{"id":"W2965595054","doi":"10.24963/ijcai.2019/636","title":"FireCast: Leveraging Deep Learning to Predict Wildfire Spread","year":2019,"lang":"en","type":"article","venue":"","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":116,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Random forest; Geographic information system; Climate change; Machine learning; Meteorology; Artificial intelligence; Remote sensing; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003319385,0.0001528722,0.000162141,0.00003329149,0.00009098378,0.00004809015,0.000261007,0.00005564541,0.006666021],"category_scores_gemma":[0.00006092052,0.0001362741,0.0000486418,0.0002281052,0.00001985677,0.0002621033,0.000244489,0.0001602886,0.03020241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001875643,"about_ca_system_score_gemma":0.000003641612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001573289,"about_ca_topic_score_gemma":0.0002081362,"domain_scores_codex":[0.9986098,0.00007348075,0.0001673668,0.0004195988,0.0003459391,0.000383853],"domain_scores_gemma":[0.9993851,0.00009394116,0.00004447048,0.0003061825,0.000002295737,0.0001679662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001148161,0.00002511701,0.8935297,0.00001418269,0.000009352545,0.000009105675,0.001049735,0.007186996,0.008962629,0.000006299152,0.002768089,0.08642734],"study_design_scores_gemma":[0.0005627109,0.0004011061,0.5755792,0.00009656407,0.00001067763,0.00003856003,0.000346711,0.2680023,0.003092556,0.00002194917,0.1512669,0.0005807132],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.897623,0.00001414334,0.0005733852,0.0002001087,0.0003432041,0.0004244839,4.198644e-7,0.0001926548,0.1006286],"genre_scores_gemma":[0.9839233,0.000001389596,0.0007593686,0.0003710219,0.00004929841,0.0000188913,0.000002381699,0.0000270259,0.01484734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3179504,"threshold_uncertainty_score":0.994242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004984461185114209,"score_gpt":0.191770765722553,"score_spread":0.1867863045374388,"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."}}