{"id":"W3206655586","doi":"10.1109/tgrs.2021.3114635","title":"Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada; University of Waterloo","funders":"Global Water Futures; National Oceanic and Atmospheric Administration; Nuclear Safety and Security Commission; U.S. Geological Survey; National Aeronautics and Space Administration","keywords":"Multispectral image; Hyperspectral imaging; Remote sensing; Artificial intelligence; Imaging spectrometer; Algorithm; Computer science; Artificial neural network; Spectral bands; Mathematics; Physics; Spectrometer; Geology; Optics","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":[0.0003367658,0.0001164571,0.0001780526,0.0001757233,0.0002494161,0.00008690661,0.00004149697,0.00004985753,0.00004996175],"category_scores_gemma":[0.00001252777,0.00009437701,0.00005242729,0.0003942935,0.00007635813,0.0001822959,0.000001217498,0.0002512764,0.000002032988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001346685,"about_ca_system_score_gemma":0.0000885703,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01574042,"about_ca_topic_score_gemma":0.03928862,"domain_scores_codex":[0.998916,0.000143915,0.000209141,0.0002983385,0.0001915047,0.0002411496],"domain_scores_gemma":[0.9995996,0.0001113748,0.00006436921,0.0001131103,0.00003108407,0.00008049739],"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":[0.0002114261,0.00006666269,0.02733352,0.0001026536,0.000029889,0.000147395,0.0008486341,0.03240814,0.02617889,0.000009314802,0.000002019863,0.9126614],"study_design_scores_gemma":[0.000265145,0.0003967342,0.2369399,0.0002104438,0.000008388439,0.0001232771,0.0003862571,0.7598697,0.001591481,0.00005082109,0.00002756065,0.0001303266],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9794067,0.0000539039,0.0190817,0.00008859557,0.0001693351,0.0000730243,0.00002027616,0.00001559545,0.001090841],"genre_scores_gemma":[0.9963028,0.0002658201,0.003281881,0.00001684691,0.00001634523,1.958226e-8,0.000006119617,0.000002820949,0.0001072828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9125311,"threshold_uncertainty_score":0.9908139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02370564869623371,"score_gpt":0.2665965982378891,"score_spread":0.2428909495416554,"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."}}