Satellite and speech data for usable land assessment
A satellite image shows the shape and structure of a landscape. An observation from agricultural practice can add context about how land is used or what has changed on the ground. ReSeDiUm investigates how these different clues can be brought together to identify and assess usable land.
Image analysis examines features in the satellite data; speech processing makes the content of spoken observations available for analysis. The central question is how what can be seen in an image relates to what people working in agriculture report about it.
The project connects the development of AI methods with questions in agriculture, environmental analysis and spatial planning. A useful evaluation asks what information each source adds and under which conditions their joint analysis helps.
© FILA
Satellite images show the landscape; observations documented in language provide additional context for its analysis.
Research topics
- Development of AI algorithms for the analysis of satellite data.
- Analysis and processing of speech data from agricultural practice.
- Linking visual features with the content of human observations.
- Combining both data types with the aim of improving land assessment accuracy.
Funding
This work was supported by the European Regional Development Fund (ERDF) and the state of Saxony-Anhalt as part of the program Saxony-Anhalt SCIENCE - Research and Innovation (ERDF) 2021-2027 in the project ReSeDiUm (funding code ZS/2023/12/182669).
Approved project period: 1 March 2024 to 31 December 2027.
© EFRE
