{"id":"W4415547721","doi":"10.1016/j.ese.2025.100632","title":"A hierarchical transformer and graph neural network model for high-accuracy watershed nitrate prediction","year":2025,"lang":"en","type":"article","venue":"Environmental Science and Ecotechnology","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and Technology of the People's Republic of China; Ministry of Natural Resources; Ministry of Science and Technology","keywords":"Interpretability; Artificial neural network; Watershed; Water quality; Graph; Transformer; Multivariate statistics; Fuzzy logic","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004690216,0.0001630038,0.0001646824,0.00008129007,0.0006957912,0.00004192996,0.0002553302,0.0001736297,0.00006227875],"category_scores_gemma":[0.00005281117,0.0001343493,0.00002699578,0.0003193679,0.003172449,0.0003148965,0.0002220716,0.0002210342,0.000009373995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001161796,"about_ca_system_score_gemma":0.000009199754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002868141,"about_ca_topic_score_gemma":0.00002199426,"domain_scores_codex":[0.9983929,0.00001757767,0.0002051718,0.0006218671,0.0001861703,0.0005763108],"domain_scores_gemma":[0.9996348,0.00004809349,0.00003976402,0.0001705028,0.000001712744,0.000105125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002998772,0.0002669249,0.05543774,0.00002866608,0.00003148979,0.000008653806,0.0006589319,0.1875441,0.5006224,0.004529151,0.001088769,0.2494833],"study_design_scores_gemma":[0.0007315929,0.0003759003,0.02927112,0.000009762914,0.00003125272,0.00002933987,0.00003620546,0.8953763,0.006658642,0.06634053,0.0008900757,0.0002493004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896207,0.00003934822,0.007080028,0.00245394,0.00009147186,0.0003600369,0.00001651792,0.00008797811,0.0002499763],"genre_scores_gemma":[0.9955657,0.00008667848,0.0034613,0.0006755578,0.00001314247,0.00005760487,0.000007054531,0.000007142505,0.0001258344],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7078322,"threshold_uncertainty_score":0.9995403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00856923500480631,"score_gpt":0.2092474949964312,"score_spread":0.2006782599916249,"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."}}