Spatial Data Science Hangout Series: Reproducibility

The Center for Spatial Studies invites you to join us on Thursday May 20 at 9:00 a.m PT for the next Spatial Data Science Hangout on Reproducibility in Data Science Research. For this special event, we are thrilled to welcome two reproducibility experts as speakers: Daniel Nüst (Institute for Geoinformatics, University of Münster) and Casey O’Hara (BREN School, UC Santa Barbara). 

Don’t miss this event! Everyone is welcome to participate, just keep in mind that these hangouts are meant to be a comfortable environment for graduate students and early career researchers to brainstorm, talk through their imaginative ideas, discuss, and learn from each other.  

To participate in this event, please register here

Upon registration, you will receive a confirmation email with Zoom login details

Casey O’Hara is a PhD candidate in the BREN School at UCSB. After completing his MESM degree in 2014, Casey has worked on the Ocean Health Index, applying data science to communicate the range of economic, ecological, and cultural benefits people can sustainably derive from healthy oceans. In his research, he applies spatial analysis and data science principles to examine the ecological and socioeconomic impacts of human activity and climate change on marine biodiversity.

Abstract: In his talk, Casey will give a short introduction to his paper on better science in less time using open data science tools, including a quick introduction to GitHub for version control and communication, and a comparison of the pros and cons of spatial analysis using ArcMap GIS, ArcMap ModelBuilder, and R. Casey will wrap up his talk by presenting some quick results from his most recent paper: At-risk marine biodiversity faces extensive, expanding, and intensifying human impacts.

Daniel Nüst ( is a researcher at the Spatio-temporal Modelling Lab at the Institute for Geoinformatics at the University of Münster. Daniel pursues a Ph.D. in the context of the DFG project, Opening Reproducible Research, where he develops tools for creation and execution of research compendia in geography and the geosciences. His professional interest is improving the scholarly publication process with new information technology—of course, with Open Source software! Daniel is reproducibility chair at the AGILE conference series and vice chair of the German association for research software engineering.

Abstract: In his talk, Daniel will give a short introduction to his paper on practical reproducibility in geography and geosciences and present some advanced technologies for reproducibility (notebooks, containers, Binder). Daniel will wrap up his talk by discussing  how reproducibility should be taken into account during peer review and give a brief overview of the initiatives CODECHECK and Reproducible AGILE. 


Spatial Data Science Hangout Series: Reminder

Our Spatial Data Hangout will take place tomorrow (Thursday), December 3 from 10:00 to 11:00 am (Pacific Time). Please join us for this special session focused on Graph Data and Networks, and led by Rui Zhu, Su Burtner, Gengchen Mai, and Mike Johnson.

Zoom Meeting Link:

Meeting ID: 886 9383 0517
Passcode: geohangout

We look forward to seeing you!

Spatial Data Science Hangout Series: Call for Speakers

The Center for Spatial Studies will again be hosting a special Spatial Data Hangout on Thursday, December 3 at 10:00 a.m. All grad students are invited to attend! We are fully aware that your schedule is already crowded with  Zoom meetings, but we are hopeful that this will be  an excuse for you to hang out with other geography grads and  learn a bit about the cool projects or ideas they have been working on this year.

This spatial data science hangout will focus on learning and discussing all sorts of graph data (and analytics that involve graphs) used to do research in our department. This includes everything related to representing and reasoning on data. This is  an opportunity for you to: (i) teach others about the tools you use to represent data for spatial reasoning, –this might include some coding, (ii) discuss common graphs for spatial analytics in your research field, (iii) discuss the process you use to create a graph that you are proud of, or (iv) present early-stage ideas, projects that you might not complete yet or learned lessons from “failed” projects. This is meant to be a safe space for people to talk through ideas, and learn from each other.  Some potential topics include spatial networks in their broadest sense, such as: 

  • Social networks
  • Transportation networks 
  • Biological networks
  • Other types of networks in your domain (stream networks)
  • Knowledge graphs

We are looking for folks who would like to lead/co-lead sessions! Depending on the number of speakers, you might be able to participate with a lightning talk or a 15-minute talk. If you are interested in participating in this, please contact Marcela Suárez at by November 27 (preferably sooner), and otherwise mark your calendar to attend.

Spatial Data Science Hangouts

For a variety of (often historic) reasons, our research community has split itself into subfields such as geographic information science, geo-informatics, spatial cognition, transportation studies, spatial statistics, remote sensing, cartography, and so forth. Each of these sub-communities comes with its own journals, conferences, writing styles, accepted terminology, funding agencies, datasets, and core topics.

Unfortunately, the interaction across these communities is spotty at best. A few years ago, we showed [1] that even within the geographic information science and geo-informatics communities, the fragmentation is so high that only four authors in total had full papers at all four main conferences. The risk of such fragmentation is that each of these sub-communities may be too small to survive as an academic discipline in the long term.

Leaving the data science hype aside, spatial data science may be an important chance to establish an overarching, unifying community of researchers interested in scientific aspects of representing, publishing, retrieving, and integrating spatial data that is strong enough to make a long-term impact.

To explore this idea, the spatial center invites all students interested in spatial data science to casual hangouts.

