Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur

Kód výsledku v IS VaVaI

RIV/60460709:41210/21:85813 - isvavai.cz

Výsledek na webu

https://www.sciencedirect.com/science/article/pii/S0341816221003921?via%3Dihub

DOI - Digital Object Identifier

10.1016/j.catena.2021.105534

Jazyk výsledku

angličtina

Název v původním jazyce

Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur

Popis výsledku v původním jazyce

As a widely used soil mapping method, the kriging method involves a high sampling point to generate quality and accurate maps. Combining kriging and machine learning (ML) can produce soil maps with fewer number sampling points. This study objective was to implement a hybrid approach based on the Cokriging (Cok) and an ML technique, i.e., Gaussian process regression (GPR). The hybrid method called the Cok-GPR method uses the Cok as a predictor method of the soil sulphur and then uses GPR to improve the prediction accuracy. The proposed method was compared with the Cok and the GPR models, respectively, in a case study. Soil samples (115) were collected from the topsoil at the agricultural site of approximately 889,8 km2 size. S, Ca, K, Mg, Na, P, and V were estimated via Inductively Coupled Plasma Optical Emission Spectroscopy (ICP-OES). All the models were evaluated by MAE, RMSE and R2 criteria. The proposed Cok-GPR model can be applied to efficiently predict soil nutrient element levels at the region

Název v anglickém jazyce

Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur

Popis výsledku anglicky

As a widely used soil mapping method, the kriging method involves a high sampling point to generate quality and accurate maps. Combining kriging and machine learning (ML) can produce soil maps with fewer number sampling points. This study objective was to implement a hybrid approach based on the Cokriging (Cok) and an ML technique, i.e., Gaussian process regression (GPR). The hybrid method called the Cok-GPR method uses the Cok as a predictor method of the soil sulphur and then uses GPR to improve the prediction accuracy. The proposed method was compared with the Cok and the GPR models, respectively, in a case study. Soil samples (115) were collected from the topsoil at the agricultural site of approximately 889,8 km2 size. S, Ca, K, Mg, Na, P, and V were estimated via Inductively Coupled Plasma Optical Emission Spectroscopy (ICP-OES). All the models were evaluated by MAE, RMSE and R2 criteria. The proposed Cok-GPR model can be applied to efficiently predict soil nutrient element levels at the region

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

40104 - Soil science

Projekt

EF16_019/0000845: Centrum pro studium vzniku a transformací nutričně významných látek v potravním řetězci v interakci s potenciálně rizikovými látkami antropogenního původu: komplexní posouzení rizika kontaminace půdy pro kvalitu zemědělské produkce

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název periodika

Catena

ISSN

0341-8162

e-ISSN

1872-6887

Svazek periodika

206

Číslo periodika v rámci svazku

nov

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

18

Strana od-do

0-0

Kód UT WoS článku

000688449100043

EID výsledku v databázi Scopus

2-s2.0-85109415740