Thursday, August 31, 2023

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.

Wednesday, August 30, 2023

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.

Tuesday, August 29, 2023

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. 

Monday, August 28, 2023

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.

Saturday, August 26, 2023

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)

Friday, August 25, 2023

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

Thursday, August 24, 2023

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.

Wednesday, August 23, 2023

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."

Tuesday, August 22, 2023

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

Monday, August 21, 2023

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.

Saturday, August 19, 2023

The AI Diplomacy Map

According to the interactive map Deeplomacy the "relationship between Iraq and the United States has been turbulent, complex, and marked by periods of conflict and cooperation." Deeplomacy also informs me that the relationship between Russia and Ukraine has recently "drastically worsened".

Deeplomacy is a new map tool which can explain the historical and current diplomatic relationships between any two countries in the world. For example you can explore Russia's relationships with other countries around the world simply by clicking on a country on the Deeplomcacy map. The map will then open an information window with a summary of the diplomatic relationship between the two countries.

When you select a country on the map Deeplomacy will also instantly color every other country on the map based on the selected country's diplomatic relationships. For example, if you select the United States then Canada and the UK are colored green of the map, to indicate that both countries have a 'good' relationship with the US. On the other hand Russia, Syria and Iran are all colored red on the map to show that these countries have a 'bad' relationship with the US.

The diplomatic summary relationships are derived from ChatGPT 4's Large Language Model AI. These summaries are based on the prompt "Describe relationship between Country X & Country Y .... then provide a final verdict of good/bad/neutral relationship". It is important to note that there is a September 2021 knowledge cut-off date on the underlying data that the AI model is trained on. In the fast moving world of global geo-politics this is a significant drawback for the map (for example Russia's invasion of Ukraine is not factored into Deeplomacy's diplomatic relationship summaries).

Friday, August 18, 2023


After last week's post on the growing number of interactive map games called City Guesser I was contacted by DoudouOSM on Mastodon, who pointed me towards GeoClash, an alternative to GeoGuessr built on Mapillary panoramic images and Leaflet rather than Google Maps.

GeoClash, like GeoGuessr requires you to identify locations based on 'Street View' type images. To play GeoClash you first need to create a room in and then select to play GeoClash from the available games (you can play as a guest if you don't want to register). In each game of GeoClash you have to identify 10 random locations around the world using 'Street View' images from Mapillary. However you only have 40 seconds to explore the location and point to the correct location on the world map.

Like all GeoGuessr type games the secret to identifying locations in GeoClash is to use the visual clues in the panoramic images. These clues include the language used in street signs & adverts, the style of architecture & street furniture, and the natural environment. You are awarded points in each of the ten rounds based on how close you guess to the correct location. 

The quality of crowd-sourced images in Mapillary tend to be slightly lower quality than Google Maps Street View. Which means that GeoClash is slightly more difficult to play than GeoGuessr. However being free to play is a huge advantage in GeoClash's favor. My major gripe is that 40 seconds isn't enough time to guess each location. I need at least 120 seconds for each round.

Thursday, August 17, 2023

Cinematic Mapping

Steve Attewell has created a fun Akira Kurosawa inspired interactive map. His Akira map allows you to explore a 3D map of the world through the lens of the most famous Japanese film-maker.

I don't know enough about Kurosawa's films to judge if Steve's map is an accurate simulation of the great director's style and aesthetic. I do know (by peaking at the HTML) that Steve's map works by applying a number of effects to a Mapbox map. These effects seem to include a blur, a tilt-shift effect, a lens reflection and a 'lens grime' effect. From what I can tell these effects are all created using SVG Filters.

Steve's Akira map is just the latest of his experiments to view the map of the world through rose tinted 3D glasses. Some of Steve's other map experiments include the Manga Map,  the Camera Lens Effect, the 3D Stereoscopic Anaglyph and Crossview Map, the Stippler Art Effect and the Terrain Elevation Viewer.

Wednesday, August 16, 2023

US Air Force WWII Photos

This aerial photo shows Manchester United's Old Trafford football stadium. The photo was taken during World War II, on May 30, 1944, by a US Air Force photographic reconnaissance (PR) aircraft. The stadium (top left) was hit by a German bomb in March 1941 and the damage caused to the south stand can be seen in the USAAF aerial photograph.

