Integrated modelling for mapping spatial sources of dust in central Asia-An important dust source in the global atmospheric system

doi:10.1016/j.apr.2021.101173

IEECAS OpenIR > 古环境研究室

	Integrated modelling for mapping spatial sources of dust in central Asia-An important dust source in the global atmospheric system
	Gholami, Hamid 1; Mohammadifar, Aliakbar 1; Malakooti, Hossein 2; Esmaeilpour, Yahya 1; Golzari, Shahram 3,4; Mohammadi, Fariborz 5,6; Li, Yue 7,8,9; Song, Yougui7,8 ; Kaskaoutis, Dimitris G.10,11; Fitzsimmons, Kathryn Elizabeth 12; Collins, Adrian L.13
通讯作者	Gholami, Hamid(hgholami@hormozgan.ac.ir)
	2021-09-01
发表期刊	ATMOSPHERIC POLLUTION RESEARCH
ISSN	1309-1042
卷号	12 期号:9 页码:12
摘要	Spatial mapping of dust sources in arid and semi-arid regions is necessary to mitigate on-site and off-site impacts. In this study, we apply a novel integrated modelling approach including leave one feature out (LOFO) - as a technique for feature selection -, deep learning (DL) models (gcForest and bidirectional long short-term memory (Bi-LSTM)), game theory (GT) and a Gaussian copula-based multivariate (GCBM) model for mapping dust sources in Central Asia (CA). Eight factors (precipitation, cation exchange capacity, bulk density, wind speed, slope, silt content, lithology and coarse fragment content) were selected by LOFO as effective for controlling dust emissions, and were used in the novel modelling process. Six statistical indicators were utilized to assess the performance of the two DL models and a hybrid copula-gcForest model, while a sensitivity analysis of the models was also carried out. The hybrid copula-gcForest model was identified as the most accurate, predicting that 16%, 7.1%, 9.5% and 67.4% of the study area is grouped at low, moderate, high and very high susceptibility classes for dust emissions, respectively. Based on permutation feature importance measure (PFIM) and Shapely Additive exPlanations (SHAP), bulk density, precipitation and coarse fragment content were evaluated as the three most important factors with the highest contributions to the predictive model output. The study area suffers from intense wind erosion and the generated spatial maps of dust sources may be helpful for mitigating and controlling dust phenomena in CA.
关键词	Dust spatial mapping Effective factors Deep learning Hybrid copula-gcForest model Gaussian copula model Model sensitivity Central asia
DOI	10.1016/j.apr.2021.101173
关键词[WOS]	JAZMURIAN BASIN ; SOUTHWEST ASIA ; WESTERN CHINA ; MINERAL DUST ; CASPIAN SEA ; TIAN-SHAN ; TRANSPORT ; EROSION ; DESERT ; REGION
收录类别	SCI ; SCI
语种	英语
资助项目	Faculty of Agriculture and Natural Resources, University of Hormozgan, Iran ; Institute of Earth Environment, Chinese Academy of Sciences ; project PANhellenic infrastructure for Atmospheric Composition and climatE change, PANACEA - Operational Programme Competitiveness, Entrepreneurship and Innovation (NSRF 2014-2020)[MIS 5021516] ; UKRI-BBSRC (UK Research and Innovation-Biotechnology and Biological Sciences Research Council)[BBS/E/C/000I0330]
WOS研究方向	Environmental Sciences & Ecology
项目资助者	Faculty of Agriculture and Natural Resources, University of Hormozgan, Iran ; Institute of Earth Environment, Chinese Academy of Sciences ; project PANhellenic infrastructure for Atmospheric Composition and climatE change, PANACEA - Operational Programme Competitiveness, Entrepreneurship and Innovation (NSRF 2014-2020) ; UKRI-BBSRC (UK Research and Innovation-Biotechnology and Biological Sciences Research Council)
WOS类目	Environmental Sciences
WOS记录号	WOS:000697680600003
出版者	TURKISH NATL COMMITTEE AIR POLLUTION RES & CONTROL-TUNCAP
引用统计	被引频次：31[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ieecas.cn/handle/361006/17029
专题	古环境研究室第四纪科学与全球变化卓越创新中心
通讯作者	Gholami, Hamid
作者单位	1.Univ Hormozgan, Dept Nat Resources Engn, Bandar Abbas, Hormozgan, Iran 2.Univ Hormozgan, Fac Marine Sci & Technol, Bandar Abbas, Hormozgan, Iran 3.Univ Hormozgan, Dept Elect & Comp Engn, Bandar Abbas, Hormozgan, Iran 4.Univ Hormozgan, Deep Learning Res Grp, Bandar Abbas, Hormozgan, Iran 5.Univ Hormozgan, Minab Higher Educ Ctr, Dept Agr, Bandar Abbas, Iran 6.Univ Hormozgan, Hormoz Res Ctr, Hormozgan, Iran 7.Chinese Acad Sci, Inst Earth Environm, State Key Lab Loess & Quaternary Geol, Xian 710061, Peoples R China 8.CAS Ctr Excellence Quaternary Sci & Global Change, Xian 710061, Peoples R China 9.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 10.Natl Observ Athens, Inst Environm Res & Sustainable Dev, Athens 15784, Greece 11.Univ Crete, Dept Chem, Environm Chem Proc Lab, Iraklion 71003, Greece 12.Max Planck Inst Evolutionary Anthropol, Dept Human Evolut, Deutsch Pl 6, D-04103 Leipzig, Germany 13.Rothamsted Res, Sustainable Agr Sci Dept, Okehampton EX20 2SB, Devon, England
推荐引用方式 GB/T 7714	Gholami, Hamid,Mohammadifar, Aliakbar,Malakooti, Hossein,et al. Integrated modelling for mapping spatial sources of dust in central Asia-An important dust source in the global atmospheric system[J]. ATMOSPHERIC POLLUTION RESEARCH,2021,12(9):12.
APA	Gholami, Hamid.,Mohammadifar, Aliakbar.,Malakooti, Hossein.,Esmaeilpour, Yahya.,Golzari, Shahram.,...&Collins, Adrian L..(2021).Integrated modelling for mapping spatial sources of dust in central Asia-An important dust source in the global atmospheric system.ATMOSPHERIC POLLUTION RESEARCH,12(9),12.
MLA	Gholami, Hamid,et al."Integrated modelling for mapping spatial sources of dust in central Asia-An important dust source in the global atmospheric system".ATMOSPHERIC POLLUTION RESEARCH 12.9(2021):12.