干旱区生态环境知识资源中心(Arid): Spatial prediction of soil organic carbon stocks in an arid rangeland using machine learning algorithms

Arid

DOI	10.1007/s10661-021-09543-8
	Spatial prediction of soil organic carbon stocks in an arid rangeland using machine learning algorithms
	Rostaminia, Mahmood; Rahmani, Asghar; Mousavi, Sayed Roholla; Taghizadeh-Mehrjardi, Rohullah; Maghsodi, Ziba
通讯作者	Rostaminia, M (corresponding author), Ilam Univ, Agr Fac, Soil & Water Dept, Ilam, Iran.
来源期刊	ENVIRONMENTAL MONITORING AND ASSESSMENT
ISSN	0167-6369
EISSN	1573-2959
出版年	2021
卷号	193 期号:12
英文摘要	Assessing the role of machine learning (ML) models concerning environmental predictors on spatial variation of soil organic carbon stocks (SOCS) in arid rangelands is very necessary. This study was conducted to explore the variability of surface SOCS in rangeland in the west of Iran using ML approaches. A number of 33 environmental predictors derived from Sentinel-2B and DEM were used. The optimal soil sampling (n = 80) position was determined by Latin hypercube sampling (cLHS) method. Robust and popular random Forest (RF), cubist (CB) along with random forest-ordinary kriging (RF-OK), and cubist-ordinary kriging (CB-OK) hybrid ML models were applied to the prediction of SOCS. Ten-fold CV was implemented for modeling performance and uncertainty map. According to data analysis, the maximum, minimum, and average values of SOCS are 44.50, 10.50, and 20.50 (ton. ha(-1)) at the surface depth (0-30 cm), respectively. In general, normalized and standardized height covariates had a higher effect related to other predictors. On the other hand, two remote sensing (RS) indices, including salinity ratio (salinity) and GNDVI index, had a better impact on SOCS variability. The external validation of model performance indicated that RF-OK with (R-2 = 0.75, RMSE = 6.33 ton. ha(-1)) with the high and low uncertainty range (3.33-9.50 ton. ha(-1)) was the outperformed ML model in compare with other models as RF (R-2 = 0.65, RMSE = 7.38 ton. ha(-1)), CB-OK (R-2 = 0.56, RMSE = 9.22 ton. ha(-1)), and CB (R-2 = 0.33, RMSE = 10.42 ton. ha(-1)). In general, the hybrid models improved the accuracy of RF and CB with increased 0.11 until 0.23 of R-2, and 1.05 to 1.2 (ton. ha(-1)) decreased RMSE of model's prediction. Hence, we conclude that the topographic attributes (especially normalized and standardized height) were the most critical factors in controlling surface SOCS in arid rangelands when combining with robust RF ML model, and optimized soil sampling methods like RF-cLHS can prepare acceptable soil properties maps.
英文关键词	Arid rangelands Sentinel-2B indices Soil organic carbon Uncertainty Hybrid models Limited data
类型	Article
语种	英语
开放获取类型	Bronze
收录类别	SCI-E
WOS记录号	WOS:000719914200004
WOS关键词	DEM DERIVATIVES ; RESOLUTION MAP ; NEURAL-NETWORK ; TOTAL NITROGEN ; RANDOM FOREST ; LAND-COVER ; REGRESSION ; MATTER ; SELECTION ; VARIABILITY
WOS类目	Environmental Sciences
WOS研究方向	Environmental Sciences & Ecology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/374096
作者单位	[Rostaminia, Mahmood] Ilam Univ, Agr Fac, Soil & Water Dept, Ilam, Iran; [Rahmani, Asghar; Mousavi, Sayed Roholla] Univ Tehran, Coll Agr & Nat Resources, Fac Agr Engn & Technol, Soil Sci & Engn Dept, Karaj, Iran; [Taghizadeh-Mehrjardi, Rohullah] Ardakan Univ, Fac Agr & Nat Resources, Ardakan, Iran; [Taghizadeh-Mehrjardi, Rohullah] Eberhard Karls Univ Tubingen, Inst Geog, Soil Sci & Geomorphol, D-72070 Tubingen, Germany; [Maghsodi, Ziba] Lorestan Univ, Coll Agr & Nat Resources, Soil Resources Management, Khorramabad, Iran
推荐引用方式 GB/T 7714	Rostaminia, Mahmood,Rahmani, Asghar,Mousavi, Sayed Roholla,et al. Spatial prediction of soil organic carbon stocks in an arid rangeland using machine learning algorithms[J],2021,193(12).
APA	Rostaminia, Mahmood,Rahmani, Asghar,Mousavi, Sayed Roholla,Taghizadeh-Mehrjardi, Rohullah,&Maghsodi, Ziba.(2021).Spatial prediction of soil organic carbon stocks in an arid rangeland using machine learning algorithms.ENVIRONMENTAL MONITORING AND ASSESSMENT,193(12).
MLA	Rostaminia, Mahmood,et al."Spatial prediction of soil organic carbon stocks in an arid rangeland using machine learning algorithms".ENVIRONMENTAL MONITORING AND ASSESSMENT 193.12(2021).