{"id":"W7117532950","doi":"10.48550/arxiv.2512.21948","title":"Interpretable Machine Learning-Derived Spectral Indices for Vegetation Monitoring","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Discriminative model; Pairwise comparison; Polynomial; Feature (linguistics); Pattern recognition (psychology); Simple (philosophy); Feature selection; Base (topology); Product (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001119702,0.001159787,0.0005296476,0.00121713,0.0001907509,0.0009625725,0.0008886225,0.0005584113,0.002102303],"category_scores_gemma":[0.003721042,0.0003351504,0.000826014,0.001138215,0.0003871676,0.001407497,0.0006978529,0.001272346,0.001160956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005966449,"about_ca_system_score_gemma":0.0007667197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002491679,"about_ca_topic_score_gemma":0.00407359,"domain_scores_codex":[0.9995919,0.00008285768,0.0000280892,0.0001303984,0.000132933,0.00003372433],"domain_scores_gemma":[0.9990963,0.0003881819,0.0001414947,0.0001496863,0.0002013268,0.00002311775],"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":[0.0001810756,0.000268805,0.009365814,0.0003985834,0.0001274664,0.0001697443,0.0001882949,0.2277618,0.08566801,0.01823652,0.009120052,0.6485139],"study_design_scores_gemma":[0.00001579207,0.0000527745,0.003250571,0.00003470959,0.00002914365,0.00008166332,0.00005564962,0.9554917,0.01389408,0.02086398,0.006203346,0.00002656256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01910643,0.0004466713,0.9744415,0.0002374583,0.00002752803,0.00005388827,0.0009468535,0.003392966,0.001346764],"genre_scores_gemma":[0.2842465,0.0007922176,0.7069654,0.0001613833,0.00008058466,0.0002087189,0.005117569,0.000471057,0.001956587],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002491679,"threshold_uncertainty_score":0.007032931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05452183243591709,"score_gpt":0.1989603753915632,"score_spread":0.1444385429556461,"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."}}