We shared lessons from UC’s Data Science Initiative on building reliable, trusted data infrastructures for field science, presenting SAVIIA (hybrid local–cloud architecture & governance) to connect RCER stations’ scientific and operational data and turn them into reproducible, reusable research assets.
An argument for moving from prediction to prescription where high-quality data, explicit uncertainty, and decision governance can turn models into actions that withstand scrutiny.
At Notre Dame’s inaugural RISE AI Conference, I joined the 'Impact of AI in Latin America' panel to discuss equitable AI development -- data governance, capacity building, compute access, and collaborative models for public-good applications.
Conversation with PLANEO Magazine on how data science can support just and sustainable cities, from descriptive, predictive, and prescriptive analytics to governance, equity, and collaboration.
Interview featured in *El Mercurio - Chile Tecnológico* highlighting how data science tools tripled oncology patient care in a pilot project at Hospital de La Florida, developed in collaboration with Universidad Católica.
At PASC 2025, I presented our work on building a trusted and scalable data infrastructure to support the Regional Field Stations Network (RCER) at Universidad Católica. The talk introduced SAVIIA—a platform that integrates scientific and operational datasets across distributed field stations using structured governance, local orchestration tools, and cloud-based pipelines. By improving data reliability, accessibility, and integration, the initiative aims to empower researchers, foster interdisciplinary collaboration, and enhance reproducibility in field-based science.
A hybrid local–cloud platform and governance model that turns field-station data into reliable, reusable, and decision-ready assets across UC’s RCER network.
In this presentation, I summarized our work on connecting prediction and prescription in energy management for residential microgrids, using stochastic optimization and machine learning to improve decision-making under uncertainty in systems with variable generation and storage.
Opinion piece in *El País* exploring how data-driven innovation can improve oncology waitlist management in Chile through digitalization, automation, and optimization.