Fusing machine learning for fault detection with stochastic optimization to orchestrate robust, resource-aware maintenance schedules under uncertainty.
Using operations research methodologies, we are developing new tools for observatory operations.
We aim to fuse open satellite data with local socio-environmental indicators in the Exploradores Valley, building explainable, uncertainty-aware metrics for territorial management on top of a governed, reproducible data platform.
A hybrid ecosystem and governance model that turns field station data into reliable, reusable, and decision-ready assets across UC's RCER network, using ECHO for local orchestration and SAVIIA for online governance.
Developing a cloud-based analytical platform to optimize predictive and prescriptive maintenance across industrial systems.
We are studying data-driven prioritization models that can help hospitals manage their oncology waiting lists with application in the South Eastern Metropolitan Health Service
FONDECYT Regular project. Developing resource cost-aware scheduling solutions to optimize performance under uncertainty, with applications in astronomy and other industries.
Using deep learning spatial-temporal graph models for seasonal forecasting of extreme temperature events.
We are combining machine learning and stochastic optimization tools to develop optimal energy management systems for fotovoltaic generation with storage.