This aerial reconnaissance photo of Manchester is just one of the 3,600 pictures which can be seen in Historic England's new map of photos taken by USAAF photographic reconnaissance units in the UK during 1943 and 1944, after the US joined the war in December 1941. The US air force photos can be explored on Historic England's USAAF Collection interactive map. On this map orange polygons are used to show the area captured by a reconnaissance photo. You can view a photo simply by clicking on these colored polygons. 

Most of the photos on the map are top-down vertical aerial photographs. However the map also includes over 400 oblique 'bird's eye' aerial photos. Historic England's introduction to the map includes a section What Can I See in the Photographs? which picks out some of the reconnaissance photos taken of ancient monuments, airfields, military sites, and a number of different UK towns & cities.

The USAAF aerial photos can also be viewed on Historic England's Aerial Photograph EXplorer interactive map. This map also includes thousands of aerial photographs taken by the Royal Air Force between 1938 and 1945.

You can explore some of the bomb damage caused by German bomb raids on London on the Layers of London interactive map. Layers of London is an interactive map which gives you access to lots of historic maps and historical information about the UK capital city. It includes a fascinating layer of aerial photographs of London taken just after the war entitled the London RAF Aerial Collection (1945-1949)

After World War II the Royal Air Force methodically flew over the whole of Britain to photograph the country from the air. This resulted in 24,000 photographs of London. This aerial imagery provides a stunning visual record of London just after World War II. Bomb damage from the Blitz is clearly visible in lots of the imagery. 

In the screenshot of West Ham above you can clearly see where the bombs fell. The rows of Victorian era terraced housing are interrupted by temporary white prefab buildings (at the center of the image). These new cheap prefab buildings were erected to replace houses bombed out during the war. If you walk this neighborhood today you can still clearly see where the bombs fell. If any building is post-World War II then you can be sure it was built on the location of a bombed out Victorian era building.

Also See

The Luftwaffe Map of Kiev - an aerial photo map of Kiev created by the Germans in preparation for the 1941 Battle of Kiev.

Tuesday, August 15, 2023

The Meteor Shower Map

If, like me, clouds and city lights have so far ruined your view of the Perseid meteor shower then you might enjoy this beautiful Meteor Showers From Space interactive map. The peak viewing time to see the Perseids was on Aug 12 & 13, although the shower will be active for much of August.

The Perseid meteor shower is caused by Earth passing through the ice and rock debris tail of Comet Swift-Tuttle. You can view a simulation of the comet's tail on the Meteor Showers From Space interactive map. This map simulates the path of the comet's tail over time (starting in August of this year). You can select to overlay the orbits of the planets around the sun on top of this simulation. You can also select your viewpoint of the Perseids (from Earth or from the Solar System).

Meteor Showers From Space also allows you to explore simulations of a number of other meteor showers, including the Leonids, the Ursids and Lyrids. You can also select to view 'Everything at once' if you want to see all 12 available meteor showers on the same map. 

Monday, August 14, 2023

Neighborhood Colors

Kiezcolors is an interactive map which shows the distribution of land use in Berlin neighborhoods. On the map areas are colored to show whether they are used for business, housing, roads, nature etc. Alongside the street map a tree-map is also used to show the percentage of land used by each category within the highlighted area (the circle of 'undefined' radius).

You can use the map's search facility to center the map on any Berlin address, or you can simply pan the map to your desired location. The tree-map updates automatically to always show the distribution of land use in the circle at the center of the map.

When you have centered the map on the desired location you can then download a postcard shaped version of the resulting tree-map, visualizing the distribution of land use in your Berlin neighborhood. You can even download an SVG image of the reverse side of the postcard.

Saturday, August 12, 2023

Competing in the Tour de France

The New York Times has discovered a way for amateur cyclists to compete against the world's elite in the Tour de France. In Watch Amateurs Race Against the Tour de France's Top Climbers the newspaper has used Strava data to compare how amateur cyclists have performed on certain mountain stages in the Tour de France when compared to the fastest Tour de France cyclists (who posted their rides to Strava).

Using a number of animated maps the Times has created some lovely illustrations of the huge gap between amateur and elite cyclists. By comparing the progress of both amateur and professional cyclists on the same map (even though the rides were undertaken on different days) it is possible to make a direct comparison between the amateurs and professionals (although I don't imagine many people are going to be too surprised by the resulting maps).

