{"id":"W4381839875","doi":"10.3390/hydrology10050110","title":"Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia","year":2023,"lang":"en","type":"article","venue":"Hydrology","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Mean squared error; Random forest; Support vector machine; Water quality; Algorithm; AdaBoost; Artificial neural network; Regression; Machine learning; Statistics; Regression analysis; Mathematics; Remote sensing; Artificial intelligence; Environmental science; Computer science; Geography; Ecology","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":[],"consensus_categories":[],"category_scores_codex":[0.000785697,0.0001531519,0.0003484386,0.0001879231,0.00009204807,0.00001055116,0.0002493908,0.0003402269,0.00006017572],"category_scores_gemma":[0.0003423739,0.0001254161,0.00005102293,0.0003775945,0.0004066771,0.00007378835,0.0007629422,0.0006423126,0.00007516533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001309383,"about_ca_system_score_gemma":0.00000586505,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008966329,"about_ca_topic_score_gemma":0.0002425241,"domain_scores_codex":[0.9978944,0.0003735143,0.0005021521,0.0004296528,0.0002918864,0.0005084075],"domain_scores_gemma":[0.9992667,0.0002785511,0.0001038682,0.0002902619,0.000004035978,0.00005655381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003451137,0.00001589404,0.8787893,0.000008954195,0.00001447407,0.00007012202,0.001294441,0.004822191,0.1087868,0.00001401396,0.000001841219,0.006147489],"study_design_scores_gemma":[0.0006313072,0.0001225168,0.4837337,0.00002890218,0.00001829177,0.00001578284,0.0001683227,0.3409417,0.1703445,0.003563448,0.0001865294,0.0002449567],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.997159,0.000007012374,0.001505539,0.000661296,0.0002017195,0.0000822103,0.000004434122,0.0003152459,0.00006356648],"genre_scores_gemma":[0.9838439,0.000007035646,0.01600314,0.00002241626,0.00006128567,5.391046e-7,0.00002012805,0.00001877092,0.00002275092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3950556,"threshold_uncertainty_score":0.997633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03985666574656969,"score_gpt":0.2981025038010587,"score_spread":0.258245838054489,"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."}}