寒地水稻抗旱相关性状主成分分析及综合评价

张巩亮; 李逸; 魏媛媛; 赵海成; 陈可馨; 黄纪情; 刘梦红; 李红宇

doi:10.19303/j.issn.1008-0384.2020.08.001

寒地水稻抗旱相关性状主成分分析及综合评价

doi: 10.19303/j.issn.1008-0384.2020.08.001

张巩亮^1,,
李逸¹,
魏媛媛¹,
赵海成¹,
陈可馨¹,
黄纪情¹,
刘梦红¹,
李红宇^{1, 2, ,}

1.
黑龙江八一农垦大学农学院，黑龙江大庆　163319
2.
黑龙江省现代农业栽培技术与作物种质改良重点实验室，黑龙江大庆　163319

基金项目: 国家重点研发计划项目（2017YFD0100506）；黑龙江农垦总局试验示范项目（HNK135-02-02）；黑龙江八一农垦大学科研团队平台支持计划项目（TDJH201802）

详细信息

作者简介:
张巩亮（1998−），男，硕士研究生，研究方向：水稻高产优质栽培（E-mail：2398337728@qq.com）

通讯作者:
李红宇（1979−），男，博士，副教授，主要从事水稻高产优质生理生态及遗传多样性研究（E-mail：ndrice@163.com）

中图分类号: S 511
计量
- 文章访问数: 1216
- HTML全文浏览量: 439
- PDF下载量: 56
- 被引次数: 0
出版历程
- 收稿日期: 2020-05-02
- 修回日期: 2020-08-06
- 刊出日期: 2020-08-19

Principal Component Analysis and Comprehensive Evaluation on Drought Resistance-related Traits of Rice for Cultivation in Cold Regions

1.
Agricultural College, Heilongjiang Bayi Agricultural University, Daqing, Heilongjiang　163319, China
2.
Heilongjiang Provincial Key Laboratory of Modern Agricultural Cultivation and Crop Germplasm Improvement, Daqing, Heilongjiang　163319, China

