{"id":"W4415699064","doi":"10.1016/j.eiar.2025.108245","title":"Integrating participatory GIS, remote sensing, and explainable machine learning to assess forest provisioning services","year":2025,"lang":"en","type":"article","venue":"Environmental Impact Assessment Review","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council; Cornell Atkinson Center for Sustainability, Cornell University; David R. Atkinson Center for a Sustainable Future , Cornell University; Social Sciences and Humanities Research Council of Canada; International Development Research Centre; McKnight Foundation","keywords":"Provisioning; Livelihood; Random forest; Geospatial analysis; Vegetation (pathology); Participatory sensing; Forest inventory; Citizen journalism; Index (typography)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009270185,0.000480293,0.0005700493,0.00006336071,0.000479325,0.0001819714,0.0002631097,0.0001003337,0.000475747],"category_scores_gemma":[0.00007728767,0.0003514031,0.0001439647,0.0003830685,0.0001187581,0.0004146678,0.0007495622,0.0005454965,0.0001314652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009995711,"about_ca_system_score_gemma":0.00002344166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001472106,"about_ca_topic_score_gemma":0.0003276789,"domain_scores_codex":[0.9972076,0.0003745698,0.0005566471,0.0007147024,0.0005267796,0.0006196425],"domain_scores_gemma":[0.9988649,0.0001211417,0.0002551158,0.0004452798,0.000005606843,0.0003079764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001950456,0.0001496538,0.4702215,0.001344757,0.0001290531,0.00007239458,0.0007660131,0.004037281,0.03248476,0.00002015657,0.002775141,0.4879798],"study_design_scores_gemma":[0.0007044866,0.000518957,0.7689328,0.01089398,0.0003734141,0.0001407063,0.001105457,0.1121907,0.001097891,0.0001881484,0.1025953,0.001258202],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9690527,0.01141612,0.007342965,0.001143623,0.0001740106,0.001920121,0.000008608565,0.0001589629,0.008782874],"genre_scores_gemma":[0.9598408,0.00708723,0.02919453,0.002173622,0.00003597883,0.00000512381,0.00008064999,0.00004424066,0.001537866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4867216,"threshold_uncertainty_score":0.9998938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01618482653077884,"score_gpt":0.3222563624580064,"score_spread":0.3060715359272276,"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."}}