Hold the Mayo: Yeah, a Sandwich Map

Nothing worse than being in a place where you know there are zillions of places to shop and eat, but you really don't know where anything is. Around the next corner? Street level at the next subway stop? Somewhere right in front of you? Tired of being lost in this regard, NYC sandwich guru and data scientist Dan DeWitz took matters into his own hands and came up with his own solution for the next time he has that certain palate craving.

Background

Held this past March 22-30, Open Data Week is an annual festival of community-driven events organized by the NYC Open Data Team at the Office of Technology and Innovation (OTI), BetaNYC, and Data Through Design.  It is held each March to coincide with the anniversary of the City’s first open data law which was signed in March 2012.  Additionally, one of the highlights of Open Data Week is the NYC School of Data which includes a myriad of workshops, panels, and demonstrations with the intent of  demystifying the policies and practices around data and technology in the City.  This year’s program included over 30 presentations.  At its foundation, an immerseful week of users, open data, open software, and open development discussions.

Not all of the week’s presentations are specific to GIS technology as topics such as law, journalism, government budget transparency, data analytics, career development, even data comics, and much more are covered in the  agenda.   And as Open Data Week has evolved over the years, there’s also always been a healthy dose of the traditional GIS and mapping concepts which the geospatial community is actively engaged in.  Though always the space for the unexpected mapping product and presentation, too.  Something a little out-of-the-box and out of the norm.  This year was no different.

Ye​ah, ​a Sandwich Map.

Background

As part of the Data Week’s events, Dan DeWitz led an online interactive hour-long workshop  showing attendees how he built the sandwich map from scratch.  Working from his Jupyter Notebook, DeWitz illustrated how  he used ChatGPT as a coding partner, as well as python code, to scrape a list of  sandwich names – and associated information – from a website and create an interactive sandwich map using the Google Maps API and GitHub Pages.

New York Times Article

Central to the map was a New York Times article published ​February 18, 2024.  Authored by Nikita Richardson, the article was  based on three months of work by  New York Times Food staff which covered all five boroughs in search of heroes, bodega staples, breakfast specialties, veggie entrees, and much more.  The intent wasn’t to necessarily rank the sandwiches but much more so to illustrate the culinary diversity across the New York City urban landscape.  As mappers and always worrying about icons and how to symbolize our work, the images depicting the  sandwich categories are a treat, too.  Which DeWitz was able to scrape and use in his web map as well.

Nine sandwich types were identified in the article: Breakfast Bangers, Hero Worship, Veg In, Pastrami City, Gotham Greats, “Let Me Get, Uhh..”, Diner Party, Honorary New Yorkers, and Extremely Online. Something for everyone!

 Scraping and Geocoding

DeWitz’s initial dialog with ChatGPT to start building and ultimately generating the sandwich map is shown in the image below.  He initially intended to be able to parse each of the variables shown – sandwich and restaurant names, addresses, description, and images from the Times website, but determined large language models (LLM) like ChatGPT still can’t parse websites just from a URL.  Dewitz notes,  “I used Python to  scrape data from a page and guiding the model through each step: identifying the structure of the site, selecting relevant HTML elements, handling errors, formatting results, and mapping the output – all while applying judgment about what matters and why”.

DeWitz’s initial dialog with ChatGPT to start building and ultimately generating the sandwich map

For geocoding, DeWitz used the Google Maps API and ChatGPT handled writing most of the python code – most of which was the focus of his Data Week presentation.  DeWitz felt the Google Maps API did a good job with the addresses, particularly in context that the restaurant addresses included only a cross street and didn’t have the city name or zip – as presented in the Times article. For example, just passing the text (address) below, which was scraped from the article, to the Google Maps API, was good enough for most of the shops and the API returned the correct lat/long:

135 India Street (Manhattan Avenue)

For the remaining shops that did not match, he queried the API by restaurant name and then manually looked at the results and filtered as needed.  The web map base map also comes from the Google Maps API.

In the Jupyter Notebook, the interface is made up of individual cells with some containing text and others with code that can be executed.  The blocks with a tinted blue background are the ones where users write and execute Python code. This code sometimes comes AI engines such as chatgpt.com or the chatgpt assistant which is integrated into the Jupyter Notebook. All of the major steps and coding DeWitz used in the development process is available on his GitHub page which is available here

The End Product

For those wanting to take a deeper dive into the process and product, a  recording of the actual Data Week online presentation can be found at this YouTube link.   And of course, here’s the online Iconic NYC Sandwiches interactive map.

Interesting to note in context of determining that he actually accomplished what he set out to do, DeWitz feels the process had a built in quality assurance test. “Since I’m making a map, the output itself is the quality assurance test— especially that now I can actually use the map to go to restaurants and shops.”

It certainly appears that the QA passed.

Contact:

Dan DeWitz
dewitz.dan@gmail.com

10 Questions: ChatGPT for New York State GIS

I thought I was going to get out in front of all the ChatGPT for GIS discussion for the New York State GIS community, but that turned out to be off by a magnitude of sorts.  YouTube is already replete with ChatGPT for GIS tutorials and if we wait until next week there will probably be another ChatGPT alternative.  (I found the Matt Forrest YouTube video a good ChatGPT for GIS intro – actually formed a question after one of his examples).  Even Amazon jumped into the frey recently with their Amazon Bedrock option.  Take your pick, Bing Chat, Chatsonic, YouChat, Google Bard (available via a waiting list) and a whole host of others on the market in 2023. 

