Analysis of the Evolution of a Rural Landscape by Combining SAR Geodata with GIS Techniques
- 27 Downloads
In the last decades, Mediterranean rural landscapes have undergone significant changes, with relevant considerable environmental and socio-economic impacts. These phenomena are often triggered by agricultural abandonment, especially in environmentally-sensitive areas, which are usually located in marginal and less profitable regions, and which could indeed irremediably compromise the identity and role of these Mediterranean landscapes. On the other hand, the progressive increase of available multi-source geodata allows to reconstruct the landscape original structure, providing new tools able to prevent negative impacts on environment. Hence, thanks to the development of increasingly advanced and open-source GIS tools, it is possible to implement several geodata typologies that can be mutually integrated in an increasingly efficient approach. In this paper the process of landscape reshaping pattern is analyzed in a study area of Basilicata region (Southern Italy) using remote sensing. In particular, the vegetation component of a landscape has been assessed by means of SAR images by using an artificial intelligence approach, that is machine learning to understand landscape dynamics in two different time periods. In this way, it has been possible to integrate data of different source and composition into landscape analysis methodologies, hence developing a suitable tool for planning and managing the rural landscape.
KeywordsRemote sensing SAR Geographical information system Rural landscape Artificial intelligence Machine learning
Authors gracefully thank Geocart Srl company for providing the SAR images used in this work.
- Andria, G., D’orazio, A., Lay Ekuakille, A., Moretti, M., Pieri, P., Tralli, F., & Tropeano, M. (2000). Accuracy assessment in photo interpretation of remote sensing ERS-2/SAR images. In 17th IEEE—IMTC2000, Baltimore, USA, May 1–4.Google Scholar
- Bhateja, V., Tripathi, A., Gupta, A., & Lay-Ekuakille (2015). Speckle suppression in SAR images employing modified anisotropic diffusion filtering in wavelet domain for environment monitoring. Measurement, 74, 246–254.Google Scholar
- Lay-Ekuakille, A., Pelillo, V., Dellisanti, C., & Tralli, F. (2002). Sar aided method for rural soil evaluation. SPIE2002 Remote Sensing, 22–27 September in Crete, Greece.Google Scholar
- Liu, S., Qi, Z., Li, X. & AndYeh, A. G. (2019). Integration of convolutional neural networks and object-based post-classification refinement for land use and land cover mapping with optical and SAR data. Remote Sens, 11, 690.Google Scholar
- Losurdo, A., Pacifico, S., Sarli, V., Colangelo, A., & Leggeri, M. (2008). Integration of differential SAR interferometry and ancillary GIS data for the study of superficialdeformations. EARSeLe Proceedings 7, 1/2008.Google Scholar
- Scheiber, R., Hajnsek, I., Horn, R., Papathanassiou, K. P., Prats, P., & Moreira, A. (2008). Recent developments and applications of multi-pass airborne interferometric SAR using the E-SAR system. In 7th European Conference on Synthetic Aperture Radar, Friedrichshafen, Germany, 2008, pp. 1–4.Google Scholar
- Zhu, X. X., Tuia, D., Mou, L., Xia, G., Zhang, L., Xu, F., & Fraundorfer, F. (2017). Deep learning in remote sensing: A comprehensive review and list of resources. In IEEE Geoscience and Remote Sensing Magazine, pp. 8–36.Google Scholar