Search results for "artificial"

showing 10 items of 7394 documents

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…

010504 meteorology & atmospheric sciencesFeature extraction0211 other engineering and technologiesRelative spectral alignment02 engineering and technology3107 Atomic and Molecular Physics and Optics01 natural sciencesCross-sensorCanonical correlation analysis1706 Computer Science Applications910 Geography & travelComputers in Earth SciencesEngineering (miscellaneous)021101 geological & geomatics engineering0105 earth and related environmental sciencesMathematicsGround truthbusiness.industry1903 Computers in Earth SciencesKernel methodsPattern recognitionReal imageAtomic and Molecular Physics and OpticsComputer Science Applications10122 Institute of GeographyTransformation (function)Kernel methodChange detectionFeature extraction2201 Engineering (miscellaneous)Artificial intelligencebusinessCanonical correlationChange detectionCurse of dimensionalityISPRS Journal of Photogrammetry and Remote Sensing
researchProduct

Crop specific algorithms trained over ground measurements provide the best performance for GAI and fAPAR estimates from Landsat-8 observations

2021

Abstract Estimation of Green Area Index (GAI) and fraction of Absorbed Photosynthetically Active Radiation (fAPAR) from decametric satellites was investigated in this study using a large database of ground measurements over croplands. It covers six main crop types including rice, corn, wheat and barley, sunflower, soybean and other types of crops. Ground measurements were completed using either digital hemispherical cameras, LAI-2000 or AccuPAR devices over sites representative of a decametric pixel. Sites were spread over the globe and the data collected at several growth stages concurrently to the acquisition of Landsat-8 images. Several machine learning techniques were investigated to re…

010504 meteorology & atmospheric sciencesMean squared errorArtificial neural networkCalibration (statistics)0208 environmental biotechnologyEmpirical modellingSoil ScienceGeology02 engineering and technology01 natural sciencesNormalized Difference Vegetation Index020801 environmental engineeringSupport vector machineData pointKrigingComputers in Earth SciencesAlgorithm0105 earth and related environmental sciencesRemote sensingMathematicsRemote Sensing of Environment
researchProduct

Hyperspectral dimensionality reduction for biophysical variable statistical retrieval

2017

Abstract Current and upcoming airborne and spaceborne imaging spectrometers lead to vast hyperspectral data streams. This scenario calls for automated and optimized spectral dimensionality reduction techniques to enable fast and efficient hyperspectral data processing, such as inferring vegetation properties. In preparation of next generation biophysical variable retrieval methods applicable to hyperspectral data, we present the evaluation of 11 dimensionality reduction (DR) methods in combination with advanced machine learning regression algorithms (MLRAs) for statistical variable retrieval. Two unique hyperspectral datasets were analyzed on the predictive power of DR + MLRA methods to ret…

010504 meteorology & atmospheric sciencesMean squared errorComputer science0211 other engineering and technologies02 engineering and technologycomputer.software_genre01 natural sciencessymbols.namesakeLinear regressionComputers in Earth SciencesEngineering (miscellaneous)Gaussian processHyMap021101 geological & geomatics engineering0105 earth and related environmental sciencesData stream miningbusiness.industryDimensionality reductionHyperspectral imagingPattern recognitionAtomic and Molecular Physics and OpticsComputer Science ApplicationsKernel (statistics)symbolsData miningArtificial intelligencebusinesscomputerISPRS Journal of Photogrammetry and Remote Sensing
researchProduct

Empirical and physical estimation of Canopy Water Content from CHRIS/PROBA data

2013

20 páginas, 4 tablas, 7 figuras.

