采用超分辨率生成对抗方法的多重混合模型用于湍流反应流研究

该研究项目旨在开发一种动态混合模型，利用超分辨率生成对抗网络技术增强大涡动模拟能力，以预测氢气及可持续燃料火焰的燃烧现象，从而解决燃烧建模中的挑战。申请者应具备流体力学、编程及数据分析方面的技能，并拥有工程或应用数学领域的背景。

About the project AI for Zero-Carbon Combustion. Develop a dynamic mixed model powered by super-resolution GANs to predict hydrogen and sustainable-fuel flames in large eddy simulation. Combine deep learning, physics and exascale computing to help design future zero-carbon energy systems. Ideal for engineering, physics or maths graduates passionate about AI and fluids. Teach neural networks the physics of flames and help power a hydrogen future. Hydrogen and carbon-neutral fuels are key to net zero, but their flames are notoriously hard to predict. They switch between combustion regimes, develop intrinsic instabilities and push energy back up the scales. Today’s turbulence-combustion models can’t keep up. Your PhD will change that. You’ll advance a new hybrid approach: a dynamic mixed model powered by super-resolution GANs. It pairs the robustness of physics-based closures with AI’s ability to reconstruct unresolved small-scale flow features. The goal is large eddy simulation models that generalise beyond their training data, need less high-fidelity data and run on the world’s fastest supercomputers. What you’ll do generate DNS databases of hydrogen and sustainable-fuel flames push the super-resolution dynamic mixed model to new flame regimes and fuels build physics directly into the learning open the black box: discover what GAN discriminators really learn embed your models in a CFD code and validate them in real LES scale your work to exascale computing Why join us build on published, cutting-edge research work where AI, supercomputing and clean energy meet gain machine-learning, CFD and HPC skills prized by industry and academia Training will be provided on HPC, programming, machine learning, and fluid dynamics will be realized through participation in Summer Schools and European Training events (e.g. Cypher COST) The School of Engineering is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.

入学要求 英国2:1荣誉学位，或以下学科中的国际同等学位： 机械工程 航空航天工程 化学工程 能源工程 物理学 应用数学 理想的技能： 流体动力学 湍流 数据分析 编程经验（Python、C++或Fortran） 对人工智能与流体动力学的热爱

资助：竞争性资助 学费与资助 我们为英国本土学生和国际学生提供多种资助机会。符合条件的学生可通过“地平线欧洲”学费减免，自动免除国际学生学费与英国本土学生学费之间的差额。 大学通过竞争性遴选授予的校长助学金，为遴选排名靠前的申请人支付国际学生学费与英国本土学生学费之间的差额。 本校各学院通过竞争性遴选提供的博士奖助金，通常为遴选排名靠前的申请人支付按英国本土学生标准收取的学费，并提供生活津贴。 资助采用滚动授予方式，因此请尽早申请，以尽可能增加进入资助评选的机会。 如需了解更多信息，请访问我们的研究生研究资助页面。

如何申请 您需： 选择课程类型（研究型）、2027/28学年、工程与物理科学学院 选择全日制或非全日制 搜索工程与环境博士项目（7175） 在申请表第2部分填写导师姓名 申请材料应包括： 您的CV（个人简历） 2份学术推荐信 截至目前的学位课程成绩单和证书 英语语言资格证明（如适用）