{"id":"W4395685193","doi":"10.2139/ssrn.4808170","title":"Ai Modelling Based High-Resolution Satellite Imagery Analysis for Evaluating Chlorophyll-A Level in Large Inland Water – a Great Lake Case Study","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Water Quality Monitoring and Analysis","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; Concordia University","funders":"","keywords":"Satellite imagery; Satellite; Remote sensing; Environmental science; High resolution; Satellite image; Chlorophyll a; Water level; Geology; Geography; Cartography; Engineering","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":[0.0003197262,0.0005641236,0.000348631,0.000901695,0.0003353805,0.0008750032,0.00046132,0.0006053229,0.00125572],"category_scores_gemma":[0.0007548915,0.0002622476,0.000427703,0.0009804771,0.0002830442,0.0006530439,0.0003792164,0.0002805606,0.0001929405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009482292,"about_ca_system_score_gemma":0.0006397326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06319454,"about_ca_topic_score_gemma":0.05794217,"domain_scores_codex":[0.9998572,0.00004096297,0.000008743305,0.00002853459,0.00003978662,0.00002473512],"domain_scores_gemma":[0.9996878,0.0001460737,0.00003963908,0.00002631585,0.00007914706,0.00002098859],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004148635,0.0005302808,0.04177712,0.000158866,0.000164622,0.0007542235,0.0002367805,0.8683963,0.02226779,0.00114309,0.001734482,0.06242166],"study_design_scores_gemma":[0.000008511838,0.00002305959,0.00825599,0.00000196175,0.0000138568,0.00001115804,0.00004051889,0.9905413,0.0008668225,0.0001173881,0.0001111359,0.000008296768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.985179,0.00009131683,0.01049442,0.0001476552,0.000009948928,0.00003777695,0.0003570855,0.0003962399,0.003286646],"genre_scores_gemma":[0.9920039,0.00005006246,0.006573016,0.00000818595,0.000005688934,0.00001710171,0.0002068424,0.00002859765,0.001106662],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06319454,"threshold_uncertainty_score":0.1256534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05828095481616166,"score_gpt":0.3244704294359878,"score_spread":0.2661894746198261,"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."}}