Author Image

Hi, I am Juan

Juan Martín Marcenaro

Geospatial Consultant

Hello! I’m Juan Martín, a civil engineer with a strong passion for earth sciences. As a Geospatial Consultant, I specialize in:

  • Remote Sensing and GIS: Utilizing satellite and aerial imagery to analyze and interpret geographical data.

  • Geospatial Data Science and Statistics: Applying data science techniques to understand and solve complex geospatial problems.

  • Machine Learning Models: Developing predictive models to uncover patterns and drive insights.

  • Web Tools and Integrations: Creating functional and user-friendly web applications to enhance data accessibility and integration.

To support these specializations, I bring advanced skills in: QGIS, Python, GDAL, Google Earth Engine, JavaScript, Node.js, SQL, Git, HTML and CSS.

These skills enable me to deliver high-quality results and innovative solutions in my work. Feel free to explore my portfolio and get in touch if you’d like to discuss how we can work together!

Recent Posts

Hero Image
GOES Visualizer

Project Overview In this opportunity we’ll go over a project developed through the combination of Google Earth Engine and Node.js once again. Data we’ll be retrieved and processed through GEE Python API and afterwards served to a local website interface using Node.js We’ll walk through: Retrieving and processing data from Google Earth Engine using Python, serving this data through a local Node.js server and, building a responsive dashboard for data visualization.

Friday, September 27, 2024 Read
Hero Image
Calculate slopes from a DEM using GDAL and Python

Project Overview In this post, we’ll explore the capabilities of GDAL tools alongside Python to automate the process and calculate the mean slope of multiple basins from a Digital Elevation Model (DEM). To begin with, we’ll need to set up an Anaconda environment with GDAL installed in it. I strongly recommend following the steps detailed in this tutorial. The project is reproducible and available on my (Github repository)[https://github.com/jm-marcenaro/Personal-blog-posts], feel free to visit!

Friday, September 27, 2024 Read
Hero Image
GFS Dashboard

Project Overview In this opportunity we’ll go over a project developed through the combination of Google Earth Engine and Node.js. Data we’ll be retrieved and processed through GEE Python API and afterwards served to a local dashboard using Node.js We’ll walk through: Retrieving and processing data from Google Earth Engine using Python, serving this data through a local Node.js server and, building a responsive dashboard for data visualization. By the end of this project, you’ll learn how to integrate these powerful tools to visualize complex geospatial datasets in real time.

Thursday, September 26, 2024 Read
Hero Image
GEE Python API: NDVI, precipitation and real evapotranspiration

Project Overview In this post, we’ll explore the correlation between multiple environmental data variables using the Google Earth Engine (GEE) Python API. Specifically, we’ll analyze yearly aggregated Normalized Difference Vegetation Index (NDVI), precipitation, and real evapotranspiration (ETr) over a region of interest spanning approximately 5,000 km² and over a five-year period (2019-2023). NDVI data will be extracted from the Sentinel-2 satellites. Precipitation data will be sourced from the CHIRPS dataset. Real evapotranspiration (ETr) data will be obtained from the MODIS satellite.

Monday, September 2, 2024 Read
Hero Image
QGIS: Batch Processing

Project Overview In this tutorial, we’ll explore the capabilities of batch processing in QGIS. Batch processing is incredibly helpful for repetitive tasks that can otherwise consume a lot of time and effort. By automating these tasks, you can focus on more important aspects of your project, increasing both efficiency and productivity. Let me set up an example where we’ll fully leverage the power of batch processing in QGIS. Case Example We’ve got a set of 12 MODIS land surface temperature (LST) images for an area of interest.

Tuesday, August 20, 2024 Read
Hero Image
GEE Python API and CHIRPS: Analyzing precipitation in Buenos Aires - Part 2

Project Overview In this post, we continue our exploration of the 2023 severe drought in Buenos Aires province, Argentina. In our previous post, we used the CHIRPS dataset to analyze the extent and impact of the drought. Now, we’ll take our analysis a step further by extracting time series data from specific coordinates within the affected region. To ensure that you can follow along and reproduce the results, all the code used in this analysis is available in my GitHub repository.

Thursday, August 15, 2024 Read