{"id":"W3200742127","doi":"10.1109/lgrs.2021.3112198","title":"Exploiting Spectral–Spatial Information Using Deep Random Forest for Hyperspectral Imagery Classification","year":2021,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Space Agency","keywords":"Hyperspectral imaging; Random forest; Artificial intelligence; Overfitting; Computer science; Pattern recognition (psychology); Spatial analysis; Convolutional neural network; Contextual image classification; Deep learning; Support vector machine; Remote sensing; Artificial neural network; Image (mathematics); Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000703795,0.001004562,0.0007969365,0.001390175,0.0003399699,0.0004485208,0.0008560646,0.0007073814,0.0009893384],"category_scores_gemma":[0.0008656304,0.0002672167,0.0009299452,0.001472682,0.0003682454,0.001139922,0.00052694,0.0008639803,0.0004942126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000434306,"about_ca_system_score_gemma":0.0005937245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006372906,"about_ca_topic_score_gemma":0.009313272,"domain_scores_codex":[0.9996608,0.00006013718,0.00001706712,0.0000922812,0.0001011597,0.00006846661],"domain_scores_gemma":[0.9996743,0.0001014198,0.00005194973,0.00005747767,0.00009496033,0.00001983379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002069789,0.0002387478,0.004370077,0.0001370727,0.0001397076,0.0001275693,0.00007872983,0.2296906,0.02763375,0.003691977,0.005958182,0.7277266],"study_design_scores_gemma":[0.000005702047,0.00001868636,0.0005781219,0.000005838263,0.0000156763,0.00003591987,0.000009234589,0.9933861,0.003470345,0.001752046,0.0007129659,0.000009393155],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04275072,0.0009206958,0.9528276,0.0001949713,0.00004844816,0.00003133575,0.0001621541,0.001733418,0.001330542],"genre_scores_gemma":[0.615178,0.0008427925,0.3790767,0.0002654684,0.0001038053,0.00008218482,0.001520801,0.0001563334,0.002773956],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006372906,"threshold_uncertainty_score":0.01267159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02148102911426475,"score_gpt":0.2306347873943891,"score_spread":0.2091537582801243,"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."}}