No, the robots aren’t taking over and I suspect we won’t see any of the early Terminator Cyberdyne Systems androids applying for your local GIS Analyst position anytime soon – though it might be a solution for those long dreadful digitizing jobs in the cart lab.  One way or another, Chatbot AI technology is definitely here to stay, evolve, and become another piece of the geospatial toolbox.  

Nothing specific or implied in any the questions.  Just random chains of thought though it does take a little getting used to putting the questions together vs. a basic Google search.  And it does seem to help to refresh and ask the same question twice – or even three times – to get more detailed results.  Never was a programmer, so a little short on questions in that space.

A lot here.  Actually 17 questions in all.  Straight copy and paste. Skim through as you want – find a topic/question you might be interested in.  There are tons more which could have been included.

Without any further adieu, my first machine interview: 

eSpatiallyNewYork:  What freshwater fish datasets are best for mapping fish population based on water depth in the Great Lakes?

ChatGPT:  There are several freshwater fish datasets that can be useful for mapping fish populations based on water depth in the Great Lakes. Here are a few options:

  1. Great Lakes Acoustic Telemetry Observation System (GLATOS) – This dataset provide information on the movements and behaviors of tagged fish in the Great Lakes.  It includes data on depth, temperature, and location, which can be used to create maps of fish populations based on water depth.
  2. Great Lakes Fishery Commission (GLFC) – The GLFC maintains a database of fish populations in the Great Lakes.  This dataset includes information on fish specifies, size, and location, which can be used to map fish population based on water depth.
  3. Great Lakes Environmental Database (GLENDA) – GLENDA is a comprehensive database of environmental data for the Great Lake region.  It includes information on water depth,  temperature, and environmental factors that can be used to map fish populations.
  4. USGS Great Lakes Science Center – The USGS Great Lakes Science Center conducts research on fish populations in the Great Lake and maintains a database of fish surveys.  This dataset includes information on fish species, abundance, and location which can be used to map fish populations based on water depth.

Ultimately, the best freshwater fish dataset for mapping fish populations based on water depth in the Great Lakes will depend on the specific research question and the type of analysis being conducted.

eSpatiallyNewYork:  To what degree of accuracy can I map features from New York State orthophotography?

ChatGPT:  The degree of accuracy with which you can map features from New York State orthophotography depends on various factors such as the resolution of the imagery, the accuracy of the ground control points used for georeferencing, and the skill and expertise of the analyst.

New York State orthophotography typically has a resolution ranging from 0.5 to 1 meter, which means that individual features such as buildings, roads, and other infrastructure can be identified and mapped with a reasonable level of accuracy. However, mapping smaller features such as individual trees, shrubs, or small structures may be more challenging, as these features may not be visible at this resolution.

The accuracy of mapping also depends on the quality of the georeferencing. The accuracy of the ground control points used for georeferencing should be of a similar or higher resolution than the orthophotography itself. This ensures that the imagery is correctly aligned with the ground, allowing for accurate measurements and mapping.

The skill and expertise of the analyst are also critical factors in the accuracy of mapping features from orthophotography. A trained analyst with experience in image interpretation and feature extraction techniques can accurately identify and map features with a high degree of accuracy.

Overall, mapping features from New York State orthophotography can provide a reasonable degree of accuracy for larger features such as buildings, roads, and other infrastructure. However, mapping smaller features may require higher resolution imagery or other sources of data. It is always important to validate and verify the accuracy of the mapping results through ground truthing and other quality control measures.

Continue reading

COVID Era Geospatial Applications to Support Empire State Communities

Here in southeastern New York State, it’s amazing how fast the COVID wave came and went. At first, mid-March to mid-May seemed like an eternity, but now, not so much.  I likened the preparation for COVID to preparing for Super Storm Sandy.  Albeit phenomenally different, the buildup and the anxiety of waiting for it to show up.  Peering out the windows to see the outcome of a completely different kind of damage and suffering  altogether.  Physical and psychological.  Now July, it seems and feels like we can see the first wave of the pandemic in the rear view mirror.  But then as we refocus on the road in front of us, we know there are speed bumps ahead of us.  Not if, but when.

There were a plethora of interesting and meaningful geospatial viewers created across the state during the mid-March to mid-May time frame.  Most included highlighting COVID case numbers by larger units of geography (municipal or zip code boundaries),  generalized heat or pattern maps, impacts to businesses and institutions, as well as  information on hotlines and sources of assistance.  However, its pretty well documented the geospatial community across the state has struggled with being part of providing detailed spatial analysis or mapping support functions at the address level.   Or for that matter, even being asked to participate in this regard.

Personal health related data is uber protected with its use regulated and governed by the Health Insurance Portability and Accountability Act (HIPPA).  HIPPA  regulations reign supreme and contributed to a lesser involvement of GIS analysts in  providing geospatial content, metrics and analytics during the pandemic.  There is also the unspoken reluctance on the part of the public health community to release data sets  which might be difficult to understand or easily misinterpreted by the general public.  Department of Health  professionals often cautious to release data – particularly in new instances such as the COVID pandemic – and leaving analysis/interpretation  to internal professional staff only.  Ultimately though,  releasing some flavor of the data but in a more generalized context.

NYS Department of Health (DOH)  COVID-19 reporting has improved dramatically since the pandemic appeared in March.  Though while numbers  are made available only on a county basis, users can access and visualize the data in a variety of ways.  Reporting and posting of the data has become much more timely.  DOH is also now publishing a regional “Early Warning Monitoring Dashboard“.

