Wherobots’ Post

I've been watching the devastation in California unfold. As homes, businesses, and schools are destroyed my heart goes out to all those effected. In September 2024, I wrote a workshop for Wherobots at the Spatial Data Science Conference around fire risk in Southern California. We calculated several weighted normalized risk factors including burn probability statistics, building density and count, and distance nearest fire station. On top of the risk mapping, Apache Sedona contains the Getis Ord G* statistics for calculating Hot and Cold spots. When I overlay the current fire perimeters on my analysis looks pretty spot on. Amazing how well even naive spatial analysis and statistics can accurately describe our world 😉. Blue to Red == Low to High Z score; High Z-scores especially in the areas around the perimeter have P-Values less than .05

💧 Episode 3: Uncovering Hidden Secrets Underground 💧 Flint’s water became hazardous by an invisible threat:  Lead, leaching from the city’s aging pipes. But how do you fight what you can’t find? Digging up the whole city to locate lead pipes was costly and time-consuming. That's when data science stepped in, revealing the hidden dangers beneath the surface (like a magical fortune teller 🧙♀️) and providing the city with a map that pinpoints riskiest areas. 📌 See the magic happen✨—check out the impact and results of this data science project below. The data scientist heroes of this episode are: Jacob Abernethy, Alex Chojnacki, Chengyu Dai, Arya Farahi, Eric Schwartz, Guangsha Shi, Jared Webb, Daniel Zhang Did you know ❓ BlueConduit was born out of the Flint water crisis, when researchers at the University of Michigan saw a chance to make a lasting difference—empowering communities to fight the threat of toxic lead in their water and protect their future. 👀 And if you haven't seen episodes 1 and 2 yet, you can find them here: 1. Episode 1: https://lnkd.in/dvURfCsQ 2. Episode 2: https://lnkd.in/dgGQwPvN Links to the research papers: 1. https://lnkd.in/dzDuK2ja 2. https://lnkd.in/dTh3z-9x #DataScience #FlintWaterCrisis #Datory

Just finished our paper on using knowledge graphs to bridge domains and find spatial relationships between unrelated datasets within data lakes. This project with Federico Larrieu was a blast and really opened my eyes to the serious potential and power of knowledge graphs. In this project, we aimed to uncover spatially related interactions across heterogeneous datasets by leveraging knowledge graphs, Apache Sedona, Apache Spark, and datasets supplied by the Urban Sustain Project. By doing this, we built the first steps of a framework that can be used to eventually query various datasets in simple terms such as "Find all lakes in Fort Collins within a 10-mile radius of power plants with elevated heavy metals contamination". With this data, we can observe environmental interactions that may be unnoticed otherwise and help lead to proactive solutions so we can avoid disasters like the Chesapeake Bay pollution crisis.

🌎 Let there be zarr! Dynamical NOAA GFS hourly analysis is now live. Today, we are excited to announce the first entry into dynamical’s catalog: an hourly GFS analysis from 2015-01-15 to present. https://lnkd.in/eQrqf6nD Our pals at Source Cooperative are generously providing storage for this first catalog entry. Their team is wonderful and their mission is badass - check them and the broader Radiant Earth organization out. --- Last week, we announced dynamical.org to the world. The response was unexpected: in just seven days, over a hundred nerds registered themselves as testers with many more following along for the ride. Apparently, we are not alone in our frustration with yesterday's weather data. Together we can create a future of well-organized data about our most beloved chaotic system!

Brilliant blog by my good friend Woody Walton . Have you considered the strata of your data? What’s strata? Read on to learn more … #elastic #strata #data

I'm excited to share my latest blog post, where I delve into the fascinating world of binary trees. In this article, I explore the structure and characteristics of binary trees, specifically focusing on the example of [x<<1 2 x<<1 3]. If you're interested in understanding how binary trees operate and their applications in data structures, this post is a must-read. Check it out here: https://lnkd.in/g2ytFzc2.

Map three of a three post series using Justice 40 data. The entire series was intended to show how data can be manipulated and categorized at different scales. Map one contained the least amount of detailed data and the second transitioned to more, but this map shows the most amount of detail that can be presented in a clear way. Justice 40 measures up to 18 categories of topics that indicate the tract is underserved by the federal government. The Justice 40 initiative strives for all federal agancies to allocate 40% of their budgets to these areas. This maped used QGIS freeware and was the simplist to produce. Climate and Economic Justice Screening Tool - https://lnkd.in/eh8ibHra

Identifying Continuous Data: Analyzing Tree Statistics in a Park In this video, we answer the question, "Which one of the following data types is continuous?" We break down four options: A) The number of species of trees in a park B) The number of representatives of each species in the park C) The rankings of the trees, from most numerous to least numerous D) The average height of a sample of trees Join us as we explore the concepts of discrete and continuous data, explain each option, and reveal the correct answer. Perfect for students and enthusiasts looking to deepen their understanding of data types!

🌍 “Bushfires: A Natural Part of Australia’s Ecosystem… or a Growing Catastrophe?” 🔥 What if we could turn the tide on bushfires with a blend of cutting-edge technology and age-old land management practices? Check out my 3-minute pitch on how New South Wales can lead the way in safeguarding our future. I’m currently studying Actuarial Studies and Commerce at UNSW, where I’m passionate about using data-driven insights to solve real-world problems. As part of my COMM2501 project at UNSW, I’ve been investigating the growing issue of bushfires in New South Wales. With the increasing frequency and intensity of these fires, it’s clear that a new approach is needed. In this video, I explore how we can combine modern technology with strategic land management to protect our communities and natural heritage. Throughout this course, I have learned a lot about how to effectively turn data into a useful story to convey a messge. Overall, my self-assessment of my data story on this topic is 6/10. Poon Leung #unswDataVisComm

This Fall 2024 semester at BYU Idaho, I had the opportunity to work on a 50 hour project in which I started creating a data science portfolio with two analyses covering two separate topics. In order to do this, I came up with topics I'm passionate about, the first being movies and the second being weather patterns. For the topic of movies, I was able to compare a movie's genre, audience score, and rating (G, PG, PG-13, R) to the success it had at the box office using each movie's worldwide gross earnings. For the topic of weather patterns, I was able to look more closely at Idaho Falls, Idaho's weather patterns and create a weather model predictor. Below is a link to my project that I completed for those curious on the findings I was able to get from these two analyses! #datascience #RStudio