Search results for "Gaussian process"

showing 10 items of 128 documents

Intelligent Sampling for Vegetation Nitrogen Mapping Based on Hybrid Machine Learning Algorithms

2021

Upcoming satellite imaging spectroscopy missions will deliver spatiotemporal explicit data streams to be exploited for mapping vegetation properties, such as nitrogen (N) content. Within retrieval workflows for real-time mapping over agricultural regions, such crop-specific information products need to be derived precisely and rapidly. To allow fast processing, intelligent sampling schemes for training databases should be incorporated to establish efficient machine learning (ML) models. In this study, we implemented active learning (AL) heuristics using kernel ridge regression (KRR) to minimize and optimize a training database for variational heteroscedastic Gaussian processes regression (V…

Training setMean squared errorActive learning (machine learning)Data stream miningComputer scienceFrame (networking)0211 other engineering and technologiesSampling (statistics)02 engineering and technologyVegetation15. Life on landGeotechnical Engineering and Engineering Geologycomputer.software_genreArticleEuclidean distancesymbols.namesakesymbolsData miningElectrical and Electronic EngineeringGaussian processcomputer021101 geological & geomatics engineering
researchProduct

Quantifying Fundamental Vegetation Traits over Europe Using the Sentinel-3 OLCI Catalogue in Google Earth Engine

2022

Thanks to the emergence of cloud-computing platforms and the ability of machine learning methods to solve prediction problems efficiently, this work presents a workflow to automate spatiotemporal mapping of essential vegetation traits from Sentinel-3 (S3) imagery. The traits included leaf chlorophyll content (LCC), leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fractional vegetation cover (FVC), being fundamental for assessing photosynthetic activity on Earth. The workflow involved Gaussian process regression (GPR) algorithms trained on top-of-atmosphere (TOA) radiance simulations generated by the coupled canopy radiative transfer model (RTM) SC…

Vegetation traitsTime seriesvegetation traits; Sentinel-3; TOA radiance; OLCI; Gaussian process regression; machine learning; hybrid method; time series; Google Earth EngineTOA radianceMachine learningHybrid methodGeneral Earth and Planetary SciencesMatemática AplicadaSentinel-3OLCIGoogle Earth EngineGaussian process regressionRemote Sensing
researchProduct

Parabolic pulse generation through passive reshaping of gaussian pulses in a normally dispersive fiber

2007

We numerically and experimentally demonstrate that a Gaussian pulse can be reshaped into a pulse with a stable parabolic intensity profile during propagation in normally dispersive nonlinear fibers.

[PHYS.PHYS.PHYS-OPTICS] Physics [physics]/Physics [physics]/Optics [physics.optics]Materials scienceGaussianPhysics::Optics02 engineering and technology01 natural sciences010309 opticssymbols.namesake020210 optoelectronics & photonicsOpticsFiber Bragg grating0103 physical sciences0202 electrical engineering electronic engineering information engineeringFiberGaussian processComputer Science::DatabasesComputingMilieux_MISCELLANEOUS[PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics][ PHYS.PHYS.PHYS-OPTICS ] Physics [physics]/Physics [physics]/Optics [physics.optics]Pulse (signal processing)business.industrySecond-harmonic generationNonlinear opticsPulse shapingsymbolsbusiness
researchProduct

Pulsating Dissipative Light Bullets

2009

Finding domains of existence for (3+1)D spatio-temporal dissipative solitons, also called “dissipative light bullets”, by direct numerical solving of a cubic-quintic Ginzburg-Landau equation (CGLE) is a lengthy procedure [1,2]. Variational approaches pave the way for quicker soliton solution mapping, as long as tractable trial functions remain suitable approximations for exact solutions [3,4].

[PHYS.PHYS.PHYS-OPTICS] Physics [physics]/Physics [physics]/Optics [physics.optics]Physics[PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics][ PHYS.PHYS.PHYS-OPTICS ] Physics [physics]/Physics [physics]/Optics [physics.optics]Nonlinear optics01 natural sciences010305 fluids & plasmassymbols.namesakeDissipative solitonClassical mechanics0103 physical sciencessymbolsDissipative systemGinzburg–Landau theorySoliton010306 general physicsDispersion (water waves)Nonlinear Sciences::Pattern Formation and SolitonsGaussian processBifurcationComputingMilieux_MISCELLANEOUS
researchProduct

A Hybrid Algorithm Based on WiFi for Robust and Effective Indoor Positioning

2019

Indoor positioning based on the Wireless Fidelity (WiFi) protocol and the Pedestrian Dead Reckoning (PDR) approach is widely exploited because of the existing WiFi infrastructure in buildings and the advancement of built-in smartphone sensors. In this work, a hybrid algorithm that combines WiFi fingerprinting and PDR to both exploit their advantages as well as limiting the impact of their disadvantages is proposed. Specifically, to build a probability map from noisy Received Signal Strength (RSS), a Gaussian Process (GP) regression is deployed to estimate and construct the RSS fingerprints with incomplete data. Mean and variance of generated points are used to estimate WiFi fingerprinting p…

business.industryComputer scienceRSSReal-time computingComputingMilieux_LEGALASPECTSOFCOMPUTING020206 networking & telecommunications02 engineering and technologycomputer.file_formatHybrid algorithmData setsymbols.namesakeInertial measurement unitDead reckoning0202 electrical engineering electronic engineering information engineeringsymbolsWireless020201 artificial intelligence & image processingbusinessParticle filterVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550Gaussian processcomputer2019 19th International Symposium on Communications and Information Technologies (ISCIT)
researchProduct

