{"id":"W2052191396","doi":"10.1177/0037549709103510","title":"Defining Transition Rules with Reinforcement Learning for Modeling Land Cover Change","year":2009,"lang":"en","type":"article","venue":"SIMULATION","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":"Computer science; Land cover; Reinforcement learning; Probabilistic logic; Cover (algebra); Resource (disambiguation); Set (abstract data type); Geographic information system; Variety (cybernetics); Machine learning; Land use; Natural resource management; Artificial intelligence; Natural resource; Geography; Remote sensing; Ecology","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":[0.00008712269,0.00005534819,0.00005632972,0.00001364617,0.000122579,0.00002145092,0.00002516759,0.00002699593,0.0000937263],"category_scores_gemma":[0.000002130738,0.00004201799,0.00001608555,0.00003797675,0.000001400077,0.0003176817,0.000003965798,0.00002519985,0.00006297342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003135775,"about_ca_system_score_gemma":0.000001316577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009635648,"about_ca_topic_score_gemma":0.00005478919,"domain_scores_codex":[0.9995942,0.000007868623,0.00008397476,0.0001046993,0.0001024603,0.0001067721],"domain_scores_gemma":[0.9998789,0.00001627123,0.00003415467,0.00004390084,0.000005744143,0.00002104668],"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":[0.00005049885,0.000005043822,0.003759305,0.000008312984,0.000002056634,1.890491e-7,0.000670286,0.9932177,0.00002554851,0.00002037256,8.611018e-7,0.002239792],"study_design_scores_gemma":[0.0003972365,0.0001348561,0.002792688,0.00003080289,0.00001140009,3.358203e-7,0.00002197649,0.9960423,0.00002963386,0.0002109081,0.0002545922,0.00007324095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8877559,0.00001700076,0.1110561,0.00007810313,0.0000139425,0.0001994653,8.637706e-7,0.00003109911,0.0008475215],"genre_scores_gemma":[0.9992489,0.000003857305,0.0004377536,0.0001625062,0.00004225198,0.00001113674,0.00007655399,0.000004754194,0.00001225751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.111493,"threshold_uncertainty_score":0.1713444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02150551013874979,"score_gpt":0.2391172857339085,"score_spread":0.2176117755951587,"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."}}