Continue reading

Google Earth in the Classrooms

Chromebooks, Google Classroom and Google Earth Together Provide a Framework for Teaching Geography and many other subjects in K-12

I actually started drafting an article on Google Earth in the classroom last fall but since then it’s been one thing or another pushing things to the back burner.  Mostly work priorities but then COVID-19 sent everything sideways.  Seemingly pointing us all in a new and uncharted direction.  A new and greater reliance on the internet as many of us found ourselves working remotely.

The remote work force in many of our extended families includes teachers of whom I now have even greater respect after watching what is involved in teaching remotely and online.  The lesson plans, prep work, surgically attached to the computer, and the seemingly endless hours of the encompassing interaction with students – and parents – well beyond the normal eight-hour work day.

In a roundabout way watching this teaching workflow unfold during the COVID lockdown brought me back to the Google Earth article.  Google’s presence in the classroom is ubiquitous built around Google Classroom which I can only imagine will grow immensely as remote K-12 education expands in the future.  Wrapped in with kabillons of lesson plans, templates, covering every education topic, discussion groups, forums, and blogs from around the world – everything built on top of Google technology.  Easily delivered and made available to the masses at all levels of the educational spectrum with the uber cheap and incredibly functional Google Chomebook.  (btw – using one as I type).   And easily accessible within this framework – and bringing me back to the beginning of this article – is the Google Earth product for use in the classroom.  It’s an incredible product to augment K-12 classroom teaching and not just for geography.

Continue reading

The Definitive Map for New York State Media Arts

New Online Application Shows Locations and Services for Organizations and Artists Across the State

Image from Heidi Neilson’s Southern Florida Beachball Antenna Archive (2017)

While the Empire State geospatial community is accustomed to seeing terms such as Google Maps JavaScript API, GeoJSON, and HTML as part of the conversation in building online mapping applications for government and business, we increasingly see the use of these same online mapping development tools in the nonprofit sector as well.  One such example is the newly updated New York Media Arts Map which is a project of of the New York State Council on the Arts (NYSCA) Electronic Media and Film program, managed by Wave Farm.  Though Wave Farm is more commonly recognized as an arts organization dedicated to transmission arts with FM and online radio stations, it is their regrant partnership through NYSCA which ultimately led to its stewardship of the online Media Arts Map. Serving in this capacity, Wave Farm assists in administering and distributing grant funds, ranging from $500 to $10,000, to dozens of New York State individual artists and organizations – all of which are included in the Map.

The Map

At its core, the Map is an extensive online catalogue of Media Artists, whose interdisciplinary work includes a wide range of fields including visual art, film, computer graphics, data visualization, sculpture, architecture, music, photography – even drones – and much more. The Map lists organizations which are recent grantees of the NYSCA Electronic Media and Film program (EMF) and the Media Arts Assistance Fund (MAAF).  In all, there are 198 organizations and 69 artists included in the Map.  First launched in 2009 and originally hosted by Rhizome, the 2014 update is the work of Peter Berry who is a developer affiliated with Supercosm, a Seattle, WA based firm which focuses on work with nonprofits.  In addition to the software components already mentioned, Peter’s work on the back end of the map includes the use of open source pieces CakePHP and Apache bundled with MySQL.

In addition to providing location information on organizations and artists included on the map, pull down menus along the top tool bar include additional statewide media arts information on meetings and workshops, partnership reports, and information on funding opportunities.

The Search box offers a wide range of options to filter the organization/artist database. Search queries provide a description of the types of work, services, and types of media arts offered as well as online contact information.

Intersection of Media Arts and Technology

It’s interesting to see, albeit even on some small level, how  the media arts world finds itself close to the geospatial space.  For example, take the work of  Harvestworks which supports the creation of art works achieved through the use of new and evolving technologies and provides an environment for experimentation with project consultants, technicians, instructors and innovative practitioners in all branches of the electronic arts.  A recent report by the organization entitled Common Ground provides “an overview of how and where transdisciplinary work is taking place in New York State, and makes recommendations to encourage further opportunities for artists that, when combined with environmental research, can aid engage the public, encourage environmental stewardship, and benefit communities”.

The report was published by the Harvestworks Digital Media Arts Center and The New York City Urban Field Station which is a partnership of the U.S. Forest Service, New York City Department of Parks and Recreation, and the Natural Areas Conservancy. (The Field Station in NYC supports the Arts and Humanities Residency Program. Check out the Summer 2018 Moon Arrow project – a time lapse compilation of the Moon Arrow pointing to the moon on New York City shorelines).  Open data, building code and hackathons in the geospatial space of your interest?  Then take a look the work of the School for Poetic Computation.  And how about drones?  While the technology is evolving incredibly fast, there was the 2018 Art Omi, Wave Farm and eteam live performance of The Aerial Actor which focused on the rising use of drones in science and art.  Actual drones were used as both carriers of messages and actors in the performance.  “The Map is a vital resource identifying art and technology projects and activity throughout New York State supported by NYSCA Electronic Media & Film”, says Galen Joseph-Hunter, Executive Director, Wave Farm. “It is also a useful tool for showing a geographic picture of how support is distributed throughout the state.”

Summary

So stop for a minute, grab a cup of coffee and put down the pen, I mean your mouse, and take a deep drive into the New York Media Arts Map site.  See what’s in your region, maybe even your neighborhood.  Support the statewide media arts community.  Cool stuff – all from the traditional artistic settings to the avant garde and experimental.  And sometimes, just a one-off from the geospatial space we work in.

Enjoy.

