Text Recognition Map Search

The David Rumsey Map Collection has unveiled its new amazing Text on Maps feature which allows users to search one of the world's largest collections of digitized maps by text. The David Rumsey Map Collection contains over 57,000 geo-referenced vintage maps. Using the new Text on Maps feature you can now search for where any word appears on any of those 57,000 maps.

Old maps are an invaluable source of historical geographical information such as the names of streets, landmarks, rivers, etc. Text recognition can identify and extract these elements, enabling researchers to study and analyze the evolution of landscapes, urban planning, or changes in geographical features over time. Text recognition can also aid in comparing and analyzing various versions or editions of vintage maps. By extracting and comparing textual information, researchers could use the Text on Maps new search facility to identify similarities or differences in map features, annotations, or historical details, contributing to a more nuanced understanding of how cartography has developed over time.

There are numerous ways in which Text on Maps could prove an invaluable aid in many areas of research.

Search for Vintage Maps for a Place-Name

Text on Maps is an incredibly useful method to search maps in the David Rumsey Map Collection. For example, suppose you want to search through old maps of your home town to explore how it has changed over time. Now you simply have to type in the name of your town and the David Rumsey Collection will return all the maps that include a place-name label with your town's name. 

Search Maps for Points of Interest

You can use Text on Maps to find points of interest on digitized maps, for example gold mine, lighthouse, windmill, post office etc.

Search Maps for Mythical Places

You could use Text on Maps to search for mentions of mythical locations or people, for example Camelot, Atlantis, El Dorado, Shangri-la, etc.

Search for Mythical People

Text on Maps can be used to search for references to mythical (or Biblical) people on maps in the David Rumsey Maps Collection, for example Magog, Moses, King Arthur etc.

I am certain that Text on Maps can be used in lots of other ways to aid anyone who needs or wants to undertake research using vintage maps. Let us know in the comments how you would use Text on Maps to search the David Rumsey Map Collection.

Mapping Hurricane Idalia

Hurricane Idalia is expected to make landfall in Florida early Tuesday morning. Overnight the hurricane developed into a powerful Category 3 storm and it is now forecast to become a dangerous Category 4 hurricane. 

NOAA's National Hurricane Center has produced a number of maps showing the forecast track of Hurricane Idalia, the wind speed probabilities, storm surge warnings and rainfall potential. The Warnings map includes a layer which provides information on the most likely arrival times of tropical storm winds along the hurricane's forecast path. 

NBC has created a live streaming YouTube channel Tracking Hurricane Idalia which is switching between a map using the latest satellite images to track the storm's progress and a map showing the storm's forecast path with estimated times of arrival along the mapped path. You can also follow the storm in near real-time using the Windy or Earth :: interactive maps. These animated wind maps update every few hours to show the latest weather forecasts around the world.

Florida's Division of Emergency Management has a web page devoted to Emergency Info for Idalia. This page includes information on open shelters, evacuation orders & evacuation zones, and the latest executive orders.

NASA also posted on Twitter this amazing video of Hurricane Idalia, captured on board the International Space Station.

NOAA's map of the forecast path of Hurricane Idalia includes a forecast cone. If you are unsure about what NOAA's 'cone of uncertainty' actually means then you should read USA Today's How the National Hurricane Center Predicts & Tracks a Powerful Storm's Path. As well as explaining how NOAA's forecast cones show where the center of a storm is most likely to move it also does a great job of explaining how NOAA actually forecast's a storm's path & intensity, and how, from the predicted path, degrees of uncertainty are also calculated.

NIMBY Mapping

In July the German government introduced a draft bill to legalize cannabis for personal use. However, under the draft bill, the consumption of cannabis will remain prohibited within a 200-meter radius of schools, children's and youth facilities, playgrounds, publicly accessible sports facilities, and in pedestrian zones between 7 am and 8 pm.

According to the Berliner Morgenpost these restrictions mean that even if the law passes it will still "be generally difficult to legally light up a joint in Germany's city centers". To illustrate this point the newspaper has published an interactive map Weed Prohibition Zones which shows all the areas in Germany which fall within one of the proposed prohibited areas. 

The map effectively draws 200 meter circles around schools and other prohibited areas to show where smoking cannabis will still be illegal. The map reveals that if you live in a rural area then you probably won't need to travel very far (if at all) to find a legal place to smoke cannabis. However if you live in a large city (such as Berlin) then you may find it very difficult to find a nearby location which is not in one of the prohibited areas.

The Berliner Morgenpost map reminds me a lot of Dan Cookson's interactive map London Schools 400m Exclusion Zones. In 2017 the London mayor introduced plans to introduce 400 meter fast food exclusion zones around schools. The purpose of these exclusion zones were to help fight the rise of child obesity.

