Blog
Hands-on articles about GeoAI, computer vision, remote sensing, data science and operations research.
20 articles
RAG projects rarely fail for lack of data; the problem usually lies in whether the retrieval method can support questions that depend on relationships between entities. In this article, I compare a traditional vector RAG with a geospatial GraphRAG built on Op…
When people talk about automation in geoprocessing, they usually picture a script running in a loop or a bot answering predefined commands. In critic…
When I started combining large language models (LLMs) with geographic data, my first temptation was to treat latitude and longitude as "just two more…
While reading a paper on multivariate solar power forecasting with multilevel data fusion, one practical idea kept coming back to me, that with large…
AI models for remote sensing deliver increasingly impressive results on academic benchmarks, but moving them into operational environments, where rea…
It's been a long time since I last posted here on the blog. But recently, while looking at search trends on Google Trends, I noticed a remarkable ris…
While working with a radar imagery dataset provided by ICEYE, an innovative company in synthetic aperture radar (SAR) technology, I ran into noisy, l…
Training AI models often means working close to the state of the art, yet we still have to estimate how long it will take to get a model into product…
Working with data from the Sensor Data Management System (SDMS), provided by the US Air Force, is a really interesting challenge. In this post, I tra…
Many people starting out in data science don't know how those neat, ready-to-use image samples for training deep learning models are actually produce…
As part of my MBA in Operations Research and Decision Making, I turned a class assignment into a real decision problem, choosing a new high-performan…
It is no secret that Brazil's agricultural industry is booming, and much of that is thanks to the trend and production cycle analyses that help produ…
One of the most common questions among people starting out in data analysis is where to get the data they need for their work. Here I list some of th…
A friend who owns a truck fleet asked me to help distribute deliveries so that each truck would use as much of its space and weight capacity as possi…
On a sunny day in the middle of the Brazilian semi-arid region, a representative of Fintech λλ reached out asking me to improve their customer credit…
Telecom companies rely on analyses of customer dissatisfaction to retain and win customers. In this project I build a churn prediction model from scr…
Credit card fraud is one of the main concerns of financial institutions. In this post, I explore a dataset of European card transactions and build a …
Environmental preservation, and our wildlife in particular, has always interested me. In this project, I use Facebook's Prophet framework and Austin …
Ah, Rio de Janeiro, what a marvelous city! But not everything is rosy. In this exploratory analysis of public crime data from ISP-RJ, I look at vehic…
Airbnb is already considered the largest hospitality company in the world, yet it does not own a single hotel. In this post, I run an exploratory ana…
No articles match your search.