Contact:

Galen Joseph-Hunter
Executive Director
Wave Farm
Radio: WGXC 90.7-FM, Transmission Arts, Grants
518-622-2598
galen@wavefarm.org

The Geography of an Adirondack High Peaks Unsupported Thru-Hike Record

Background

Since early July this summer when our youngest son Lukas and close friend Mike Jock completed and established  a new record for an unsupported thru-hike of the 46 Adirondack High Peaks, I’ve been asked by various friends and colleagues across the region (who became aware of the accomplishment) as to whether or not any professional geospatial/GIS technology was used in some capacity in supporting the effort.   Each time my humbling answer has been pretty much the same:  Not Really.  However, they did carry some new gadgetry which is currently used ubiquitously across the adventure and extreme sports landscape to collect data that was used to authenticate their achievement.  But more on that later.

Starting their trek at the trail head to Seward Mountain at 3:30 AM Thursday, June 27th on the west side of the Adirondacks, the two covered the 46 High Peaks in 7 days, 2 hours, and 52 minutes finishing by summitting Mount Esther, on the northern shoulder of Whiteface shortly after 3 AM on July 4th. Ultimately making it down to the Mount Ester trail head at 6:20 AM to complete the trip.   All said, nearly 212 miles and 70,000 feet gained in elevation – more than twice the elevation of Mt. Everest.  They averaged well over a marathon a day, covering some 25-30 miles. On the final day they kept moving for more than 23 hours covering 45 miles.

Michael, left, and Lukas at the summit of Armstrong Mountain with Gothics Mountain in the background. The two were soccer teammates at SUNY Cortland. Mike King photo.

Preparation was more old school than one would think.  Nothing in this space replaces on-the-ground knowledge of the trails, trail junctions, where and when to bushwhack, locations of rock cairns for reference points, as well as planning and hiking/testing certain stretches of the route ahead of time.  Yeah, practice runs.  Luke had the benefit of many years of experience having first started ADK trail hiking since he was barely in kindergarten.  Like many other young children, his first “mountain” being Mt. Jo overlooking Heart Lake adjacent Adirondack Loj.  Safe to assume that through the family ties, his spatial orientation has always been pretty decent. Mike, a local boy, grew up in the Plattsburgh area.

This was their third attempt.   And such accomplishments don’t come without the element of good fortune avoiding injuries (which was the case in 2018) and a bunch of days with generally decent weather.  The 2018 attempt was also impacted due to an encounter with a black bear.  Yet another ADK backcountry hiker lesson in overnight food storage.

Given the enormity, location, and challenges of the effort, it would clearly not be safe, if not irresponsible,  to rely solely on the new generation of lightweight/handheld navigational devices as a means to lead one through the Adirondack Mountain wilderness.  There is no substitute for first-hand knowledge of the trail network and a pre-determined plan.  They carried only the essentials such as lighweight sleeping bags, tents, change of clothing, raingear, first aid/basic emergency gear, water filters,  and food.  Counting every ounce in keeping their backpacks to about 40 pounds.  Even omitting the weight of gas canisters/gas stove and in doing so did not prepare anything hot the entire trip.  Zero assistance.

Cool Gadgets

It’s amazing how far the adventure mapping and video/data collection market has evolved since GoPro technology was introduced nearly a decade ago, if not earlier.  The ability to playback Mike and Luke’s accomplishment – made available below via a series of links – is amazingly made possible by just a one simple mobile (wearable) component.  They used a Garmin Fenix 5 GPS Watch to collect X,Y and elevation data which, based on wireless connectivity, automatically uploads to Garmin Connect.  Upon completion of their hike, the entire trip dataset was downloaded to Relive an outdoor 3D video website which allows further rendering and interactive use of the data.    Two Anker PowerCore 26800 pre-charged power banks kept their phones and Garmin device charged.   Of sufficient size to recharge their phones/devices numerous times over.  They took two but in fact only needed one.   The Garmin app also collects heart rate, estimated calories burned, pace (minutes per mile), elevataion gain/loss, and total daily distance – all of which is made available in interactive and graphic form.  In addition to the default Google basemap, data can be rendered on other base maps including satellite, terrain, OpenStreetMap, and Here.  Amazingly compact, yet powerful tools.

The Daily Numbers

The following section includes a brief narrative – Mike’s own words- and links which can be used to highlight trail and body metrics as well as mapping visuals for each hiking day.  For those familiar with hiking and trekking in the Adirondacks, the visuals certainly help put Luke and Mike’s daily segments in better perspective.

Hold on to your seats.

Thursday June 27

Hiker Notes: 3:30 am depart from Corey’s Road.   Day consisted of seven mountains: Seward, Donaldson, Emmons, Seymour, Santanoni, Panther & Couchsachraga. Out and backed the first four.  Trekked approximately 10 miles to Santanoni range.  Set up camp at the base, then we went up the expressway to summit Santanoni first, followed by Panther, and then finished with Couchsachraga. We came down the Panther brook trail before staying at camp at base of expressway again. Approximately 37.84 miles.

Instructions for all similar images below: Click on map for additional graphics and daily metrics. Or click the black triangle button at the bottom of the screen to see hiker movement over the course of the day.

Instructions for all similar Relive 3D Interactive links below: Click on the icon circled in red to see daily hiker movement on top of a 3D base map and associated photos. Clicking on the “View Interactive Route” button enables the ability to interact with the map and trail data “twirling” the image to see from the north, east, south, and west perspective.

Friday June 28

Hiker Notes: From camp, hiked over to Allen mountain, out and backed it before moving up towards Colden/Avalanche Lakes. We out and backed Mount Marshall before setting up camp over the dam at Lake Colden. We summited two mountains and covered approximately 28.47 miles.