Dan Cookson created an interactive map which revealed that this would make it very difficult in the future to open a fast food location in large areas of central London. The Berliner Morgenpost's map improves on Dan's map via the simple process of merging all the overlapping polygons. The result is a much clearer differentiation in the newspaper's map between the prohibition and legal zones. 

Terraforming the Metaverse

This morning I've been helping create a satellite map of a world that doesn't exist. Thanks to the combined forces of the human imagination and the cutting-edge power of AI technology, I've been able to contribute to a new digital landscape that is being created in real-time. That's right people - today I helped terraform the metaverse! 

This Map Does Not Exist is an AI generated satellite map which is being created by Artificial Intelligence in response to user prompts. You can contribute to the map yourself by finding a blank space on the map and by clicking on the 'generate a custom landscape' button. You are then asked to enter a prompt for the creation of the satellite image at that location. Based on your prompt a new satellite-realistic map tile will then be added to the interactive map. 

The nature of your prompt is only limited by your imagination. You can choose to create a satellite image of anything you want. It could be an icy mountain range or it could be a colossal, giant chicken egg. The project's GitHub page doesn't provide much information on how This Map Does Not Exist actually works. However the description a 'collaborative inpainter' provides some clues. ‘Inpainting’ is a technique employed by AI image creation tools to seamlessly fill in missing portions of an image. Therefore the 'terrain diffusion' tool used by the map is probably an AI image inpainter creation tool that has been trained on satellite imagery.

Obviously the format of This Map Does Not Exist doesn't have to be that of a satellite map. You could create a 'This Picture Does Not Exist' map which was an emerging collaborative painting, similar to the collaborative images that have emerged on r/place.

How the Blitz Changed London

In East London you can usually tell where German bombs fell in World War II by the age of the buildings. For example in my street the majority of houses were built in the Victorian age. All the homes built in the later half of the 20th Century were all built on homes destroyed by falling bombs during the war.

The Economist has added a new factor to my bomb site detection observations - building height. In How the Blitz Changed London The Economist notes that the destruction of buildings in London during the blitz allowed the city to build bigger and taller buildings after the war - in the long run 'supercharging' the city's economy.

At the core of The Economist's article is a map of London which uses red markers to show the locations of all the German bombs that fell on the city during World War II. On this 21st Century map all the buildings are shaded to show building heights (the darker red the building the taller it is). The Economist's central argument is that after the war taller buildings could be built on the locations of destroyed buildings. This is evident in the fact that now the heavily bombed City and East London areas of London have some of the city's tallest buildings, drastically "expanding the amount of commercial floor space".

The Economist's conclusion that German bombing enabled the City of London to build taller buildings has the ring of truth about it. The argument is based on work by Gerard Dericks of Oxford Brookes University and Hans Koster of Vrije Universiteit Amsterdam, which show that the heaviest bombed areas of London now have the highest density of workers. However I would like to be able to explore the Economist's map for myself. It is a shame that after building such a wonderful map of bomb sites and building heights that The Economist won't let us actually play with it. 

If you do want to explore a map of London bomb damage for yourself then check-out the Layers of London map, which includes an overlay of the London County Council Bomb Damage Maps. You could also try the Bomb Sight map (although the map isn't loading for me today)

Finding Shade from the City Heat

If you need to find a shaded oasis in the concrete jungle of New York City then you can use Cornell University's new Tree Folio NYC interactive map. Tree Folio NYC uses data from a 2021 New York LiDAR survey and the 2015 New York Street Tree Survey to map the shadows cast by buildings and individual tree canopies in New York at any time of day and on any day of the year.

If you zoom-in to any street in New York on the map you can select any building or tree to view them in 3D and to visualize the shade that they cast at any point during day-light. Using the two time-controls at the bottom of the map you can select any day of the year and/or any time of day to view the areas that will be in shade at any selected time.

You can also hover over any tree on the Tree Folio NYC map to learn what species of tree it is, its trunk diameter, and its current health. According to Cornell University factors such as tree health and canopy size contribute to the amount of shade a tree will cast. The University was able to use a 2021 LiDAR survey to create a 3D picture of the tree canopy of 666,000 New York trees, from which it was then able to calculate the amount of shade cast by each tree for any time of day and any day of the year.

Also See

JveuxDuSoleil - an interactive map which simulates shadows from buildings throughout the day

ShadeMap - mapping the location of shadows from the sun for any time and day of the year

Shadowmap - view solar shadows anywhere on Earth at any time of the day or year

A New Google Map of the Brain

If you've ever wanted to look inside someone's brain then you might like the European Commission's new 'Google Map' of the human brain. This new 3D map allows you to take a look inside a human skull and explore atlases of the brain's regions and neural connections.

