{"id":"W4392502765","doi":"10.1021/acs.est.3c05784","title":"Using Knowledge-Guided Machine Learning To Assess Patterns of Areal Change in Waterbodies across the Contiguous United States","year":2024,"lang":"en","type":"article","venue":"Environmental Science & Technology","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"McGill University; Division of Environmental Biology; Office of Advanced Cyberinfrastructure; Division of Graduate Education; Higher Education Authority; Los Alamos National Laboratory; Natural Sciences and Engineering Research Council of Canada; Laboratory Directed Research and Development; Division of Biological Infrastructure; Los Alamos National Laboratory Foundation; Dundalk Institute of Technology; National Science Foundation","keywords":"Proxy (statistics); Change detection; Environmental change; Environmental science; Physical geography; Machine learning; Cartography; Hydrology (agriculture); Climate change; Geography; Ecology; Computer science; Remote sensing; Geology; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001269138,0.0002450053,0.0002140593,0.001785392,0.0002979658,0.0005834242,0.0003387117,0.0003793618,0.0003810263],"category_scores_gemma":[0.006033442,0.0001212542,0.0003284252,0.001151161,0.0004089688,0.0006863457,0.0006556076,0.0002924248,0.00008555445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162389,"about_ca_system_score_gemma":0.0006310651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05716495,"about_ca_topic_score_gemma":0.1131072,"domain_scores_codex":[0.999477,0.000228581,0.00004486914,0.0001355432,0.00006381382,0.00005018912],"domain_scores_gemma":[0.997887,0.001193453,0.0004650584,0.0001788801,0.0001958097,0.00007991525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008034288,0.0001522418,0.9203973,0.00002122175,0.000161226,0.00004308872,0.0002022871,0.04382109,0.0004919266,0.0002040057,0.000447724,0.03397746],"study_design_scores_gemma":[0.00001382388,0.00009891564,0.578957,0.00002105296,0.00004756378,0.00003084732,0.0004645193,0.4175355,0.0006950763,0.001653895,0.0004640245,0.00001776989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960924,0.00005466136,0.002956841,0.0000989425,0.00000216534,0.00001573311,0.0002922634,0.00005191709,0.0004351634],"genre_scores_gemma":[0.9972398,0.00001732577,0.00227372,0.00001956134,0.000002458557,0.00000943312,0.0003804928,0.000002557929,0.0000545351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05716495,"threshold_uncertainty_score":0.1136644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04226755834448338,"score_gpt":0.312900812613671,"score_spread":0.2706332542691876,"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."}}