Search results for "Logic"
showing 10 items of 33629 documents
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.
SVM-based classification of High resolution Urban Satellites Images using Dense SURF and Spectral Information
2018
Remote-sensing focusing on image classification knows a large progress and receives the attention of the remote-sensing community day by day. Combining many kinds of extracted features has been successfully applied to High resolution urban satellite images using support vector machine (SVM). In this paper, we present a methodology that is promoting a performed classification by using pixel-wise SURF description features combined with spectral information in Cielab space for the first time on common scenes of urban imagery. The proposed method gives a promising classification accuracy when compared with the two types of features used separately.
Land Use Affects Carbon Sources to the Pelagic Food Web in a Small Boreal Lake
2016
Small humic forest lakes often have high contributions of methane-derived carbon in their food webs but little is known about the temporal stability of this carbon pathway and how it responds to environmental changes on longer time scales. We reconstructed past variations in the contribution of methanogenic carbon in the pelagic food web of a small boreal lake in Finland by analyzing the stable carbon isotopic composition (δ13C values) of chitinous fossils of planktivorous invertebrates in sediments from the lake. The δ13C values of zooplankton remains show several marked shifts (approx. 10 ‰), consistent with changes in the proportional contribution of carbon from methane-oxidizing bacteri…
Interpretation of the nitrogen isotopic composition of Precambrian sedimentary rocks: Assumptions and perspectives
2016
International audience; Nitrogen isotope compositions in sedimentary rocks (d(15)N(sed)) are routinely used for reconstructing Cenozoic N-biogeochemical cycling and are also being increasingly applied to understanding the evolution of ancient environments. Here we review the existing knowledge and rationale behind the use of d(15)N(sed) as a proxy for the Precambrian N-biogeochemical cycle with the aims of (i) identifying the major uncertainties that affect analyses and interpretation of nitrogen isotopes in ancient sedimentary rocks, (ii) developing a framework for interpreting the Precambrian d(15)N(sed) record, (iii) testing this framework against a database of Precambrian d(15)N(sed) va…
Increase inabovegroundfreshlitterquantityover-stimulatessoil respiration inatemperatedeciduousforest
2010
In the context of climate change, the amount of carbon allocated to soil, particularly fresh litter, is predicted to increase with terrestrial ecosystem productivity, and may alter soil carbon storage capacities. In this study we performed a 1-year litter-manipulation experiment to examine how soil CO2 efflux was altered by the amount of fresh litter. Three treatments were applied: litter exclusion (E), control (C, natural amount: 486 g m −2 ) and litter addition (A, twice the natural amount: 972 g m −2
Linking photosynthesis and sun-induced fluorescence at sub-daily to seasonal scales
2018
Abstract Due to its close link to the photosynthetic process, sun-induced chlorophyll fluorescence (F) opens new possibilities to study dynamics of photosynthetic light reactions and to quantify CO2 assimilation rates. Although recent studies show that F is linearly related to gross primary production (GPP) on coarse spatial and temporal scales, it is argued that this relationship may be mainly driven by seasonal changes in absorbed photochemical active radiation (APAR) and less by the plant light use efficiency (LUE). In this work a high-resolution spectrometer was used to continuously measure red and far-red fluorescence and different reflectance indices within a sugar beet field during t…
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 …
Transferring deep learning models for cloud detection between Landsat-8 and Proba-V
2020
Abstract Accurate cloud detection algorithms are mandatory to analyze the large streams of data coming from the different optical Earth observation satellites. Deep learning (DL) based cloud detection schemes provide very accurate cloud detection models. However, training these models for a given sensor requires large datasets of manually labeled samples, which are very costly or even impossible to create when the satellite has not been launched yet. In this work, we present an approach that exploits manually labeled datasets from one satellite to train deep learning models for cloud detection that can be applied (or transferred) to other satellites. We take into account the physical proper…
Diving into exoplanets: Are water seas the most common?
2019
One of the basic tenets of exobiology is the need for a liquid substratum in which life can arise, evolve, and develop. The most common version of this idea involves the necessity of water to act as such a substratum, both because that is the case on Earth and because it seems to be the most viable liquid for chemical reactions that lead to life. Other liquid media that could harbor life, however, have occasionally been put forth. In this work, we investigate the relative probability of finding superficial seas on rocky worlds that could be composed of nine different, potentially abundant, liquids, including water. We study the phase space size of habitable zones defined for those substance…
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…