{"id":"W4225913161","doi":"10.1017/eds.2022.2","title":"Evolution of machine learning in environmental science—A perspective","year":2022,"lang":"en","type":"article","venue":"Environmental Data Science","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of British Columbia; University of British Columbia","funders":"","keywords":"Parametrization (atmospheric modeling); Perspective (graphical); Computer science; Artificial intelligence; Artificial neural network; Machine learning; Climate science; Data assimilation; Deep learning; Convolutional neural network; General Circulation Model; Climate change; Physics; Meteorology; 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":["sts","open_science","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.00326723,0.0001952904,0.0001915856,0.0002708544,0.001329793,0.00003470502,0.003066578,0.00002777272,0.005378509],"category_scores_gemma":[0.0002233261,0.0001986003,0.0000338355,0.001570441,0.007015243,0.00161517,0.009462032,0.0005289286,0.0002006575],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005339806,"about_ca_system_score_gemma":0.00008290609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001311037,"about_ca_topic_score_gemma":0.00003554123,"domain_scores_codex":[0.9953518,0.000140986,0.0003502716,0.001349001,0.002110489,0.0006974874],"domain_scores_gemma":[0.9986412,0.00005103568,0.0001967115,0.000930243,0.000001330628,0.0001795139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003359809,0.0005273837,0.3378569,0.000001160677,0.000001877693,0.00001705827,0.0008726016,0.09439182,0.5637677,0.0002475762,0.00003263904,0.002249735],"study_design_scores_gemma":[0.0007447324,0.0006438684,0.6523187,0.000007484208,0.00001415628,0.0001118621,0.003228066,0.3304555,0.006950476,0.0008073635,0.004154177,0.0005636066],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99503,0.0001207305,0.00006567637,0.0001078274,0.0001471631,0.00024394,0.0003264566,0.00003382498,0.003924415],"genre_scores_gemma":[0.9985408,0.00001446946,0.001129995,0.00006219769,0.00001207557,0.0000144076,0.00006510135,0.00001404989,0.0001468652],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5568172,"threshold_uncertainty_score":0.9999703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01709476070128623,"score_gpt":0.2403423857968685,"score_spread":0.2232476250955823,"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."}}