INSPIRE standards as a framework for artificial intelligence applications: a landslide example

Roberti, Gioachino; McGregor, Jacob; Lam, Sharon; Bigelow, David; Boyko, Blake; Ahern, Chris; Wang, Victoria; Barnhart, Bryan; Smyth, Clinton; Poole, David; Richard, Stephen

doi:https://doi.org/10.5194/nhess-20-3455-2020

Articles | Volume 20, issue 12

https://doi.org/10.5194/nhess-20-3455-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/nhess-20-3455-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 20, issue 12

Research article

|

16 Dec 2020

Research article |

| 16 Dec 2020

INSPIRE standards as a framework for artificial intelligence applications: a landslide example

Gioachino Roberti, Jacob McGregor, Sharon Lam, David Bigelow, Blake Boyko, Chris Ahern, Victoria Wang, Bryan Barnhart, Clinton Smyth, David Poole, and Stephen Richard

Data sets

TINITALY, a digital elevation model of Italy with a 10 m-cell size (Version 1.0) S. Tarquini, I. Isola, M. Favalli, and A. Battistini https://doi.org/10.13127/TINITALY/1.0

INSPIRE Natural Risk Zone Schema Extension for Susceptibility Area Minerva Intelligence https://github.com/minervaintelligence/INSPIRE-NZ-Susceptibility

European Landscape Dynamics J. Feranec, T. Soukup, G, Hazeu, and G. Jaffrain https://doi.org/10.1201/9781315372860

Derivation and analysis of a high-resolution estimate of global permafrost zonation S. Gruber https://doi.org/10.5194/tc-6-221-2012

Short summary

We show how INSPIRE, the European initiative to standardize data across borders, can be used to produce explainable AI-based applications. We do so by producing landslide susceptibility maps for the Veneto region in Italy. EU countries are mandated by law to implement the INSPIRE data framework by 2021, but they are aligning and serving INSPIRE data at a slow pace. Our paper can provide a boost to INSPIRE implementation as it shows the value of standardized data.