{"id":"W4409318887","doi":"10.1038/s43247-025-02160-0","title":"High-resolution naturalness mapping can support conservation policy objectives and identify locations for strongly protected areas in France","year":2025,"lang":"en","type":"article","venue":"Communications Earth & Environment","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bell (Canada)","funders":"Université de Toulouse; University of Leeds; Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement; UK Research and Innovation","keywords":"Naturalness; Environmental resource management; Resolution (logic); Nature Conservation; Geography; Computer science; Environmental planning; Remote sensing; Environmental science; Physics; Artificial intelligence; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001213727,0.0003297281,0.0001825575,0.002580042,0.0006134157,0.001646866,0.0003256947,0.0005535898,0.004318225],"category_scores_gemma":[0.002580785,0.0001132175,0.0002841663,0.001945455,0.0003729529,0.0007369638,0.001034168,0.0002489962,0.0005891409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00112024,"about_ca_system_score_gemma":0.001116803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07363832,"about_ca_topic_score_gemma":0.1316179,"domain_scores_codex":[0.999312,0.000371427,0.00001871689,0.00009422611,0.0001060826,0.00009756174],"domain_scores_gemma":[0.998619,0.0006415131,0.0001877632,0.0001879128,0.0002946069,0.00006929485],"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":[0.0004708183,0.0002312524,0.2936832,0.0004987037,0.0001967732,0.001385632,0.009137153,0.1415603,0.02032019,0.02702443,0.0294723,0.4760192],"study_design_scores_gemma":[0.00007460782,0.0001898436,0.5561828,0.0004552804,0.0001006702,0.0005271698,0.009809529,0.2222177,0.007698729,0.01606144,0.1864596,0.0002226053],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.848322,0.0009141139,0.0863948,0.001831272,0.00007219939,0.0002220583,0.007456876,0.00169911,0.05308753],"genre_scores_gemma":[0.9372818,0.0001709959,0.05720467,0.00007304661,0.00001612,0.0001094758,0.002444619,0.0000693003,0.002629962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07363832,"threshold_uncertainty_score":0.1464194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01383499372922193,"score_gpt":0.2496872954603326,"score_spread":0.2358523017311107,"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."}}