{"id":"W4307111613","doi":"10.1098/rsta.2021.0288","title":"Status and prospects for drought forecasting: opportunities in artificial intelligence and hybrid physical–statistical forecasting","year":2022,"lang":"en","type":"article","venue":"Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Climate Program Office; Office of International Science and Engineering; National Oceanic and Atmospheric Administration; National Science Foundation","keywords":"Robustness (evolution); Computer science; Artificial intelligence; Machine learning; Climate model; Stability (learning theory); Process (computing); Climate change; Ecology","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":[],"consensus_categories":[],"category_scores_codex":[0.0003441952,0.0001392224,0.0002676971,0.00002039398,0.000529309,0.00002828066,0.0001464174,0.00002579282,0.00003849298],"category_scores_gemma":[0.00009845938,0.0001018382,0.000111584,0.0002532758,0.001142733,0.0001028567,0.0001153081,0.0002680348,3.715625e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002958667,"about_ca_system_score_gemma":0.00001044611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002159843,"about_ca_topic_score_gemma":0.000001613923,"domain_scores_codex":[0.9988754,0.00003365346,0.0002174343,0.0003012555,0.0002755745,0.0002966401],"domain_scores_gemma":[0.9990234,0.0007353416,0.00004825305,0.00008178495,0.000005675806,0.0001055832],"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":[0.00007900566,0.001373454,0.0006336259,0.0005105938,0.0001074993,0.000005558473,0.007074428,0.5749428,0.000678711,0.396133,0.00001439248,0.0184469],"study_design_scores_gemma":[0.00004673628,0.0001224577,0.0001139771,0.00001020784,0.00003424366,0.000005490397,0.0001651166,0.6294715,0.0001077235,0.369835,0.000007251081,0.00008017715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9200637,0.00002909818,0.07728764,0.002112126,0.00002774021,0.0002360868,0.00003594011,0.00002022959,0.0001874918],"genre_scores_gemma":[0.9954435,0.000004715289,0.004385994,0.00003616711,0.00003674468,0.0000719607,8.558928e-7,0.000007423116,0.00001263396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07537986,"threshold_uncertainty_score":0.4210446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06219997670061932,"score_gpt":0.2524765436759519,"score_spread":0.1902765669753326,"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."}}