home.social

#georeferencing — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #georeferencing, aggregated by home.social.

fetched live
  1. Turn floor plans or drone photos into interactive maps in minutes. Our Georeferencer makes it easy; simply click matching points to align your image & get instant results. Ready to map your assets? maptiler.link/4ejyyKg #MapTiler #Georeferencing #GIS

  2. Using GPS in the year 1565 There’s a wonderful web app (“Allmaps Here”) that shows your GPS location on old maps. I love it. www.verbeeld.be/2024/11/17/u... #maps #allmapshere #cartography #georeferencing

  3. Using GPS in the year 1565 There’s a wonderful web app (“Allmaps Here”) that shows your GPS location on old maps. I love it. www.verbeeld.be/2024/11/17/u... #maps #allmapshere #cartography #georeferencing

  4. I want to use QGIS to geo reference an image, then later edit the image in GNU IMP, but preserve the location tags.

    Is this difficult? Do I need to save off the location data somehow?

    #QGIS #georeferencing

  5. I want to use QGIS to geo reference an image, then later edit the image in GNU IMP, but preserve the location tags.

    Is this difficult? Do I need to save off the location data somehow?

    #QGIS #georeferencing

  6. University of North Carolina: UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections. “A new study from UNC-Chapel Hill researchers shows that advanced artificial intelligence tools, specifically large language models (LLMs), can accurately determine the locations where plant specimens were originally collected, a process known as georeferencing. This […]

    https://rbfirehose.com/2026/02/05/university-of-north-carolina-unc-chapel-hill-study-shows-ai-can-dramatically-speed-up-digitizing-natural-history-collections-2/
  7. University of North Carolina: UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections. “A new study from UNC-Chapel Hill researchers shows that advanced artificial intelligence tools, specifically large language models (LLMs), can accurately determine the locations where plant specimens were originally collected, a process known as georeferencing. This […]

    https://rbfirehose.com/2026/02/05/university-of-north-carolina-unc-chapel-hill-study-shows-ai-can-dramatically-speed-up-digitizing-natural-history-collections-2/
  8. UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections – EurekAlert!

    News Release 5-Dec-2025

    Image: UNC research team check a plant specimen at the UNC Herbarium. view more  Credit: Shanna Oberreiter

    UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections, University of North Carolina at Chapel Hill

    A new study from UNC-Chapel Hill researchers shows that advanced artificial intelligence tools, specifically large language models (LLMs), can accurately determine the locations where plant specimens were originally collected, a process known as georeferencing. This task has traditionally been slow, expensive and dependent on significant manual effort. The team found that LLMs can complete this work with near-human accuracy while being significantly faster and more cost-effective. 

    “Our study explores how large language models can take on one of the biggest bottlenecks in digitizing plant collections,” said Yuyang Xie, first author and postdoctoral researcher in the department of biology at UNC. “We are pioneering the use of these tools for georeferencing, a breakthrough that will accelerate the digitization of plant specimens and unlock new possibilities for ecological research.” 

    The research set out to answer a central question: Can AI automate one of the most time-consuming steps in digitizing natural history collections? The Carolina team found out that yes, it can. LLMs not only performed georeferencing with an error margin of less than 10 kilometers, outperforming traditional methods, but also completed the task at a fraction of the time and cost. 

    “Recent advances in LLMs can potentially transform the georeferencing process, making it faster and more accurate,” said Xiao Feng, corresponding author and assistant professor in the department of biology at UNC. “This gives researchers unprecedented opportunities to advance our understanding of global biodiversity distributions.” 

    The implications are significant. An estimated 2–3 billion herbarium specimens exist worldwide, but only a small fraction have been digitized. Without digital records and spatial data, researchers face major limitations in tracking biodiversity loss, understanding species movement under climate change and analyzing ecosystem shifts. By deploying AI-powered georeferencing, scientists may soon be able to rapidly digitize vast natural history collections that have remained largely inaccessible. 

