035,0.002807376,0.0007740445,0.1401584],"study_design_scores_gemma":[0.000001505691,0.00000730021,0.0002786397,0.000001368812,0.000002243044,0.000002252416,0.000002735371,0.9986359,0.0001940568,0.0007986221,0.00007387519,0.000001372417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1804737,0.0002878245,0.8167958,0.0002768367,0.00003676359,0.00005780019,0.0002716112,0.0006133827,0.001186333],"genre_scores_gemma":[0.8983343,0.00009130424,0.1001292,0.00007454891,0.00002720674,0.00006293047,0.000451049,0.00004695732,0.0007825086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008405685,"threshold_uncertainty_score":0.0167135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06002529462782408,"score_gpt":0.2334799799667409,"score_spread":0.1734546853389169,"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."}}