Assessing the impact of forest management alternatives on wildfire resistance.An application to forest stands in Vale do Sousa, Portugal.

Deep Learning Approaches for OEE Forecasting: a Semiconductor Manufacturing Case Study

La diffusione di dispositivi informatici e di rilevamento basati su semiconduttori ha reso l'industria manifatturiera dei semiconduttori molto esigente. È diventato fondamentale ottimizzare i processi produttivi, individuando le possibili perdite di efficienza produttiva. Questi possono essere misurati mediante la misura dell'efficienza complessiva delle apparecchiature (OEE). Pertanto, essere in grado di prevedere i valori del futuro OEE può migliorare la produzione in modo efficiente. Quest...

Floquet counterdiabatic protocols for Quantum Annealing on Parity architecture

Combinatorial Optimization problems can be addressed with quantum computing techniques: the solution of an optimization problem can be encoded in the ground state of a quantum spin system, which in turn can be experimentally prepared through a suitable algorithm like Quantum Annealing. Still, annealing applications have to face several challenges. Firstly, the limited spin connectivity of current hardware requires the use of clever encoding strategies. In this sense, the Parity architecture c...

AI BASED DETECTION OF LUNAR SINUOUS RILLES AND COMPARISION WITH MANUAL DETECTION METHODS

Lunar sinuous rilles are thought to be lava channels or collapsed lava tubes formed during mare volcanism. A global distribution map cataloguing the rilles will help us in understanding the type of volcanism and lava flow viscosity, as well as detect potential lava tube entries and decide the safer landing spots for future moon missions. In this progressing project, using the SELENE KAGUYA multiband images and the survey conducted in 2013 that catalogued nearly 200 sinuous rilles on the Moon’...

Development and calibration of a predictive physics-based model for solar array power degradation in spacecraft

Accurate modeling and simulation of solar array power degradation in spacecraft is essential for mission planning, remaining useful life assessment, and lifetime extension. A relevant example is European Space Agency (ESA)’s Cluster spacecraft fleet, launched in 2000 and operated at the European Space Operation Centre (ESOC), whose solar arrays have suffered severe degradation due to space radiation causing challenges to routine operations. However, currently available physics-based and machi...

Incorporating Machine Learning for Value-Based Pricing: An Innovative Framework Combining Quotation and Sales Analytics

This thesis explores a novel approach to pricing strategy, enriching the domain of value-based pricing within the context of B2B companies. By integrating advanced data science and machine learning techniques, the research harnesses the power of quotation data to provide a methodology incorporating both quote acceptance probabilities and price point simulations. This innovative approach promises to offer businesses in the B2B sector a deeper understanding of customer price sensitivity, enabli...

Modelling carbon dynamics in Lagrangian oceanic ecosystems: applications to fertilization experiments and mesoscale eddies

Marine plankton play a crucial role in carbon storage, global climate, and ecosystem function. Planktonic ecosystems are embedded in patches of water that are continuously moving, stretching, and diluting. In this work, we present an ecosystem model that describes biomass production and carbon dynamics within a Lagrangian patch in the ocean. First, we illustrate its theoretical background from both a physical and biological perspective. Then, we show that our framework is able to reproduce ob...

Anomaly detection of multivariate time series for industrial machinery

In industrial contexts, anomaly detection is crucial for identifying deviations from normal operating conditions, ensuring proactive maintenance, minimising downtime, and optimising the reliability and efficiency of industrial processes. Advanced machinery, constantly monitored by diverse sensors, generates multiple temporal sequences of data that can be analysed for evaluating performance. Within this setting, this thesis delves into a real-world scenario, focusing on the analysis of multiva...

Combining IDA ICE and MATLAB: co-simulation environment for advanced control strategies in buildings

The energy building sector is at the forefront of modern efforts to improve energy efficiency and user comfort. As buildings become more complex and dynamic, the need for advanced control strategies and precise simulation tools becomes increasingly important. This work addresses the critical challenge of developing a dedicated co-simulation environment for integrating advanced controllers. By combining IDA ICE as building energy simulation software and MATLAB for controller design, the resear...