Selected Publications

Wind power is the Non-Conventional Renewable Energy that has become more relevant in recent years. Given the stochastic behavior of wind speed it is necessary to have efficient prediction models at different horizons. Several kind of models have been used to forecast wind power, but using the same kind of model to forecast at different horizons is not recommendable, therefore a multi-model system needs to be implemented. We propose an scalable wind power forecasting system for multiple horizons using open source software, focusing on the forecast model selection, validated with Chilean wind farms data. Showing that RNN models can make significantly better forecasts than traditional models and can scale easily.
In IWAIPR, 2018

Performing astronomical data analysis using only personal computers is becoming impractical for the very large data sets produced nowadays. As analysis is not a task that can be automatized to its full extent, the idea of moving processing where the data is located means also moving the whole scientific process towards the archives and data centers. Using Jupyter Notebooks as a remote service is a recent trend in data analysis that aims to deal with this problem, but harnessing the infrastructure to serve the astronomer without increasing the complexity of the service is a challenge. In this paper we present the architecture and features of JOVIAL, a Cloud service where astronomers can safely use Jupyter notebooks over a personal space designed for high-performance processing under the high-availability principle. We show that features existing only in specific packages can be adapted to run in the notebooks, and that algorithms can be adapted to run across the data center without necessarily redesigning them.
In Astronomy and Computing, 2018


More Publications

Multi-horizon Scalable Wind Power Forecast System

Notebook-based Astronomical Data Analysis in the Cloud

Chilean Virtual Observatory

Towards Large-Scale RoI Indexing for Content-Aware Data Discovery

PDF Chilean Virtual Observatory

JOVIAL: Jupyter OVerrIde for Astronomical Libraries

PDF Chilean Virtual Observatory


Programming Languages

Python, R, C/C++, Matlab


Working with frequentist statistics and data driven models.


Spanish, English, German.