{"id":"W4386275737","doi":"10.1109/jstars.2023.3310162","title":"A Comparative Analysis of Machine Learning Methods for Algal Bloom Detection Using Remote Sensing Images","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Water Quality Monitoring and Analysis","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources; National Geographic Society","keywords":"Algal bloom; Eutrophication; Random forest; Bloom; Support vector machine; Red tide; Computer science; Algae; Environmental science; Robustness (evolution); Remote sensing; Artificial intelligence; Machine learning; Oceanography; Ecology; Phytoplankton; Geology; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007429923,0.001433097,0.0009703859,0.004516425,0.0003862105,0.001084477,0.0006959832,0.001099574,0.0005545513],"category_scores_gemma":[0.01146131,0.0002728782,0.00127366,0.001740343,0.0003483531,0.001739212,0.0005246594,0.0006903342,0.0003342655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00066683,"about_ca_system_score_gemma":0.0005668832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004409316,"about_ca_topic_score_gemma":0.003046989,"domain_scores_codex":[0.9967302,0.0009101419,0.0002997778,0.0004411919,0.001407473,0.0002112081],"domain_scores_gemma":[0.9926596,0.004502603,0.0004390617,0.0004178181,0.001867526,0.0001134107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001098287,0.0003807227,0.05068623,0.0008095686,0.001021325,0.0001949961,0.0001809248,0.1471442,0.008525916,0.001890149,0.004164898,0.7839029],"study_design_scores_gemma":[0.00002347527,0.0004291687,0.02850518,0.00009278888,0.0001838971,0.0001297336,0.0001394095,0.960317,0.007269794,0.0008695201,0.001983747,0.00005626846],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6225306,0.03013038,0.3329298,0.0009721828,0.000702475,0.0002869188,0.001017393,0.00257439,0.008855975],"genre_scores_gemma":[0.8830187,0.004424149,0.1090606,0.0001822129,0.0001771302,0.0001418809,0.001258517,0.0001146246,0.001622107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007429923,"threshold_uncertainty_score":0.03929371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06655974111870763,"score_gpt":0.3373571127861449,"score_spread":0.2707973716674373,"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."}}