June 28thRelive 3D Interactive

Saturday June 29

Hiker Notes: The ADK Loj Loop day. Summitting eight mountains and doing a big circle before returning to the same place we camped the night before. We started by going up the backside of Colden, then Tabletop, Phelps, Street, Nye, Wright, Algonquin and finishing on Iroquis. Approximately 32.18 miles

Note: The only day “noise” was either user generated or introduced by the Garmin device itself. In the vicinity of Street and Nye – Illustrated by the “straight” additional red line. Also reflected in the Relive 3D viewer.

June 29thRelive 3D Interactive

Sunday June 30

Hiker Notes:   Audible day. Started by moving to the base of Cliff and Redfield (out and bacs), then trekking up towards Gray, Skylight, Marcy, Haystack, Basin and finishing with Saddleback. Due to it raining all day, made the game time decision to check out and head towards Johns Brook Lodge where we camped at the trailhead of Big Slide Mountain (setting ourselves up the next day to finish the Great Range and start moving east). Summitted eight mountains and covered approximately 22.5 miles.

June 30th:  Relive 3D Interactive

Monday July 1

Hiker Notes:  Out and backed Big Slide early in the AM, before climbing up towards Great Range. First we summited Lower Wolf Jaw, then Upper Wolf Jaw, Armstrong, Gothics and Sawteeth. We then headed down trail to Lower Ausable Lake. Next we did Colvin and Blake before camping between those two mountains.   In total we summited eight peaks again and covered 23.97 miles.

July 1st:  Relive 3D Interactive

Tuesday July 2

Hiker Notes: Started by ascending Nippletop, moved on over to Dial, then bushwhacked down towards the Dix Range. Once we got down from bushwhack/brook we dropped bags and then out and backed the entire Dix Range: Dix, Hough, South Dix, Grace Peak & Macomb. From there we got our bags again and then moved our stuff over to Roaring Brook and the base of Giant Mountain. In total we covered 25.26 miles and summitted seven peaks.

July 2nd:  Relive 3D Interactive

 Wednesday July 3

Hiker Notes:  The 24 hour day. Woke up at 3 am and went to get Giant and Rocky Ridge Peak (out and backs). From there we picked up our stuff again and schlepped ourselves 5.5 miles down route 73 toward Marcy airfield. Next up was cutting from one side of 73 to the Lake Placid side of 73 along the ridge trail that summitted Porter and Cascade Mountains. Off of those we had then a 10 mile stretch on route 73 and then River Road towards the trai lhead to Whiteface mountain. Using the trail by Connery pond we entered that portion at 1030 PM and was able to summit both Whiteface and then Esther by 3:15 am. About 23 hour and 30 minutes of moving time we summitted our final 6 peaks and covered 44.18 miles. Passed out for an hour and reached Memorial Highway by 06:22 AM, where a time-stamped photo was taken.

July 3nd:  Relive 3D Interactive (Part 1)  Incredible day!!

July 4th:  Relive 3D Interactive (Part 2)

Summary

Quite an effort  and on top of setting the record, between this trip and last year’s attempt, the two helped raise nearly $18,000 for the Dubin Breast Center at Mount Sinai Hospital in New York.  Their accomplishment was covered by Backpacker Magazine as well as a selected number of upstate New York online publications (UpstateNewYork and NNY360) among others.  The articles are generally similar in content though do offer more details about food and other daily nuances/items which I omitted here.  Choosing rather to highlight and focus on the immense geographic element of the effort.

Both Luke and Mike are personal trainers living and working out of New York City.  More information can be found on their website Team Adventure Portal.

Geogames: The Intersection of Geospatial and Games

Behind the scenes in the various worlds of films, games, science, military, government, and even the maker culture, is how “geo” has been gradually verging/bringing all of these industries together. The proliferation of smart phones with maps and searches for food and entertainment, geotagging, as well as ride sharing has brought “geo-data” to everyone and seemingly everything.  Though geospatial data, geospatial analysis, and basic mapping and cartographic concepts have been well established for many years, it’s only been within recent years that technology has enabled science to push and combine animation and gaming with real world geometry.

Here in the Empire State, faculty at Rochester Institute of Technology (RIT),  recently ranked #4 in the United States in Video Game Design Schools, Brian Tomaszewski and David Schwartz, are currently working on this technology “convergence” supported through a grant from the National Science Foundation (NSF).  This effort combines Dr. Tomaszewki’s recognized work focusing on GIS (geographical information systems) applications in the areas of disaster management and risk assessment.  He currently serves as Associate Professor and runs the Center for Geographic Information Science and Technology. Augmenting this work is Dr. Schwartz’s background and ongoing work in game programming, prototyping, and design, which he uses to build academic collaborations across RIT program areas including liberal and visual arts, engineering, business, and now the geospatial sciences. He serves as Director and Associate Professor in the  School of Interactive Games and Media (IGM).

“The world of games has long sought academic legitimacy, which for the most part has been achieved, by demonstrating ‘seriousness,’” notes Schwartz.  Some of the best games are great at teaching players to play those games, many of which have been designed at RIT: Lost and Found (religion), IPAR (computing security), and others.

Lost & Found is a game series that teaches medieval religious legal systems with attention to period accuracy and cultural and historical context. Both games are set in Fustat (Old Cairo) in the 12th Century.

If designers can capture that same immersive engagement for learning, training, education, then game development can make traditional learning, or “non-fun” entertaining and more participatory. There have been several great examples, and there are all kinds of offshoots with government, military, humanitarian, scientific applications, e.g., Instructional Design, Games for Health, and Cybersecurity.

