{"id":"W4406880555","doi":"","title":"Améliorer la fiabilité des modèles d'apprentissage profond en vue d'accroitre l'observabilité des installations photovoltaïques en toiture en France","year":2024,"lang":"en","type":"dissertation","venue":"theses.fr (ABES)","topic":"Photovoltaic System Optimization Techniques","field":"Energy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"","keywords":"Observability; Photovoltaic system; Reliability (semiconductor); Reliability engineering; Deep learning; Engineering; Computer science; Environmental science; Architectural engineering; Artificial intelligence; Electrical engineering; Mathematics; Physics; Power (physics)","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":[0.0017204,0.001266281,0.001024748,0.0005956165,0.0006170007,0.002214746,0.001454851,0.001684063,0.003863544],"category_scores_gemma":[0.006007305,0.0007049489,0.001417509,0.0004366737,0.0005222035,0.001512823,0.0008233273,0.002023896,0.0007111656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001291268,"about_ca_system_score_gemma":0.002318487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05410315,"about_ca_topic_score_gemma":0.03695465,"domain_scores_codex":[0.9993605,0.0001786613,0.00003223371,0.0001877951,0.000141952,0.00009874386],"domain_scores_gemma":[0.997804,0.001335537,0.0001252276,0.0001672151,0.0005033819,0.00006463968],"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":[0.00008053106,0.00004734646,0.002121593,0.00005606061,0.00003885421,0.00002666003,0.00005531795,0.9733022,0.0008980081,0.000796831,0.0004086143,0.02216795],"study_design_scores_gemma":[0.000006767421,0.0000199668,0.000240725,0.000007924187,0.000008226017,0.000004230621,0.00001249137,0.9984671,0.0005484401,0.0002713369,0.0004088901,0.000003841136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.317759,0.001351665,0.662357,0.001097577,0.0002914098,0.0001841641,0.0007957972,0.005223491,0.01093981],"genre_scores_gemma":[0.8773498,0.0004228668,0.1146425,0.0001401065,0.0000357846,0.0001849141,0.0007690482,0.0002605977,0.006194451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05410315,"threshold_uncertainty_score":0.1075764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01038324598784931,"score_gpt":0.264005627110968,"score_spread":0.2536223811231187,"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."}}