Fused

💥 Fused is hiring. Join the community of builders. 🥷 Backend engineer: https://lnkd.in/guyZZu4j 🤺 Frontend engineer: https://lnkd.in/gQTM3R3C 👉 Learn more: https://lnkd.in/gehSXFvN

Fused-partitioned Overture Maps Foundation data is updated for October 2024 on Source Cooperative! Image made entirely in Fused. Can you recognize which city I'm looking at here?

Fused-partitioned Overture Maps Foundation data is updated for October 2024 on Source Cooperative! Image made entirely in Fused. Can you recognize which city I'm looking at here?

Wow! 🙏 to Fused app builder (https://lnkd.in/gYtEUKHM powered by streamlit) and some LLM coding support, here is my "Cube Factory" fused app for effortless GeoML visualization and data curation. Goal is to give time back to Data Scientists to do actual research rather than low level data engineering. (Funny to think < 3 weeks ago I had never touched a front end app before, nor even thought myself having the capability....) Combine resources like Sentinel 1 SAR imagery, 13 bands of Sentinel 2, Digital Elevation, Scene Classification and Cropland Data Layers sandwiched into datacubes for ML ingestion. Choose your survey period and region of interest graphically by directly drawing on the map. 🚀 🌎 #machinelearning #geospatial #datascience #earthobservation #transformers

🛰️ Easily create custom tiles from satellite imagery to train AI models! 👨🔬 In his latest blog post, Gabriel Durkin , DPhil. showcases how he built the "Cube Factory" app to generate tiles from Sentinel 2 imagery as input to an ML model to predict Land Use Segmentation. 🖼️ By automating image chipping and source harmonization (time, space, and projection) to prepare training data, Data Scientists can dedicate more time to research — without operational reliance on engineering. 📖 Read it here: https://lnkd.in/gvqjmKKq 💻 Try his app here: https://lnkd.in/g6N7yePM

Welcome to the newest member of our team: Marko Letic Marko joins us as a Founding Engineer, bringing his experience working at startups and building data applications 🛠️ He is also an organizer of the Armada JS - JavaScript Conference - one of the largest in Serbia 🇷🇸

❄️ Integrate Snowflake with a Honeycomb Maps and DuckDB WASM frontend. 🚚 In this blog post, Stefano Bourscheid showcases how GLS evaluates parcel delivery routes - without compromising performance or breaking the bank on query costs. 📖 Read it here: https://lnkd.in/gk8Zsp5E ✌ Shoutout to Carston Hernke!

Vegetation Near Buildings in San Francisco - Overture Maps & Fused The purple raster layer is vegetation segmentation and the buildings are also colored by that data by transforming the raster to vector. The darker red in the buildings means more vegetation. I got some feedback on my last map so I figured I'd try and share again this way. One of the comments said that more vegetation means more effective cooling. I used a slightly coarser resolution here that I believe achieves that. Maybe you can see as the tiles are made the more purple means darker red for buildings. It's possible for the downtown portion that the buildings are bigger and for that reason join with more of the hexagons from the vegetation there. But there does seem to be vegetation density there. I added a screenshot in the comments.

🌽 Easily implement Zonal Stats on crop-specific land cover maps with Kristin Scholten's latest UDF! In Part 2 of her blog post series, Kristin explains how she loads the USDA Cropland Data Layer to identify corn-growing regions. Her UDF then masks a Solar Induced Fluorescence raster then aggregates it across U.S. counties. 📖 Read it here: https://lnkd.in/g-Y4jZjt

Vegetation Near Buildings in Minneapolis - Overture Maps and Fused There is a Fused UDF called Vegetation Segmentation that isolates vegetation from hi-res imagery in real time. That is the purple raster layer here. I converted the array output from that UDF into vector data, then I joined with Overture buildings via H3. The buildings are colored by the density of vegetation around them (darker means more).