Best Paper for the period 2022-2025
The Jack Dangermond Award was established in 2017 to encourage and stimulate submission of high-quality scientific papers by individual authors or groups to the ISPRS International Journal of Geo-Information, to promote and advertise the journal, and to honor the outstanding contributions of Jack Dangermond, founder and CEO of ESRI, to research and development in the Geospatial Information Sciences. The Award is presented to authors of the best paper, written in English and published exclusively in the ISPRS Journal during the four-year period from January of a Congress year to December of the year prior to the next Congress. The award consists of a monetary grant of USD 10,000 and a certificate. It is sponsored by MDPI and ESRI.
A five-member jury of high scientific standing, whose expertise covers the main topics included in the scope of the Journal, comprising four experts proposed by the Editor-in-Chief of the Journal and one scientist proposed by ESRI, evaluates the papers. Each best paper of the preceding four years was announced in the ISPRS eBulletin, on the ISPRS and MDPI websites. The best of these four papers is selected by the jury as winner of the award.
For the period 2022 - 2025, the winning paper is:
"Mining Spatiotemporal Mobility Patterns Using Improved Deep Time Series Clustering".
by Zhang, Ziyi 1, Li, Diya 2, Zhang, Zhe 1,2, Duffield, Nick 1
1 Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843, USA
2 Department of Geography, Texas A&M
3 Texas A&M Institute of Data Science, Texas A&M University, College Station, TX 77843, USA
 |
|
 |
|
 |
|
 |
| Ziyi Zhang |
|
Diya Li |
|
Zhe Zhang |
|
Nick Duffield |
published in 2024, volume 13(11), 374.
https://doi.org/10.3390/ijgi13110374
Jury's rationale for the paper selection
The winning paper addresses issues in spatiotemporal mobility pattern mining, a core challenge in geo-information science. The authors propose an improved deep time series clustering method that uniquely integrates a temporal autoencoder with dynamic time warping-based K-means clustering. This innovation robustly addresses persistent challenges of high dimensionality, noise, outliers, and time distortions in mobility data. The framework demonstrably outperforms existing techniques on both synthetic and real-world datasets. Crucially, its application to U.S. COVID-19 mobility data reveals actionable insights into rural-urban behavioral differences and policy impacts, directly demonstrating societal values.
By blending cutting-edge deep learning with classical clustering in a reproducible, data-driven framework, this work advances unsupervised spatiotemporal analysis and provides a reliable foundation for evidence-based decision-making in urban planning, public health, and disaster response.
The Jury felt this well-written contribution represents a genuine scientific advance in spatiotemporal mobility pattern mining and, therefore, very deserving of the Jack Dangermond Award for 2022-2025.
The Jack Dangermond Award will be presented by Lena Halounová, President of ISPRS, and representatives of the sponsors at the 25th ISPRS Congress Plenary Session in Toronto, Canada, on Monday, 6 July 2026.
On behalf of the ISPRS and the Jack Dangermond Award Jury, I would like to congratulate the authors on this distinction and thank them for their contribution. I would also like to thank the sponsors of the Award, and the Jury members for their thorough evaluations.
Wolfgang Kainz
Editor-in-Chief
ISPRS International Journal of Geo-Information
University of Vienna, Vienna, Austria
E-mail address: wolfgang.kainz@univie.ac.at