Digital soil mapping using machine learning-based methods to predict soil organic carbon in two different districts in the Czech Republic

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60460709%3A41210%2F24%3A100048" target="_blank" >RIV/60460709:41210/24:100048 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.17221/119/2023-SWR" target="_blank" >https://doi.org/10.17221/119/2023-SWR</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.17221/119/2023-SWR" target="_blank" >10.17221/119/2023-SWR</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Digital soil mapping using machine learning-based methods to predict soil organic carbon in two different districts in the Czech Republic

Popis výsledku v původním jazyce

Soil organic carbon (SOC) is an important soil characteristic as well as a way how to mitigate climate change. Information on its content and spatial distribution is thus crucial. Digital soil mapping (DSM) is a suitable way to evaluate spatial distribution of soil properties thanks to its ability to obtain accurate information about soil. This research aims to apply machine learning algorithms using various environmental covariates to generate digital SOC maps for mineral top-soils in the Liberec and Domažlice districts, located in the Czech Republic. The soil class, land cover, and geology maps as well as terrain covariates extracted from the digital elevation model and remote sensing data were used as covariates in modelling. The spatial distribution of SOC was predicted based on its relationships with covariates using random forest (RF), cubist, and quantile random forest (QRF) models. Results of the RF model showed that land cover (vegetation) and elevation were the most important environmental variables in the SOC prediction in both districts. The RF had better efficiency and accuracy than the cubist and QRF to predict SOC in both districts. The greatest R2 value (0.63) was observed in the Domažlice district using the RF model. However, cubist and QRF showed appropriate performance in both districts, too.

Název v anglickém jazyce

Digital soil mapping using machine learning-based methods to predict soil organic carbon in two different districts in the Czech Republic

Popis výsledku anglicky

Soil organic carbon (SOC) is an important soil characteristic as well as a way how to mitigate climate change. Information on its content and spatial distribution is thus crucial. Digital soil mapping (DSM) is a suitable way to evaluate spatial distribution of soil properties thanks to its ability to obtain accurate information about soil. This research aims to apply machine learning algorithms using various environmental covariates to generate digital SOC maps for mineral top-soils in the Liberec and Domažlice districts, located in the Czech Republic. The soil class, land cover, and geology maps as well as terrain covariates extracted from the digital elevation model and remote sensing data were used as covariates in modelling. The spatial distribution of SOC was predicted based on its relationships with covariates using random forest (RF), cubist, and quantile random forest (QRF) models. Results of the RF model showed that land cover (vegetation) and elevation were the most important environmental variables in the SOC prediction in both districts. The RF had better efficiency and accuracy than the cubist and QRF to predict SOC in both districts. The greatest R2 value (0.63) was observed in the Domažlice district using the RF model. However, cubist and QRF showed appropriate performance in both districts, too.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

40104 - Soil science

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název periodika

Soil and Water Research

ISSN

1801-5395

e-ISSN

1801-5395

Svazek periodika

19

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

18

Strana od-do

32-49

Kód UT WoS článku

001148213900001

EID výsledku v databázi Scopus

2-s2.0-85185780012