Search results for "Gaussian process"

showing 10 items of 128 documents

Multi-Season Phenology Mapping of Nile Delta Croplands Using Time Series of Sentinel-2 and Landsat 8 Green LAI

2022

Space-based cropland phenology monitoring substantially assists agricultural managing practices and plays an important role in crop yield predictions. Multitemporal satellite observations allow analyzing vegetation seasonal dynamics over large areas by using vegetation indices or by deriving biophysical variables. The Nile Delta represents about half of all agricultural lands of Egypt. In this region, intensifying farming systems are predominant and multi-cropping rotations schemes are increasing, requiring a high temporal and spatial resolution monitoring for capturing successive crop growth cycles. This study presents a workflow for cropland phenology characterization and mapping based on…

Landsat 8Land surface phenologyGreen leaf area indexgreen leaf area index; Sentinel-2; Landsat 8; land surface phenology; Gaussian Process Regression (GPR); time series analysisGaussian Process Regression (GPR)Time series analysisGeneral Earth and Planetary SciencesMatemática AplicadaSentinel-2Remote Sensing
researchProduct

Seasonal Mapping of Irrigated Winter Wheat Traits in Argentina with a Hybrid Retrieval Workflow Using Sentinel-2 Imagery

2022

Earth observation offers an unprecedented opportunity to monitor intensively cultivated areas providing key support to assess fertilizer needs and crop water uptake. Routinely, vegetation traits mapping can help farmers to monitor plant development along the crop’s phenological cycle, which is particularly relevant for irrigated agricultural areas. The high spatial and temporal resolution of the Sentinel-2 (S2) multispectral instrument leverages the possibility to estimate leaf area index (LAI), canopy chlorophyll content (CCC), and vegetation water content (VWC) from space. Therefore, our study presents a hybrid retrieval workflow combining a physically-based strategy with a machine learni…

Leaf Area IndexVegetation Water and Chlorophyll ContentActive LearningContenido de Agua y Clorofila de la VegetaciónDimencionality ReductionÍndice de Superficie FoliarAprendizaje ActivoReducción de DimensionalidadKrigingImágenesHybrid Retrieval WorkflowFlujo de Trabajo de Recuperación HíbridoGeneral Earth and Planetary SciencesImageryleaf area index; vegetation water and chlorophyll content; Gaussian processes regression; hybrid retrieval workflow; dimensionality reduction; active learningKrigeageRemote Sensing
researchProduct

Physics-Aware Gaussian Processes for Earth Observation

2017

Earth observation from satellite sensory data pose challenging problems, where machine learning is currently a key player. In recent years, Gaussian Process (GP) regression and other kernel methods have excelled in biophysical parameter estimation tasks from space. GP regression is based on solid Bayesian statistics, and generally yield efficient and accurate parameter estimates. However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only. Very often a forward model encoding the well-understood physical relations is available though. In this work, we review three GP models that respect and learn the physics of the underlying processes …

MatemáticasEstimation theory0211 other engineering and technologiesContext (language use)02 engineering and technologyMissing dataBayesian statisticssymbols.namesakeKernel method0202 electrical engineering electronic engineering information engineeringsymbolsGeología020201 artificial intelligence & image processingGaussian process emulatorGaussian processAlgorithm021101 geological & geomatics engineeringInterpolation
researchProduct

Constraint handling in efficient global optimization

2017

Real-world optimization problems are often subject to several constraints which are expensive to evaluate in terms of cost or time. Although a lot of effort is devoted to make use of surrogate models for expensive optimization tasks, not many strong surrogate-assisted algorithms can address the challenging constrained problems. Efficient Global Optimization (EGO) is a Kriging-based surrogate-assisted algorithm. It was originally proposed to address unconstrained problems and later was modified to solve constrained problems. However, these type of algorithms still suffer from several issues, mainly: (1) early stagnation, (2) problems with multiple active constraints and (3) frequent crashes.…