摘要

摘要: 目的建立寒地水稻移栽至成熟期抗旱综合评价指标体系，筛选抗旱水稻种质资源。方法以穗重、穗粒数、结实率等13个性状为指标，采用主成分分析法及聚类分析等方法对30个寒地水稻种质资源（样本）进行抗旱性综合评价。用25个样本以抗旱力特征指标值为输入，对应抗旱综合评价值为输出，利用误差反向传播（Error Back Propagation，BP）神经网络算法构建学习模型；其余5个样本为验证样本，评价学习模型的预测准确性。变换3组学习样本构建3个学习模型，对比3个模型的预测准确性，验证建模方法的合理性与稳定性。结果利用主成分分析将干旱胁迫下13个单项指标转化为5个相互独立的综合指标，累积贡献率达83.761%。依据参试材料抗旱综合评价值进行聚类分析，将30个参试样本划分为强抗旱型、抗旱型、中间抗旱型、旱敏感型4类。第1类强抗旱型的有1个（农丰3055），第2类抗旱型的有12个，第3类中间抗旱型的有6个，第4类旱敏感型的有11个。基于水稻性状指标与抗旱综合评价值相关性分析结果，筛选出穗重、穗粒数、结实率、产量、生物产量和经济系数6项指标作为水稻抗旱适宜性评价的特征指标。以特征指标值为输入层，综合评价值为输出层，建立BP神经网络学习模型，可实现水稻抗旱指标适宜性的定量预测。该方法建立的学习模型有较高的预测准确性与稳定性，变换学习样本得到的3个学习模型的预测值与实际值相对误差均不超过10%，实际值与模型预测值线性拟合后决定系数R²均大于0.9。结论构建的BP神经网络学习模型，可以实现水稻抗旱指标适宜性的定量预测，且具有较高的预测准确性与稳定性，可比单一的回归分析更准确地预测水稻抗旱适宜性评价的特征指标；穗重、穗粒数、结实率、产量、生物产量和经济系数可作为水稻农业抗旱能力鉴定的综合指标；参试的30个寒地水稻样本中，农丰3055为强抗旱种质资源。
- 寒地水稻 /
- 抗旱性 /
- 主成分分析 /
- 聚类分析 /
- BP神经网络
Abstract: Objective A comprehensive indexing system to evaluate drought resistance of rice to be transplanted to maturity in cold regions was established and tested for screening suitable germplasms for the farming. Method Including panicle weight, grains per panicle, seed setting rate, and others, 13 traits were selected as indicators for the principal component and cluster analyses to study the drought resistance of 30 cold-region rice germplasms. Using the indicators from 25 of the specimens as input and the corresponding evaluation criteria as output, a learning model was formulated by the backward propagation (BP) of errors neural network algorithm. The remaining 5 germplasm specimens were reserved for validating the model on prediction accuracy. Subsequently, 3 transformed learning models were generated to compare their predictabilities and verify their suitability and stability for the application. Result The principal component analysis organized the 13 drought resistance indicators into 5 comprehensive indices with a cumulative contribution rate of 83.761%. Based on the results of the evaluation criteria on the 30 specimens, a cluster analysis divided the germplasms into the strongly drought resistant (SDR), drought resistant (DR), intermediately drought resistant (IDR), and drought sensitive (DS) types. Accordingly, Nongfeng 3055 was classified to be the SDR type, 12 germplasms the DR type, 6 germplasms the IDR type, and 11 germplasms DS. The correlation analysis indicated 6 indices, including panicle weight, grains per panicle, seed setting rate, grain yield, biomass, and economic coefficient, closely associated with the drought resistance indicators for the suitability evaluation on rice. Thus, taking these indicators for input and the evaluation criteria for output, BP neural network models were established for the quantitative prediction. The 3 transformed models exhibited high prediction accuracy and stability, along with a relative error between the predicted and actual values below 10%. Furthermore, the linearity coefficients, R², of the models were all greater than 0.9. Conclusion The BP neural network models could satisfactorily render quantitative prediction with high accuracy and stability on drought resistance of rice for cultivation on locations. Using weight, grains per panicle, seed setting rate, grain yield, biomass, and economic coefficient as the resistance indicators, the models performed superior to the single regression analysis. They determined, among the 30 rice varieties investigated, Nongfeng 3055 to be a highly drought-resistant germplasm most suitable for cultivation in regions of cold climate.
- rice for cold-region cultivation /
- drought tolerance /
- principal component analysis /
- cluster analysis /
- BP neural network

HTML全文

图 1 30个参试材料抗旱能力的系统聚类分析

Figure 1. System clustering on draught resistance of 30 specimens

下载: 全尺寸图片幻灯片

图 2 BP神经网络结构

Figure 2. Makeup of BP neural network

下载: 全尺寸图片幻灯片

图 3 水稻抗旱指标适宜性模型稳定性验证

Figure 3. Verified stability of model on evaluating drought resistance indicators of rice suitable for cultivation

下载: 全尺寸图片幻灯片

表 1 参试材料名称及来源

Table 1. Names and origins of specimens

代号 Code	名称 Name	代号 Code	名称 Name
H01	农丰8号 Nongfeng 8hao	H16	农丰3027 Nongfeng3027
H02	农丰1704 Nongfeng1704	H17	农丰3035 Nongfeng3035
H03	农丰1705 Nongfeng1705	H18	农丰3056 Nongfeng3056
H04	农丰3085 Nongfeng3085	H19	农丰3062 Nongfeng3062
H05	农丰3068 Nongfeng3068	H20	农丰3081 Nongfeng3081
H06	农丰3055 Nongfeng3055	H21	农丰3084 Nongfeng3084
H07	稻坚强 Dao Jiangqiang	H22	农丰3156 Nongfeng3156
H08	DPB120	H23	农丰3161 Nongfeng3161
H09	DPB70	H24	农丰3162 Nongfeng3162
H10	DPB15	H25	农丰3163 Nongfeng3163
H11	绥粳21 Suijing 21	H26	农丰3169 Nongfeng3169
H12	农丰3007 Nongfeng3007	H27	农丰3186 Nongfeng3186
H13	农丰3021 Nongfeng3021	H28	农丰3210 Nongfeng3210
H14	农丰3022 Nongfeng3022	H29	农丰3221 Nongfeng3221
H15	农丰3023 Nongfeng3023	H30	农丰3226 Nongfeng3226

