Numbers do not speak for themselves!. We make them talk.
An essential part of data analysis is communication. We need to arrange information in a comfortable and digestible way to communicate, highlight and visualise critical areas.
Dashboards take your data visualisation to the next level. They connect different visualisation components and make a whole and integrated data visualisation stories. Web application Dashboards also allow users to interact with the data and the visualisation, offering them to see and adjust what they want or need.
It has never been easier to create a dashboard in Python. We have several dashboard tools…
Road accidents — a leading cause of all deaths globally — is a major problem around the globe. Can a Machine Learning model help us understand, classify and predict crash severity based on spatial data?
This will be a three-part series article. In this first article, I will train a baseline model for one city. We will use Pycaret, a convenient Low-code machine learning library.
In the next article, we will use Geospatial Feature Engineering to improve our base model. The final part will scale the process to train a model for the whole of USA country car accidents.
Machine learning(ML) is hard to learn; especially it’s algorithms, data preprocessing and training models.
It is not the case anymore!
With the rise and availability of both no-code and low-code machine learning libraries and platforms, there are fewer barriers to use and apply machine learning models on your applications.
Low-code/No-code platforms and libraries enable users to run machine learning models easily by providing a ready-to-use code and functions. You can access these functions either through a web interface or writing minimal code.
While no-code platforms are the easiest way to train a Machine Learning model through drag and drop interface…
GIS skills and education have changed over the past years. “I’ve been GIS. Now I’m geospatial.” writes Will Cadell in a recent article titled Geospatial Is Not GIS.
As a GIS person typically produces cartographic and analytical products using desktop software, Geospatial data scientist creates code and runs pipelines that produce analytical products and cartographic representations. The difference might seem subtle, but it requires a new set of tools and mindset.
The GIS skills are still relevant, but there are a lot of other skillsets necessary for geospatial data scientists to succeed, some obvious while others are less known. A…
The satellite-based earth observation data is increasing at a rapid base, thanks to technological development in remote sensing platforms, and breakthroughs in data collection and storage. Today, we have more than 768 earth observation satellites in orbit, compared with only 150 in 2018.
As a Geospatial or earth observation data scientist, you have a vast array of tools and resources to choose. In this article, I highlight the best open source tools in the market that are integrated into the data science ecosystem.
Your wish granted. GEE is all in one package. Google Earth Engine(GEE) is by far the complete…
Recently, I thought back to a few years ago, when I tried to process a large geospatial dataset with Python. You can only guess how it ended. My laptop refused to cooperate and froze spectacularly without failing.
Fast forward today, I was experimenting with RAPIDS AI Suite and came across the same dataset. I immediately knew what to do. So I jumped into coding.
The RAPIDS suite of open source software libraries and APIs gives you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs.
In this tutorial, I will go through a complete…
I have been keeping a close eye on Unfolded Studio since its launch, and so far, there is fantastic stuff out of the box for Geospatial big data visualization right in the browser.
If you have used Kepler GL for your data visualization, the new Unfolded Studio application feels home. The same creators of the Kepler GL have delivered this beautiful data visualization tool.
The difference between the two tools is summarized in the FAQ here:
Satellite imagery datasets are enormous and require large storage capacity. The new standardized Spatio Temporal Asset Catalogs (STAC) open up a whole new phase in the earth observation industry.
You can search, find, browse, analyze and process satellite images using Cloud Optimised GeoTiff( COG). Using the asset catalog and metadata of satellite imagery tiles for any place on earth. That means you can carry out all your geoprocessing tasks without ever downloading a single image.
This article will highlight What COG is, its internal structure and benefits, and how you can search and access STAC enabled COG in python without…
Last year October, I have started sharing my thoughts and articles exclusively in a new publication — Spatial Data Science. Since then, the publication has grown into a community, and we are already 700 members.
Thank you for reading my articles and allowing me to share my thoughts and learn and grow together. I could not let it pass the occasion of reviewing the past quarter performance and seeing a perfect 700 members of the spatial data science community here at Medium.
I have a lot of articles and tutorials to share this year. I will also be…
The wait is over. Now we can use the next-generation data science User Interface (UI) — JupyterLab 3.0.
The release of JupyterLab 3 brings many features and improvements. Jupyter Lab has evolved throughout the years to be one of my favorite data science tools.
This article will highlight some of the significant improvements and additions to JupyterLab in this release.
Table of content (TOC) was available in JupyterLab through installing an extension. …
Geographic data science