Most of us don't have easy access to the locations used in the Tour de France. Instead you could use Strava (or any interactive map) to map out a cycle route of the same length as a Tour de France stage (the Times article gives the lengths of each stage that they have mapped). You could then compare the times you achieve cycling over the same distance to those achieved by the professionals in the Tour de France (you could even cheat a little by creating a route with hardly any climbs). 

Sepp Kuss completed the Puy de Dôme (Stage 9), which is 2.8 miles, in 16.40 minutes. According to this Average Speed Calculator that is an average of 10.08 mph. Apparently Google Maps estimates cycling journey times by using an average of 10 mph. So you might even be able to beat Sepp Kuss if you cycle on a flat or downhill route. Martin Catherineau, that amateur cyclist used in the Times article, completed the Puy de Dôme in 41 minutes, 58 seconds.

Friday, August 11, 2023

Mapping the Amazon Underworld

Welcome to the Amazon Underworld is an in-depth investigative series examining the crime and violence that is ravaging the Amazon rainforest. The project, which was conducted by 37 journalists and media professionals from 11 countries, uses satellite imagery, data analysis, and field reporting to map out the criminal gangs and the illicit economies that are driving deforestation, violence, and human rights abuses in the Amazon. 

In a series of articles InfoAmazonia reveals how criminal organizations are exploiting the region's natural resources, how armed groups are terrorizing indigenous communities, and how governments are often complicit in the violence. The stories also show how the Amazon underworld is having a devastating impact on the environment, with deforestation rates reaching record levels in recent years. 

Story maps and other interactive maps are used throughout Welcome to the Amazon Underworld. For example, in the series' introductory article, a story map is used to show which criminal gangs operate in which regions of the Amazon (the team discovered that crime syndicates and armed gangs operate in 69.5% of municipalities in the Amazonian border regions of Bolivia, Brazil, Colombia, Ecuador, Peru and Venezuela). Other maps are used in the other articles in this investigative series - often to explore where and how particular gangs operate in specific regions of the Amazon.

Thursday, August 10, 2023

City Guesser

One little known rule of GIS is that if you make an interactive geography game then you have to call it 'City Guessr' or 'City Guesser'. At least I assume that is why there are so many online map games bearing that epithet.

CityGuessr is a fun daily challenge which requires you to identify a location shown on an interactive map. Identifying a location from an unlabeled map can be very hard so each day you are provided with a number of clues to that day's challenge.

Each of the provided clues are worth a number of points. Use a clue and the designated number of points are deducted from your score. If you like CityGuessr (and you haven't played it before) then you don't need to wait until tomorrow for another game. Go to the CityGuessr MyPage and you can play any day's challenge that you haven't yet completed. You can also view how many times you have played and how many daily challenges you have won.

Fans of GeoGuessr should have no problem understanding how to play Cityguessr. In Cityguessr you are shown a Street View panorama of a random city. All you have to do is identify the city using the visual clues (street signs, street furniture, architectural signs etc) within the Street View images. 

In most cities you can explore a little by using the arrow signs in Street View to move yourself around. However you only have 150 seconds before you have to make a guess. Unfortunately sometimes Cityguessr gives you a user submitted Street View and you are unable to explore - which can make identifying the correct city very difficult. It's still fun to try though and if you do guess right it makes it even more satisfying.

City-Guesser is a fun map quiz which tests your knowledge of world cities. In City-Guesser you are shown the maps of major cities around the world. All you have to do is name which city is being shown in each map. To ensure that the game isn't ridiculously easy all the place-name labels have been removed from each city map. 

If you guess a location correctly you proceed to the next round. Guess wrong and the game is over. You get points for each correct answer. The game keeps a record of the maximum level you reach (the number of correct answers in one game) and your highest score. Your aim therefore is to beat your own high score and your highest level reached. Or you can try and beat me. So far I've reached level 7.

City Guesser is a fun location guessing game, which requires you to identify a location revealed in a video and point to it on an interactive map. 

The game shows you a random video of someone walking around a city or a famous monument. You have to pick up on the visual clues in the video (such as the languages & words used in street signs and the design of the street furniture) to identify where you think the video was shot. Once you have made your guess you just need to click on an interactive map and you are awarded points based on how close you got to the real location. 

