{"id":"W7083578569","doi":"10.1016/j.enconman.2025.120565","title":"Advancing predictive modeling in conventional solar stills: a deep learning approach leveraging data augmentation and convolutional neural networks","year":2025,"lang":"en","type":"article","venue":"Energy Conversion and Management","topic":"Solar-Powered Water Purification Methods","field":"Energy","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"University of British Columbia; King Abdulaziz University","keywords":"Kriging; Convolutional neural network; Gaussian process; Artificial neural network; Hyperparameter; Deep learning; Multilayer perceptron; Mean squared error; Kernel (algebra)","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":[],"consensus_categories":[],"category_scores_codex":[0.0006856347,0.0001732741,0.0001783262,0.0003147539,0.0002363894,0.00007238219,0.0001846503,0.00007570477,0.00003541668],"category_scores_gemma":[0.00003064384,0.0001915284,0.00002562549,0.0002427213,0.00005869567,0.0004137599,0.0005071826,0.0001852436,7.088097e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201216,"about_ca_system_score_gemma":0.00001452073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003009491,"about_ca_topic_score_gemma":0.00002668044,"domain_scores_codex":[0.9983245,0.0002857101,0.0003176599,0.0006052192,0.0002043341,0.0002625715],"domain_scores_gemma":[0.9994712,0.00008443673,0.00008619235,0.0002414849,0.00004662095,0.00007000751],"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":[0.0001311112,0.00005219352,0.002136706,0.00008957922,0.0001211277,0.000006731686,0.0002455065,0.9268159,0.00004602978,0.02633647,0.0001473007,0.04387135],"study_design_scores_gemma":[0.001674486,0.00001639307,0.002319571,0.00006002081,0.00005690254,0.000003004806,0.001729126,0.985898,0.00002020601,0.0006794035,0.007381259,0.0001616116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01615121,0.001088378,0.9792073,0.0002012336,0.0003147267,0.0001813611,0.000002490918,0.00008920395,0.002764053],"genre_scores_gemma":[0.9807696,0.0009710027,0.01621742,0.0004071872,0.0000412723,0.00004789188,0.0005636663,0.00001570762,0.0009662521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646184,"threshold_uncertainty_score":0.7810301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02581129381472135,"score_gpt":0.2681796764992647,"score_spread":0.2423683826845433,"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."}}