The Architecture of Land Degradation Early Warning Based on Earth Observation

Early detection and prevention of natural and anthropogenic degradation processes are especially relevant. This paper proposes a suitable architecture of a cloud-based early warning system for assessing land degradation based on satellite Earth observation and other necessary geospatial data. The ea...

Full description

Saved in:

Bibliographic Details
Published in:	2023 International Conference on Information and Digital Technologies (IDT) pp. 125 - 132
Main Authors:	Popov, Mykhailo, Stankevich, Sergey, Kozlova, Anna, Piestova, Iryna, Khyzhnyak, Anna, Zaitseva, Elena, Levashenko, Vitaly, Seredinin, Eugeny, Maltsev, Sergii, Lypska, Yuliia, Kukharuk, Alina, Rashchuk, Vita, Smitiukh, Anhelina
Format:	Conference Proceeding
Language:	English
Published:	IEEE 22-06-2023
Subjects:	Degradation distributed data processing architecture early warning Earth Earth observation geoinformation technology Geospatial analysis heterogeneous geospatial data land degradation Predictive models Radar imaging satellite data product Spaceborne radar Time series analysis
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Early detection and prevention of natural and anthropogenic degradation processes are especially relevant. This paper proposes a suitable architecture of a cloud-based early warning system for assessing land degradation based on satellite Earth observation and other necessary geospatial data. The early warning system is based on efficient methods for the time series of land degradation indicators fusion and algorithms for land degradation risk assessment. Earth observation data includes multispectral and radar satellite imagery and derived data products. Ground-truth data construct auxiliary data in concert with topographic., geoclimatic., cadastral., socioeconomic., and other statistical data. The use of the ArcGIS Online Portal is suggested for the processing of heterogeneous geospatial data. As a result., the authors intend to build a general knowledge-based model for assessing and predicting land degradation.
ISSN:	2575-677X
DOI:	10.1109/IDT59031.2023.10194406