{"id":"W4407853950","doi":"10.1016/j.scitotenv.2025.178901","title":"A spatiotemporal CNN-LSTM deep learning model for predicting soil temperature in diverse large-scale regional climates","year":2025,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Research Council Canada; National Research Council","keywords":"Scale (ratio); Deep learning; Climatology; Computer science; Artificial intelligence; Environmental science; Geology; Cartography; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001529337,0.0001451134,0.0001489373,0.00003915982,0.0007113375,0.00003268707,0.0007530848,0.0000665277,0.00007398859],"category_scores_gemma":[0.0001744621,0.00008612844,0.00009464491,0.0003730701,0.001468015,0.0001769333,0.001031925,0.0002837302,0.00001710719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002953198,"about_ca_system_score_gemma":0.00002544607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009167736,"about_ca_topic_score_gemma":0.00002406505,"domain_scores_codex":[0.9982547,0.00007496237,0.0002612978,0.0004050602,0.0005497341,0.0004542997],"domain_scores_gemma":[0.99935,0.00009199997,0.0001469739,0.0003547652,0.000004772045,0.00005145593],"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":[0.00002648822,0.00007650116,0.0042473,0.000005242226,0.000002862383,2.216864e-7,0.001222575,0.9585368,0.03533538,0.0001027835,0.00004339506,0.0004004322],"study_design_scores_gemma":[0.0002819802,0.00004951139,0.02004238,0.00004000838,0.00001457545,0.0000018962,0.0002409367,0.9733205,0.004191244,0.001685605,0.00003338678,0.0000978997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996451,0.00002415096,0.0005357591,0.001526026,0.00009203045,0.0003685577,0.000007361084,0.00001987014,0.0009752961],"genre_scores_gemma":[0.9966002,0.000008808121,0.001722979,0.0001016484,0.0000134878,0.00002550781,0.0000018227,0.000007170417,0.001518433],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03114414,"threshold_uncertainty_score":0.5471105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362032892556106,"score_gpt":0.2274293968866681,"score_spread":0.213809067961107,"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."}}