Search results for "Form."

Efficient remote sensing image classification with Gaussian processes and Fourier features

2017

This paper presents an efficient methodology for approximating kernel functions in Gaussian process classification (GPC). Two models are introduced. We first include the standard random Fourier features (RFF) approximation into GPC, which largely improves the computational efficiency and permits large scale remote sensing data classification. In addition, we develop a novel approach which avoids randomly sampling a number of Fourier frequencies, and alternatively learns the optimal ones using a variational Bayes approach. The performance of the proposed methods is illustrated in complex problems of cloud detection from multispectral imagery.

SAR Image Classification Combining Structural and Statistical Methods

2011

The main objective of this paper is to develop a new technique of SAR image classification. This technique combines structural parameters, including the Sill, the slope, the fractal dimension and the range, with statistical methods in a supervised image classification. Thanks to the range parameter, we define the suitable size of the image window used in the proposed approach of supervised image classification. This approach is based on a new way of characterising different classes identified on the image. The first step consists in determining relevant area of interest. The second step consists in characterising each area identified, by a matrix. The last step consists in automating the pr…

A geological field trip to the Côte d'Ivoire-Ghana transform margin

1998

Abstract During the Equanaute survey (June 1992), fourteen submersible dives were performed between 4950 and 2250 m water depths across the southern slope of the Cote d'Ivoire-Ghana Marginal Ridge (CIGMR), in the eastern Equatorial Atlantic. The CIGMR, a high-standing topographic marginal ridge along the Cote d'Ivoire-Ghana transform margin, is believed to result from a complex structural evolution due to the specific wrench-related rifting between Western Equatorial Africa and Northeastern Brazil, in Early Cretaceous times. In this paper we report and discuss geological observations made during dives, and sample analyses to resolve the lithology, paleoenvironmental conditions, age and orig…

Apparent boudinage in dykes

2004

Intrusive rocks may be arranged in the form of strings of lenses or beads, as found on the Cap de Creus Peninsula, NE Spain, and in the South Finland Migmatite-Granite Belt. These structures first appear to be the result of stretching and boudinage of intrusive sheets or dykes. However, closer examination reveals that they are not boudins, but are instead primary intrusive structures. A detailed study was performed on a swarm of pegmatite intrusions at Cap de Creus. Layering is often continuous between beads, and, in some cases, individual beads exhibit a very irregular shape. These observations are shown to be incompatible with an origin by boudinage. Analogue experiments were used to test…

Exploring Effective Ecosystems in Disaster Management: Case studies of Japan and Nepal

2017

Understanding deep learning in land use classification based on Sentinel-2 time series

2020

AbstractThe use of deep learning (DL) approaches for the analysis of remote sensing (RS) data is rapidly increasing. DL techniques have provided excellent results in applications ranging from parameter estimation to image classification and anomaly detection. Although the vast majority of studies report precision indicators, there is a lack of studies dealing with the interpretability of the predictions. This shortcoming hampers a wider adoption of DL approaches by a wider users community, as model’s decisions are not accountable. In applications that involve the management of public budgets or policy compliance, a better interpretability of predictions is strictly required. This work aims …

Soil development on sediments and evaporites of the Messinian crisis

2020

Abstract Vast areas in the Mediterranean are characterised by evaporite deposits of the Messinian crises (c. 6–5.3 Ma BP). During this period, large deposits were built up in shallow lagoon-like systems and are now found in southern Italy, Albania, Cyprus and Turkey. So far, soil formation on evaporites has been studied predominantly in subarid to arid environments. Although the formation of soils has received new significance, little is known about the evolutional trajectories on evaporites of the Mediterranean. We therefore studied soil formation in the Caltanissetta basin (Sicily) where evaporites are most widespread. The lithologies included the sequence: marine clay deposits, laminated…

Ground deformation reveals the scale-invariant conduit dynamics driving explosive basaltic eruptions

2021

The mild activity of basaltic volcanoes is punctuated by violent explosive eruptions that occur without obvious precursors. Modelling the source processes of these sudden blasts is challenging. Here, we use two decades of ground deformation (tilt) records from Stromboli volcano to shed light, with unprecedented detail, on the short-term (minute-scale) conduit processes that drive such violent volcanic eruptions. We find that explosive eruptions, with source parameters spanning seven orders of magnitude, all share a common pre-blast ground inflation trend. We explain this exponential inflation using a model in which pressure build-up is caused by the rapid expansion of volatile-rich magma ri…

Morphological Properties of Slender Ca ${\rm{II}}$ H Fibrils Observed by Sunrise II

2017

R. Gafeira et. al.

Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysis

2015

In this paper we present an approach to perform relative spectral alignment between optical cross-sensor acquisitions. The proposed method aims at projecting the images from two different and possibly disjoint input spaces into a common latent space, in which standard change detection algorithms can be applied. The system relies on the regularized kernel canonical correlation analysis transformation (kCCA), which can accommodate nonlinear dependencies between pixels by means of kernel functions. To learn the projections, the method employs a subset of samples belonging to the unchanged areas or to uninteresting radiometric differences. Since the availability of ground truth information to p…