{"id":"W4401721583","doi":"10.1080/20964471.2024.2386091","title":"Projecting multiclass global land-use and land-cover change using deep learning and spherical geographic automata model","year":2024,"lang":"en","type":"article","venue":"Big Earth Data","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deforestation (computer science); Land cover; Global change; Urbanization; Infill; Sustainability; Environmental change; Land use, land-use change and forestry; Land use; Environmental resource management; Climate change; Process (computing); Computer science; Cellular automaton; Geography; Environmental science; Artificial intelligence; Civil engineering; Engineering; Geology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002214253,0.0001236767,0.0001229516,0.00001776264,0.0001533559,0.0003294028,0.0001601524,0.00006220103,0.00004262494],"category_scores_gemma":[0.00002164536,0.00009345969,0.00001424859,0.0001860369,0.00002323292,0.000954524,0.0008327607,0.0001021545,0.00005045754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001363588,"about_ca_system_score_gemma":0.000006525886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004583938,"about_ca_topic_score_gemma":0.004535639,"domain_scores_codex":[0.9989682,0.00003937959,0.0001199353,0.000454821,0.0001677747,0.000249925],"domain_scores_gemma":[0.999586,0.00003860584,0.00003009596,0.0002524343,0.000002973012,0.00008990533],"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":[0.00001043482,0.00001385064,0.9805114,0.00009938136,0.00001771538,0.00002662223,0.00016841,0.001237241,0.000109534,0.000001674165,0.00001277691,0.01779094],"study_design_scores_gemma":[0.0001786023,0.00001654937,0.1104004,0.0000765264,0.00002963278,0.00004484954,0.00001831402,0.8851529,0.000004318908,0.00001156349,0.003938471,0.0001278477],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9980831,0.0007533005,0.0005371575,0.00004577006,0.00008255265,0.0001504231,0.0001297077,0.000109781,0.0001082762],"genre_scores_gemma":[0.9968561,0.0003087827,0.002580312,0.00006232729,0.00008907686,0.000003733326,0.00007190042,0.00001214059,0.00001562905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8839157,"threshold_uncertainty_score":0.6929573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08496265188208524,"score_gpt":0.284025435694942,"score_spread":0.1990627838128567,"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."}}