{"id":"W7029964224","doi":"","title":"Machine Learning for Biodiversity Monitoring from Remote Sensing and Citizen Science Data","year":2024,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Citizen science; Biodiversity; Environmental monitoring; Remote sensing application","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0011923,0.0006344438,0.0005446093,0.0005914214,0.001636425,0.0005012057,0.0008023112,0.0004695448,0.000007228998],"category_scores_gemma":[0.001622014,0.0007581843,0.000113898,0.0006878479,0.0001965161,0.001071832,0.0003663372,0.001834882,0.0001093486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000775377,"about_ca_system_score_gemma":0.00004842147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006504814,"about_ca_topic_score_gemma":0.0002265606,"domain_scores_codex":[0.9965301,0.0001020911,0.0005456796,0.001523198,0.0006507555,0.0006482468],"domain_scores_gemma":[0.9976902,0.0003741463,0.000208867,0.001129905,0.0003285422,0.0002683552],"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":[0.00004759017,0.000006487041,0.00001995042,0.000545079,0.0001505897,0.00004456597,0.00003662377,0.0003708643,0.3965023,0.0001207343,0.000007565659,0.6021476],"study_design_scores_gemma":[0.001102748,0.00007941692,0.002050929,0.002792608,0.001071389,0.0000567911,0.00101428,0.6040325,0.340326,0.008728588,0.0361628,0.002582031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9840723,0.001644491,0.0001613203,0.00001845054,0.004422898,0.0006699972,0.00244643,0.00135408,0.005210025],"genre_scores_gemma":[0.9722549,0.0007656727,0.02151361,0.00001415798,0.0001648973,0.0000012167,0.004155066,0.0002218512,0.0009086033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6036616,"threshold_uncertainty_score":0.9996633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03723037815256608,"score_gpt":0.2590012848459498,"score_spread":0.2217709066933837,"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."}}