干旱区生态环境知识资源中心(Arid): Ground Observations and Environmental Covariates Integration for Mapping of Soil Salinity: A Machine Learning-Based Approach

Arid

DOI	10.3390/rs13234825
	Ground Observations and Environmental Covariates Integration for Mapping of Soil Salinity: A Machine Learning-Based Approach
	Naimi, Salman; Ayoubi, Shamsollah; Zeraatpisheh, Mojtaba; Dematte, Jose Alexandre Melo
通讯作者	Zeraatpisheh, M (corresponding author), Henan Univ, Henan Key Lab Earth Syst Observat & Modeling, Kaifeng 475004, Peoples R China. ; Zeraatpisheh, M (corresponding author), Henan Univ, Coll Geog & Environm Sci, Kaifeng 475004, Peoples R China.
来源期刊	REMOTE SENSING
EISSN	2072-4292
出版年	2021
卷号	13 期号:23
英文摘要	Soil salinization is a severe danger to agricultural activity in arid and semi-arid areas, reducing crop production and contributing to land destruction. This investigation aimed to utilize machine learning algorithms to predict spatial soil salinity (dS m(-1)) by combining environmental covariates derived from remotely sensed (RS) data, a digital elevation model (DEM), and proximal sensing (PS). The study is located in an arid region, southern Iran (52 degrees 51 '-53 degrees 02 ' E; 28 degrees 16 '-28 degrees 29 ' N), in which we collected 300 surface soil samples and acquired the spectral data with RS (Sentinel-2) and PS (electromagnetic induction instrument (EMI) and portable X-ray fluorescence (pXRF)). Afterward, we analyzed the data using five machine learning methods as follows: random forest-RF, k-nearest neighbors-kNN, support vector machines-SVM, partial least squares regression-PLSR, artificial neural networks-ANN, and the ensemble of individual models. To estimate the electrical conductivity of the saturated paste extract (ECe), we built three scenarios, including Scenario (1): Synthetic Soil Image (SySI) bands and salinity indices derived from it; Scenario (2): RS data, PS data, topographic attributes, and geology and geomorphology maps; and Scenario (3): the combination of Scenarios (1) and (2). The best prediction accuracy was obtained for the RF model in Scenario (3) (R-2 = 0.48 and RMSE = 2.49), followed by Scenario (2) (RF model, R-2 = 0.47 and RMSE = 2.50) and Scenario (1) for the SVM model (R-2 = 0.26 and RMSE = 2.97). According to ensemble modeling, a combined strategy with the five models exceeded the performance of all the single ones and predicted soil salinity in all scenarios. The results revealed that the ensemble modeling method had higher reliability and more accurate predictive soil salinity than the individual approach. Relative improvement (RI%) showed that the R-2 index in the ensemble model improved compared to the most precise prediction for the Scenarios (1), (2), and (3) with 120.95%, 56.82%, and 66.71%, respectively. We applied the best model in each scenario for mapping the soil salinity in the selected area, which indicated that ECe tended to increase from the northwestern to south and southeastern regions. The area with high ECe was located in the regions that mainly had low elevations and playa. The areas with low ECe were located in the higher elevations with steeper slopes and alluvial fans, and thus, relief had great importance. This study provides a precise, cost-effective, and scientific base prediction for decision-making purposes to map soil salinity in arid regions.
英文关键词	soil salinization machine learning remote and proximal sensing Sentinel-2 MSI SySI soil health
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000735069300001
WOS关键词	SPATIAL-DISTRIBUTION ; SENTINEL-2 MSI ; RANDOM FOREST ; WET SEASONS ; REGRESSION ; PREDICTION ; REGION ; CLASSIFICATION ; REFLECTANCE ; PLAIN
WOS类目	Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/373927
作者单位	[Naimi, Salman; Ayoubi, Shamsollah] Isfahan Univ Technol, Coll Agr, Dept Soil Sci, Esfahan 84115683111, Iran; [Zeraatpisheh, Mojtaba] Henan Univ, Henan Key Lab Earth Syst Observat & Modeling, Kaifeng 475004, Peoples R China; [Zeraatpisheh, Mojtaba] Henan Univ, Coll Geog & Environm Sci, Kaifeng 475004, Peoples R China; [Dematte, Jose Alexandre Melo] Luiz de Queiroz Coll Agr, Dept Soil Sci, BR-13418900 Piracicaba, SP, Brazil
推荐引用方式 GB/T 7714	Naimi, Salman,Ayoubi, Shamsollah,Zeraatpisheh, Mojtaba,et al. Ground Observations and Environmental Covariates Integration for Mapping of Soil Salinity: A Machine Learning-Based Approach[J],2021,13(23).
APA	Naimi, Salman,Ayoubi, Shamsollah,Zeraatpisheh, Mojtaba,&Dematte, Jose Alexandre Melo.(2021).Ground Observations and Environmental Covariates Integration for Mapping of Soil Salinity: A Machine Learning-Based Approach.REMOTE SENSING,13(23).
MLA	Naimi, Salman,et al."Ground Observations and Environmental Covariates Integration for Mapping of Soil Salinity: A Machine Learning-Based Approach".REMOTE SENSING 13.23(2021).