The European Brain Research Infrastructure (EBRAINS) is funded by the European Commission to accelerate brain research and innovation in Europe. It aims to provide a collaborative platform for researchers, clinicians, and technology developers working in the field of neuroscience and brain-related disciplines. One of the project's outcomes is the Siibra Explorer, an interactive atlas of a human, monkey, rat and mouse brain.

The Siibra Explorer is a 'Google Map' of the brain. It is an online interactive tool for exploring maps of the brain and for visualizing brain data. The varied brain atlases provided by the Siibra Explorer provide detailed anatomical information and labels of the brain regions, allowing researchers to understand the organization and connectivity of different brain structures. Different brain data (such as MRI and other types of neuroscientific data) can be overlaid on top of the 3D brain model. Users can even use their own data with the Siibra Explorer, enabling them to analyze and visualize their data on a 3D model of the brain.

The Siibra Explorer maps includes its own coordinate system. This means that researchers and scientists can easily share and collaborate brain data and share information with other users, simply by sharing the URL of their current map view.

Using AI to Geolocate Photos

Recently Google added Google Lens to Bard, its AI chatbot. Today I decided to test how good Bard is at identifying locations in photographs by giving it a few screenshots of random locations from Street View and seeing how accurate Bard is at geolocating the actual locations shown.

Let's start with an easy one. I showed Bard the above picture of Tower Bridge in London and asked it 'Where was this photo taken?'.

Bard replied, 

"The photo you sent me shows a sign on a fence with the text "VISIT OUR PALACES TIME AND AGAIN". The background of the photo shows Tower Bridge in London, England. The distinctive towers and bascules of the bridge make it one of the most recognizable landmarks in London. 

The sign is located on the north bank of the River Thames, near Tower Bridge. This is a popular tourist destination, and the sign is likely promoting the Historic Royal Palaces, which are a group of palaces and castles in London that are owned by the British government. 

The photo was taken in London, England, near Tower Bridge."

Bard identified the location of Tower Bridge perfectly, even identifying that the 'sign' in the photo is on the north bank of the Thames. From Bard's response it is also clear that Bard performs text recognition on submitted images. Which could obviously help in identifying locations. 

Now, let's try a more difficult image. This image shows a bust of the illustrator Paul Gavarni, in Place St. Georges in Paris.

Bard replied to my query of 'where was this photo taken?',

"The photo you sent me shows a statue of Joan of Arc in the middle of a city street. The statue is located in Paris, France, on the Place des Pyramides. The square is named after the Luxor Obelisk, which was brought to Paris from Egypt in 1836."

Bard correctly identified the city as Paris. However it misidentified the statue as being of Joan of Arc, which is presumably why it identified the wrong Paris address for the photo. 

Luckily (or because I'm using Street View) I have another photograph taken on the same spot on the Place St. Georges, showing the view in the opposite direction.

This time, thanks to text recognition, Bard was able to identify the correct location. 

"The photo you sent me shows the front of a theater with the sign "Théâtre Saint-Georges". The theater is located at 51 rue Saint-Georges in the 9th arrondissement of Paris, France. 

The Théâtre Saint-Georges is a private theater that was built in 1929. It has a capacity of 498 seats and is known for its productions of comedies and musicals. The photo was taken in Paris, France, at the Théâtre Saint-Georges. 

I can tell this because the sign on the theater clearly says "Théâtre Saint-Georges" and the theater is located at 51 rue Saint-Georges in Paris. Additionally, the architecture of the theater is consistent with the style of Parisian theaters from the early 20th century."

From my very limited testing I think I agree with Bellingcat that Bard "struggle(s) with analysing images and (is) prone to seeing details which are not there". You can read Bellingcat's more thorough analysis of using Bing AI and Bard to find the location in images in their article Can AI Chatbots Be Used for Geolocation.

Bellingcat concludes that both Bard and Bing AI currently require "extensive prompting from the user before they could arrive at any halfway satisfactory geolocation". 

Bellingcat's analysis suggests that both Bard and Bing can often identify prominent landmarks. However Bellingcat's test also uncovered that neither AI model is able to identify logos in images (which obviously might help in correctly geolocating an image). In Bing's response to a query it actually shared its geolocating methodology with Bellingcat. This is:

• reverse image search - trying to find similar images online
• using metadata - EXIF data attached to images
• looking for recognizable landmarks
• using visual clues such as signs, flags, languages, license plates.

