{"id":"W3158543373","doi":"10.1016/j.scitotenv.2021.147319","title":"Efficacy of machine learning techniques in predicting groundwater fluctuations in agro-ecological zones of India","year":2021,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Groundwater; Environmental science; Ecology; Water resource management; Environmental resource management; Geology; Biology; Geotechnical engineering","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":[0.001537375,0.0001000712,0.0001862038,0.00004831856,0.000128835,0.000007809826,0.0005484395,0.00004951076,0.0004417629],"category_scores_gemma":[0.0005472445,0.00005671448,0.00006189645,0.0006134259,0.002088065,0.0001050558,0.00106814,0.0002507928,0.000008374708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001715063,"about_ca_system_score_gemma":0.00001834696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000316207,"about_ca_topic_score_gemma":0.00001294691,"domain_scores_codex":[0.9983241,0.0002042042,0.0004024471,0.0002662519,0.0005474152,0.000255562],"domain_scores_gemma":[0.9992431,0.0001926003,0.0002118402,0.0003171595,0.000004093893,0.00003121687],"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":[0.00001612832,0.0004272826,0.04209352,0.000005798991,0.00000305252,0.000002332152,0.001095169,0.4462532,0.5083925,0.00007749933,8.779948e-7,0.00163272],"study_design_scores_gemma":[0.0001716973,0.0001421415,0.805187,0.00004132424,0.000007811943,0.000009301442,0.00007609522,0.01666148,0.1769821,0.0006446835,0.00000659394,0.00006979743],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983004,0.00001948991,0.00003323023,0.0003663757,0.00003450427,0.00020882,0.000001730703,0.000008611814,0.001026822],"genre_scores_gemma":[0.9980218,0.00001186823,0.001796806,0.00001097338,0.000005227572,0.000008574129,7.516176e-7,0.00000467564,0.0001393457],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7630935,"threshold_uncertainty_score":0.7693564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01180788008951615,"score_gpt":0.2252366139685475,"score_spread":0.2134287338790314,"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."}}