globalchange  > 气候减缓与适应
DOI: 10.1007/s00704-018-2708-x
WOS ID: WOS:000477054700037
Title:
Forecasting wildfire disease on tobacco: toward developing a high-accuracy prediction model for disease index using local climate factors and support vector regression
Author: Cai, X. H.1,2,3; Chen, T.4; Wang, R. Y.1,2,3; Fan, Y. J.1,2,3; Li, Y.1,2,3; Hu, S. N.1,2,3; Yuan, Z. M.1,2,3; Li, H. G.5; Li, X. Y.5; Zhao, S. Y.6; Zhou, Q. M.4; Zhou, W.1,2,3,7
Corresponding Author: Zhou, Q. M. ; Zhou, W.
Source Publication: THEORETICAL AND APPLIED CLIMATOLOGY
ISSN: 0177-798X
EISSN: 1434-4483
Publishing Year: 2019
Volume: 137, Issue:3-4, Pages:2139-2149
Language: 英语
WOS Keyword: DIMENSIONAL DESCRIPTOR SELECTION ; ADMET EVALUATION ; QSAR MODELS ; TOXICITY ; DESIGN
WOS Category: Meteorology & Atmospheric Sciences
WOS Research Area: Meteorology & Atmospheric Sciences
English Abstract:

Tobacco wildfire disease is common globally, and climate change may increase the risk of outbreaks. Therefore, there is an urgent need to establish an effective climate model to forecast the occurrence of wildfire disease. To design such a model, we collected data for 40 wildfire disease indices via tobacco field surveys and data for 15 climate factors of Guiyang County in China from 2012 to 2016. First, we built multiple linear regression (MLR), stepwise linear regression (SLR) and support vector regression (SVR) models using three climate features (precipitation, mean daily temperature and sunshine duration), and we could not find an effective model. Second, we built three corresponding models using expanded 15 climate features and an in-house WDEM method (the worst descriptor elimination multi-roundly), and the independent test results showed that the best SVR model had not only a higher predictive accuracy (Qext2=0.94) but also a better stability. Finally, we further evaluated the biological significance of their retained climate features and the single-factor effects of the best model according to the interpretability analysis, and our results indicated that (1) the three climate factors (minimum value of wind velocity, daily range of temperature and daily pressure) strongly affected the occurrence of wildfire disease; (2) the ranges of relative humidity and sunshine hours were negatively correlated with the occurrence of wildfire disease, while daily mean vapour pressure was positively correlated with the occurrence of the disease. Our work enables a useful theoretical prediction for wildfire disease, especially in terms of climate-related predictions.


Citation statistics:
Document Type: 期刊论文
Identifier: http://119.78.100.158/handle/2HF3EXSE/125417
Appears in Collections:气候减缓与适应

Files in This Item:

There are no files associated with this item.


Affiliation: 1.Hunan Agr Univ, Hunan Prov Engn & Technol Res Ctr Agr Big Data An, Changsha 410128, Hunan, Peoples R China
2.Hunan Agr Univ, Hunan Prov Key Lab Biol & Control Plant Dis & Ins, Changsha 410128, Hunan, Peoples R China
3.Hunan Agr Univ, Hunan Prov Engn & Technol Res Ctr Biopesticide &, Changsha 410128, Hunan, Peoples R China
4.Hunan Agr Univ, Coll Agr, Changsha 410128, Hunan, Peoples R China
5.Hunan Tobacco Co, Chenzhou Co, Chenzhou 423000, Peoples R China
6.Hunan Tobacco Co, Changsha 410004, Hunan, Peoples R China
7.Texas A&M Univ, Dept Soil & Crop Sci, College Stn, TX 77843 USA

Recommended Citation:
Cai, X. H.,Chen, T.,Wang, R. Y.,et al. Forecasting wildfire disease on tobacco: toward developing a high-accuracy prediction model for disease index using local climate factors and support vector regression[J]. THEORETICAL AND APPLIED CLIMATOLOGY,2019-01-01,137(3-4):2139-2149
Service
Recommend this item
Sava as my favorate item
Show this item's statistics
Export Endnote File
Google Scholar
Similar articles in Google Scholar
[Cai, X. H.]'s Articles
[Chen, T.]'s Articles
[Wang, R. Y.]'s Articles
百度学术
Similar articles in Baidu Scholar
[Cai, X. H.]'s Articles
[Chen, T.]'s Articles
[Wang, R. Y.]'s Articles
CSDL cross search
Similar articles in CSDL Cross Search
[Cai, X. H.]‘s Articles
[Chen, T.]‘s Articles
[Wang, R. Y.]‘s Articles
Related Copyright Policies
Null
收藏/分享
所有评论 (0)
暂无评论
 

Items in IR are protected by copyright, with all rights reserved, unless otherwise indicated.