{"id":"W4412581300","doi":"10.1016/j.jag.2025.104742","title":"Machine learning-guided field site selection for river classification","year":2025,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Hydrology and Sediment Transport Processes","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kensington Health","funders":"Arts and Science Council; Office of the President, University of California; National Institute of Food and Agriculture; University of California; Directorate-General for Climate Action","keywords":"Site selection; Selection (genetic algorithm); Field (mathematics); Geography; Cartography; Machine learning; Artificial intelligence; Archaeology; Computer science; Political science; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001634126,0.0007435873,0.001157584,0.001546149,0.0006315792,0.0008165385,0.002139877,0.001091969,0.002756673],"category_scores_gemma":[0.004272354,0.0004161107,0.0007553372,0.001589737,0.0008805366,0.001484215,0.0009924127,0.001195336,0.000831642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027456,"about_ca_system_score_gemma":0.001601435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00646356,"about_ca_topic_score_gemma":0.01028019,"domain_scores_codex":[0.9989605,0.0003202495,0.00005428695,0.0003704598,0.0001770842,0.0001174479],"domain_scores_gemma":[0.9975012,0.001247472,0.0002156263,0.0003924707,0.0005119764,0.0001312576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001811284,0.0003103762,0.008931702,0.0001558276,0.00005927103,0.0001261445,0.0001737523,0.4380578,0.007390556,0.008507978,0.007616091,0.5284894],"study_design_scores_gemma":[0.00001509001,0.00003486438,0.0006347024,0.000007949509,0.000006601106,0.00002065552,0.00002791883,0.9911274,0.001275111,0.005706307,0.001134716,0.000008748715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02745411,0.0002561781,0.9682666,0.0001831076,0.00002653893,0.0001291933,0.0001822842,0.001719234,0.00178274],"genre_scores_gemma":[0.52115,0.0001474339,0.4746331,0.0002325568,0.00006878798,0.0002857159,0.0008952926,0.0001525809,0.00243466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00646356,"threshold_uncertainty_score":0.01285189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01330252114583331,"score_gpt":0.2446742116342007,"score_spread":0.2313716904883674,"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."}}