Gaurav Chakrabarty

Geoinformatics | IT | PG Dip Applied Geoinformatics
#RDBMS #SQL #PLSQL #Python #Pyspark
#RemoteSensing #GIS #MachineLearning #WebGIS

[Gaurav Chakrabarty @chakrabarty_g]

Machine Learning on Geospatial Datasets for Segmentation, Prediction and... https://t.co/JXy78GqN7k via @YouTube

[Gaurav Chakrabarty @chakrabarty_g]

Completed the webinar on "Estimating Biomass and Change with GEDI and the OBIWAN API".
Thanks for some great sessions.
#nasa #biomass #arset #api #GEDI

[Qiusheng Wu @giswqs]

GeoLibre now supports rendering Google Photorealistic 3D Tiles!

GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private.

Try it out with your own Google Maps API key:

- Launch GeoLibre web: https://t.co/8gMtkVtfnm
- GitHub: https://t.co/VXq8c1o2Nd
- Documentation: https://t.co/7VA2AQoCUc

#GIS #Geospatial #OpenSource #RemoteSensing #MapLibre #GeoLibre

[Amirhossein Ahrari @Enginn3r]

Google #EarthEngine Tutorial-200 Published: #Lake Area and #Precipitation #Correlation Analysis using #Landsat8 and 9
https://t.co/r9Gej5ac2B

[Qiusheng Wu @giswqs]

GeoLibre v1.2.0 is here!

GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. One application that runs everywhere: in your web browser, as a native desktop app, on your phone, and inside a Jupyter notebook. No account, no server, no cost. Everything runs locally and your data stays private.

This release packs in 35+ pull requests of new capabilities. A few highlights:

- Run SQL right in the browser. The SQL Workspace pairs DuckDB Spatial with a new in-browser PostGIS engine (PGlite), so you can query layers, local files, and remote URLs without a server.
- A smarter attribute table. Add fields, run a field calculator, and explore your data with a built-in Charts panel (histogram, scatter, bar, line, and box plots).
- More ways to add data. OpenStreetMap PBF extracts, Cloud-Optimized NetCDF/HDF via kerchunk, georeferenced video overlays, authenticated 3D Tiles, and a https://t.co/Iu3zs18eJk Layer builder for custom overlays.
- Better visualization. Heatmap rendering, point clustering, and H3 hexagonal grids for spatial binning.
- New analysis and routing. A Directions plugin, plus Spatial Join, Select by Value, and Select by Location vector tools.
- Print and share. A print layout composer that exports your map to PNG or PDF.
- Work faster. A command palette (Ctrl/Cmd + K), global keyboard shortcuts, and undo/redo for layer and style operations.
- Built for everyone. New internationalization framework, an accessibility pass with automated axe checks, an installable offline-capable PWA web build, React error boundaries, and Playwright end-to-end tests.

Try the live demo: https://t.co/hOVekblXMc
Star it on GitHub: https://t.co/VXq8c1o2Nd
Docs and roadmap: https://t.co/7VA2AQoCUc
Release notes: https://t.co/G7VorFZxIy

#GIS #OpenSource #Geospatial #MapLibre #WebGIS #DuckDB #GeoLibre

[Qiusheng Wu @giswqs]

GeoLibre v0.5.0 is out! This update significantly expands data format support, making it easier to work with a wide range of geospatial datasets in a lightweight, modern GIS environment.

Newly supported formats and services include: GeoJSON, Shapefile, GeoPackage, GeoParquet, KML/KMZ, FlatGeobuf, PMTiles MBTiles, GeoTIFF, Zarr, LiDAR point clouds, Gaussian Splatting, and ArcGIS services.

GeoLibre is a lightweight, cloud-native GIS built with MapLibre and Tauri. It runs directly in the browser and is also available as a standalone cross-platform desktop application at only ~30 MB.

GitHub: https://t.co/VXq8c1oACL
Website: https://t.co/7VA2AQpaJK
Live demo: https://t.co/Cq5Mg3oRDo

Feedback, ideas, and contributions are welcome.

