Nursulu Kuzhagaliyeva

ORCID: 0000-0003-1367-0890
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Combustion Engine Technologies
  • Vehicle emissions and performance
  • Machine Learning in Materials Science
  • Catalysis and Oxidation Reactions
  • Air Quality Monitoring and Forecasting
  • Energy, Environment, and Transportation Policies
  • Protein Structure and Dynamics
  • Chemical Thermodynamics and Molecular Structure
  • Computational Drug Discovery Methods
  • Fire Detection and Safety Systems
  • Heat transfer and supercritical fluids
  • Combustion and flame dynamics
  • Biodiesel Production and Applications

King Abdullah University of Science and Technology
2020-2024

Kootenay Association for Science & Technology
2024

High-performance fuel design is imperative to achieve cleaner burning and high-efficiency engine systems. We introduce a data-driven artificial intelligence (AI) framework liquid fuels exhibiting tailor-made properties for combustion applications improve efficiency lower carbon emissions. The approach constrained optimization task integrating two parts: (i) deep learning (DL) model predict the of pure components mixtures (ii) search algorithms efficiently navigate in chemical space. Our...

10.1038/s42004-022-00722-3 article EN cc-by Communications Chemistry 2022-09-16

Deep learning models are being widely used in the field of combustion. Given black-box nature typical neural network based models, uncertainty quantification (UQ) is critical to ensure reliability predictions as well training datasets, and for a principled noise its various sources. However, uncertainties developed seldom quantified, which primarily attributed huge incremental cost adding UQ already computationally expensive deep models. In this work, methods with different ranges...

10.1016/j.jaecs.2023.100211 article EN cc-by-nc-nd Applications in Energy and Combustion Science 2023-09-24

<div class="section abstract"><div class="htmlview paragraph">The accurate prediction of engine performance maps can guide data-driven optimization technologies to control fuel use and associated emissions. However, operational are scarcely reported in literature often have missing data. Assessment missing-data resilient algorithms the context data could enable better processing real-world driving cycles, where is a more pervasive phenomenon. The goal this study is, therefore,...

10.4271/2024-01-2016 article EN SAE technical papers on CD-ROM/SAE technical paper series 2024-04-09
Coming Soon ...