010504 meteorology & atmospheric sciencesMean squared errorScience0211 other engineering and technologies02 engineering and technologyCHRIS/PROBA01 natural sciencescanopy water content;model inversion;neural networks;look up tables;empirical up-scalingmodel inversionEmpirical up-scalingAtmospheric radiative transfer codeslook up tablesRadiative transferModel inversion021101 geological & geomatics engineering0105 earth and related environmental sciencesMathematicsRemote sensingArtificial neural networkCanopy water contentQHyperspectral imagingInversion (meteorology)Sigmoid functionSpectral bandsempirical up-scaling15. Life on landneural networks[SDE]Environmental SciencesGeneral Earth and Planetary SciencesLook up tablescanopy water contentNeural networkscanopy water content; model inversion; neural networks; look up tables; empirical up-scaling; CHRIS/PROBA
researchProduct

Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran

2021

The identification of landslide-prone areas is an essential step in landslide hazard assessment and mitigation of landslide-related losses. In this study, we applied two novel deep learning algorithms, the recurrent neural network (RNN) and convolutional neural network (CNN), for national-scale landslide susceptibility mapping of Iran. We prepared a dataset comprising 4069 historical landslide locations and 11 conditioning factors (altitude, slope degree, profile curvature, distance to river, aspect, plan curvature, distance to road, distance to fault, rainfall, geology and land-sue) to construct a geospatial database and divided the data into the training and the testing dataset. We then d…

010504 meteorology & atmospheric sciencesReceiver operating characteristicbusiness.industryDeep learningSpatial databaselcsh:QE1-996.5Deep learningLandslideIranLandslide susceptibility010502 geochemistry & geophysicsRNN01 natural sciencesConvolutional neural networklcsh:GeologyLandslideRecurrent neural networkGeneral Earth and Planetary SciencesArtificial intelligenceScale (map)businessAlgorithmCNNGeology0105 earth and related environmental sciencesGeoscience Frontiers
researchProduct

Modelling Complex Volume Shape Using Ellipsoid: Application to Pore Space Representation

2017

Natural shapes have complex volume forms that are usually difficult to model using simple analytical equations. The complexity of the representation is due to the heterogeneity of the physical environment and the variety of phenomena involved. In this study we consider the representation of the porous media. Thanks to the technological advances in Computed Topography scanners, the acquisition of images of complex shapes becomes possible. However, and unfortunately, the image data is not directly usable for simulation purposes. In this paper, we investigate the modeling of such shapes using a piece wise approximation of image data by ellipsoids. We propose to use a split-merge strategy and a…

010504 meteorology & atmospheric sciencesScale (ratio)Computer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONTangentApproximation algorithmContext (language use)02 engineering and technologyComputational geometry01 natural sciencesEllipsoid0202 electrical engineering electronic engineering information engineeringPiecewise020201 artificial intelligence & image processingRepresentation (mathematics)AlgorithmComputingMethodologies_COMPUTERGRAPHICS0105 earth and related environmental sciences2017 13th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)
researchProduct

Predicting year of plantation with hyperspectral and lidar data

2017

This paper introduces a methodology for predicting the year of plantation (YOP) from remote sensing data. The application has important implications in forestry management and inventorying. We exploit hyperspectral and LiDAR data in combination with state-of-the-art machine learning classifiers. In particular, we present a complete processing chain to extract spectral, textural and morphological features from both sensory data. Features are then combined and fed a Gaussian Process Classifier (GPC) trained to predict YOP in a forest area in North Carolina (US). The GPC algorithm provides accurate YOP estimates, reports spatially explicit maps and associated confidence maps, and provides sens…

010504 meteorology & atmospheric sciencesbusiness.industryComputer scienceForest managementFeature extraction0211 other engineering and technologiesHyperspectral imagingPattern recognition02 engineering and technologyVegetation15. Life on land01 natural sciencessymbols.namesakeLidarsymbolsLidar dataArtificial intelligencebusinessClassifier (UML)Gaussian process021101 geological & geomatics engineering0105 earth and related environmental sciences2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
researchProduct

