Predicting soil organic carbon stocks in different layers of
forest soils in the Czech Republic

J 2023

Predicting soil organic carbon stocks in different layers of forest soils in the Czech Republic

SARKODIE, Vincent Yaw Oppong; Radim VASAT; Nastaran POULADI; Vit SRAMEK; Milan SÁŇKA et al.

Základní údaje

Originální název

Predicting soil organic carbon stocks in different layers of forest soils in the Czech Republic

Autoři

SARKODIE, Vincent Yaw Oppong; Radim VASAT; Nastaran POULADI; Vit SRAMEK; Milan SÁŇKA; Vera FADRHONSOVA; Katerina Neudertova HELLEBRANDOVA a Lubos BORUVKA

Vydání

Geoderma Regional, AMSTERDAM, Elsevier B.V. 2023, 2352-0094

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

40104 Soil science

Stát vydavatele

Nizozemské království

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 3.100

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14310/23:00131498

Organizační jednotka

Přírodovědecká fakulta

Klíčová slova anglicky

Cambisol; Climate change; Cubist; Digital soil mapping; Forest soils; Machine learning; Random forests

Štítky

143180, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 25. 8. 2023 11:14, Mgr. Michaela Hylsová, Ph.D.

Anotace

V originále

Carbon dioxide, the most produced anthropogenic greenhouse gas, could be moderated by sequestering carbon in forest soils. Forest soils store more carbon than there is in the atmosphere. Thus, the smallest variation in soil carbon levels could trigger a significant change in atmospheric carbon. This study focused on predicting the spatial distribution of carbon stocks within surface organic and mineral topsoil and subsoil layers of the forty-one natural forest areas of the Czech Republic. Cubist and Random Forests machine learning algorithms were employed with a grid search hyper tuning to improve prediction accuracy. We used the five-fold cross-validation to verify the model accuracy using Root Mean Square Error (RMSE), coefficient of determination (R2), and Mean Absolute Error (MAE). Random Forests yielded lower RMSE of 1.10 kg/m2, 3.85 kg/m2, and 4.77 kg/m2 in the surface organic horizon (F + H layer), mineral topsoil (0-30 cm layers) and subsoil horizons (30-80 cm layers), respectively, compared to the RMSE values of Cubist, which were 1.14 kg/m2, 3.90 kg/m2, and 4.91 kg/m2 in the surface organic, mineral topsoil and subsoil horizons, respectively. R2 values of both models were low for all three horizons considered. Random Forests were the preferred algorithm for SOC stock prediction in all layers of the forest soils. Cubist predicted the spatial distribution of SOC stocks with more covariates than Random Forests. Altitude was the most important covariate for the spatial distribution of SOC stocks for both Random Forests and Cubist in all soil horizons considered. High SOC stocks for all soil horizons are spatially concentrated in soil horizons along the country borders in the mountaineous natural forest areas.

Citovat

SARKODIE, Vincent Yaw Oppong; Radim VASAT; Nastaran POULADI; Vit SRAMEK; Milan SÁŇKA; Vera FADRHONSOVA; Katerina Neudertova HELLEBRANDOVA a Lubos BORUVKA. Predicting soil organic carbon stocks in different layers of forest soils in the Czech Republic. Geoderma Regional. AMSTERDAM: Elsevier B.V., 2023, roč. 34, September 2023, s. 1-9. ISSN 2352-0094. Dostupné z: https://doi.org/10.1016/j.geodrs.2023.e00658.

@article{2304037,
   author = {Sarkodie, Vincent Yaw Oppong and Vasat, Radim and Pouladi, Nastaran and Sramek, Vit and Sáňka, Milan and Fadrhonsova, Vera and Hellebrandova, Katerina Neudertova and Boruvka, Lubos},
   article_location = {AMSTERDAM},
   article_number = {September 2023},
   doi = {https://doi.org/10.1016/j.geodrs.2023.e00658},
   keywords = {Cambisol; Climate change; Cubist; Digital soil mapping; Forest soils; Machine learning; Random forests},
   language = {eng},
   issn = {2352-0094},
   journal = {Geoderma Regional},
   title = {Predicting soil organic carbon stocks in different layers of forest soils in the Czech Republic},
   url = {https://www.sciencedirect.com/science/article/pii/S2352009423000548?via%3Dihub},
   volume = {34},
   year = {2023}
}

TY  - JOUR
ID  - 2304037
AU  - Sarkodie, Vincent Yaw Oppong - Vasat, Radim - Pouladi, Nastaran - Sramek, Vit - Sáňka, Milan - Fadrhonsova, Vera - Hellebrandova, Katerina Neudertova - Boruvka, Lubos
PY  - 2023
TI  - Predicting soil organic carbon stocks in different layers of forest soils in the Czech Republic
JF  - Geoderma Regional
VL  - 34
IS  - September 2023
SP  - 1-9
EP  - 1-9
PB  - Elsevier B.V.
SN  - 23520094
KW  - Cambisol
KW  - Climate change
KW  - Cubist
KW  - Digital soil mapping
KW  - Forest soils
KW  - Machine learning
KW  - Random forests
UR  - https://www.sciencedirect.com/science/article/pii/S2352009423000548?via%3Dihub
N2  - Carbon dioxide, the most produced anthropogenic greenhouse gas, could be moderated by sequestering carbon in forest soils. Forest soils store more carbon than there is in the atmosphere. Thus, the smallest variation in soil carbon levels could trigger a significant change in atmospheric carbon. This study focused on predicting the spatial distribution of carbon stocks within surface organic and mineral topsoil and subsoil layers of the forty-one natural forest areas of the Czech Republic. Cubist and Random Forests machine learning algorithms were employed with a grid search hyper tuning to improve prediction accuracy. We used the five-fold cross-validation to verify the model accuracy using Root Mean Square Error (RMSE), coefficient of determination (R2), and Mean Absolute Error (MAE). Random Forests yielded lower RMSE of 1.10 kg/m2, 3.85 kg/m2, and 4.77 kg/m2 in the surface organic horizon (F + H layer), mineral topsoil (0-30 cm layers) and subsoil horizons (30-80 cm layers), respectively, compared to the RMSE values of Cubist, which were 1.14 kg/m2, 3.90 kg/m2, and 4.91 kg/m2 in the surface organic, mineral topsoil and subsoil horizons, respectively. R2 values of both models were low for all three horizons considered. Random Forests were the preferred algorithm for SOC stock prediction in all layers of the forest soils. Cubist predicted the spatial distribution of SOC stocks with more covariates than Random Forests. Altitude was the most important covariate for the spatial distribution of SOC stocks for both Random Forests and Cubist in all soil horizons considered. High SOC stocks for all soil horizons are spatially concentrated in soil horizons along the country borders in the mountaineous natural forest areas.
ER  -

SARKODIE, Vincent Yaw Oppong; Radim VASAT; Nastaran POULADI; Vit SRAMEK; Milan SÁŇKA; Vera FADRHONSOVA; Katerina Neudertova HELLEBRANDOVA a Lubos BORUVKA. Predicting soil organic carbon stocks in different layers of forest soils in the Czech Republic. \textit{Geoderma Regional}. AMSTERDAM: Elsevier B.V., 2023, roč.~34, September 2023, s.~1-9. ISSN~2352-0094. Dostupné z: https://doi.org/10.1016/j.geodrs.2023.e00658.

Přehled o publikaci