I am an cloud data specialist who loves using technology to improve science. I blend the latest cloud data ingestion, orchestration and analysis tools to optimize scientific workflows.
I use data management, statistical models and geospatial tools to process complex and large environmental data analysing and uncovering hidden patterns in data. I am very passionate about teaching and applying reproducible research and the use of open source programming languages to analyse and visualise data.
PhD Natural and Physical Sciences (Geochemistry), 2021
James Cook University, Australia
Master in Geography (Postgraduate Fulbright Scholar), 2017
University of Georgia, United States
B.S. in Chemistry, 2014
Universidad de Costa Rica, Costa Rica
B.A. in Anthropology, 2013
Universidad de Costa Rica, Costa Rica
Azure Data Factory, Synapse Analytics, Azure Blob Storage, Azure Machine Learning, Azure Databricks, Git, GitHub
Python and R to perform supervised and unsupervised data mining techniques. Bayesian modelling and Soil and Water Assessment Tool (SWAT). Use of decision trees, random forest, K neighbors and XG Boost to predict environmental indicator
Apache Spark and Databricks
Reproducible and open science using RMarkdown, Jupyter Notebooks and Git. Application of the FAIR Data Principles and use of Relational Databases (SQL)
Cloud fundamental concepts and hands on tutorials. Data science subjects and workshops: The Carpentries R for Reproducible Scientific Analysis, Statistical Comparisons, Data Visualisation, Data Mining and Foundations of Data Science. Sample of teaching slides
Geoprocessing, spatial statistics, remote sensing using Python