Schedule 2020–2021 (also available on our Google Calendar)

Spring 2021 Reproducibility in Data Science Research
Fall 2020Graph Data and Networks
Fall 2019Why and how to apply for a professorship?
Spring 2019Open Knowledge Network (OKN) proposals
Winter 2019The Lunch Incubator: Spatial Data Science Hangouts


[1] Table 1:

Spatial Data Science Hangout Series: November 2019

T next seminar in the Center for Spatial Studies’ Spatial Data Hangouts series will be on Tuesday, 11/19 from 11:30 a.m.12:30 p.m. at 3512 Phelps Hall. All grad students are invited to attend.

Continuing the theme of finding academic employment, where we discuss why and how to apply for a professorship, we will continue last month’s discussion of the academic hiring process and talk about interviews on-site and per teleconference. We will also do at least one test run to give you a chance to practice. Hence, if you would like to volunteer and be interviewed in front of the other students, please let Jano or Karen know.

We will be providing a light lunch after the discussion. Please contact Karen Doehner if you plan to attend.


Spatial Data Science Hangout Series: Fall 2019

Spatial Data Science Hangouts Poster

After a successful first run in the last academic year, the Center for Spatial Studies will again be hosting the Spatial Data Hangouts, with the first one on Thursday, 10/17 from 11:30 a.m.12:30 p.m. at 3512 Phelps Hall. All grad students are invited to attend.

With the season for academic jobs starting, the next few spatial data science hangouts will be used to to discuss why and how to apply for a professorship, eg., how to write your cover letters, what makes a good recommendation letter, how to structure your CV, how to score during the on-site interviews and your talk, how to negotiate, and so on.

We will focus on jobs in spatial data science, GIScience, remote sensing, spatial cognition, and so on, but most of what we will discuss applies to academic employment in general. We will do all this in a hands-on, interactive style.

We will be providing a light lunch after the discussion. Please contact Karen Doehner if you plan to attend.


Spatial Data Science Symposium 2019

Spatial Data Science Symposium

“Setting the Spatial Data Science Agenda”

December 9–11, 2019

Upham Hotel (

Santa Barbara, California

Visit the official SDSS site


Space and time matter not only for the obvious reason that everything happens somewhere and at some time, but because knowing where and when things happen is critical to understanding why and how they happened or will happen. Spatial data science is concerned with the representation, modeling, and simulation of spatial processes, as well as with the publication, retrieval, reuse, integration, and analysis of spatial data. It generalizes and unifies research from fields such as geographic information science, geoinformatics, geo/spatial statistics, remote sensing, and transportation studies, and fosters the application of methods developed in these fields to outside disciplines ranging from the social to the physical sciences. In doing so, research on spatial data science must address a variety of new challenges that relate to the diversity of the utilized data and the underlying conceptual models from various domains, the opportunistic reuse of existing data, the scalability of its methods, the support of users not familiar with the language and methods of traditional geographic information systems, the reproducibility of its results that are often generated by complex chains of methods, the uncertainty arising from the use of its methods and data, the visualization of complex spatiotemporal processes and data about them, and, finally, the data collection, analysis, and visualization playing out in near real-time. Spatial data science does not only utilize advanced techniques from fields such as machine learning or big data storage and retrieval, but it also contributes back to them. Recent work, for instance, has shown that spatially-explicit machine learning methods substantially outperform more general data when applied to spatial data even though this spatial component may seem of secondary importance at first glance.


Instead of being restricted by a historically grown partition into small and overlapping communities that deal with spatial data in one way or the other, the overarching goal of this symposium is to put spatial data science at the forefront of a unified field that explores the current research and application landscape to define an agenda for spatial data science for the next 10 years.


Forty-three experts from academia and industry convened to share and develop visions, insights, and best practices. Plenary presentations and intense exchanges in small breakout discussion groups offered opportunities for knowledge transfer.

Save the Date: Spatial Hangouts 2

Dear all,
After a successful first Spatial Data Science Hangout, we would like to run a follow-up on Monday March 18, 2019 from 12-1pm. We got a lot of positive feedback form many of you but even more importantly several useful suggestions on how to change the formula for the hangout and we will implement them for next week. We will also have a light lunch available for you. Finally, you can also join our slack channel if you plan to regularly participate in the hangout series:

The Lunch Incubator: A Spatial Data Hangout Recap


What a treat it was to host the Center for Spatial Studies’ first Spatial Data Science hangout. Almost 30 usually dispersed graduate students crept out from their hiding places into the bright of day this Tuesday, having heard the call of an informal gathering of spatial data scientists. Initially smelling the hor d’oeuvres from C’est Cheese, they stayed to hear Dr. Janowicz propose two moonshot ideas to advance the field of Spatial Data Science. If we want to make Spatial Data Science a field with a vision, he imagines, we need a big, crazy idea to drive towards. What could that idea be? How about a Geo-Turing test: say a user asks a GIS question of a machine and is unable to tell the difference between a machine’s and a GIS analyst’s results? Or, as another crazy idea, how about detecting and resolving spatial trends of civil destruction, before the Great Filter is upon us?

Students then hopped into the mingling space to grab some Mediterranean food and discuss the ideas they’d just heard. What more was there to learn and do? What next could be done? Inter-lab discussion brought a chance to catch up with old friends and get new ways to think about these topics.


We plan to host many more productive discussions on a monthly or a bi-weekly basis by bringing together bright young minds in a space with some brain food and a provocative thought.  

If you were unable to make it and are dreaming of the pita, or have ideas for topics of discussion, please contact or join the Spatial Data Slack channel.


Join us for Spatial Data Hangout 2 on March 15!