Mathematical optimizationConstraint optimizationOptimization problemL-reduction0211 other engineering and technologiesGaussian processes02 engineering and technologyexpensive optimizationMulti-objective optimizationEngineering optimizationSurrogate modelsKriging0202 electrical engineering electronic engineering information engineeringMulti-swarm optimizationGlobal optimization/dk/atira/pure/subjectarea/asjc/1700/1712constraint optimizationMathematicsta113EGO/dk/atira/pure/subjectarea/asjc/1700/1706Expensive optimization021103 operations researchConstrained optimizationComputer Science Applicationssurrogate modelsKrigingComputational Theory and Mathematics020201 artificial intelligence & image processing/dk/atira/pure/subjectarea/asjc/1700/1703SoftwareProceedings of the Genetic and Evolutionary Computation Conference
researchProduct

A Highly Flexible Trajectory Model Based on the Primitives of Brownian Fields—Part II: Analysis of the Statistical Properties

2016

In the first part of our paper, we have proposed a highly flexible trajectory model based on the primitives of Brownian fields (BFs). In this second part, we study the statistical properties of that trajectory model in depth. These properties include the autocorrelation function (ACF), mean, and the variance of the path along each axis. We also derive the distribution of the angle-of-motion (AOM) process, the incremental traveling length process, and the overall traveling length. It is shown that the path process is in general non-stationary. We show that the AOM and the incremental traveling length processes can be modeled by the phase and the envelope of a complex Gaussian process with no…

Mathematical optimizationUniform distribution (continuous)Applied MathematicsGaussianAutocorrelationMathematical analysis020206 networking & telecommunications020302 automobile design & engineering02 engineering and technologyComputer Science ApplicationsComplex normal distributionsymbols.namesake0203 mechanical engineeringLog-normal distribution0202 electrical engineering electronic engineering information engineeringsymbolsTrajectoryElectrical and Electronic EngineeringGaussian processRandom variableMathematicsIEEE Transactions on Wireless Communications
researchProduct

Spectral Approach to Equivalent Statistical Quadratization and Cubicization Methods for Nonlinear Oscillators

2003

Random vibrations of nonlinear systems subjected to Gaussian input are investigated by a technique based on statistical quadratization, and cubicization. In this context, and depending on the nature of the given nonlinearity, statistics of the stationary response are obtained via an equivalent system with a polynomial nonlinearity of either quadratic or cubic order, which can be solved by the Volterra series method. The Volterra series response is expanded in a trigonometric Fourier series over an adequately long interval T, and exact expressions are derived for the Fourier coefficients of the second- and third-order response in terms of the Fourier coefficients of the first-order, Gaussian…

Mechanical EngineeringGaussianMathematical analysisVolterra seriesTrigonometric seriessymbols.namesakeNonlinear systemMechanics of MaterialsFrequency domainsymbolsRandom vibrationFourier seriesGaussian processMathematicsJournal of Engineering Mechanics
researchProduct

Path integral solution handled by Fast Gauss Transform

2009

Abstract The path integral solution method is an effective tool for evaluating the response of non-linear systems under Normal White Noise, in terms of probability density function (PDF). In this paper it has been observed that, using short-time Gaussian approximation, the PDF at a given time instant is the Gauss Transform of the PDF at an earlier close time instant. Taking full advantage of the so-called Fast Gauss Transform a new integration method is proposed. In order to overcome some unsatisfactory trends of the classical Fast Gauss Transform, a new version termed as Symmetric Fast Gauss Transform is also proposed. Moreover, extensions to the two Fast Gauss Transform to MDOF systems ar…

