{"id":"W4210548402","doi":"10.3390/rs14030698","title":"Deep Learning for Vegetation Health Forecasting: A Case Study in Kenya","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Natural Environment Research Council; Engineering and Physical Sciences Research Council; Institute for Catastrophic Loss Reduction; Sight Research UK; Lloyd's Register; Alan Turing Institute; Lloyd's Register Foundation","keywords":"Arid; Vegetation (pathology); Baseline (sea); Climatology; Environmental science; Surface runoff; Meteorology; Environmental resource management; Geography; Geology; Ecology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008917045,0.00006921678,0.0001359309,0.00006566753,0.0006289685,0.000009490769,0.00003874531,0.00001801592,0.00003834973],"category_scores_gemma":[0.00006962084,0.00007718107,0.00004087297,0.0003381484,0.00002166898,0.00005313054,0.00009036751,0.0001939595,0.000007506616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002564475,"about_ca_system_score_gemma":0.000009663467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003118315,"about_ca_topic_score_gemma":0.009643592,"domain_scores_codex":[0.9989235,0.0002897617,0.0001884835,0.0002395578,0.0001299141,0.0002288062],"domain_scores_gemma":[0.9996661,0.0001019723,0.00009516611,0.00009384054,0.000003130396,0.00003980305],"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":[0.00001861143,0.00003770016,0.01261536,0.000004827576,0.000009456123,0.0008231127,0.00959724,0.6851327,0.0000835979,5.443666e-7,0.000007532009,0.2916694],"study_design_scores_gemma":[0.0003579057,0.0002092814,0.000966709,0.000002737343,0.00001311034,0.0007429039,0.004772026,0.9923828,0.00000528321,0.0001604713,0.0003115978,0.00007514766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9762357,0.00003848067,0.02275612,0.0001824512,0.00004657482,0.0002794221,8.503071e-8,0.00002246834,0.0004387289],"genre_scores_gemma":[0.9946887,9.14353e-7,0.00501686,0.0001765062,0.00001768857,1.59961e-7,0.000003733883,0.000009855631,0.00008551194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3072502,"threshold_uncertainty_score":0.5381351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02937250579575604,"score_gpt":0.2806530265360655,"score_spread":0.2512805207403094,"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."}}