ゲルハルト @gerhrdd

Imagery Insights significantly expands, leveraging innovation from Google Earth AI, to help you transform how you understand our planet and make decisions ➡️ goo.gle/4ctPJYu 🦅 We will be launching Aerial and Satellite Insights to put global high-res imagery at your fingertips. Broaden your analysis from city street details to a bird's-eye view of the planet to make data-driven decisions at scale. 🛰️ Aerial and Satellite Models with Google Cloud's Model Garden transforms geospatial workflows with planetary-scale insights, without model training or maintenance. And, unlock insights from the data you already own. ☀️ Solar Insights, a high-res dataset designed to pinpoint market opportunities and accelerate solar adoption, provides analysis-ready data on per-building solar potential, roof statistics, and existing solar arrays across over 90% of buildings in the U.S. and Europe, to help identify high-value customers and optimize network planning. 🏙️ Street View Insights will be elevated in the coming weeks with the release of powerful LiDAR data, which includes access to Google Street View's repository of 280B+ 360 degree and 3D images, with more precise measurements to more accurately determine dimensions right from your desk. Learn more and sign up for early access at the link above.

keyboard_arrow_left Previous keyboard_arrow_right Next

¿Necesitas un #GeoJSON actualizado de #México? Acabo de publicar la división política estatal y municipal (2024) en formato GeoJSON — lista para mapear… o para imprimirla y colorearla con tus colores Mapita. figshare.com/articles/datas…

Con el ATLAS GLOBAL DE LA CONSTRUCCIÓN podéis conocer la altura de 2.750 millones de edificios del mundo 🏙️. Y otros muchos datos. Obra de la Universidad Técnica de Múnich (TUM). github.com/zhu-xlab/Globa… tubvsig-so2sat-vm1.srv.mwn.de

Mapa que busca identificar el grado de consolidación urbana a lo largo de la ciudad de México, bajo el supuesto que a mayor número de habitantes, viviendas y unidades económicas se tiene una mayor consolidación. #30DayMapChallenge

Le di una manito de gato a mi sitio web. Ya son más de 100 posts enseñando a programar en R! 📊👩🏻‍💻 Yo aprendí autodidacta, gracias a lo que compartían otr@s, así que mi sitio también es para ayudar a que más gente aprenda 💜 bastianolea.rbind.io #rstats

keyboard_arrow_left Previous keyboard_arrow_right Next

Visualize geospatial data in BigQuery! BigQuery Studio offers an integrated geography data viewer. When your query results contain one or more GEOGRAPHY type columns, you can view the results in an interactive map. Check it out, here → goo.gle/4oqqwBo

Comparing groups is often one of the main goals in data visualizations. The ggplot2 package in R, along with its powerful extensions, makes it easy to create visualizations that highlight differences, trends, and relationships between groups. Whether you're analyzing means, distributions, or proportions, ggplot2 provides the tools you need for clear and impactful group comparisons. These are my top 5 packages for visualizing group comparisons in ggplot2: 1️⃣ ggstatsplot: Perfect for adding statistical comparisons directly to your plots. Displays p-values, confidence intervals, and effect sizes seamlessly for group comparisons. 2️⃣ ggpubr: Simplifies comparisons by adding summary statistics (like means and medians) and p-values to boxplots, bar charts, and more. 3️⃣ ggsignif: Adds significance brackets with p-values above boxplots, bar charts, or violin plots, making group comparisons clear and easy to interpret. 4️⃣ gghighlight: Highlights specific groups in crowded plots, letting you focus on key comparisons without losing the context of the full data set. 5️⃣ ggbeeswarm: Adds jittered scatterplots to boxplots or violin plots, allowing you to see the distribution of raw data points within each group for a more detailed comparison. In the graph shown here, you can see how these packages enhance group comparisons: the top left plot, created with ggpubr, shows statistical comparisons in a boxplot with significance brackets. The top right, created with gghighlight, presents faceted histograms for side-by-side comparisons. Both bottom plots, created with ggstatsplot, combine violin-boxplots with p-values (bottom left) and stacked bar charts with proportions and annotated statistical metrics (bottom right) for clarity. If you’d like to learn how to create visualizations like these, join my online course, Data Visualization in R Using ggplot2 & Friends. I’ll guide you step-by-step to mastering group comparisons and creating polished visualizations! Take a look here for more details: statisticsglobe.com/online-course-… #R4DS #Python #DataVisualization #Rpackage #tidyverse #Pythonprogramming #RStats #database #DataViz #DataScience #coding #DataAnalytics #ggplot2

Principal Component Analysis (PCA) is a powerful statistical technique used to simplify complex data sets. By reducing the number of variables, PCA helps in identifying patterns and makes data easier to explore and visualize. Here’s how you can implement PCA in R, step-by-step: 1️⃣ Prepare Your Data: Load your data into R. Ensure it's scaled or normalized if the variables are on different scales. data <- read.csv("your_data.csv") data_scaled <- scale(data) 2️⃣ Apply PCA: Use the prcomp() function to perform PCA. Setting center and scale. to TRUE ensures data is centered and scaled. pca_result <- prcomp(data_scaled, center = TRUE, scale. = TRUE) 3️⃣ Examine the Summary: Check the summary of the PCA results to understand the proportion of variance each principal component accounts for. summary(pca_result) 4️⃣ Visualize PCA: Plotting your PCA can help visualize the distribution of the data along the principal components. plot(pca_result$x[, 1:2], col = as.factor(data$YourTargetVariable)) 5️⃣ Interpret Results: Analyze the loadings of the principal components to determine which variables contribute most to each component. loadings <- pca_result$rotation Discover the power of PCA with our R programming course at Statistics Globe! For more information, visit this link: statisticsglobe.com/online-course-… #RStats #DataAnalytics #Python #R4DS #Statistics