    “This technology allows us to unlock millions of records that are currently sitting in cabinets,” said Xie. “With the power of LLMs, we can rapidly digitize plant specimen data that will be critical for addressing global environmental challenges.” 

    Traditional approaches to georeferencing rely on manual interpretation, specialized software, or multiple rounds of expert review. The UNC study is among the first to apply LLMs to this task and to show they can outperform existing methods in accuracy, efficiency, and scalability. This new approach opens the door to digitizing natural history collections at a speed never before possible. 

    The research paper is available online in Nature Plants at: https://www.nature.com/articles/s41477-025-02162-y  

    Continue/Read Original Article Here: UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections | EurekAlert!

    Tags: AI, artificial intelligence, Biology Department, Carolina Team, Collections, Digitize Content, EurekAlert!, Georeferencing, Large Language Models (LLM), LLMs, Natural History, Nature, UNC-Chapel Hill, Xiao Feng, Yuyang Xie

    #AI #artificialIntelligence #BiologyDepartment #CarolinaTeam #Collections #DigitizeContent #EurekAlert #Georeferencing #LargeLanguageModelsLLM #LLMs #NaturalHistory #Nature #UNCChapelHill #XiaoFeng #YuyangXie

  9. UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections – EurekAlert!

    News Release 5-Dec-2025

    Image: UNC research team check a plant specimen at the UNC Herbarium. view more  Credit: Shanna Oberreiter

    UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections, University of North Carolina at Chapel Hill

    A new study from UNC-Chapel Hill researchers shows that advanced artificial intelligence tools, specifically large language models (LLMs), can accurately determine the locations where plant specimens were originally collected, a process known as georeferencing. This task has traditionally been slow, expensive and dependent on significant manual effort. The team found that LLMs can complete this work with near-human accuracy while being significantly faster and more cost-effective. 

    “Our study explores how large language models can take on one of the biggest bottlenecks in digitizing plant collections,” said Yuyang Xie, first author and postdoctoral researcher in the department of biology at UNC. “We are pioneering the use of these tools for georeferencing, a breakthrough that will accelerate the digitization of plant specimens and unlock new possibilities for ecological research.” 

    The research set out to answer a central question: Can AI automate one of the most time-consuming steps in digitizing natural history collections? The Carolina team found out that yes, it can. LLMs not only performed georeferencing with an error margin of less than 10 kilometers, outperforming traditional methods, but also completed the task at a fraction of the time and cost. 

    “Recent advances in LLMs can potentially transform the georeferencing process, making it faster and more accurate,” said Xiao Feng, corresponding author and assistant professor in the department of biology at UNC. “This gives researchers unprecedented opportunities to advance our understanding of global biodiversity distributions.” 

    The implications are significant. An estimated 2–3 billion herbarium specimens exist worldwide, but only a small fraction have been digitized. Without digital records and spatial data, researchers face major limitations in tracking biodiversity loss, understanding species movement under climate change and analyzing ecosystem shifts. By deploying AI-powered georeferencing, scientists may soon be able to rapidly digitize vast natural history collections that have remained largely inaccessible. 

    “This technology allows us to unlock millions of records that are currently sitting in cabinets,” said Xie. “With the power of LLMs, we can rapidly digitize plant specimen data that will be critical for addressing global environmental challenges.” 

    Traditional approaches to georeferencing rely on manual interpretation, specialized software, or multiple rounds of expert review. The UNC study is among the first to apply LLMs to this task and to show they can outperform existing methods in accuracy, efficiency, and scalability. This new approach opens the door to digitizing natural history collections at a speed never before possible. 

    The research paper is available online in Nature Plants at: https://www.nature.com/articles/s41477-025-02162-y  

    Continue/Read Original Article Here: UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections | EurekAlert!