There are a number of different games that you can play. You can choose to view videos just from one country - or you can play either a Worldwide or Europe game - featuring videos from across the world or from just within Europe. I'm not exactly well traveled so I was surprised at how many European cities I could identify from the videos. I didn't do so well on American cities. This may be partly to do with the fact that there are less cultural differences between different American cities than there are between different European cities. It is also obviously partly to do with my lack of knowledge of American cities. 

There is also monuments quiz, which shows you videos of famous monuments around the world. I'm happy to report that I'm the world champion at identifying well known monuments.

Wednesday, August 09, 2023

Mapping 3D Game Worlds

noclip is an amazing website which lets you move around and explore some of your favorite computer games in glorious 3D.

The term 'noclip' is a common command used to debug computer games. It refers to the process of turning off collision detection in a game world so that the player may pass through solid objects in the rendered environment. This is exactly what the noclip website allows you to do.

Select and load a game world from the noclip 'Games' menu and you can then explore that world in 3D. Using your mouse you can look around this world and using your keyboards 'W', 'A', 'S' & 'D' keys you can move around the game's 3D environment. As the 'noclip' name suggests there is no collision detection, which means you are able to freely pass through walls, trees and other obstacles to explore every nook and cranny of your chosen game world.

There are well over 80 computer/video game worlds to explore in noclip. Although you can only explore certain sections or levels in some of these game worlds.

I've stopped reviewing interactive maps of video game worlds because they are now ubiquitous and fairly easy for players to find. However if you desperate to find a 2D interactive map of your favorite game (in order to find that last karok seed or GTA action figure) then you could try Map Genie or IGN, both of whom now have huge collections of game world interactive maps.

Tuesday, August 08, 2023

Global Burning

The Pudding has released another stunning data visualization story. Mapping Record-High Heat in U.S. Cities is an interactive map which shows how many days since your city recorded its record high temperature (for today or of all time).

July was the hottest month on Earth in the last 120,000 years. This followed the hottest June ever recorded. Global Heating is happening, which is why The Pudding's map shows a lot of American cities have recorded their hottest ever temperatures this summer. 

If The Pudding's map, or your own lived experience, doesn't convince you that climate change is occurring then you can also explore your city's heat records for yourself on The Pudding's Tracking Heat Records in 400 U.S. Cities. This data story allows you to explore 134 years of recorded high temperatures in your city to see how these have changed over time.

Americans should by now be getting used to record high temperatures. During the course of last year's summer over 7,000 daily temperature records were smashed in the United States. This led the Washington Post to visualize where temperature records were broken during the summer of 2022. 

The animated map in the Post's Maps Show Extreme Heat visualizes where daily temperature records were broken from June 1 through September 7, 2022. Daily temperature records are broken when the highest ever temperature is recorded at a weather station on a specific calendar date. As you can tell from the animated map above the heat last year came in waves. 

You can also see that record temperatures were set in locations across the whole of the country. Heat-waves struck at different times in different parts of the country but no parts of the country escaped last year's record heat entirely.

Monday, August 07, 2023

30 Second Data Viz with OSM GPT

I reviewed OSM GPT for the first time earlier today and I have to say I was very impressed with how easy it is to use in order to extract data from OpenStreetMap. 

OSM GPT's natural language interface for searching OSM is great for geographical searches - for example to find all cafes within 1,000 meters of a location ('get cafes within 1000 meters'). OSM GPT can also be used for creating some very quick data visualizations - by using different colors to display the results of two or more different searches.

The map in the screenshot above shows all Streets (colored green) and all Avenues (colored yellow) in Miami. The map illustrates perfectly how all roads named 'Street' in Miami run almost exclusively west to east while all 'Avenues' run north to south. It took me less than 30 seconds to create this visualization in OSM GPT by typing in two queries:
"get roads named 'Street'"
"get roads named 'Avenue'"
I then used the eyedropper tool in OSM GPT to color Streets green and Avenues yellow.
Here is similar map showing the orientation of streets and avenues in Manhattan. This time all the 'Streets' are colored blue and the 'Avenues' are yellow.