Some of the underlying concepts and building blocks of mashing gaming and GIS software, what is called geogames and location-based games, together include, but not limited to, are:

  • Focusing on creating applications around a recent and “real life” historical event that has relevance to end users
  • Using industry accepted development tools to create the geogame
  • Demonstrate that a location-based game based on real-world data can promote and teach spatial thinking skills
  • Provide a “game” to emergency responders and local users that provides a framework for future refinements and enhancements to the game
  • Demonstrate that a serious geogames have academic and research merit

With respect to the intersection of gaming and geospatial, Pokemon Go has recently demonstrated people interacting with a virtual world “on top” of the real world, incorporating location-based data into visual interactive, decision-making environment. “The Games for Change” organization based in New York City has generated considerable attention to showing how game creators and social innovators drive real-world change using games that help people to learn, and improve their communities.

Convergence of Films and Games through GIS

One reason for the excitement on the evolution of geogames is this convergence of various disciplines, technologies, and software environments. Geogames being developed at RIT include free and open source software (FOSS), such as Open Street Map for ubiquitous baseline street data, as well as  Unity—a leading and popular game engine for rapidly making games. Unity (which is free for certain applications) has been incredibly important for the “indie” game scene, as well many other industries in professional games, movies, advertising, marketing, and more.

Other key aspects of the convergence include ESRI’s CityEngine, which historically has been used for urban design and 3D modeling.  It has had success in various films in making the worlds for Toy Story 2 and Coco. Even RIT’s hometown of Rochester, New York, was an early adopter of City Engine. Other pieces include real-world geospatial datasets, such as elevation models and flooding reach information.

Taking real-world mapping data into City Engine and then porting everything into a game engine enables game developers to visualize a real-world city or landscape. The game then renders graphics and animation,  handles interactions (player controls and responses), and embeds (through a lot more programming and design) the game rules (what happens, or outcomes, when the player interacts in specific ways.

Project Lily Pad:  Bringing the Pieces Together

Tomaszewski and Schwartz’s NSF grant and support of RIT’s computing college includes research experience for undergraduates (REU), which took eight undergraduate students from around the United States and four School of Interactive Games and Media (IGM) students from RIT to study how geogames can improve visualization for disaster planning.  Their study area was city of Dickinson, Texas, where Hurricane Harvey hit the city on August 30, 2017.

The program was developed integrating GIS and game technology by transferring (and updating) data/models from Open Street Map to ArcGIS to CityEngine and finally to Unity. Both local elevation model and flood data were used to model the city and create the game with almost real-life accuracy as best the team could in only a few weeks of summer work!

Project Lily Pad was developed over Summer 2018 with the purpose of teaching spatial thinking in terms of disaster resilience. The game is set in the city of Dickinson, Texas, which was impacted by Hurricane Harvey on August 20, 2017.

Through a series of lectures and background on geogame research, game jams (rapid prototyping of games), game design, programming, geographical information systems (GIS), spatial thinking, and more, the students developed and implemented Project Lily Pad—a serious geogame to demonstrate how to educate citizens about wayfinding in a disaster, like a flood. The name “Lily Pad” derives from the concept of higher elevations where people go to rise above flooding.

Responders in the Dickinson flooding had a chance to review the first generation of the geogame and offered suggestions. There is a new team of REU and IGM students who will collaborate this summer to improve the game, its workflow, and learn more about what a geogame can do as part of RIT’s new MAGIC building. This project is just one of many that bring together films, games, and other technology. Future ideas include investigating virtual reality (VR) for deeper immersion for players, using procedural generation for creating urban environments, and involving residents for crowd sourcing accuracy of urban environments.  It is hoped the geogame concept can be applied for planning for other disaster scenarios besides flooding. The Lily Pad user manual and a game download can be accessed here.

The above images are screenshots from the game. The main character has to navigate Dickinson using a “paper” map and notepad. Playing the game repeated helps the player to develop spatial reasoning of the actual town.

Summary

While the concept has been around for a while (ArcNews Summer 2017), the convergence of geospatial technologies and the game world is only now beginning to take hold in the Empire State.  We are fortunate to have work and research being done in this space at a university, which has strong and established geospatial/GIS and game development credentials. The School of Interactive Games and Media has recently hired tenure-track faculty with research interests in geogames, and so, we look forward to more from RIT in their continuing work this summer and into the coming years.

Contact: 
David Schwartz, PhD
Rochester Institute of Technology
disvks@rit.edu

Editor’s Note:  The author acknowledges the contribution of David Schwartz towards the development and content of this article.

Best of the Show: New York Giant Traveling Map

While the recent statewide GIS conference in Lake Placid featured several presentations and vendor displays in emerging  areas of geospatial development across the Empire State, one presentation –  and an interactive one no less –  was certainly one of the most refreshing and welcomed.  Why’s that, you ask?  Well, consider the following:   (1) it contains  no technical jargon or  software programming speak,  fancy charts or diagrams, (2) has connections to the  educational community, (3) applicable anywhere in the Empire State,  (4) absolutely and completely different, and  (5) suitable for all ages –  Rated “G”!  Yes, the New York Giant Traveling Map which was presented by Susan B. Hoskins, Senior Extension Associate at Cornell University.

Susan B. Hoskins demonstrates use of the NYS Giant Traveling Map to conference attendees during 2017 GeoCon in Lake Placid. Note: No shoes allowed – the geoenabled version of the game Twister?

