The Holuhraun lava flow was the largest effusive eruption in Iceland for 230 years, with an estimated lava bulk volume of ~1.44 km3 and covering an area of ~84 km2. The six month long eruption at Holuhraun 2014–2015 generated a diverse surface environment. ...

The subject of this thesis is blind hyperspectral unmixing using deep learning based autoencoders. Two methods based on autoencoders are proposed and analyzed. Both methods seek to exploit the spatial correlations in the hyperspectral images to improve ...

Capsule networks can be considered to be the next era of deep learning and have recently shown their advantages in supervised classification. Instead of using scalar values to represent features, the capsule networks use vectors to represent features, ...

Carriers of large recurrent copy number variants (CNVs) have a higher risk of developing neurodevelopmental disorders. The 16p11.2 distal CNV predisposes carriers to e.g., autism spectrum disorder and schizophrenia. We compared subcortical brain volumes ...

Email Print Request Permissions With respect to recent advances in remote sensing technologies, the spatial resolution of airborne and spaceborne sensors is getting finer, which enables us to precisely analyze even small objects on the Earth. This ...

Lava flow thicknesses, volumes, and effusion rates provide essential information for understanding the behavior of eruptions and their associated deformation signals. Preeruption and posteruption elevation models were generated from historical stereo ...

In this paper, we develop a hyperspectral feature extraction method called sparse and smooth low-rank analysis (SSLRA). First, we propose a new low-rank model for hyperspectral images (HSIs) where we decompose the HSI into smooth and sparse components. ...

Hyperspectral image (HSI) is usually corrupted by various types of noise, including Gaussian noise, impulse noise, stripes, deadlines, and so on. Recently, sparse and low-rank matrix decomposition (SLRMD) has demonstrated to be an effective tool in ...

In remote sensing, acquired optical images of high spectral resolution have usually a lower spatial resolution than images of lower spectral resolution. This is due to physical, cost and complexity constraints. To make the most of the available imagery, ...

So far, a large number of advanced techniques have been developed to enhance and extract the spatially semantic information in hyperspectral image processing and analysis. However, locally semantic change, such as scene composition, relative position ...