    #AI #artificialIntelligence #BiologyDepartment #CarolinaTeam #Collections #DigitizeContent #EurekAlert #Georeferencing #LargeLanguageModelsLLM #LLMs #NaturalHistory #Nature #UNCChapelHill #XiaoFeng #YuyangXie

  10. University of North Carolina: UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections. “A new study from UNC-Chapel Hill researchers shows that advanced artificial intelligence tools, specifically large language models (LLMs), can accurately determine the locations where plant specimens were originally collected, a process known as georeferencing. This […]

    https://rbfirehose.com/2025/12/06/university-of-north-carolina-unc-chapel-hill-study-shows-ai-can-dramatically-speed-up-digitizing-natural-history-collections/

  11. University of North Carolina: UNC-Chapel Hill study shows AI can dramatically speed up digitizing natural history collections. “A new study from UNC-Chapel Hill researchers shows that advanced artificial intelligence tools, specifically large language models (LLMs), can accurately determine the locations where plant specimens were originally collected, a process known as georeferencing. This […]

    https://rbfirehose.com/2025/12/06/university-of-north-carolina-unc-chapel-hill-study-shows-ai-can-dramatically-speed-up-digitizing-natural-history-collections/

  12. #Georeferencing #historical #maps by their coordinates is not without its pitfalls. A location in LAT / LON can only be intrepreted with spatial context. While there are some historical proj-strings out there (e.g. DHDN, EPSG:4314), one needs to calculate them for other historical spatial reference systems (SRS) using identical coordinates. Thanks to @jjimenezshaw there is now an accessible solution in #python 🤩 👇
    github.com/jjimenezshaw/helmer @fidkarten @historicum_net @DHd @oldmapgallery

  13. #Georeferencing #historical #maps by their coordinates is not without its pitfalls. A location in LAT / LON can only be intrepreted with spatial context. While there are some historical proj-strings out there (e.g. DHDN, EPSG:4314), one needs to calculate them for other historical spatial reference systems (SRS) using identical coordinates. Thanks to @jjimenezshaw there is now an accessible solution in #python 🤩 👇
    github.com/jjimenezshaw/helmer @fidkarten @historicum_net @DHd @oldmapgallery

  14. Georeferencing old maps with Allmaps to have a time machine that allows you to take tours of past cities and landscapes #georeferencing

    verbeeld.be/2024/11/17/using-g

  15. Georeferencing old maps with Allmaps to have a time machine that allows you to take tours of past cities and landscapes #georeferencing

    verbeeld.be/2024/11/17/using-g

  16. Using GPS on old city maps 🗺️

    There used to be a canal where this big white office building is now. I’ve taken this photo from the location of the pink dot on the map.

    How to place your GPS location on an old map near you: verbeeld.be/2024/11/17/using-g

    This specific map of Antwerp can be found here: here.allmaps.org/?url=https%3A

    #maps #allmapshere #cartography #georeferencing

  17. Using GPS on old city maps 🗺️

    There used to be a canal where this big white office building is now. I’ve taken this photo from the location of the pink dot on the map.

    How to place your GPS location on an old map near you: verbeeld.be/2024/11/17/using-g

    This specific map of Antwerp can be found here: here.allmaps.org/?url=https%3A

    #maps #allmapshere #cartography #georeferencing

  18. Using GPS in the year 1565

    There’s a wonderful web app (“Allmaps Here”) that shows your GPS location on old maps. I love it.

    verbeeld.be/2024/11/17/using-g

    #maps #allmapshere #cartography #georeferencing

  19. Using GPS in the year 1565

    There’s a wonderful web app (“Allmaps Here”) that shows your GPS location on old maps. I love it.

    verbeeld.be/2024/11/17/using-g

    #maps #allmapshere #cartography #georeferencing

  20. When I saw this, I was like "uh oh, it looks like someone screwed up the ground control points..."

    But no, it turns out that's what the street actually looks like 🤣

    #Georeferencing
    #NighttimeLights
    #Dortmund

  21. When I saw this, I was like "uh oh, it looks like someone screwed up the ground control points..."

    But no, it turns out that's what the street actually looks like 🤣

    #Georeferencing
    #NighttimeLights
    #Dortmund

  22. 1/3 Got 3D?