#geospatial #opensource #maplibre

[Qiusheng Wu @giswqs]

Working with Planet Tanager Hyperspectral Data (426 Bands) in QGIS with HyperCoast

Learn how to access, visualize, and analyze Planet’s Tanager hyperspectral imagery in QGIS using the HyperCoast plugin. In this tutorial, you will explore freely available Planet Tanager open data with over 426 spectral bands and learn how to stream imagery, download HDF5 datasets, inspect spectral signatures, and perform hyperspectral visualization directly inside QGIS.

Video Tutorial: https://t.co/QfPIevlsNR
HyperCoast: https://t.co/1GPh3h73Rv
QGIS Plugin: https://t.co/6CB4ApMkhd
Tanager STAC Repo: https://t.co/8Bn8I9T5bR
Tanager STAC Browser: https://t.co/ll9Hq1VEQS

#opendata #geospatial #hypercoast #QGIS #Tanager #hyperspectral

[Python Programming @PythonPr]

Python Cheat Sheet for Beginners

[Python Programming @PythonPr]

9 Must-Know Python-Pandas Operations for Working with Data
Image Credit: Brij Kishore Pandey

[Amirhossein Ahrari @Enginn3r]

Google #EarthEngine Tutorial-195 Published: Pre-#Flood and Post-Flood Histogram Analysis using #Landsat Images
https://t.co/5RiArz9ube

[Qiusheng Wu @giswqs]

Search and Visualize NASA Earth Data in QGIS with OpenGeoAgent

Learn how to search, stream, visualize, and download NASA Earth observation data directly within QGIS using the NASA Earthdata Plugin and the OpenGeoAgent Plugin.

In this tutorial, you will also see how OpenGeoAgent enables natural language and voice-based geospatial workflows for searching datasets, customizing visualizations, and interpreting satellite imagery using multimodal AI models. This workflow combines QGIS, NASA Earthdata, and AI-powered automation to simplify geospatial data discovery and visualization.

Video: https://t.co/hIKCqePs3r
NASA Earthdata Plugin: https://t.co/YGSDfHmnkB
OpenGeoAgent Plugin: https://t.co/WgiWV1wGMS

#geospatial #opendata #qgis #geoagent

[Python Programming @PythonPr]

Layers of AI

[Tom Yeh @ProfTomYeh]

Softmax vs Sigmoid ✍️ Interact 👉 https://t.co/cYcveibilc

= Softmax =

Softmax is how deep networks turn raw scores into a probability distribution — the final layer of every classifier, and the core of every attention head in a transformer. To see what it does, picture five boba tea shops on the same block, all competing for your dollar. Five candidates: a, b, c, d, e — different chains, different brewing styles, different pearls. A boba reviewer hands you a 𝘤𝘩𝘦𝘸𝘪𝘯𝘦𝘴𝘴 𝘴𝘤𝘰𝘳𝘦 for each — higher means perfectly chewy "QQ" pearls with the right bite (ask a Taiwanese friend to find out what QQ means). Negative scores are real: mushy bobas, overcooked pearls, a batch left sitting too long.

How do you turn five chewiness scores into an allocation that adds to a whole dollar? You could spend everything at the chewiest shop, but that ignores how good the runners-up are. Softmax is the smooth alternative.

Read the diagram left to right. First, raise each score to e^{x} — this does two things: it turns negative chewiness into small positives, and it stretches the gaps between scores exponentially. Then sum all five into a single total Z. Finally, divide each e^{x} by Z to get a probability. The five probabilities add up to one, so you can read them as percentages of your dollar. The chewiest shop gets the biggest slice — but never the whole dollar. That's the point of softmax: it ranks confidently while still leaving room for the others.

= Sigmoid =

Sigmoid squashes any real number into a probability between 0 and 1 — the classic activation for binary classification, and still the gating function inside LSTMs and GRUs. Same boba block as the previous Softmax example, narrowed to just two contenders — a hot new shop `a` with chewiness score x, and your usual go-to `b` whose score is pinned at zero (the neutral baseline you've come to expect).

Sigmoid is just softmax with two players, one of them pinned to zero.

Read the diagram left to right. First, raise each score to e^{x} — for the usual shop `b` whose score is zero, this is just e^0 = 1 (the constant baseline). Then sum the two into a total Z. Finally, divide each e^{x} by Z to get a probability. The two probabilities add up to one — the new shop wins more of your dollar when its pearls get chewier, and your usual keeps the rest. That's the point of sigmoid: it turns a single chewiness score into a clean 0-to-1 chance you'll try the new place over your usual.