The Map

In celebration of the 30th anniversary of state geographic alliances, National Geographic produced a Giant Traveling Map for each state.  Two copies were gifted to the New York Geographic Alliance in 2016 headed by Timothy McDonnell, geosciences faculty at Monroe Community College in Rochester.  Since then the New York 4-H Geospatial Sciences program has gotten involved to help promote the map in 4-H programs and classrooms statewide.  The 4-H Geospatial Science and Technology Program, within Cornell Cooperative Extension, provides educator professional development in GPS, GIS and the tools of remote sensing.  The geography lessons learned on the Giant Traveling Map are fundamental to using technology in map making.  Many youth and adult mentors take these skills and technology lending library and apply them to community mapping projects.

The Giant Traveling Map of New York, measures 15 X 20 feet and includes major cities, water bodies, mountains, Indian Reservations and National Parks.

The map “kit” comes complete with a curriculum of six activities that help youth explore map features and symbols, grids, map scale, orientation and direction, and the basics of Geographic Information Systems.  Props included in the kit are orange cones for marking points, yellow plastic chain, blue yarn and a ball of string to map “linear features, a compass rose and map legends.  Teachers and users of the map can determine how far is it from New York City to Albany by comparing one’s foot to the scale bar and walk along the Hudson River.  Or finding the Erie Canal?  Follow the canal path from Albany to B-uf-fa-lo-ooo, just like the song.

To date, the following schools and organizations have hosted the Map:

Additionally, McDonnell states: “The Map can be used in middle schools to support 7th Grade curriculums for social studies which includes New York history and geography”.  The Geographic  Alliance  maintains other resources specifically designed for middle school including  The Atlas of New York: Legacies of the Erie Canal and Lessons for the Atlas of New York.  More information can be found under the Resources link on their website.

The Map Travels to Westchester County

After  the Lake Placid conference, the Map traveled to Solomon Schechter elementary school in White Plains where it was used by 4th grade teacher  Amy Sroka who expressed accolades after having used the map..  After a week in the classroom, one of Ms. Sroka’s students commented:

I learned a bunch of names of different towns and cities. It was really fun trying to find the locations of a lot of the places. While I was studying the map, I discovered that there are actually so many more mountains in New York State than I had thought there were…I really enjoyed the map!”

If your school, family gathering, or organization is interested in using the Map, contact Tim McDowell at the New York Geographic Alliance.  It is also available for sale through National Geographic for $750.

Highest Lakes in New York State

While planning on some Summer 2017 High Peaks hikes and overnights with my sons, I got to thinking about some previous communications I had with long time colleagues John Barge at the Adirondack Park Agency and Doug Freehafer at the U.S.Geological Water Science Center in Troy about other state highest geographic features.   Most know about the “46ers” – a.k.a the 46 mountains in New York State above 4,000’.  (Yours truly having bagged about ½ of them.)  But what about other geographic features and facts that might make good trivia questions –  like what are the “highest” lakes and water bodies in the Empire State?

No problemo.  Doug pointed me to the U.S. Geological Survey Geographic Names Information System (GNIS) search engine in which I queried for all New York State lakes over 2,500’ and the search returned 35 lakes  based on the National Elevation Dataset.  Surprisingly not are all in the Adirondacks.

The GNIS query builder is easy-to-use and allows users to search on names for geographic features such as harbors, islands, harbors, basins, summits and much more.

Saving the search results and converting to a spreadsheet, it’s easy enough to add the lake X,Ys to a  ArcGIS Online viewer (or any viewer of choice for that matter) called the Highest Lakes in New York State.   As shown in the following images, the highest lakes are located near Mt. Marcy (Lake Tear of the Clouds at 4,321’ and Moss Pond at 4,4,252’) with Hodge Pond showing up at 2,592’ (#26 highest)  much further south in Sullivan County.

Eight out the ten highest lakes are in Essex County though not all are found on the Mt.Marcy USGS quadrangle. What other quads are in play?

USGS 1:24,000 quadrangle grid covering the Adirondack High Peaks region from The National Map viewer application.

Won’t find any summer lifeguards on duty at these lakes and the water temperature probably won’t be the same as your shower water, but it’s nice to know if your back country trips might take you close enough to potential swimming or fishing holes?  (Our lastest route and trip manifest did not include any of these water bodies.)   GNIS is a great source of national and Empire State geographic features which we’ll occasionally explore in future eSpatiallyNewYork posts.

Enjoy your summer!

Jonathan Levy: Cartography Remixed

Jonathan Levy is yet another geospatial enthusiast I have made contact with via the burgeoning GeoNYC Meetup group. It’s a small world indeed as Jonathan and I share some common interests including music, sports, and time spent in one of my most favorite spaces: Idaho. His path down the cartographic road might be considered a bit different than the conventionally trained geospatial professional.  However, what is coming out the other end today is a wide range of interesting cartographic products and services.  Enough for an interesting dialog and blog post – including some interesting personal stuff on the side.  Enjoy.

Jonathan Levy grew up in the Durham and Chapel Hill areas of North Carolina spending lots of time running around in the outdoors.  His dad was a huge fan of National Geographic exposing Jonathan to both the beauty and vastness of the publication’s cartographic products and at the same time taking him camping and trail hiking around  in the Appalachian Mountains.  In his teens, he completed an Outward Bound course which introduced him to orienteering and using maps for navigation and survival.

