Technical blog
Data engineering, geoinformation and real-world practices.
Technical notes on ETL, Python, PostgreSQL/PostGIS, spatial analysis and lessons learned from production projects.
From orders to a logistics network: an optimization and machine learning project
What I built, how the algorithms connect, and what the capacitated facility location experiments demonstrate.
MILP: turning a logistics decision into a verifiable model
Variables, constraints, capacity, and costs: build the three-center example and verify its optimum.
Linear relaxation: how much better could a solution become?
Learn to interpret bounds, gaps, and capacity sensitivity without mistaking a fractional solution for an operational network.
Greedy and local search: build quickly, then improve deliberately
How immediate choices, neighborhood moves, and local optima work in capacitated assignment.
LNS: reorganizing part of a network to escape a local optimum
Destruction, MILP repair, seeds, and convergence traces in large neighborhood search.
Predicting demand: from a population baseline to Poisson and boosting
How to define the target, validate geographically, and interpret errors without treating one marketplace as the whole market.
Population forecasting: trends, damping, and temporal testing
How to project population without confusing census revisions with growth or future population with guaranteed orders.
K-means: finding municipal profiles without inventing natural categories
Scaling, choosing k, silhouette, and stability for interpreting territorial clusters.
Candidate scoring: learning to filter without losing good decisions
Logistic regression and boosting as optimizer filters: what they predict and how to measure the cost of excluding candidates.
Scenarios and SAA: deciding before demand is known
Sensitivity, two-stage decisions, VSS, and computational uncertainty for evaluating a logistics network.
Spatial data segmentation: concepts and applications
What segmentation is, how it differs from classification, key algorithms and their use in QGIS with Orfeo Toolbox and in PostGIS with Python.
Automatic image classification with GeoAI in QGIS
A step-by-step guide to classifying satellite images with the OpenGeoAI plugin in QGIS: installation, preparation, training and interpretation of results.
Python for data analysis: from CSV to insight
The complete workflow with pandas and matplotlib: loading, exploration, cleaning, transformation, statistical analysis and visualization using real examples.
Microservices: scalable architecture and the importance of sound modeling
Why the data model is the most important decision in microservices, how to define bounded contexts and when not splitting is the right choice.
Kubernetes: container orchestration step by step
Cluster architecture, key components, installation with Minikube, your first deployment, service exposure and scaling from scratch.
ETL with Python and geoinformation: production pipelines
Why a well-designed pipeline needs layered architecture, explicit validation and complete traceability from the source to PostGIS.