💻 I took several completely independent datasets and "pitted" them against each other. One of the results is shown in this chart: the more "concrete" (roads, buildings, parking lots) my machine learning model identified in a community, the higher the surface temperature recorded by the thermal sensor.

🔥 The result: Data from different sources confirm one another. The difference in surface temperature between "green" and "concrete" residential areas averages 8–10°C throughout the summer. On certain days, this gap is likely even wider.

📉 This chart shows only established residential communities. If industrial zones were included, the trend would be even more dramatic. While modeling errors certainly exist, the overall physical pattern is undeniable.

#Calgary #OpenData #UrbanHeat #LULC #DataScience #ClimateAction #YYC #GreennesOfCalgary #ClimateEquity #EnvironmentalEquity #CityPlanning #MachineLearning #RemoteSensing #RStats #Sentinel1 #Sentinel2 #Landsat #fossgis

#𝟯𝟬𝗗𝗮𝘆𝗠𝗮𝗽𝗖𝗵𝗮𝗹𝗹𝗲𝗻𝗴𝗲 - 𝗗𝗮𝘆 𝟮𝟵: 𝗥𝗮𝘀𝘁𝗲𝗿
𝘖𝘚𝘔-𝘣𝘢𝘴𝘦𝘥 𝘓𝘜𝘓𝘊 𝘮𝘢𝘱 of 𝘒𝘢𝘳𝘭𝘴𝘳𝘶𝘩𝘦, 𝘎𝘦𝘳𝘮𝘢𝘯𝘺 2021🛰️🗺️

Satellite imagery shows how our landscapes evolve. In the LaVerDi project, HeiGIT and @BKG combine OSM data with Copernicus Sentinel-2 imagery to make land-use and land-cover monitoring across Germany more precise and responsive.

🔍 More about LaVerDi: https://heigit.org/laverdi/

#OpenStreetMap #OpenData #LULC #Karlsruhe

Here is a quick land-cover breakdown for the Carpathian National Nature Park (Ivano-Frankivsk region, Ukraine), based on Copernicus Global Land Service remote-sensing data.

The results show that closed evergreen needle-leaf forest dominates the territory (almost 60%), followed by mixed and deciduous forests. Urban areas, shrubs, and agricultural lands occupy only a tiny fraction of the park.

This is part of my long-term project of analysing protected areas using open satellite datasets and reproducible geospatial workflows.

#RemoteSensing #EarthObservation #Copernicus #LandCover #GIS
#RStats #Rspatial #Conservation #Carpathians #Ukraine #Biodiversity
#NationalParks #OpenData #EnvironmentalScience #LULC

A few years ago, I carried out a personal initiative project while working at UkrGazVydobuvannya (Oil&Gas).

In 2019–2020, I performed a full land-cover analysis for all company license areas using openly available Copernicus Global Land Cover data.

I built two variants of the analysis based on FAO UN land-cover classifications and calculated Shannon diversity indices for each license area.
Later, I expanded the work and produced detailed plots and spatial summaries for every site.

These analytics were used by both field personnel and upper management — for general environmental understanding and for environmental impact assessment (EIA) related to the company’s production activities.

Everything was done using open data and the R language.

#LandCover #Copernicus #RStats #OpenData #EnvironmentalScience #GIS #ShannonIndex #RemoteSensing #Ukraine #FOSS #DataScience #LULC #LandCover #CopernicusLandCover #Energy #UGV

My experiment with land-cover classification for Calgary using satellite imagery and with a machine-learning model trained on data from another continent.

The results turned out surprisingly good — most classes transferred almost perfectly.
The only noticeable shift was the Forest class: tree and shrub vegetation in the source region differs from Calgary’s, so the model mapped it conservatively here.

Still, the general structure of the landscape was captured very well, and community-level land-cover profiles look consistent.

#Rstats #RemoteSensing #GIS #MachineLearning #LandCover #Calgary #EarthObservation #LULC #GreennessOfCalgary #QGIS #UrbanHealth #Alberta #Canada #Sentinel #Copernicus #CopernicusSentinel #Sentinel1 #Sentinel2 #ESA #DataScience #FOSS #UrbanEcology #UrbanNature

🌳 Random Forests and Living Trees

English translation of my earlier article on applying satellite imagery and machine learning to map urban land cover.

What started as a local research project in Kryvyi Rih turned into something much larger — the results sparked a heated discussion among residents, officials, and industry representatives about the real condition of green buffers around large industrial sites.

The methodology developed during that work is still being used today — adapted for new environmental and urban projects.

🔗 https://www.datastory.org.ua/random-forests-and-living-trees/

#RemoteSensing #MachineLearning #LandCoverMapping #UrbanEcology #EnvironmentalMonitoring #RandomForest #GeospatialAnalysis #GIS #RStats #SAGAGIS #QGIS #IndependentResearch #OpenSource #EnvironmentalDataScience #KryvyiRih #LULC

𝗟𝗨𝗟𝗖 𝗖𝗵𝗮𝗻𝗴𝗲: 𝗵𝗼𝘄 𝘁𝗼 𝗰𝗮𝗹𝗰𝘂𝗹𝗮𝘁𝗲 𝗰𝗮𝗿𝗯𝗼𝗻 𝗲𝗺𝗶𝘀𝘀𝗶𝗼𝗻𝘀 𝗳𝗿𝗼𝗺 𝗹𝗮𝗻𝗱 𝘂𝘀𝗲 𝗮𝗻𝗱 𝗹𝗮𝗻𝗱 𝗰𝗼𝘃𝗲𝗿 𝗰𝗵𝗮𝗻𝗴𝗲

With the 𝗖𝗹𝗶𝗺𝗮𝘁𝗲 𝗔𝗰𝘁𝗶𝗼𝗻 𝗡𝗮𝘃𝗶𝗴𝗮𝘁𝗼𝗿, you can calculate high-resolution estimates of emissions caused by #LULC changes.
This makes it easier to plan locally targeted climate mitigation measures.

📑 Read more: https://heigit.org/unveiling-the-heigit-climate-action-navigator-part-4-land-use-and-land-cover-change-emissions/
📊 Try it out: https://climate-action.heigit.org/

#EarthOvershootDay #MoveTheDate