{"id":"W4417078149","doi":"10.1080/17538947.2025.2594247","title":"Deep learning for multi-source precipitation fusion on the Qinghai–Tibet Plateau","year":2025,"lang":"en","type":"article","venue":"International Journal of Digital Earth","topic":"Precipitation Measurement and Analysis","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute on Governance","funders":"National Key Research and Development Program of China; Key Technologies Research and Development Program; National Natural Science Foundation of China","keywords":"Precipitation; Plateau (mathematics); Deep learning; Convolutional neural network; Mean squared error; Rain gauge; Correlation coefficient; Feature (linguistics); Water cycle","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":[],"consensus_categories":[],"category_scores_codex":[0.0004228746,0.00008450027,0.0001062465,0.0002247211,0.0001242029,0.0003154284,0.0003011435,0.00003095413,0.0002007716],"category_scores_gemma":[0.0007786427,0.00005552412,0.0001549895,0.000130816,0.00002944637,0.0004474169,0.000009496782,0.0001526248,0.00004164269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008809669,"about_ca_system_score_gemma":0.00003985437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001082804,"about_ca_topic_score_gemma":0.0000819572,"domain_scores_codex":[0.9989716,0.00004647811,0.0003145766,0.00009818946,0.0004621019,0.0001070015],"domain_scores_gemma":[0.9987581,0.0004833362,0.0002611901,0.00004969579,0.000406525,0.00004109089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000518925,0.00009621522,0.2747043,0.000008931916,0.0004883669,0.000005822447,0.0006998617,0.1747187,0.0002299766,0.0007483833,0.0007185402,0.547062],"study_design_scores_gemma":[0.0026172,0.0006766498,0.460342,0.0003502239,0.0001067474,0.00001755537,0.001718601,0.4750207,0.001208467,0.004521334,0.05311628,0.000304206],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.825008,0.0003129404,0.157894,0.003884893,0.001437781,0.0002104735,0.00002834011,0.0000272756,0.01119636],"genre_scores_gemma":[0.996788,0.00002668911,0.0007143789,0.0002631126,0.0001587808,6.163386e-7,0.00005471642,0.000002442395,0.001991278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5467578,"threshold_uncertainty_score":0.3041683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03105661387133226,"score_gpt":0.2668438159151829,"score_spread":0.2357872020438506,"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."}}