干旱区生态环境知识资源中心(Arid): Dynamic Forecast of Desert Locust Presence Using Machine Learning with a Multivariate Time Lag Sliding Window Technique

Arid

DOI	10.3390/rs14030747
	Dynamic Forecast of Desert Locust Presence Using Machine Learning with a Multivariate Time Lag Sliding Window Technique
	Sun, Ruiqi; Huang, Wenjiang; Dong, Yingying; Zhao, Longlong; Zhang, Biyao; Ma, Huiqin; Geng, Yun; Ruan, Chao; Xing, Naichen; Chen, Xidong; Li, Xueling
通讯作者	Dong, YY (corresponding author)，Chinese Acad Sci, Aerosp Informat Res Inst, State Key Lab Remote Sensing Sci, Beijing 100094, Peoples R China. ; Dong, YY (corresponding author)，Univ Chinese Acad Sci, Beijing 100049, Peoples R China.
来源期刊	REMOTE SENSING
EISSN	2072-4292
出版年	2022
卷号	14 期号:3
英文摘要	Desert locust plagues can easily cause a regional food crisis and thus affect social stability. Preventive control of the disaster highlights the early detection of hopper gregarization before they form devastating swarms. However, the response of hopper band emergence to environmental fluctuation exhibits a time lag. To realize the dynamic forecast of band occurrence with optimal temporal predictors, we proposed an SVM-based model with a temporal sliding window technique by coupling multisource time-series imagery with historical locust ground survey observations from between 2000-2020. The sliding window method was based on a lagging variable importance ranking used to analyze the temporal organization of environmental indicators in band-forming sequences and eventually facilitate the early prediction of band emergence. Statistical results show that hopper bands are more likely to occur within 41-64 days after increased rainfall; soil moisture dynamics increasing by approximately 0.05 m(3)/m(3) then decreasing may enhance the chance of observing bands after 73-80 days. While sparse vegetation areas with NDVI increasing from 0.18 to 0.25 tend to witness bands after 17-40 days. The forecast model combining the optimal time lags of these dynamic indicators with other static indicators allows for a 16-day extended outlook of band presence in Somalia, Ethiopia, and Kenya. Monthly predictions from February to December 2020 display an overall accuracy of 77.46%, with an average ROC-AUC of 0.767 and a mean F-score close to 0.772. The multivariate forecast framework based on the lagging effect can realize the early warning of band presence in different spatiotemporal scenarios, supporting early decisions and response strategies for desert locust preventive management.
英文关键词	desert locust environmental indicator dynamic forecast machine learning time lag
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:000755369100001
WOS关键词	SCHISTOCERCA-GREGARIA ORTHOPTERA ; ECOLOGICAL CONDITIONS ; POPULATION-DYNAMICS ; EARTH OBSERVATION ; HABITAT ; VEGETATION ; MODEL ; PLAGUE ; INFORMATION ; FRAMEWORK
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/2XILL650/376416
作者单位	[Sun, Ruiqi; Huang, Wenjiang; Dong, Yingying; Zhang, Biyao; Ma, Huiqin; Geng, Yun; Ruan, Chao; Li, Xueling] Chinese Acad Sci, Aerosp Informat Res Inst, State Key Lab Remote Sensing Sci, Beijing 100094, Peoples R China; [Sun, Ruiqi; Huang, Wenjiang; Dong, Yingying; Geng, Yun; Ruan, Chao] Univ Chinese Acad Sci, Beijing 100049, Peoples R China; [Zhao, Longlong] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China; [Xing, Naichen] China Aero Geophys Survey & Remote Sensing Ctr Na, Beijing 100083, Peoples R China; [Chen, Xidong] North China Univ Water Resources & Elect Power, Zhengzhou 450046, Peoples R China
推荐引用方式 GB/T 7714	Sun, Ruiqi,Huang, Wenjiang,Dong, Yingying,et al. Dynamic Forecast of Desert Locust Presence Using Machine Learning with a Multivariate Time Lag Sliding Window Technique[J],2022,14(3).
APA	Sun, Ruiqi.,Huang, Wenjiang.,Dong, Yingying.,Zhao, Longlong.,Zhang, Biyao.,...&Li, Xueling.(2022).Dynamic Forecast of Desert Locust Presence Using Machine Learning with a Multivariate Time Lag Sliding Window Technique.REMOTE SENSING,14(3).
MLA	Sun, Ruiqi,et al."Dynamic Forecast of Desert Locust Presence Using Machine Learning with a Multivariate Time Lag Sliding Window Technique".REMOTE SENSING 14.3(2022).