Modelling diverse soil parameters with visible to longwave infrared spectroscopy using PLSR employed by an automatic modelling engine

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00025798%3A_____%2F17%3A00000002" target="_blank" >RIV/00025798:_____/17:00000002 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.3390/rs9020134" target="_blank" >http://dx.doi.org/10.3390/rs9020134</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/rs9020134" target="_blank" >10.3390/rs9020134</a>

Result language

angličtina

Original language name

Modelling diverse soil parameters with visible to longwave infrared spectroscopy using PLSR employed by an automatic modelling engine

Original language description

The study tested a data mining engine (PARCUDA®) to predict various soil attributes (BC, CEC, BS, pH, Corg, Pb, Hg, As, Zn and Cu) using reflectance data acquired for both optical and thermal infrared regions. The PARCUDA® was designed to utilize large data in parallel and automatic processing to build and process hundreds of diverse models in a unified manner while avoiding bias and deviations caused by the operator(s). The system is able to systematically assess the effect of diverse preprocessing techniques; additionally it analyses other parameters, such as different spectral resolutions and spectral coverages, that affect soil properties. Accordingly, the system was used to extract models across both optical and thermal infrared spectral regions, which holds significant chromophores. In total, 2880 models were evaluated where each model was generated with a different preprocessing scheme of the input spectral data. The models were assessed using statistical parameters such as R2 SEP, RPD and by physical explanation (spectral assignments). It was found that the smoothing procedure is the most beneficial preprocessing stage, especially when combined with spectral derivation (1st or 2nd derivatives). Automatically and without any operator intervention the PARACUDA® engine enabled the best prediction models to be found out of all the combinations tested. Furthermore, the PARACUDA® engine and the presented processing scheme proved to be efficient tools for getting a better understanding of the geochemical properties of the samples studied (e.g., mineral associations).

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20705 - Remote sensing

Project

<a href="/en/project/8G15004" target="_blank" >8G15004: SOIL, DEGRADATION, SPECTROSCOPY, SUPERSPECTRAL DATA, QUANTITATIVE MODELING</a><br>

Continuities

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

Publication year

2017

Confidentiality

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

Name of the periodical

Remote Sensing

ISSN

1424-8220

e-ISSN

—

Volume of the periodical

9

Issue of the periodical within the volume

2

Country of publishing house

CH - SWITZERLAND

Number of pages

22

Pages from-to

Article n. 134

UT code for WoS article

000397013700036

EID of the result in the Scopus database

2-s2.0-85013676577