下载: 导出CSV

表 2 参试材料抗旱系数的描述性分析

Table 2. Descriptive analysis on drought resistant coefficients of specimens

指标 Index	平均值 Average	标准差 SD	变异系数 CV/%	分布区间 Range
NP	0.846	0.098	11.54	0.620～0.992
GP	0.814	0.096	11.78	0.669～0.997
SSR/%	0.733	0.133	11.25	0.401～0.931
KGW/g	0.894	0.050	5.54	0.714～0.970
Y/（kg·hm⁻²）	0.475	0.118	24.83	0.214～0.868
Bio/g	0.648	0.063	9.74	0.527～0.748
PW/g	0.607	0.104	17.10	0.375～0.818
TE/m	0.817	0.037	4.56	0.746～0.886
MNT/个	0.806	0.109	13.52	0.625～1.000
LAH/cm²	0.741	0.102	13.76	0.562～0.990
LWH/g	0.758	0.107	14.06	0.565～0.990
MWH/g	0.585	0.072	12.32	0.452～0.744
EC	0.786	0.091	11.61	0.543～0.994
注：NP：每平方米穗数；GP：穗粒数；SSR：结实率；KGW：千粒重；Y：产量；Bio：每穴生物产量；PW：穗重；TE：拔节期株高；MNT：每穗最高分蘖数；LAH：齐穗期叶面积；LWH：齐穗期叶重；MWH：齐穗期每穴干物重；EC：经济系数。（表3-4及图2同） Note: NP: Number of panicles; GP: Grains per panicle; SSR: Seed setting rate; KGW: 1000-grain weight; Y: Yield; Bio: Biomass; PW: Panicle weight; TE: Tiller number at elongation stage; MNT: Maximum number of tillers; LAH: Leaf area at full heading stage; LWH: Leaf weight at full heading stage; MWH: Dry matter weight at full heading stage; EC: Economic coefficient. Same for Table 3-Table 4, Fig. 2.

下载: 导出CSV

表 3 参试材料13个性状抗旱系数的相关分析

Table 3. Correlation among 13 drought resistance indicators on specimens

指标 Index	D	PW	NP	GP	SSR	KGW/g	Y	Bio	EC	TE	MNT	MWH	LWH	LAH
D	1
PW	0.88^**	1
NP	−0.17	−0.43^*	1
GP	0.68^**	0.57^**	−0.38^*	1
SSR	0.79^**	0.74^**	−0.13	0.25	1
KGW	−0.08	−0.07	0.01	−0.52^**	0.19	1
Y	0.77^**	0.48^**	0.3	0.36^*	0.78^**	0.17	1
Bio	0.51^**	0.32	0.49^**	0.11	0.25	0.03	0.49^**	1
EC	0.66^**	0.69^**	0.07	0.26	0.74^**	−0.07	0.64^**	0.18	1
TE	0.3	0.3	−0.45^*	0.43^*	0.05	−0.13	−0.02	−0.04	−0.05	1
MNT	−0.16	−0.42^*	0.35	−0.04	−0.3	−0.11	0.01	0.2	−0.32	−0.33	1
MWH	−0.22	−0.12	−0.35	−0.04	−0.40^*	−0.12	−0.51^**	−0.25	−0.26	0.16	0.14	1
LWH	0	−0.09	−0.09	0.16	−0.37^*	−0.22	−0.29	0.06	−0.28	0.07	0.32	0.51^**	1
LAH	−0.12	−0.17	−0.22	0.16	−0.47^**	−0.22	−0.42^*	−0.02	−0.48^**	0.08	0.38^*	0.69^**	0.73^**	1
注：和分别表示在5%和1%水平差异显著；NS：不显著。 Note: and ** indicate significant differences at 5% and 1% level, respectively; NS: No significant difference.