If you have trouble getting OSM GPT to run these queries in your town you can click the 'Manual Query' button instead and copy and paste this query to search for all roads named 'Street':

out skel qt;

Just change the word 'Street' to 'Avenue' to view all the roads named 'Avenue' (or to 'Lane', 'Alley, 'Close', 'Hill' etc for other alternatives).

In the last couple of years I've seen quite a few interactive maps which attempt to show how much inner city geographies are given over to cars by highlighting parking lots on a map. The screenshot above shows an area of Los Angeles after running the query 'get all parking'. This data viz took me only a few seconds. You can view how much of your town is a parking lot by simply centering OSM GPT on your address and typing in 'get parking'.
This map shows the space dedicated to parking lots (red) and to parks (green) in an area of Los Angeles.


This week's OSM Weekly links to a new interactive chatbot which allows you to interact with OpenStreetMap data.

Rohit Gautam's OSM GPT allows you to use natural language queries to search OpenStreetMap. For example the screenshot above shows the results of 'Get all bars' in New York. It also shows the results of a query to 'Get all McDonald's restaurants'.

I don't know how OSM GPT works but I presume it uses the ChatGPT large language model to translate user queries into recognizable OpenStreetMap tags. It then uses Overpass Turbo to query OpenStreetMap data and show you these query results on an interactive map. For example if I type 'mosque' into Overpass Turbo I don't get any results. This is because mosques are tagged 'amenity: places of worship' and 'religion: muslim' on OpenStreetMap. OSM GPT is actually able to interpret my search for 'get mosques' in London and realizes that in terms of OSM I am looking for locations tagged as 'places of worship' and 'muslim'. 

In other words OSM GPT is really a natural language interface for Overpass Turbo. Which is great as creating queries in Overpass Turbo can be very difficult for those not familiar with Overpass QL. OSM GPT even creates the Overpass Turbo query for you. Which is fantastic if, for example, you want to run a similar query on Overpass Turbo for another town or city. Another brilliant feature of OSM GPT is that it allows you to download the results of all the queries you make as a GeoJSON file. 

You can also use OSM GPT to search within a defined range of a location. For example the screenshot above shows the results of searching for 'post offices within 1,000 meters of the Embarcadero, San Francisco'.

Also See

Texttomap - enter any geographical based question into Texttomap and it will attempt to answer your question and show you the results on a map

mapsgpt - an interactive map which allows you to search using input forms to generate natural language queries.

Sunday, August 06, 2023

Swimming in Sewage

Over 50 competitors in last weekend's World Triathlon Championship Series in the UK fell ill after swimming in the sea off the coast of Sunderland. The UK's filthy rivers and sewage discharges have been largely blamed for the outbreaks of diarrhoea among those competing in the triathlon. 

In the UK the privatized water companies are allowed to discharge raw sewage into rivers when the system becomes overwhelmed, which often happens when there is heavy rain. This handy loophole seems to have encouraged the UK's privatized water companies to refrain from investing in and updating the UK's sewage infrastructure. Why invest in improving the system when you can simply discharge raw sewage whenever you need to?

Unfortunately for the water companies dumping untreated sewage into rivers is very unpopular with the public and lots of organizations have begun mapping discharges of untreated sewage. For example, two days ago Greenpeace unveiled its new interactive map Sewage Spills in Protected Areas. This map shows how many hours of sewage were discharged last year in conservation areas and areas of special scientific interest. These are areas which are home to very important natural habitats used by protected bird and animal species.

The River Trust's Sewage Map also shows you where water companies discharged untreated sewage in 2022, in this case across the whole of England and Wales. On both these maps scaled circles are used as markers. The size of the markers representing the total number of hours that untreated sewage was discharged at a location during 2022.

If you live in the Thames Water area then you can view untreated sewage discharges in near real-time on the company's EDM Map. This map provides near real-time information about storm overflow activity. Yesterday much of the area covered by the map saw lots of rain. Which means that at the moment the map contains lots of exclamation marks (indicating locations where untreated sewage has been discharged in the last 48 hours) and double exclamation marks (locations were untreated sewage is being pumped into rivers right now).

The UK isn't the only country to be experiencing sewage problems. Paris has just had to cancel a swimming event due to be held in Seine, which was designed as a test for next year's Olympic Games. According to The Guardian the event was cancelled after untreated sewage was discharged into the Seine during heavy rain.