    #GoogleEarthPro is free software that simulates 3D. It can be installed on PC/Mac/Linux. In addition to the screen controls you can rightclick-hold and slowly move your pointing device.

    Here are example #GIS KMZ files for Ventura County, CA.

    Trails and roads. Transparent background.
    mappingsupport.com/p2/kmz_demo 21MB

    Trails and roads. Scanned USGS topos.
    mappingsupport.com/p2/kmz_demo 37MB

    #Georeference #Georeferencing #Geospatial #Maps #Mapping

  23. 1/3 Got 3D?

    #GoogleEarthPro is free software that simulates 3D. It can be installed on PC/Mac/Linux. In addition to the screen controls you can rightclick-hold and slowly move your pointing device.

    Here are example #GIS KMZ files for Ventura County, CA.

    Trails and roads. Transparent background.
    mappingsupport.com/p2/kmz_demo 21MB

    Trails and roads. Scanned USGS topos.
    mappingsupport.com/p2/kmz_demo 37MB

    #Georeference #Georeferencing #Geospatial #Maps #Mapping

  24. resuming a project after *sees last modified date of text file with my notes* over 4 years ??!? (at least!?!) (#georeferencing historic aerial imagery & sanborn maps to make a zoomable web map out of it. (i last blogged about it at skorasaur.us/2018/04/georefere) #map #geochat #gischat
    eager to pick it back up.

  25. resuming a project after *sees last modified date of text file with my notes* over 4 years ??!? (at least!?!) (#georeferencing historic aerial imagery & sanborn maps to make a zoomable web map out of it. (i last blogged about it at skorasaur.us/2018/04/georefere) #map #geochat #gischat
    eager to pick it back up.

  26. @mszll no worries.

    I wonder if some vector magic could do the trick 🤔

  27. At the #NaturalHistoryMuseumLondon, we are not only imaging our collections, we also do #georeferencing. Amazingly, the more we digitise, the more data we get, and we can even reconstruct travel routes.
    E.g.; Oleg #Polunin (bionomia.net/Q266663) collected in the "Kolahoi valley", #Kashmir, in 8/1956.
    He started his travel from Pahalgam in the south, via Liddarwat (now a camping ground) towards a "pass" on 14422 ft. altitude where Polunin collected several plants.

  28. At the #NaturalHistoryMuseumLondon, we are not only imaging our collections, we also do #georeferencing. Amazingly, the more we digitise, the more data we get, and we can even reconstruct travel routes.
    E.g.; Oleg #Polunin (bionomia.net/Q266663) collected in the "Kolahoi valley", #Kashmir, in 8/1956.
    He started his travel from Pahalgam in the south, via Liddarwat (now a camping ground) towards a "pass" on 14422 ft. altitude where Polunin collected several plants.

  29. @lapingvino @factotum

    I take it for granted that users must be able to decide upon the precision of the #geocoding they use for their postings.

    And that they must also be able to decide upon the geogaphic range of search when they lookup #georef|erenced postings.

    🌺

    🏷️ #OLC #QTH #SemanticFediverse #ActivityPub #Mastodon #Friendica #Pixelfed #Fediverse #Geocode #Georeferencing #OpenLocationCode #PlusCode #Maidenhead #HamRadio #AFU #CBFunk #CitizenBand #CiBi #ActivityVocabulary

  30. @lapingvino @helge @factotum

    The location property of the #ActivityVocabulary does not only support exact locations but also areas in the sense that it allows for ›logical locations‹.

    A logical location could be ›near Berlin«, but also a #geocode with reduced precision.

    🌺

    🏷️ #OLC #QTH #SemanticFediverse #ActivityPub #Mastodon #Friendica #Pixelfed #Fediverse #Geocoding #Georef #Georeferencing #OpenLocationCode #PlusCode #Maidenhead #HamRadio #AFU #CBFunk #CitizenBand #CiBi