{"id":"W3003585919","doi":"","title":"GainForest: Scaling Climate Finance for Forest Conservation using Interpretable Machine Learning on Satellite Imagery","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Satellite imagery; Remote sensing; Computer science; Satellite; Scaling; Artificial intelligence; Environmental science; Environmental resource management; Meteorology; Machine learning; Geography; Engineering; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0005235528,0.0002563307,0.0002281837,0.0001258076,0.0003439724,0.0002024647,0.0003178212,0.00008845307,0.0006510679],"category_scores_gemma":[0.0002392227,0.0002496598,0.0001147865,0.0001610648,0.0000845233,0.000284275,0.0001415148,0.0005911144,0.0007171104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002161699,"about_ca_system_score_gemma":0.00002450319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000632542,"about_ca_topic_score_gemma":0.0001184523,"domain_scores_codex":[0.9982128,0.00009193101,0.0003861145,0.0005253695,0.0004056426,0.0003781125],"domain_scores_gemma":[0.9990193,0.0002856958,0.0003259136,0.0002329572,0.00007160541,0.00006452427],"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":[0.0003785054,0.00007985166,0.338738,0.00002751205,0.00003520506,0.000004293499,0.0004040377,0.5846626,0.02144613,0.0149793,0.00004618809,0.03919838],"study_design_scores_gemma":[0.0004746475,0.0001582384,0.02081615,0.0001930836,0.00001076649,0.000008762092,0.00006571948,0.951432,0.000482116,0.0007601487,0.02532714,0.0002712613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9212744,0.00002749314,0.01695888,0.001259459,0.0003881988,0.0005168197,0.00004127057,0.0001538746,0.05937963],"genre_scores_gemma":[0.990384,0.0001061852,0.005198496,0.0005485784,0.00007234999,0.00001125415,0.0003133262,0.00004236582,0.003323441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3667693,"threshold_uncertainty_score":0.9999956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02441489553324444,"score_gpt":0.2833920555524063,"score_spread":0.2589771600191619,"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."}}