The paramount power of selection: From Darwin to Kauffman

1995

For approximately two decades now, the Darwinian interpretation of evolution has now been challenged in many ways. Modern criticisms make it difficult, even for the staunchest Darwinians, not to take a distance from Darwin’s bold phrases on the “power” of natural selection. Let me remind you of some famous declarations of Darwin on the subject: “It may be said that natural selection is daily and hourly scrutinising, throughout the world, every variation, even the slightest; rejecting that which is bad, preserving and adding up all that is good; silently and insensibly working, whenever and wherever opportunity offers, at the improvement of each organic being in relation to its organic and i…

010506 paleontology0303 health sciencesNatural selectionbusiness.industryInterpretation (philosophy)Subject (philosophy)selectionEnvironmental ethics01 natural sciencesPower (social and political)[SHS.HISPHILSO]Humanities and Social Sciences/History Philosophy and Sociology of Sciences03 medical and health sciencesDarwin (ADL)DarwinismArtificial intelligenceForm of the GoodRelation (history of concept)business030304 developmental biology0105 earth and related environmental sciencesMathematics
researchProduct

Stage boundaries, global stratigraphy, and the time scale: towards a simplification

2004

International audience; This paper examines four facets of stratigraphic terminology and usage considered faulty and proposes corrective measures. The four perfectible areas are: (1) The system of dual nomenclature requiring discrete terminologies for the superpositional and temporal aspects of rock units. (2) The premise that a GSSP establishes the base of a stage as being coincident with the top of the preceding stage rather than simply defining it as the boundary between stages. (3) The rejection of supplementary (auxiliary) sections that would broaden the knowledge of a GSSP and enlarge the area in which it is easily usable. (4) The current dual system of nomenclature for Precambrian an…

010506 paleontologyPrecambrian-Cambrian boundaryComputer scienceStratigraphyPhanerozoiccomputer.software_genre[ SDU.STU.ST ] Sciences of the Universe [physics]/Earth Sciences/Stratigraphy01 natural sciencesCampanian-Maastrichtian boundaryBoundary (real estate)Terminologylcsh:StratigraphyStage (stratigraphy)Stages010503 geologyStratigraphy (archaeology)lcsh:QE701-7600105 earth and related environmental scienceslcsh:QE640-699GSSPChronostratigraphybusiness.industryScale (chemistry)Plio-Quaternarylcsh:QE1-996.5PaleontologyGeologyTerminologyPlio- QuaternaryCretaceous- Palaeogene boundaryDual (category theory)Global Boundary Stratotype Section and Pointlcsh:GeologyCretaceous-Palaeogene boundarylcsh:Paleontology[SDU.STU.ST]Sciences of the Universe [physics]/Earth Sciences/StratigraphyPremise[SDU.STU.ST] Sciences of the Universe [physics]/Earth Sciences/StratigraphyArtificial intelligencebusinessPrecambriancomputerNatural language processing
researchProduct

Modelling forest decline using SMOS soil moisture and vegetation optical depth

2018

Global change is increasing the risk of forest decline worldwide, impacting carbon and water cycles. Hence, there is an urgent need for predicting forest decline occurrence. To that purpose, this study links forest decline events in Catalonia, detected by the DEBOSCAT forest monitoring program, with information from the Soil Moisture and Ocean Salinity (SMOS) satellite. Firstly, this study reviews the role of the SMOS soil moisture in a previous forest decline episode occurred in 2012, where the authors concluded that dry soils increased the probability of observing decline in broadleaved forests. Secondly, the present study detects that forest decline in 2012 and 2016 was linked to very dr…

0106 biological sciences010504 meteorology & atmospheric sciencesArtificial satellites in navigationClimate changeGlobal change010603 evolutionary biology01 natural sciencesMonitoring programForest declineSalinitySatèl·lits artificials en navegacióHydric soil:Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció [Àrees temàtiques de la UPC]Soil waterEnvironmental scienceClimate changeVegetation optical depthPhysical geography:Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Satèl·lits i ràdioenllaços [Àrees temàtiques de la UPC]Soil moistureSòls -- HumitatWater cycleWater content0105 earth and related environmental sciencesSMOS
researchProduct