{"id":"W4386173941","doi":"10.1109/jiot.2023.3308564","title":"An Internet of Things and AI-Powered Framework for Long-Term Flood Risk Evaluation","year":2023,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"National Research Foundation of Korea; Ministry of Science, ICT and Future Planning","keywords":"Computer science; Deep learning; Segmentation; Artificial intelligence; Flood myth; Ground truth; Convolutional neural network; Artificial neural network; Satellite imagery; Image segmentation; Pixel; Remote sensing; Machine learning; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002202925,0.0001738064,0.0002593152,0.0001522783,0.00006461013,0.0001212139,0.0005157104,0.0001087072,0.0006523972],"category_scores_gemma":[0.0001393233,0.0001492066,0.0001289884,0.0001554843,0.0001317525,0.001030883,0.0001820349,0.0003724807,0.00002693013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001043721,"about_ca_system_score_gemma":0.00001447583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003588099,"about_ca_topic_score_gemma":0.00003131175,"domain_scores_codex":[0.9981095,0.0001212621,0.0005300821,0.0002855204,0.0006837047,0.0002699131],"domain_scores_gemma":[0.9988762,0.0001053896,0.0006247008,0.0002173108,0.00005817633,0.0001182273],"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":[0.000892924,0.0009160389,0.5848675,0.0003328828,0.000983911,0.0000423903,0.04685152,0.002264982,0.01826794,0.001517336,0.0400337,0.3030289],"study_design_scores_gemma":[0.00464194,0.003781644,0.3903379,0.001422598,0.001052328,0.00009202956,0.001358448,0.434583,0.0622214,0.09855796,0.001006882,0.0009438133],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9035681,0.00008889163,0.09443796,0.0002370006,0.0008976377,0.0003589687,0.000003272107,0.00003219203,0.0003759257],"genre_scores_gemma":[0.9888175,0.0002638331,0.01027768,0.0001829129,0.00008525074,0.00001455025,0.000008322438,0.00002391281,0.000326074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4323181,"threshold_uncertainty_score":0.7143292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01995418672550428,"score_gpt":0.3217443668894257,"score_spread":0.3017901801639214,"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."}}