Ensemble predictive model for more accurate soil organic carbon spectroscopic estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41210%2F17%3A73491" target="_blank" >RIV/60460709:41210/17:73491 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.cageo.2017.04.008" target="_blank" >http://dx.doi.org/10.1016/j.cageo.2017.04.008</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.cageo.2017.04.008" target="_blank" >10.1016/j.cageo.2017.04.008</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Ensemble predictive model for more accurate soil organic carbon spectroscopic estimation

Popis výsledku v původním jazyce

A myriad of signal pre-processing strategies and multivariate calibration techniques has been explored in attempt to improve the spectroscopic prediction of soil organic carbon (SOC) over the last few decades. Therefore, to come up with a novel, more powerful, and accurate predictive approach to beat the rank becomes a challenging task. However, there may be a way, so that to combine several individual predictions into a single final one (according to ensemble learning theory). As this approach performs best when combining in nature different predictive algorithms that are calibrated with structurally different predictor variables, we tested predictors of two different kinds: 1) reflectance values (or transforms) at each wavelength and 2) absorption feature parameters. Consequently we applied four different calibration techniques, two per each type of predictors: a) partial least squares regression and support vector machines for type 1, and b) multiple linear regression and random forest fo

Název v anglickém jazyce

Ensemble predictive model for more accurate soil organic carbon spectroscopic estimation

Popis výsledku anglicky

A myriad of signal pre-processing strategies and multivariate calibration techniques has been explored in attempt to improve the spectroscopic prediction of soil organic carbon (SOC) over the last few decades. Therefore, to come up with a novel, more powerful, and accurate predictive approach to beat the rank becomes a challenging task. However, there may be a way, so that to combine several individual predictions into a single final one (according to ensemble learning theory). As this approach performs best when combining in nature different predictive algorithms that are calibrated with structurally different predictor variables, we tested predictors of two different kinds: 1) reflectance values (or transforms) at each wavelength and 2) absorption feature parameters. Consequently we applied four different calibration techniques, two per each type of predictors: a) partial least squares regression and support vector machines for type 1, and b) multiple linear regression and random forest fo

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

40104 - Soil science

Projekt

<a href="/cs/project/QJ1230319" target="_blank" >QJ1230319: Vodní režim půd na svažitém zemědělsky využívaném území</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

COMPUTERS & GEOSCIENCES

ISSN

0098-3004

e-ISSN

—

Svazek periodika

104

Číslo periodika v rámci svazku

N

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

9

Strana od-do

75-83

Kód UT WoS článku

000402352900008

EID výsledku v databázi Scopus

2-s2.0-85018274021