The work “Production Machine Learning Frameworks for Geospatial Big Data“, with the support of NEANIAS project, has been published in 2021 IEEE International Conference on Big Data (Big Data).

Authors and Affiliations

Valsamis Ntouskos [1] Chrysa Iliopoulou [1] Konstantinos Karantzalos [1][2]

[1] Remote Sensing Lab, Ntua, Athens, Greece

[2[ Research and Innovation Center "Athena", Athens, Greece

Abstract

We explore the use of production Machine Learning (ML) frameworks for automatically building ML models for cloud-based services that exploit geospatial big data and value-added products. We combine two widely used production ML frameworks to hierarchically decompose the tasks involved with the fetching and preprocessing of the data as well as with model training, evaluation, and selection. We assess the usability, reproducibility and performance of the frameworks both qualitatively and quantitatively. We examine the challenging case of a cloud-based seabed mapping service that process multispecrtal multibeam echosounder data captured in different marine surveys, involving a number of data processing and machine learning tasks.

Acknowledgements

All backscatter raw data were provided by R2Sonic, LLC (Austin, TX, USA) in the context of the 2017 Multispectral Challenge. This research is supported by the NEANIAS project funded by the European Union under the Horizon 2020 research and innovation programme via the grant agreement No. 863448. This research is also co-financed by Greece and the European Union (European Social Fund-ESF) through the Operational Programme ‘Human Resources Development, Education and Lifelong Learning’ in the context of the project ‘Reinforcement of Postdoctoral Researchers - 2nd Cycle’ (MIS-5033021), implemented by the Greek State Scholarships Foundation (IKY).

Get the work at https://ieeexplore.ieee.org/document/9671709