Saturday Data Dive: Mapping Calgary’s Thermal Fingerprint 🛰️📊

Spent some quality time with GEE, R and Landsat-8/9 data today.

I’ve just finished processing a Median Land Surface Temperature (LST) model for Calgary, covering the entire Summer of 2025. This isn't just a single-day snapshot—it’s a robust composite of many satellite scenes, filtered to show the true intra-urban thermal zones.

Quick Takeaways:
🔹 Surface temperature in some busines area and "heat traps" peaked at over 51.3°C.
🔹 The contrast between our "Cool Islands" and "Extreme Heat Zones" is striking.
🔹 This automated workflow in R allows for a granular look at urban climate resilience that standard reports often miss.

I’m currently finalizing a full breakdown and a community-by-community analysis.
Stay tuned—the detailed article is coming soon!

#Calgary #DataScience #UrbanHeatIsland #RemoteSensing #ClimateResilience #Landsat #RStats #GIS #Sustainability #GEE #EnvironmentalData #Summer2025 #YYC #GreennessOfCalgary #Alberta #Canada

💡 New Paper!
Deep learning can predict runoff — but uncertainty matters.

This study shows that engression + LSTM delivers:
✅ Better uncertainty estimates
✅ Realistic time-series simulations
✅ Stronger performance than standard methods
A promising step toward trustworthy environmental forecasts.

👉 Learn more: https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2025GL120122

#Hydrology #MLforEarth #Uncertainty #EnvironmentalData

How much does landform position matter for vegetation dynamics across Calgary?

I explored how ΔNDVI (2025-2024) varies across geomorphon classes (summit, ridge, slope, hollow, valley, etc.) using a large spatial dataset (~194k observations).

A few key points from the analysis:
• Non-parametric Kruskal–Wallis test shows statistically significant differences between geomorphons
• However, the effect size is moderate (ε² ≈ 0.04)
• Distributions strongly overlap — landform position matters, but it is not a deterministic driver
• Median ΔNDVI tends to be higher in lower landscape positions (hollows, footslopes, valleys), consistent with moisture and accumulation controls

#EnvironmentalData #RemoteSensing #NDVI #LandscapeEcology #Geomorphology #DataAnalysis #RStats
#ReproducibleResearch #Calgary #GreennessOfCalgary #Sentinel2

Pacific Islands Ocean Observing System (Oceanography 🌊)

The Pacific Islands Ocean Observing System is a nonprofit association and one of eleven such associations in the U.S. Integrated Ocean Observing System, funded in part by the National Oceanic and Atmospheric Administration. The PacIOOS area covers eight time zones, and 2300 i...

https://en.wikipedia.org/wiki/Pacific_Islands_Ocean_Observing_System

#PacificIslandsOceanObservingSystem #Oceanography #EnvironmentalData #HydrologyOrganizations

A long time ago, when I was member of an environmental NGO and creating analytical graphics for public awareness, I developed a custom template for calendar-style diagrams.

These “danger calendars” showed how many sanitary air-quality standards were exceeded each day. The format revealed not only individual pollution spikes but also long-term patterns — seasonality, problematic months, weekday effects, and gaps in monitoring.

The example below shows air-quality exceedances in Kryvyi Rih (2014–2016), based on official data from the Hydrometeorological Service of Ukraine.

And yes — Kryvyi Rih has extremely poor air quality.

#DataVisualization #AirQuality #EnvironmentalData #RStats #EcoAnalytics #SciComm #DataScience #Ukraine #AirPollution #UrbanHealth #UrbanEcology #FOSS #ggplot2

🛰️ Today I’m sharing one of my favourite large-scale remote sensing experiments:
a Principal Component Analysis (PCA) of MODIS composite data for the three central provinces of Canada (Alberta, Saskatchewan, Manitoba).

On this map:
- PC1 emphasizes broad ecological zones and vegetation productivity
- PC2 highlights soil and surface moisture differences
- PC3 captures subtle spectral variations — often linked to geology, wetlands, disturbance patterns, or local microclimates

Even though it looks abstract, PCA is a kind of “spectral fingerprint” of the land. It summarises thousands of square kilometres into a single visual structure that shows how the Canadian Prairies and Boreal regions differ and transition into one another.

#RemoteSensing #MODIS #Geospatial #EarthObservation #Rstats #DataVisualization #PCA #SatelliteData #Canada #Alberta #Saskatchewan #Manitoba #EnvironmentalData #GeoDataArt #GeoSpectralArt

📚 A short note for those who just joined my profile

Over the past few days, I’ve been sharing many posts — not for promotion, but to open parts of my long-term research archive.

During more than a decade of independent work, I’ve accumulated a huge amount of data, methods, and materials: from geochemical modeling and groundwater studies to urban greenness mapping and environmental visualization.

Many of these works were completed years ago but remained unpublished outside of narrow expert circles — so I’m gradually bringing them here, one by one, to make them visible and interconnected.

The pace will slow down soon 🙂 — what you’re seeing now is a process of unfolding a whole scientific story.

#OpenScience #Geochemistry #Hydrology #GIScience #EnvironmentalData #UrbanEcology #IndependentResearch #ScienceCommunication #DataVisualization #Rstats #QGIS #SAGAGIS #FOSS #Linux #DataScience

🏙️ The Hellish Trade Zones
(Ukrainian: “Торговельні пекельні зони”)

An older piece from 2017 — but still relevant today.
Using Landsat-8 thermal imagery, I explored how urban heat islands form in large commercial and industrial areas completely devoid of vegetation.

These “hellish trade zones” show surface temperatures exceeding 45–50 °C, while nearby shelterbelts and green spaces remain much cooler.
The visual storytelling approach — combining satellite data, maps, and simple explanations — helped raise public awareness about urban greening and environmental health in my city.

📍 Location: Kryvyi Rih, Ukraine
🛰️ Data: Landsat-8 (July 15, 2016), thermal band 10 + NDVI
🔗 More: https://www.datastory.org.ua/%d1%82%d0%be%d1%80%d0%b3%d0%be%d0%b2%d0%b5%d0%bb%d1%8c%d0%bd%d1%96-%d0%bf%d0%b5%d0%ba%d0%b5%d0%bb%d1%8c%d0%bd%d1%96-%d0%b7%d0%be%d0%bd%d0%b8/

#UrbanHeatIsland #RemoteSensing #Landsat #UrbanEcology #ClimateChange #EnvironmentalData #UrbanGreening #Geospatial #GIScience #OpenScience #DataVisualization #Ukraine #Sustainability #KryvyiRih #UrbanHealth

🫐 The Blueberry Map Experiment — modelling meets the mountains

In 2022, while living with my family in the Czech Republic, I built a digital map of wild blueberry hotspots in the Jizera Mountains.

At first, it looked like a fun summer project — our neighbors used the map to find the best berry spots and enjoy the landscape.
But behind it was a serious experiment: I tested species distribution modelling (SDM) methods, later adapted for wide-world rare earth element prediction.

Within this “blueberry project” I:
🔹 automated the full spatial workflow in R and QGIS,
🔹 generated geomorphons and other terrain-based predictors,
🔹 built and validated ML models,
🔹 created probability maps and tested them in the field.

✨ What started as a family hobby became a field-tested workflow for predictive geoscience.

#DataScience #MachineLearning #GIS #SpatialModeling #SDM #CzechRepublic #RemoteSensing #Geoscience #RStats #EnvironmentalData #PredictiveMapping #LandscapeEcology #RareEarthElements #CriticalMinerals