Mechanical EngineeringMathematical analysisMathematicsofComputing_NUMERICALANALYSISAerospace EngineeringOcean EngineeringStatistical and Nonlinear PhysicsProbability density functionWhite noiseCondensed Matter Physicssymbols.namesakeNuclear Energy and EngineeringKronecker deltaComputingMethodologies_SYMBOLICANDALGEBRAICMANIPULATIONPath integral formulationsymbolsTwo-sided Laplace transformApplied mathematicsGauss–Seidel methodSettore ICAR/08 - Scienza Delle CostruzioniPath integral solution Fast Gauss Transform Symmetric Fast Gauss Transform Fokker-Planck equation Ito calculusS transformGaussian processCivil and Structural EngineeringMathematicsProbabilistic Engineering Mechanics
researchProduct

Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery

2021

Non-photosynthetic vegetation (NPV) biomass has been identified as a priority variable for upcoming spaceborne imaging spectroscopy missions, calling for a quantitative estimation of lignocellulosic plant material as opposed to the sole indication of surface coverage. Therefore, we propose a hybrid model for the retrieval of non-photosynthetic cropland biomass. The workflow included coupling the leaf optical model PROSPECT-PRO with the canopy reflectance model 4SAIL, which allowed us to simulate NPV biomass from carbon-based constituents (CBC) and leaf area index (LAI). PROSAIL-PRO provided a training database for a Gaussian process regression (GPR) algorithm, simulating a wide range of non…

PCACoefficient of determinationDimensionality reductionScienceQBiomassHyperspectral imaginghybrid retrievalPRISMAPROSAIL-PROVegetationNPVImaging spectroscopyCHIMEKrigingactive learningGeneral Earth and Planetary SciencesEnvironmental scienceLeaf area indexPRISMA; CHIME; NPV; Gaussian process regression; hybrid retrieval; active learning; PCA; PROSAIL-PROGaussian process regressionRemote sensingRemote Sensing
researchProduct

Emulation of Leaf, Canopy and Atmosphere Radiative Transfer Models for Fast Global Sensitivity Analysis

2016

Physically-based radiative transfer models (RTMs) help understand the interactions of radiation with vegetation and atmosphere. However, advanced RTMs can be computationally burdensome, which makes them impractical in many real applications, especially when many state conditions and model couplings need to be studied. To overcome this problem, it is proposed to substitute RTMs through surrogate meta-models also named emulators. Emulators approximate the functioning of RTMs through statistical learning regression methods, and can open many new applications because of their computational efficiency and outstanding accuracy. Emulators allow fast global sensitivity analysis (GSA) studies on adv…

PROSPECTSAIL010504 meteorology & atmospheric sciencesradiative transfer modelsScience0211 other engineering and technologies02 engineering and technologyemulatorSolar irradiance01 natural sciencessymbols.namesakeRadiative transferSensitivity (control systems)Gaussian process021101 geological & geomatics engineering0105 earth and related environmental sciencesRemote sensingMathematicsMODTRANArtificial neural networkMODTRANQDiffuse sky radiationemulator; global sensitivity analysis; machine learning; radiative transfer models; PROSPECT; SAIL; MODTRANmachine learningglobal sensitivity analysisRadiancesymbolsGeneral Earth and Planetary SciencesRemote Sensing
researchProduct

Treed Gaussian Process Regression for Solving Offline Data-Driven Continuous Multiobjective Optimization Problems

2023

Abstract For offline data-driven multiobjective optimization problems (MOPs), no new data is available during the optimization process. Approximation models (or surrogates) are first built using the provided offline data and an optimizer, e.g. a multiobjective evolutionary algorithm, can then be utilized to find Pareto optimal solutions to the problem with surrogates as objective functions. In contrast to online data-driven MOPs, these surrogates cannot be updated with new data and, hence, the approximation accuracy cannot be improved by considering new data during the optimization process. Gaussian process regression (GPR) models are widely used as surrogates because of their ability to pr…

Pareto optimalityComputational Mathematicspareto-tehokkuusgaussiset prosessitmetamodellingGaussian processeskrigingsurrogateregression treeskriging-menetelmämonitavoiteoptimointi
researchProduct