Soil Moisture Estimation based on
Multispectral and SAR Satellite Data using
Google Earth Engine and Machine Learning

Πέγιου - Μαλακού, Βασιλική - Μαρία; Pegiou - Malakou, Vasiliki - Maria

dc.contributor.author	Πέγιου - Μαλακού, Βασιλική - Μαρία	el
dc.contributor.author	Pegiou - Malakou, Vasiliki - Maria	en
dc.date.accessioned	2019-12-23T09:41:05Z
dc.date.available	2019-12-23T09:41:05Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/49633
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.17331
dc.description	Εθνικό Μετσόβιο Πολυτεχνείο--Μεταπτυχιακή Εργασία. Διεπιστημονικό-Διατμηματικό Πρόγραμμα Μεταπτυχιακών Σπουδών (Δ.Π.Μ.Σ.) “Γεωπληροφορική”	el
dc.rights	Default License
dc.subject	Τηλεπισκόπιση	en
dc.subject	Παρατήρηση της Γής	el
dc.subject	Ραντάρ	el
dc.subject	Μηχανική Μάθηση	el
dc.subject	Εδαφική υγρασία	el
dc.subject	Remote Sensing	en
dc.subject	Earth Observation	en
dc.subject	Radar	en
dc.subject	High Resolution	en
dc.subject	Deep Learning,	en
dc.subject	Soil	en
dc.title	Soil Moisture Estimation based on Multispectral and SAR Satellite Data using Google Earth Engine and Machine Learning	en
dc.title	Εκτίμηση Εδαφικής Υγρασίας από Πολυφασματικά και Ραντάρ Δορυφορικά Δεδομένα με χρήση του Google Earth Engine και Τεχνικών Μηχανικής Μάθησης	el
heal.type	masterThesis
heal.classification	ΓΕΩΠΛΗΡΟΦΟΡΙΚΗ	el
heal.classification	ΤΗΛΕΠΙΣΚΟΠΗΣΗ	el
heal.classification	GEO-INFORMATICS	en
heal.classification	Remote sensing	en
heal.classificationURI	http://data.seab.gr/concepts/0470dde7ed974578bbc4961549816f7b254efcb2
heal.classificationURI	http://data.seab.gr/concepts/29f3834f510e2fcbee2fcce329a355775dd48e27
heal.classificationURI	http://data.seab.gr/concepts/0470dde7ed974578bbc4961549816f7b254efcb2
heal.classificationURI	http://skos.um.es/unescothes/C03347
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2018-10-25
heal.abstract	Soil Moisture can be described as the level of saturation in the upper soil layer relative to the soil field capacity, regulated by the precipitation and potential evaporation, while being highly variable in space and time. It constitutes a key factor for agricultural management such as optimizing the fertilizer rates and irrigation, applying pesticides or herbicides and crop management. Moreover, soil moisture is considered as valuable information in many sectors such as Hydrology, Biogeography, Geomorphology, Agronomy and Climatology. To this end, the main objective in this master thesis was to evaluate the concurrent use of satellite multispectral and SAR radar data for estimating soil moisture in large spatial scales. In particular, Landsat 8 Surface Reflectance data as well as Sentinel 1 GRD SAR data were employed in the region of Arta across the Amvrakikos Gulf and the Amvrakikos Wetlands Natural Park. Recent studies have indicated that the amplitude derived by SAR data in VV polarization along with information about the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Moisture Index (NDMI) and the Moisture Index (MI) from multispectral data can be proxies of soil moisture. In-situ measurements from the Enhydris project were also acquired spanning three different years. Google Earth Engine was exploited for mining the satellite data through the Javascript API services. Then several experiments we performed in order to establish correlations between the Ιn-Situ and satellite data based on statistical and machine learning tools like Linear Regression, Polynomial Regression, Generalized Additive Models (based on R Statistical tool), as well deep learning models, using the TensorFlow Framework in association with the Keras library in R. Generally speaking, based on the considered relative large, multitemporal dataset, the statistical approaches did not manage to establish concrete correlations in any of the performed experiments and combinations. The MI index along with the VV backscatter though was closer to the expressed variation in the In-Situ dataset. Based on the deep machine learning framework, stronger correlations were established between the In-Situ data from Enhydris and a combination of VV amplitude and NDVI satellite observations.	en
heal.advisorName	Καράντζαλος, Κωνσταντίνος	el
heal.committeeMemberName	Αργιαλάς, Δημήτριος	el
heal.committeeMemberName	Μπαρούχας, Παντελής	el
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Αγρονόμων και Τοπογράφων Μηχανικών	el
heal.academicPublisherID	ntua
heal.numberOfPages	114 σ.	el
heal.fullTextAvailability	true