---
AI Math, Algorithms, Architectures by hand ✍️
Subscribe to my 60K+ reader newsletter 👉 https://t.co/fFt8rocGsH

[Qiusheng Wu @giswqs]

I am excited to introduce OpenGeoAgent, a powerful open-source multimodal AI agent for automated geospatial analysis and visualization!

It supports QGIS, Jupyter notebook, and Python scripting. In this tutorial, you’ll learn how to automate GIS workflows using natural language, generate maps, analyze satellite data, and even run complex hydrological models.

You can even interact with the agent using voice commands (no typing needed).

Video: https://t.co/mJ0ort5dzb
GitHub: https://t.co/WgiWV1wGMS
QGIS Plugin: https://t.co/qNRP3WPJWe

#geospatial #GeoAgent #OpenSource #AI

[Tom Yeh @ProfTomYeh]

Single vs Multi-hand Attention by hand ✍️ Resize matrices yourself 👉 https://t.co/2yRBcyz4xy

The most important fact about multi-head attention: it has the same parameter count as single-head attention. The difference is purely structural — same total Wqkv weights, partitioned into smaller q–k–v triples.

Look at the two diagrams below. Both Wqkv matrices have the same height — same number of weight rows, same number of parameters. What changes is how that single tall block is sliced.

• Left. One head. The full Wqkv produces one big QKV: a tall Q (36 rows), a tall K, a tall V. One scoring computation runs over those full-width tensors.
• Right. 3 heads. The same-height Wqkv is sliced into 3 smaller q–k–v triples — each 12 rows tall. 3 scoring computations run in parallel, each a thinner version of the left.

The compute trade-off — kind of. Same Wqkv weights. Multi-head runs the attention scoring S = Kᵀ × Q once per head, so the dot-product count multiplies by H.

• Single-head: seq × seq = 40² = 1600 dot products
• Multi-head: seq × seq × H = 40² × 3 = 4800 dot products (3×)

But each multi-head dot product is narrower — its inner dimension is head_dim instead of H × head_dim. So when you count actual scalar multiplications, the totals are equal:

• Single-head: seq² × (H × head_dim) = 40² × 36 = 57600
• Multi-head: seq² × H × head_dim = 40² × 3 × 12 = 57600

Same FLOPs. Multi-head buys you H independent attention patterns at no extra weight cost and no extra arithmetic cost — it's the same total compute, sliced into H finer-grained heads.

[Qiusheng Wu @giswqs]

All 15 of my QGIS plugins have now been upgraded to support QGIS 4.0 and Qt6.

This was a significant effort, especially with the complexity of testing functionality across multiple plugins.

If you use any of these plugins and encounter issues after upgrading, please report them on GitHub so they can be addressed quickly.

Official QGIS plugin repository: https://t.co/gAy2d9pZ3h
Custom QGIS plugin repository: https://t.co/ICEujx9Gv3

#qgis #geospatial #opensource

[Matt Dancho (Business Science) @mdancho84]

Understanding P-Values is essential for improving regression models.

In 2 minutes, I'll crush your confusion.

Let's go:

[Qiusheng Wu @giswqs]

Build a professional personal website in minutes using Markdown and GitHub Pages — no HTML required!

In this step-by-step tutorial, you’ll learn how to create a modern, responsive website using a simple Markdown-based template. Perfect for developers, researchers, and anyone who wants a clean portfolio or project site without the hassle of complex coding.

Video tutorial: https://t.co/FK1jsdG8h7
Website template: https://t.co/D6HdiMMfC3
Live demo: https://t.co/IzcNThiyNh

My new personal website was built using the same template: https://t.co/EgbGzCARAK

#opensource #mystmd #jupyter

[Python Programming @PythonPr]

How to write SQL Queries(Practice Complex SQL Queries)
https://t.co/JPucoqRcMN

[Gaurav Chakrabarty @chakrabarty_g]

Completed the webinar on-

Visualizing Land Cover and Land Use Change with NASA Satellite Imagery!
#nasa #arset #LULC #R #rstudio #python

[Daily Dose of Data Science @DailyDoseOfDS_]

Pandas → Polars → SQL → PySpark translations: