Sort by
Refine Your Search
-
emergency responders. By combining global landslide data, innovative machine‑learning methods, and new ways of representing runout, the research will produce faster and more reliable nowcasts for use
-
theory, Bayesian inference, Monte Carlo simulation, and statistical analysis of subjective data. Data science and machine learning - big data analytics, surrogate modelling, digital twin development, and
-
UKRI rate). Overview This PhD aims to improve risk assessment and mitigation of high-impact and damaging weather events by developing catastrophe model methods, and adjustment factors to address current
-
on epithelial barrier integrity, inflammation, and host transcriptional responses. The project offers interdisciplinary training in bioinformatics, advanced statistics and machine learning, anaerobic microbiology
-
the Intelligent Systems Research group (with extensive experience in deploying machine learning models for edge devices and microcontrollers and building simulation environments for IoT), and our extensive network
-
, this PhD project aims to: (i) develop physics-informed machine learning (PIML) approaches to construct surrogate models of deep geothermal systems that accurately reproduce the behaviour of high-fidelity
-
: · Learning how to express software requirements precisely using formal models. · Using these specifications to automatically generate test cases for software systems and code. · Exploring how test
-
machine learning and AI research. Strong analytical thinking, problem-solving skills, and the ability to engage with complex data challenges will be greatly valued. Experience with Python or AI frameworks