Tag Archives: 3d

POI Intelligence for Urban Asset Analysis: assetIQ

When analysing urban assets, there is genuine value in moving beyond generic neighborhood scores. The density of a coffee shop cluster, the proximity to a financial hub, or the concentration of accommodation around a transport node are signals that traditional datasets flatten into averages — or ignore entirely. assetIQ was built to change that. assetIQ is an R application powered by DuckDB and Overture Maps that extracts, classifies, and scores Points of Interest (POIs) for any location on Earth. You define a city and a search radius — from 100 meters to 25 kilometers — and the tool queries the Overture Maps Places dataset in real time, classifying each POI into thematic groups: Food & Drink, Retail, Health, Education, Transport, Accommodation, Financial Services, Leisure & Culture, Sport, and more.

The core output is an attribute value called POIQ: a normalized 0–1 score assigned to every building footprint within the area of interest, derived from a Kernel Density Estimation of the selected thematic group. A building in a dense retail corridor scores close to 1. An isolated residential block far from any commerce scores close to 0. This transforms thousands of individual points — which in raw form tell you very little — into a single, interpretable attribute per building, ready for downstream modelling, valuation, or site selection.

AERIAL SURVEYOR SIMULATOR: Reimagining Aerial Photography

For three years, my office was thousands of feet in the air. As an aerial photographer, I spent my days capturing the world’s textures, layouts, and topographies from a cockpit—a masterclass in perspective that I am now transforming into a Aerial Surveyor Simulator.

Urban development in Madrid from the mid-19th century to the present day

All existing buildings in Madrid currently listed in the Land Registry database have their year of construction recorded. This map shows, by decade, where the bulk of that urban development took place. For example, in the 1920s it was in the Salamanca district, in the 1930s in Chamartín… shifting from development in the city centre to the outskirts.

Population Estimation through Dynamic LULC-Based Settlement Validation

The foundational step of this methodology involves the deployment of a centralized processing interface within the Google Earth Engine (GEE) environment. The provided visualization captures the core interface of the custom GEE application, which serves as the hub for the multi-sensor LULC validation pipeline. Within this dashboard, users can define a specific Area of Interest (AOI)—highlighted here over the Iberian Peninsula and North Africa—and configure key parameters, including temporal ranges for the acquisition of sentinel-derived products. Crucially, the interface is designed to load and compare two primary datasets simultaneously: Dynamic World (near real-time, probability-based LULC) and ESA WorldCover (10m resolution structured LULC). The contrasting classification schemes are represented by the legends on the left and right sides of the map view, which illustrate the varying definitions of ‘Built-up’ and urban areas between the two products. Establishing this visual and statistical comparison at the application level is the prerequisite for calculating the spatial disagreement threshold, or delta, that guides the subsequent merging and population estimation phases.

Super-résolution 1 m a Madrid avec Sentinel-2 10m. Magique ! Tracking NRT!

Passer d’une résolution de 10 mètres à 1 mètre change radicalement la perspective du suivi agricole : on ne regarde plus une parcelle dans sa globalité, on observe ce qui se passe à l’intérieur même des rangs de culture. Ce saut qualitatif est possible grâce à l’algorithme S2DR3, un modèle de Deep Learning qui ne se contente pas d’agrandir les pixels, mais reconstruit l’information manquante. En s’appuyant sur les corrélations entre les différentes bandes spectrales de Sentinel-2 et en s’entraînant sur des images de très haute résolution, l’IA parvient à synthétiser une image à 1 m/pixel d’une précision étonnante.

Setting up Mapterhorn terrain in RStudio

¿Alguna vez has querido visualizar el relieve de un territorio en 3D directamente desde R, sin depender de software GIS externo? Mapterhorn es un proyecto open source que distribuye modelos digitales de elevación (MDT) de alta resolución — hasta 2 metros en España — empaquetados en formato PMTiles, un estándar moderno que permite servir datos geoespaciales sin necesidad de un servidor propio.

En este post veremos cómo configurar Mapterhorn en R usando el paquete mapgl en Rstudio, que nos permite crear mapas interactivos con terreno 3D en pocas líneas de código. El resultado: visualizaciones como la que ves abajo, con sombreado de relieve (hillshade) generado directamente desde los datos de elevación del IGN.

Aventuras y desventuras de un geógrafo en “desarrollo”

La cartografía siempre ha sido un oficio de precisión, paciencia y criterio espacial. Durante años, el flujo de trabajo de cualquier geógrafo pasaba inevitablemente por entornos de escritorio como ArcGIS Pro o QGIS: cargar capas, ajustar simbología, exportar mapas. Herramientas sólidas, probadas, indispensables. Pero algo está cambiando.

Cada vez más, el análisis espacial ocurre en la nube, en navegadores, en entornos de código. En anteriores post habéis visto algunos test/ideas/aplicaciones que he desarrollado con Javascript Google Earth Engine, que procesa imágenes satelitales a escala planetaria sin mover un solo archivo. Deck.gl y Maplibre renderizan millones de puntos en 3D directamente en el navegador. React convierte un mapa en una aplicación interactiva con pocas líneas de código.

From LIDAR USGS to DSM in a few lines of code. The magic of R

The USGS LiDAR Explorer, hosted via gishub.org, serves as a high-performance web gateway for interacting with the USGS 3D Elevation Program (3DEP) datasets. First thing, go to this GITHUB repository https://github.com/opengeos/maplibre-gl-usgs-lidar, download code for the project (code>download ZIP), get connected with RStudio, save new project and open a script window… It’s all set up!

URBAN ATLAS 2018 + WORLDPOP 100m/GHSL 100m estimates over Madrid

Urban Atlas (UA) representa el estándar de oro dentro del Copernicus Land Monitoring Service (CLMS) para el análisis de la morfología urbana en Europa. A diferencia de Corine Land Cover, UA ofrece una resolución temática y espacial drásticamente superior (Unidad Mínima de Mapeo de 0.25 ha para clases urbanas), permitiendo discriminar entre tejidos urbanos continuos y discontinuos con una precisión de densidad del 10% al 80%.

Analyzing Spatial Correlation between Purchase Power Index and Gambling Stores (2)

This GIS study applies Geographically Weighted Regression (GWR) to investigate the spatial relationship between Purchasing Power Index (PPI) and the distribution of gambling-related retail establishments within the city of Madrid. My aim is to account for spatially varying relationships driven by local urban contexts, under the assumption that the relationship between socioeconomic conditions and the presence of gambling venues varies across urban space. My hypothesis is that the socioeconomic conditions of the urban fabric can be a breeding ground for the location of betting shops, or in other words, I am attempting to Detect Urban Vulnerability to Gambling Harm.