下载: 导出CSV

表 4 前5个主成分特征向量、主成分特征值、贡献率及累计贡献率

Table 4. Power vector (PV), eigenvalues (E), contribution rate (CR), and cumulative contribution rate (CCR) of top 5 principal components

指标 Index	结实率因子 SSRV PV1	穗数因子 NPV PV2	生物量因子 BioV PV3	千粒重因子 KGWV PV4	株高因子 TV PV5
PW	0.346	0.360	0.066	0.197	−0.077
NP	0.030	−0.466	0.340	−0.153	0.065
GP	0.145	0.442	0.259	−0.311	0.071
SSR	0.432	0.082	0.014	0.242	−0.148
KGW	0.067	−0.248	−0.260	0.700	0.250
Y	0.400	−0.060	0.281	0.107	0.066
Bio	0.169	−0.102	0.495	0.199	0.405
EC	0.393	0.077	0.067	0.030	−0.461
TE	0.032	0.393	−0.126	−0.081	0.664
MNT	−0.197	−0.172	0.460	0.009	−0.084
MWH	−0.307	0.269	0.005	0.334	−0.256
LWH	−0.271	0.222	0.338	0.245	−0.071
LAH	−0.342	0.251	0.274	0.248	−0.036
E	4.213	2.726	1.953	1.112	0.885
CR/%	32.404	20.972	15.024	8.553	6.808
CCR/%	32.404	53.376	68.400	76.953	83.760

下载: 导出CSV

表 5 30个参试材料的D值及抗旱性排序

Table 5. D values and drought resistance ranking on 30 specimens

代号 Code	D	排位 Rank	代号 Code	D	排位 Rank
H01	0.4792	21	H16	0.6120	08
H02	0.4677	22	H17	0.6138	07
H03	0.5363	15	H18	0.6082	09
H04	0.6319	05	H19	0.5992	10
H05	0.6320	04	H20	0.5365	14
H06	0.7677	01	H21	0.5989	11
H07	0.1867	30	H22	0.3345	28
H08	0.6846	02	H23	0.6603	03
H09	0.4248	24	H24	0.4800	20
H10	0.2106	29	H25	0.5774	13
H11	0.3759	27	H26	0.5847	12
H12	0.4957	19	H27	0.5324	16
H13	0.5080	18	H28	0.5312	17
H14	0.4422	23	H29	0.3837	26
H15	0.3942	25	H30	0.6280	06

下载: 导出CSV

表 6 基于BP神经网络算法的水稻抗旱指标适宜性预测结果

Table 6. Prediction by BP neural network algorithm on drought resistance indicators of rice for cultivation suitability

学习模型 Learning model	验证样本 Validation sample	实际得分 Actual score	预测得分 Predicted score	相对误差 Relative error /%
1	农丰3035 Nongfeng3035	0.6138	0.6142	0.07
	农丰3163 Nongfeng3163	0.5774	0.5799	0.43
	农丰3007 Nongfeng3007	0.4957	0.5421	9.36
	DPB120	0.6846	0.6520	−4.76
	农丰3226 Nongfeng3226	0.6280	0.6068	−3.38
2	农丰3021 Nongfeng3021	0.5080	0.5547	9.19
	农丰3186 Nongfeng3186	0.5324	0.5436	2.10
	农丰3023 Nongfeng3023	0.3942	0.3817	−3.17
	农丰1705 Nongfeng1705	0.5363	0.5347	−0.30
	DPB70	0.4248	0.4478	5.41
3	农丰3062 Nongfeng3062	0.5992	0.6063	1.18
	农丰1704 Nongfeng1704	0.4677	0.4863	3.98
	农丰3210 Nongfeng3210	0.5312	0.5164	−2.79
	农丰3055 Nongfeng3055	0.7677	0.6967	−9.25
	农丰3023 Nongfeng3023	0.3942	0.3799	−3.63

下载: 导出CSV

参考文献(31)

