Search results for "Linear regression"
showing 10 items of 375 documents
Estimating the macroscopic capillary length from Beerkan infiltration experiments and its impact on saturated soil hydraulic conductivity predictions
2020
International audience; The macroscopic capillary length, λc, is a fundamental soil parameter expressing the relative importance of the capillary over gravity forces during water movement in unsaturated soil. In this investigation, we propose a simple field method for estimating λc using only a single-ring infiltration experiment of the Beerkan type and measurements of initial and saturated soil water contents. We assumed that the intercept of the linear regression fitted to the steady-state portion of the experimental infiltration curve could be used as a reliable predictor of λc. This hypothesis was validated by assessing the proposed calculation approach using both analytical and field d…
Statistical retrieval of atmospheric profiles with deep convolutional neural networks
2019
Abstract Infrared atmospheric sounders, such as IASI, provide an unprecedented source of information for atmosphere monitoring and weather forecasting. Sensors provide rich spectral information that allows retrieval of temperature and moisture profiles. From a statistical point of view, the challenge is immense: on the one hand, “underdetermination” is common place as regression needs to work on high dimensional input and output spaces; on the other hand, redundancy is present in all dimensions (spatial, spectral and temporal). On top of this, several noise sources are encountered in the data. In this paper, we present for the first time the use of convolutional neural networks for the retr…
Contribution of environmental factors to temperature distribution at different resolution levels on the forefield of the Loven Glaciers (Svalbard)
2007
ABSTRACTThe climate and its components (temperature and precipitation) are organised according to different spatial scales that are structured hierarchically. The aim of this paper is to explore the dependence between temperature and deterministic factors at different scales on a 10 km2 study area on the northwestern coast of Svalbard. A GIS was developed which contained three sources of information: temperature, remotely sensed imagery and digital elevation models (DEM), and derived raster data layers. The first layer, temperatures, was acquired at regularly observed temporal intervals from 53 stations. The second layer comprised remotely sensed images (aerial photography and SPOT imagery)…
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…
Eco-Friendly Estimation of Heavy Metal Contents in Grapevine Foliage Using In-Field Hyperspectral Data and Multivariate Analysis
2019
Heavy metal monitoring in food-producing ecosystems can play an important role in human health safety. Since they are able to interfere with plants’ physiochemical characteristics, which influence the optical properties of leaves, they can be measured by in-field spectroscopy. In this study, the predictive power of spectroscopic data is examined. Five treatments of heavy metal stress (Cu, Zn, Pb, Cr, and Cd) were applied to grapevine seedlings and hyperspectral data (350−2500 nm), and heavy metal contents were collected based on in-field and laboratory experiments. The partial least squares (PLS) method was used as a feature selection technique, and multiple linear regressions (…
Topographic descriptors and thermal inversions amid the plateaus and mountains of the Jura (France)
2018
Sixteen temperature measurement sites under forest cover are distributed across the plateaus and mountains of the Jura (France). They are composed of pairs of stations located, one at the bottom of a topographic trough, the other at least 50 m higher in altitude. Three descriptors (station elevation, altitudinal difference (amplitude) between the two stations of each site, and topographical context) are used to explain how the frequency, intensity, and duration of inversions are spatially structured. Depending on whether one considers: 1) tn (minimum temperature) or tx (maximum temperature), 2) frequency or intensity, the sign of the correlation values changes. This reflects the fact that n…
Pedotransfer functions for estimating soil water retention curve of Sicilian soils
2019
Pedotransfer functions (PTFs) make use of routinely surveyed soil data to estimate soil properties but their application to soils different from those used for their development can yield inaccurate estimates. This investigation aimed at evaluating the water retention prediction accuracy of eight existing PTFs using a database of 217 Sicilian soils exploring 11 USDA textural classes. PTFs performance was assessed by root mean square differences (RMSD) and average differences (AD) between estimated and measured data. Extended Nonlinear Regression (ENR) technique was adopted to recalibrate or develop four new PTFs and Wind’s evaporation method was applied to validate the effectiveness of the …
Note. Kinetic parameters of Bacillus stearothermophilus spores under isothermal and non-isothermal heating conditions Nota. Parámetros cinéticos del …
1998
Thermobacteriological studies using Bacillus stearotherrnophilus spores were carried out by heating the spores under isothermal and non-isothermal conditions followed by an isothermal period. Ex perimental data obtained after isothermal heating were analyzed using a two-step linear regression procedure and a one-step nonlinear regression method. Results obtained using both analytical tech niques were close, but the 90% interval of confidence for predictions was lower when the one-step nonlinear regression was used. These results indicated the convenience of using the one-step nonlin ear regression method to obtain thermal kinetic parameters for bacterial spores. Also, the parameters obtain…
Nonlinear statistical retrieval of surface emissivity from IASI data
2017
Emissivity is one of the most important parameters to improve the determination of the troposphere properties (thermodynamic properties, aerosols and trace gases concentration) and it is essential to estimate the radiative budget. With the second generation of infrared sounders, we can estimate emissivity spectra at high spectral resolution, which gives us a global view and long-term monitoring of continental surfaces. Statistically, this is an ill-posed retrieval problem, with as many output variables as inputs. We here propose nonlinear multi-output statistical regression based on kernel methods to estimate spectral emissivity given the radiances. Kernel methods can cope with high-dimensi…
The regression Tsetlin machine: a novel approach to interpretable nonlinear regression
2019
Relying simply on bitwise operators, the recently introduced Tsetlin machine (TM) has provided competitive pattern classification accuracy in several benchmarks, including text understanding. In this paper, we introduce the regression Tsetlin machine (RTM), a new class of TMs designed for continuous input and output, targeting nonlinear regression problems. In all brevity, we convert continuous input into a binary representation based on thresholding, and transform the propositional formula formed by the TM into an aggregated continuous output. Our empirical comparison of the RTM with state-of-the-art regression techniques reveals either superior or on par performance on five datasets. Thi…