{"id":"W3165296532","doi":"10.3390/rs13112046","title":"Comparing Solo Versus Ensemble Convolutional Neural Networks for Wetland Classification Using Multi-Spectral Satellite Imagery","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"","keywords":"Wetland; Swamp; Random forest; Convolutional neural network; Marsh; Artificial intelligence; Ensemble learning; Computer science; Machine learning; Decision tree; Remote sensing; Deep learning; Bog; Environmental science; Geography; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001535736,0.001169336,0.0004930067,0.0008431499,0.0003182752,0.0006116856,0.0007102326,0.0006467787,0.0006681641],"category_scores_gemma":[0.002043183,0.000205333,0.0005286356,0.0004653144,0.0002438463,0.001118604,0.0006124823,0.0005653199,0.0002419266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009745117,"about_ca_system_score_gemma":0.0009082201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04435728,"about_ca_topic_score_gemma":0.0611207,"domain_scores_codex":[0.9996721,0.00006515723,0.00002163194,0.00007353354,0.0000800838,0.00008752167],"domain_scores_gemma":[0.9992104,0.0002758077,0.00005955107,0.0001016336,0.0002862142,0.00006632444],"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":[0.003418165,0.0009691389,0.06564085,0.0002310292,0.001082334,0.0001933122,0.0001781577,0.4923647,0.009261232,0.0007717546,0.006489885,0.4193995],"study_design_scores_gemma":[0.00003462758,0.0003795099,0.01447803,0.00001927977,0.0001259339,0.00003738418,0.00009996027,0.9792392,0.00463675,0.000327185,0.0006030817,0.00001904561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787369,0.001577549,0.01395808,0.0003404992,0.0001482109,0.00005234335,0.0005558607,0.0007398789,0.003890754],"genre_scores_gemma":[0.9878231,0.0003561853,0.008270834,0.00009512591,0.00003645737,0.00002664309,0.001510804,0.00003205536,0.001848717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04435728,"threshold_uncertainty_score":0.08819818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07454239884039006,"score_gpt":0.275894950300728,"score_spread":0.2013525514603379,"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."}}