[1]	李艳, 马均, 王贺正, 等. 水稻品种苗期抗旱性鉴定指标筛选及其综合评价 [J]. 西南农业学报, 2005, 18(3):250−255. doi: 10.3969/j.issn.1001-4829.2005.03.005 LI Y, MA J, WANG H Z, et al. Studies on screening of the drought resistance assessment indexes and comprehensive evaluation of rice varieties during seedling stage [J]. Southwest China Journal of Agricultural Sciences, 2005, 18(3): 250−255.(in Chinese) doi: 10.3969/j.issn.1001-4829.2005.03.005
[2]	高焕晔, 王三根, 宗学凤, 等. 灌浆结实期高温干旱复合胁迫对稻米直链淀粉及蛋白质含量的影响 [J]. 中国生态农业学报, 2012, 20(1):40−47. doi: 10.3724/SP.J.1011.2012.00040 GAO H Y, WANG S G, ZONG X F, et al. Effects of combined high temperature and drought stress on amylose and protein contents at rice grain-filling stage [J]. Chinese Journal of Eco-Agriculture, 2012, 20(1): 40−47.(in Chinese) doi: 10.3724/SP.J.1011.2012.00040
[3]	王成瑷, 赵磊, 王伯伦, 等. 干旱胁迫对水稻生育性状与生理指标的影响 [J]. 农学学报, 2014, 4(1):4−14. doi: 10.3969/j.issn.1007-7774.2014.01.002 WANG C A, ZHAO L, WANG B L, et al. Effect of water stress of soil on growing characteristics and physiological index of rice (Oryza sativa) [J]. Journal of Agriculture, 2014, 4(1): 4−14.(in Chinese) doi: 10.3969/j.issn.1007-7774.2014.01.002
[4]	董蕾, 李吉跃. 植物干旱胁迫下水分代谢、碳饥饿与死亡机理 [J]. 生态学报, 2013, 33(18):5477−5483. doi: 10.5846/stxb201304270839 DONG L, LI J Y. Relationship among drought, hydraulic metabolic, carbon starvation and vegetation mortality [J]. Acta Ecologica Sinica, 2013, 33(18): 5477−5483.(in Chinese) doi: 10.5846/stxb201304270839
[5]	杨瑰丽, 杨美娜, 李帅良, 等. 水稻萌芽期抗旱指标筛选与抗旱性综合评价 [J]. 华南农业大学学报, 2015, 36(2):1−5. YANG G L, YANG M N, LI S L, et al. Screening and comprehensive evaluation of drought resistance indices of rice at germination stage [J]. Journal of South China Agricultural University, 2015, 36(2): 1−5.(in Chinese)
[6]	GOSWAMI A, BANERJEE R, RAHA S. Drought resistance in rice seedlings conferred by seed priming [J]. Protoplasma, 2013, 250(5): 1115−1129. doi: 10.1007/s00709-013-0487-x
[7]	周少川, 李宏, 卢德城, 等. 水稻抗旱育种材料的筛选与研究 [J]. 分子植物育种, 2010, 8(6):1202−1207. doi: 10.3969/mpb.008.001202 ZHOU S C, LI H, LU D C, et al. The exploration and screening of rice breeding materials resistant to drought [J]. Molecular Plant Breeding, 2010, 8(6): 1202−1207.(in Chinese) doi: 10.3969/mpb.008.001202
[8]	张鸿, 朱从桦, 谭杰, 等. 杂交籼稻新组合抗旱性鉴定评价及预测研究 [J]. 干旱地区农业研究, 2018, 36(2):161−169. doi: 10.7606/j.issn.1000-7601.2018.02.24 ZHANG H, ZHU C H, TAN J, et al. Study of identification, evaluation and prediction on the drought resistance of new indicia hybrid rice combinations [J]. Agricultural Research in the Arid Areas, 2018, 36(2): 161−169.(in Chinese) doi: 10.7606/j.issn.1000-7601.2018.02.24
