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

doi:10.1016/j.catena.2021.105534

	Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur
	John, Kingsley 1; Agyeman, Prince Chapman 1; Kebonye, Ndiye Michael 1; Isong, Isong Abraham 2; Ayito, Esther O.2; Ofem, Kokei Ikpi 2; Qin, Cheng-Zhi 3
刊名	CATENA
	2021-11-01
卷号	206 页码:18
关键词	Soil nutrient distribution Digital soil mapping Machine learning Cokriging Agricultural productivity
ISSN号	0341-8162
DOI	10.1016/j.catena.2021.105534
通讯作者	John, Kingsley(johnk@af.czu.cz)
英文摘要	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's 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 (Coki, i = 1 to n) 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 (n = 115) were collected from the topsoil (0-20) 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) equipment and presented as S_ICP-OES (response variable), and predictors (Ca_ICP-OES, K_ICP-OES, Mg_ICP-OES, Na_ICP-OES, P_ICP-OES, and V_ICP-OES), respectively. For GPR and Cok-GPR, an 80% (calibration) to 20% (validation) random dataset split was performed. The calibration dataset was implemented under k = 10-fold cross-validation, repeated five times. All the models were evaluated by MAE, RMSE and R2 criteria. According to the model and map performances. Cok1 model via Ca_ICP-OES, K_ICP-OES, Mg_ICP-OES gave the best model (MAE = 1.28 mg/kg RMSE = 164.42 mg/kg, R2 = 0.85). Its corresponding GPR1 approach, modelled with the same predictors produced the best (MAE = 85.43 mg/kg, RMSE = 137.59 mg/kg, R2 = 0.83). While the hybrid Cok1-GPR model produced MAE = 76.84 mg/kg, RMSE = 102.11 mg/kg, and R2 = 0.91. The model outperformed both the Cok and GPR models, respectively. The proposed Cok-GPR model can be applied to efficiently predict soil nutrient element levels at the regional level and be useful during policymaking.
资助项目	Faculty of Agrobiology, Food and Natural Resources of the Czech University of Life Sciences Prague (CZU)[SV20-5-21130] ; European Regional Development Fund[CZ.02.1.01/0.0/0.0/16_019/0000845]
WOS关键词	MACHINE LEARNING-METHODS ; ORGANIC-MATTER ; RANDOM FOREST ; ELEMENT ; INFORMATION ; PREDICTION ; FERTILIZER ; POTASSIUM ; MAGNESIUM ; CALCIUM
WOS研究方向	Geology ; Agriculture ; Water Resources
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000688449100043
资助机构	Faculty of Agrobiology, Food and Natural Resources of the Czech University of Life Sciences Prague (CZU) ; European Regional Development Fund
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/165391]
专题	中国科学院地理科学与资源研究所
通讯作者	John, Kingsley
作者单位	1.Czech Univ Life Sci, Fac Agrobiol Food & Nat Resources, Dept Soil Sci & Soil Protect, Kamycka 129, Prague 16500, Czech Republic 2.Univ Calabar, Dept Soil Sci, Calabar, Nigeria 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	John, Kingsley,Agyeman, Prince Chapman,Kebonye, Ndiye Michael,et al. Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur[J]. CATENA,2021,206:18.
APA	John, Kingsley.,Agyeman, Prince Chapman.,Kebonye, Ndiye Michael.,Isong, Isong Abraham.,Ayito, Esther O..,...&Qin, Cheng-Zhi.(2021).Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur.CATENA,206,18.
MLA	John, Kingsley,et al."Hybridization of cokriging and gaussian process regression modelling techniques in mapping soil sulphur".CATENA 206(2021):18.