{"id":"W4385621729","doi":"10.20944/preprints202308.0450.v1","title":"Graph-Based Deep Learning Model for Forecasting Chloride Concentration in Urban Streams to Protect Salt-Vulnerable Areas","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Smart Materials for Construction","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"STREAMS; Benchmarking; Environmental science; Water quality; Artificial neural network; Hydrology (agriculture); Computer science; Water resource management; Machine learning; Engineering; Business; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001556842,0.0004002773,0.0004262583,0.0001536119,0.000272826,0.00006698653,0.0004702233,0.0003050824,0.000247962],"category_scores_gemma":[0.001037768,0.0004623989,0.0001664958,0.0003122994,0.00009816874,0.0001927439,0.000943156,0.0007020716,0.0004745231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007463981,"about_ca_system_score_gemma":0.00008102939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002258934,"about_ca_topic_score_gemma":0.001563399,"domain_scores_codex":[0.9967868,0.0001814491,0.0006786741,0.001303316,0.0004142176,0.0006355274],"domain_scores_gemma":[0.9986104,0.0001336585,0.000388871,0.0006595093,0.0000378722,0.0001696365],"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":[0.0001476504,0.00002449873,0.4518591,0.00007710969,0.00001046166,0.000002640646,0.0004534613,0.533569,0.01330529,0.00001250621,0.000007299691,0.0005309798],"study_design_scores_gemma":[0.0006311902,0.00004586365,0.09882046,0.0002711226,0.00003296844,0.000003426477,0.00007257708,0.8047751,0.09047306,0.004199065,0.0001268786,0.0005483396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9586818,0.000003704162,0.0366462,0.0001447795,0.0007180919,0.003119547,0.00002882142,0.0003364056,0.000320626],"genre_scores_gemma":[0.9934616,0.00000459711,0.00345374,0.00004500478,0.0001365913,0.002407166,0.0001645082,0.00008924835,0.0002375311],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3530387,"threshold_uncertainty_score":0.9997828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1055877353113772,"score_gpt":0.299430877974261,"score_spread":0.1938431426628838,"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."}}