{"id":"W4399039669","doi":"10.1109/m2garss57310.2024.10537455","title":"Boreal biome wetland classification using multi-seasonal EO data on gee and machine learning optimization/XAI modelling","year":2024,"lang":"en","type":"article","venue":"","topic":"Peatlands and Wetlands Ecology","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ducks Unlimited Canada","funders":"","keywords":"Wetland; Biome; Gee; Remote sensing; Boreal; Environmental science; Random forest; Python (programming language); Computer science; Satellite; Taiga; Machine learning; Meteorology; Artificial intelligence; Geography; Generalized estimating equation; Ecology; Engineering","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":[0.0006745163,0.0004202169,0.0002382517,0.0007200601,0.0002097283,0.0006726226,0.0004360824,0.0002568952,0.000712428],"category_scores_gemma":[0.001305624,0.0001511398,0.00055579,0.0006340795,0.0002229929,0.0004502306,0.0004496743,0.0004191609,0.0001916484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009001237,"about_ca_system_score_gemma":0.001002469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1039004,"about_ca_topic_score_gemma":0.1594692,"domain_scores_codex":[0.9998679,0.00004118178,0.000006759783,0.00003898087,0.00002202593,0.00002301111],"domain_scores_gemma":[0.9997734,0.0001019939,0.00002337727,0.00002582995,0.00005991661,0.0000153782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001173716,0.0001156591,0.05231099,0.00005936018,0.0001384996,0.000105663,0.0001242787,0.8627093,0.00396322,0.001549124,0.001200006,0.07760643],"study_design_scores_gemma":[0.000003317097,0.000007760639,0.01282697,0.00000523255,0.00000560334,0.00001149585,0.0000428043,0.9857106,0.0005036048,0.0004550586,0.000419581,0.000007922108],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9067867,0.000208036,0.0865057,0.0003243183,0.00003001522,0.00007984365,0.001432102,0.000970391,0.003662827],"genre_scores_gemma":[0.9488863,0.0000765275,0.0484053,0.00004304438,0.00001280638,0.00003922593,0.001369345,0.00007454969,0.001092885],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1039004,"threshold_uncertainty_score":0.2065912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09152186772083092,"score_gpt":0.2911607073981483,"score_spread":0.1996388396773174,"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."}}