Did you know? The open-source geospatial world is booming — and the OSGeo community has built some of the most powerful tools for maps, analysis, databases, and geoportals. 🗺️ Here’s a quick guide to four major categories of OSGeo tools that every geo-professional, student, or tech enthusiast should know 👇 🧭 WEB MAPPING TOOLS The engines that publish your geospatial data online: 🌐 GeoServer – Publish & style spatial data as OGC services (WMS/WFS/WCS). ⚡ MapServer – High-performance web map rendering engine. 🗺️ OpenLayers – JavaScript library to build interactive maps in the browser. 🗃️ GEOPORTALS Platforms that let you organize, share, and manage maps & data: 🧩 GeoNode – A full geo-CMS (think “WordPress for maps”) with data, metadata, users & permissions. 🧭 Mapbender – Build web GIS apps with no coding — just configure & go. 🧭 MapGuide Open Source – Powerful web mapping platform for custom geoportals. 💻 DESKTOP GIS Your all-in-one GIS workbenches: 🧠 QGIS – The most popular open-source desktop GIS: editing, analysis, cartography, plugins galore. 🌿 GRASS GIS – Advanced geospatial modeling, raster processing, terrain & environmental tools. 🏔️ SAGA GIS – Lightweight but strong in terrain & hydrological analysis. 🗄️ SPATIAL DATABASES The backbone of any enterprise GIS — storing & querying spatial data: 🏛️ PostGIS – Spatial extension of PostgreSQL, enabling advanced spatial SQL queries, analysis & storage. 📦 SpatiaLite – Lightweight SQLite with spatial functions, great for mobile & offline GIS apps. 📚 All of these are part of the OSGeo ecosystem — a global community building free and open-source software for geospatial. 🔖 Save this post. 💬 Share it with a geo-nerd. 💡 Tell me in the comments: Which one do you use the most?

While teaching Principal Component Analysis (PCA), I use this interactive Python @matplotlib dashboard to demonstrate both the forward and reverse transformations during dimensionality reduction! You can add a new data point and move it around, watching it go through each step: standardization, projection onto principal components, dimensionality reduction, projection back to the standardized features, and inverse standardization! Check it out @ github.com/GeostatsGuy/Da… ∀. #DataScience #MachineLearning

🚀 GeoAI Tutorial 23: Building Detection from Aerial Imagery and LiDAR Data 🏙️🛰️ In this tutorial, I demonstrate how to train a deep learning segmentation model for building detection by combining aerial/satellite imagery with LiDAR data. You'll learn how to fuse multi-source remote sensing data to improve model accuracy and robustness. 🔗 Tutorial video: youtu.be/BvKHkSm1SDk 📓 Notebook example: opengeoai.org/examples/build… 💻 GitHub repo: github.com/opengeos/geoai 📚 Documentation: opengeoai.org 🎥 Full playlist: tinyurl.com/GeoAI-Tutorials #GeoAI #geospatial #AI #Python #DeepLearning

¿Tus mapas muestran patrones reales o solo lo parece? Descúbrelo con el Índice de Moran, una de las herramientas clave en análisis espacial.

keyboard_arrow_left Previous keyboard_arrow_right Next

📊 ¿Qué es la geoestadística y por qué es tan útil en SIG? 🧵 Abrimos hilo para explicarte qué hace, cómo se aplica y qué puedes hacer en QGIS. 👇 #Geoestadística #SIG #QGIS #AnálisisEspacial

Plugins de IA Generativa en #QGIS #AI #InteligenciaArtificial geoinnova.org/blog-territori…

keyboard_arrow_left Previous keyboard_arrow_right Next

¿Qué dijo David Harvey @profdavidharvey en el foro Vivienda Justa y Prosperidad Compartida? "No se equivoquen, hay una crisis en todo el mundo por la vivienda. Si las personas no tienen dinero, no pueden acceder a la vivienda que le gusta construir a los desarrolladores" Va 🧵

La cobertura de complejos de cine (Cinepolis y Cinemex) en las ciudades sigue una lógica relacionada con el nivel socioeconómico y con la cercanía al centro de las ciudades. Esto se aprecia muy bien en ciudades como Mérida, Toluca, Cancún, Veracruz... 🧵

keyboard_arrow_left Previous keyboard_arrow_right Next

@GerardoSlzar @Jeruiz47 Conocedor

@EI_Manny Hola que tal, quisiera contactarte.

This should not be possible 🤯 I've enhanced this 8x from 1.2MP to 77MP (10.752x7168px) using Magnific ai. 64x more pixels than the OG image. You can do the same. Each super enhance takes 10-15 minutes and can run in the background. A thread

a Portrait of Tenochtitlan, my 3D reconstruction of the capital of the Aztec Empire is released! I've been looking forward to this for a long time, and I am really curious what all of you think. Take a look: tenochtitlan.thomaskole.nl #tenochtitlan