Integrating remote sensing, machine learning, and advanced ocean modeling for the improved prediction of coastal change

集成遥感、机器学习和先进的海洋建模，以改进海岸变化的预测

• 批准号: 2618981
• 金额: --
• 依托单位: Imperial College London
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2618981
• 关键词: Integrating; remote; sensing; machine; learning

The research focuses on the use of computational techniques to develop a better understanding of the coastal environment. This project covers a wide scope and thus allows for flexibility in where to target my research on. Some of the reasons why the prior techniques are specified are due to the possibility of using real-world data such as remote sensing imagery to drive improvements in our models through machine learning techniques.Some of the current ongoing key projects within my PhD are developing improved bathymetric data covering the Chagos Archipelago and its application for understanding fluid flow through the region which can, in turn, support further research in understanding erosion patterns, the flow of materials/nutrients, etc. Another major concept being explored focuses on the usage of physics-driven machine learning algorithms to allow for a cheap/fast prediction of an expensive flow model for changes/perturbations in the local conditions.

研究的重点是利用计算技术，以更好地了解沿海环境。这个项目涵盖了广泛的范围，因此允许灵活性，在哪里针对我的研究。一些原因，为什么以前的技术是由于使用真实的的可能性，世界数据，如遥感图像，以推动我们的模型通过机器学习技术的改进。我的博士学位目前正在进行的一些关键项目正在开发改进的测深数据，涵盖查戈斯群岛及其该应用程序用于了解通过该区域的流体流动，这反过来又可以支持进一步研究，以了解侵蚀模式，材料/营养物质的流动等。正在探索的另一个主要概念集中在使用物理驱动的机器学习算法，以允许廉价/快速预测昂贵的流动模型，以适应当地条件的变化/扰动。