After graduation from high school, Jonathan attended Brandeis University majoring in Near Eastern and Judaic Studies with a minor in Environmental Studies focusing on conservation biology and environmental politics.  After finishing his undergraduate work he traveled to Grenada, West Indies, to teach environmental/social science to children with Dr. Dessima Williams.   Afterwards, he worked for Polaroid’s Corporate Environmental Department in Boston, MA for nine months before heading to Salmon, Idaho as part of the Student Conservation Association working with the U.S. Forest Service in the Frank Church Wilderness Noxious Weed Inventory program.  It was here he was introduced to Global Positioning System (GPS) data collection concepts and GIS software to make maps of field guides of rare plant species in the wilderness area.

Completing his internship work in Idaho in 2002, Jonathan was  given a grant towards graduate study at at Hunter College in New York City in the MA program specializing in Geographic Information Systems (GIS)  and Media during which time he was able to intern at the United Nations and the New York City Office of Emergency Management.  He received his Masters from Hunter College in 2005.

Getting Started

His first job out of Hunter College was with the NY State Legislative Task Force for Demographic Reapportionment which Jonathan notes “was very GIS heavy and really interesting”.  At this point he began picking up freelance work on the graphics side of things with TED.com, Maps.com and Not For Tourists – the latter of which was has continued to be a successful long term contract.

Along the way he has continued to expand his use of the ESRI software particularly with regard to the spatial/network analyst extensions as well as becoming proficient in QGIS and Carto. Because he extends his cartographic product beyond the what is available with GIS software, Jonathan uses Adobe Illustrator and Photoshop for graphics processing, texturing and post production. For 3D renderings he uses Cinema 4D, After Effects, and Sketchfab.

Sample Cartographic Products

Lower Manhattan Buildings:

This 3D rendering of buildings in Lower Manhattan show the years in which they were built from 1700 to the present. The gradations of dark orange to light orange correspond to the newest to the oldest buildings. The data used to create this map came from NYC Open Data.

Environs Map Series:

This series is a way of sharing Jonathan’s life experiences of favorite places and spaces in his  life through map renderings and illustrations.  It is his personal experience of specific places and the personal “visions” of that space.  He gets requests to produce custom maps for friends, family and clients who want their town or neighborhood mapped in this style. He’s currently working on a Valentine’s day gift for a client who wants a map of Roncolo di Quattro Castella in this style.  These images are created using: Photoshop, Adobe Illustrator, scanned textures and GIS data.

Jonathan notes: “I love seeing Long Island City from across the East River. The Pepsi and Long Island City signs are featured prominently although here I’ve replaced them with my sister and brother in law’s names in lieu of their recent marriage.”

Airbnb:

Jonathan notes this was a “fun” project. Using some fancy internal tools Airbnb developed, Jonathan helped map out neighborhood boundaries in 20+ cities across the U.S – including New York City.   It involved lots of research and involvement with city planners, residents and/or a combination thereof to get a feel for the individual city.

Sample of one NYC neighborhood maps – Chinatown – Jonathan researched and created for Airbnb helping users better define which areas and neighbors they are looking for lodging and accommodations.

Montauk 3D:

This was a personal project that was inspired by his time this past summer learning to surf in Montauk. He was struck by the interesting topography of the area. He took digital elevation model (DEM)  data, exaggerated the contours in Cinema 4D for effect, created custom topographic palettes and created a website that uses Sketchfab’s API to switch out textures on the 3D surface. Link to website: http://aws-website-montaukd-vr1zr.s3-website-us-east-1.amazonaws.com.  (Note:  Sketchfab recommends WebGL to display 3D content in real-time  which is a standard in most modern browsers.  Check your browser for compatibility at http://get.webgl.org/).

Amped Topography of Montauk: If you know the Montauk landscape and locations of specific geographic features (i.e., Lake Montauk and the Lighthouse – chances are you would find these renderings of the area very interesting – and different.

Loud Noise/Noise Complaints:

Jonathan also enjoys scrapping data from public web sites to develop maps and visuals.  While living on the Lower East Side of Manhattan, Jonathan created a Party/Loud Music Complaints map based on 311 data obtained from New York City’s Open Data Portal. These maps include and reflect his interest in rendering the “personality” of geospatial data through design choices – as illustrated in this map/web map – including a dark background, a purplish nighttime color palate and star animated Gifs.  Indeed an interesting map from a person who loves loud music and spends his spare time playing in a metal band!

Built with OpenStreetMap, this interactive map allows users to pan around Manhattan to see which NYC zip code has the largest number of noise complaints as filed through 311.

The Other Stuff

Jonathan always finds his legal mapping client work interesting as it requires mapping and data development to such a fine level of detail.  Often such work involves boundary disputes requiring the review of historical deeds and historic photogrammetry to determine boundary line changes. Looking forward he continues working with Sketchfab in context of mapping in the 3D space.  He supports Sketchfab because it is “accessible, light and has a community for sharing 3D models with annotation”.

As a one person shop, Jonathan does not have a large marketing and public relations budget and as such all of  his business development is  word-of-mouth.  He’s recently created an interactive presentation for a close friend and chef/owner Will Horowitz (Duck’s Eatery / Harry & Ida’s) which he presented at the Food on the Edge conference in Ireland. He’s working on an online platform, Common Scraps, which addresses the issue food waste.   As an extension he has produced some animated maps that show how food scraps can be saved and reused in an exchange system between local farms/suppliers and restaurants.

Jonathan covers a lot of ground and styles in his work which is more detailed and described on his website. Take a look, and if you are really lucky you might find him playing at a local club down the street with his band Autowreck.  Go check them out.

Though take some ear plugs and hold on.

Contact:  Jonathan Levy @ jl@jlcartography.com