I asked Bard how it identifies locations depicted in uploaded images. Bard responded with similar answers to those in Bing's methodology. Unfortunately Bard might actually be 'hallucinating' its methodology in its reply. As ever it is never wise to trust an AI when you don't already know the truth.

Overall Bellingcat is unimpressed with Bing AI and Bard's ability to correctly identify the locations depicted in photographs. It concludes that using "an AI chatbot to fully geolocate an image is inadvisable. At this stage of AI’s development, it might be used to assist with very simple geolocations, perhaps pointing a researcher to an area that may warrant a closer look".

Fooling Bard

I decided to see if Bard was able to locate the replica Eiffel Tower in Las Vegas. I was half expecting Bard to geolocate this image to Paris but it actually managed to identify the location perfectly and to give some convincing reasons as to how it knows this image was captured in Las Vegas.

"The picture you sent me is a replica of the Eiffel Tower in Las Vegas. The real Eiffel Tower is located in Paris, France. So, the picture was not taken in Paris, France. It was taken in Las Vegas, Nevada. 

I can tell that the picture is of a replica of the Eiffel Tower because the structure is not as tall as the real Eiffel Tower and it is missing some of the details, such as the second level balconies. Additionally, the background of the picture does not match the surroundings of the real Eiffel Tower."

I wondered how much weight Bard gives to textual clues in an image. I therefore added some text to my image saying "This is the Eiffel Tower, Paris, France". Not only did my lying fool Bard but in its geolocation response it now claimed it could see all the features of the real tower that it previously said were missing.

"The picture you sent me is of the Eiffel Tower in Paris, France. The text in the picture also says 'This is the Eiffel Tower, Paris, France.' So, the picture was definitely taken in Paris, France. 

I can tell that the picture is of the real Eiffel Tower because it is the correct height and has all of the details, such as the second level balconies. Additionally, the background of the picture matches the surroundings of the real Eiffel Tower. 

I apologize for my previous answer. I was not able to see the text in the picture the first time."

Unlocking America’s Visual Time Machine

As well as having an insatiable passion for maps I also really enjoy browsing old photographic collections. Like maps vintage photographs have the power to transport our imaginations to completely different times and places. For example Yale University's Photogrammar collection can instantly take you back to the bygone era of mid-20th Century America. 

Photogrammar provides access to a huge collection of photographs taken during the Great Depression and World War II in the United States. The photographs were taken across the whole country between 1935 and 1944 by the Farm Security Administration and the Office of War Information. The collection is an amazing resource for anyone interested in exploring and studying American history and photography from the Great Depression and World War II eras. 

The maps in Photogrammar provide a visual guide as to where the original photographs were taken and also allow you to navigate the collection by location. Click on either the Counties or the Cities and Towns maps and you can filter the photographs in the Photogrammar archive by either a specific state or an individual county, city or town.

Also See

Street View of 1940's New York - 1940s photos from the New York Works Progress Administration

Street View of 1980's New York - 1980s photos from the New York Works Progress Administration

Wymer's DC - 4,000 images from the John P. Wymer Photograph Collection shown on Street View

Roadside America - vintage pictures from the John Margolies Roadside America Photograph Archive

12 Sunsets - Ed Ruscha's 1960's photos of LA's Sunset Strip

Mapping Water Scarcity

Last week the Washington Post reported on a new analysis from the World Resources Institute which found that half of the world's population already experiences water stress at least once every year. According to the WRI's analysis 25 countries around the world are now exposed to extreme water stress and the global demand for water is now exceeding what there is available.

The Post's article Here's Where Water is Running Out in the World includes a nice Mapbox storymap which takes the reader on a guided tour of some of the countries and regions which are being hardest hit by water stress. The Post's map includes a choropleth layer showing the levels of water stress around the world. 

Later in the article the Post also uses a small multiple map visualization to show water demand around the world in different sectors (irrigation, livestock, domestic and industry). Globally farming accounts for the most water use.

You can also explore global water use on the World Resources Institute's own interactive map Aqueduct. Aqueduct allows you to explore 12 key indicators of water risk to highlight where water scarcity and water issues are, or could be, a problem in countries around the world. The map has been updated recently to include WRI's latest global water stress analysis.

The 12 key indicators can be accessed from the map side panel. You can select any of the indicators to view a choropleth map layer showing the risks around the world for each water risk indicator. The indicators include risks such as access to water, drought severity and groundwater stress. 

You can learn more about the water risks facing a particluar area by clicking on the interactive map. Selecting a location on the map will open an information window containing a breakdown of the water risks faced by your chosen location. This information includes a rating of the overall water risk and the projected risks for the area selected.