Machine Learning Methods for Spatial and Temporal Parameter Estimation

2020

Monitoring vegetation with satellite remote sensing is of paramount relevance to understand the status and health of our planet. Accurate and constant monitoring of the biosphere has large societal, economical, and environmental implications, given the increasing demand of biofuels and food by the world population. The current democratization of machine learning, big data, and high processing capabilities allow us to take such endeavor in a decisive manner. This chapter proposes three novel machine learning approaches to exploit spatial, temporal, multi-sensor, and large-scale data characteristics. We show (1) the application of multi-output Gaussian processes for gap-filling time series of…

business.industryEstimation theoryComputer scienceBig dataBiosphereVegetationMachine learningcomputer.software_genreRandom forestsymbols.namesakeKernel (statistics)symbolsArtificial intelligenceScale (map)businessGaussian processcomputer
researchProduct

Estudio integral de humedales altoandinos (andean peatlands) con Teledetección y SIG

2022

La Reserva de Producción de Fauna Chimborazo (RPFCH) es un ecosistema de alto valor situado en los andes ecuatorianos, ocupado en su mayor parte por turberas, también llamados bofedales o peatlands. El objetivo de esta tesis es el estudio de dichos ecosistemas a partir de una extensa base de datos de campo obtenida en 2016 y usando datos de teledetección óptica y radar y variables topográficas, ambientales y climáticas con SIG. Para ello se analizaron los mejores métodos para el cartografiado de los peatlands en la RPFCH, la estimación del carbono bajo el suelo (COS) en la capa 0-30 cm y la estimación del carbono almacenado en la vegetación calculado a partir de la biomasa. Como resultado s…

carbono vegetalbofedalmáquinas de aprendizaje:CIENCIAS DE LA TIERRA Y DEL ESPACIO [UNESCO]carbono orgánico del suelosentinel 2sentinel 1gaussian process regressionUNESCO::CIENCIAS DE LA TIERRA Y DEL ESPACIO
researchProduct

Evaluation of Hybrid Models to Estimate Chlorophyll and Nitrogen Content of Maize Crops in the Framework of the Future CHIME Mission

2022

In the next few years, the new Copernicus Hyperspectral Imaging Mission (CHIME) is foreseen to be launched by the European Space Agency (ESA). This mission will provide an unprecedented amount of hyperspectral data, enabling new research possibilities within several fields of natural resources, including the “agriculture and food security” domain. In order to efficiently exploit this upcoming hyperspectral data stream, new processing methods and techniques need to be studied and implemented. In this work, the hybrid approach (HYB) and its variant, featuring sampling dimensionality reduction through active learning heuristics (HAL), were applied to CHIME-like data to evaluate the…

chlorophyll contentmachine learning regression algorithmactive learningGeneral Earth and Planetary Sciencesspaceborne imaging spectroscopyradiative transfer modelingGaussian process regressionnitrogen contentRemote Sensing
researchProduct

Data Compensation with Gaussian Processes Regression: Application in Smart Building's Sensor Network

2022

Data play an essential role in the optimal control of smart buildings’ operation, especially in building energy-management for the target of nearly zero buildings. The building monitoring system is in charge of collecting and managing building data. However, device imperfections and failures of the monitoring system are likely to produce low-quality data, such as data loss and inconsistent data, which then seriously affect the control quality of the buildings. This paper proposes a new approach based on Gaussian process regression for data-quality monitoring and sensor network data compensation in smart buildings. The proposed method is proven to effectively detect and compensate for low-qu…

data compensationControl and OptimizationRenewable Energy Sustainability and the Environmentsmart building; sensor maintenance; data compensation; Gaussian process regressionsmart buildingEnergy Engineering and Power TechnologyBuilding and ConstructionElectrical and Electronic Engineeringsensor maintenanceEngineering (miscellaneous)Gaussian process regressionEnergy (miscellaneous)
researchProduct

Distributed spatial prediction for radio environment maps reconstruction in heterogeneous wireless networks

2017

Las previsiones indican que el tráfico de datos móviles se multiplicará por siete en el periodo de 2016 a 2021, creciendo con una tasa agregada anual del 47%. Para satisfacer esta demanda, tanto la industria como la academia se están centrando en las redes de quinta generación o 5G. Las redes 5G se espera que constituyan un entorno complejo e interconectado, que además proporciones múltiples servicios y aplicaciones a un número masivo de usuarios y máquinas. En este concepto se incluye la necesidad de dar soporte o de crear servicios para el paradigma conocido como el Internet de las Cosas (IoT), donde la visión es la de crear un entorno de todo conectado con todo en todo momento, con aplic…

distributed channel prediction:CIENCIAS TECNOLÓGICAS [UNESCO]krigingUNESCO::CIENCIAS TECNOLÓGICASradio environment mapsgaussian process regression
researchProduct