Building Spatio-Temporal Knowledge Graphs from Vectorized Topographic Historical Maps

Tracking #: 2918-4132

Basel Shbita
Craig A. Knoblock
Yao-Yi Chiang
Weiwei Duan
Johannes H. Uhl
Stefan Leyk

Responsible editor: 
Guest Editors ESWC 2020

Submission type: 
Full Paper
Historical maps provide rich information for researchers in many areas, including the social and natural sciences. These maps contain detailed documentation of a wide variety of natural and human-made features and their changes over time, such as changes in transportation networks or the decline of wetlands or forest areas. Analyzing changes over time in such maps can be labor-intensive for a scientist, even after the geographic features have been digitized and converted to a vector format. Knowledge Graphs (KGs) are the appropriate representations to store and link such data and support semantic and temporal querying to facilitate change analysis. KGs combine expressivity, interoperability, and standardization in the Semantic Web stack, thus providing a strong foundation for querying and analysis. In this paper, we present an automatic approach to convert vector geographic features extracted from multiple historical maps into contextualized spatio-temporal KGs. The resulting graphs can be easily queried and visualized to understand the changes in different regions over time. We evaluate our technique on railroad networks and wetland areas extracted from the United States Geological Survey (USGS) historical topographic maps for several regions over multiple map sheets and editions. We also demonstrate how the automatically constructed linked data (i.e., KGs) enable effective querying and visualization of changes over different points in time.
Full PDF Version: 


Solicited Reviews:
Click to Expand/Collapse
Review #1
By Mohamed Sherif submitted on 08/Dec/2021
Review Comment:

I thank the author for addressing all my previous comments.
I tested the newly provided SPARQL endpoint at [1] from my command line and it works fine. Still, I would encourage the authors to provide a working on-line interface for the endpoint at [1] in order to increase the dataset ease of accessibility.

All in all, I would like to accept the paper.


Review #2
By Sergio Rodriguez Mendez submitted on 24/Dec/2021
Review Comment:

* Summary: The article describes an approach to convert vector geographic features extracted from multiple historical maps into contextualized Spatio-temporal KGs. The resulting graphs can be easily queried (GeoSPARQL) to understand the changes in different regions over time. The approach and its evaluation focus on linear and polygonal geographic features.

* Overall Evaluation (ranging from 0-100):
[Criterion 1]
[Q]+ Quality: 95
[R]+ Importance/Relevance: 85
[I]+ Impact: 90
[N]+ Novelty: 80
[Criterion 2]
[W]+ Clarity, illustration, and readability: 95
[Criterion 3]
[S]+ Stability: 100
[U]+ Usefulness: 90
[P]+ Impression score: 90

* Dimensions for research contributions (ranging from 0-100):
(1) Originality (QRN): 87
(2) Significance of the results (ISU): 93
(3) Quality of writing (QWP): 93

* Overall Impression (1,2,3): 91
* Suggested Decision: [Accept]

* General comments:
The work is solid. The paper is easy to follow and understand.
There is a novelty in the proposed approach.

* Major points for improvements:
# all have been addressed

* About the data files and related software artifacts: (“Long-term stable URL for resources”)
(1) "data files are well organized and contain a README file which makes it easy to assess the data": [YES. CORRECTED]
(2) "the provided resources appear to be complete for replication of experiments": [YES. COMPLETE]
(3) "the chosen repository is appropriate for long-term repository discoverability": [YES. GitHub]
(4) "the provided data artifacts are complete": [YES]

* Minor corrections:
[A06] Indeed, this (unrotated) box is the required input to the reverse-geocoding service and poses a limitation for us. We have clarified it and described how the calculation is done (section 2.4, paragraph 5).
[R06] In the manuscript, you didn't mention that is a "limitation" of the reverse-geocoding service. Perhaps, it would be better to mention this part in section 5, paragraph 5, where you described "several limitations".

Review #3
By Alessandro Adamou submitted on 24/Jan/2022
Review Comment:

The paper describes a method to generate RDF datasets for historical maps, whose topological features change over time. The method was evaluated over a selection of US historical map data.

Having reviewed the previously submitted version of this paper, I may observe that this version contains the necessary improvements without introducing further issues. The authors have addressed my remarks both in the paper itself and in the author response, and have even addressed my "curiosity" comment in the concluding section. They have relicensed the data properly, made a release and improved its findability. In the future, they might consider separate releases for the data and for the code, although they will need to keep sharing the GitHub repository so as not to invalidate the stability of the supplied URL.

I have no further recommendation for this paper and believe it is ready for publishing. Good work.