Geodata and AI
Volume 1 • Issue 0
- ISSN: 3050-483X
Geodata and AI is an international journal that is focused on the development of machine learning and artificial intelligence for scientific discovery in geo-disciplines (research… Read more
Subscription options
Institutional subscription on ScienceDirect
Request a sales quoteGeodata and AI is an international journal that is focused on the development of machine learning and artificial intelligence for scientific discovery in geo-disciplines (research) and creation of novel digital service over the life cycle of natural or engineered geo-systems (practice). Geo-disciplines include soil science, geotechnical engineering, rock engineering, earthquake engineering, geoenvironmental engineering, engineering geology, mining, geo-hazard, geophysics and others. Geodata can be broadly defined as data produced by the characterization of the constituent ground and observation of the processes emerging from these disciplines. The heterogeneous spatial/temporal features and complex sampling characteristics (multi-source, multi-modal, uncertain, sparse, incomplete, potentially corrupted) of geodata are common in these disciplines with potential for data fusion. They are pivotal to the training of machine learning and artificial intelligence that are transformative business drivers when combined with other digital technologies.
The objectives of this international journal are to advance geodata science to address the challenges posed by geodata intrinsic and sampled features, to promote the compilation and sharing of geo-databases, to develop novel machine learning and artificial intelligence methods that are of significant value or even indispensable to actual projects, to establish benchmarks for competitive evaluation of algorithms, and to solve complex challenges such as risk and resilience related to geo-disciplines. All aspects of a geodata-centric agenda that can transform research and/or practice are of interest:
Geodata science
Geo-databases
Data fusion
Physics-informed machine learning
Trustworthy/explainable/interpretable AI
Human-machine teaming
Benchmarking
Data-driven site characterization
Machine learning guided observational method
Autonomous construction
Smart infrastructure
Data-informed risk and resilience
Building Information Modelling/Digital twin
Privacy enhancing technologies
- ISSN: 3050-483X
- Volume 1
- Issue 0