[9]	敬礼恒, 陈光辉, 刘利成, 等. 水稻种子萌发期的抗旱性鉴定指标研究 [J]. 杂交水稻, 2014, 29(3):65−69. JING L H, CHEN G H, LIU L C, et al. Studies on identification indices of drought resistance of rice in seed germination [J]. Hybrid Rice, 2014, 29(3): 65−69.(in Chinese)
[10]	钟娟, 傅志强. 不同晚稻品种抗旱性相关指标研究 [J]. 作物研究, 2015, 29(6):575−580, 602. doi: 10.3969/j.issn.1001-5280.2015.06.01 ZHONG J, FU Z Q. Drought resistance indexes of different late rice varieties [J]. Crop Research, 2015, 29(6): 575−580, 602.(in Chinese) doi: 10.3969/j.issn.1001-5280.2015.06.01
[11]	张军, 崔潇, 赵章囡, 等. 7份喀麦隆水稻种质资源萌发期抗旱性综合鉴定 [J]. 陕西农业科学, 2019, 65(4):32−34. doi: 10.3969/j.issn.0488-5368.2019.04.012 ZHANG J, CUI X, ZHAO Z A, et al. Comprehensive Identification of Drought Resistance in Seven Cameroon Rice Germplasm Resources at Stage of Germination [J]. Shaanxi Journal of Agricultural Sciences, 2019, 65(4): 32−34.(in Chinese) doi: 10.3969/j.issn.0488-5368.2019.04.012
[12]	王贺正, 李艳, 马均, 等. 水稻苗期抗旱性指标的筛选 [J]. 作物学报, 2007, 33(9):1523−1529. doi: 10.3321/j.issn:0496-3490.2007.09.020 WANG H Z, LI Y, MA J, et al. Screening indexes of drought resistance during seedling stage in rice [J]. Acta Agronomica Sinica, 2007, 33(9): 1523−1529.(in Chinese) doi: 10.3321/j.issn:0496-3490.2007.09.020
[13]	刘云开, 方宝华, 庞冰, 等. 水稻品种节水抗旱适应性筛选研究 [J]. 湖南农业科学, 2009(5):24−26, 30. doi: 10.3969/j.issn.1006-060X.2009.05.009 LIU Y K, FANG B H, PANG B, et al. Screening of rice varieties for adaptability to water saving and drought resistance [J]. Hunan Agricultural Sciences, 2009(5): 24−26, 30.(in Chinese) doi: 10.3969/j.issn.1006-060X.2009.05.009
[14]	刘三雄, 黎用朝, 吴俊, 等. 应用隶属函数法综合评价水稻主栽品种抗旱性的研究 [J]. 杂交水稻, 2015, 30(1):74−78. LIU S X, LI Y C, WU J, et al. Evaluation of drought tolerance of widely-used rice varieties with subordinate function [J]. Hybrid Rice, 2015, 30(1): 74−78.(in Chinese)
[15]	徐建欣, 杨洁, 胡祥伟, 等. 云南陆稻芽期抗旱性鉴定指标筛选及其综合评价 [J]. 西南农业学报, 2015, 28(4):1455−1464. XU J X, YANG J, HU X W, et al. Screening of drought resistance identification indexes and comprehensive evaluation of Yunnan upland rice varieties during germinating stage [J]. Southwest China Journal of Agricultural Sciences, 2015, 28(4): 1455−1464.(in Chinese)
[16]	ZHANG F T, CUI F L, ZHANG L X, et al. Development and identification of a introgression line with strong drought resistance at seedling stage derived from Oryza sativa L. mating with Oryza rufi pogon Griff [J]. Euphytica, 2014, 200(1): 1−7. doi: 10.1007/s10681-014-1121-5
[17]	王英, 张浩, 马军韬, 等. 水稻抗旱研究进展与展望 [J]. 热带作物学报, 2018, 39(5):1038−1043. doi: 10.3969/j.issn.1000-2561.2018.05.031 WANG Y, ZHANG H, MA J T, et al. Advances in drought tolerance of rice [J]. Chinese Journal of Tropical Crops, 2018, 39(5): 1038−1043.(in Chinese) doi: 10.3969/j.issn.1000-2561.2018.05.031
[18]	张灿军, 姚宇卿, 王育红, 等. 旱稻抗旱性鉴定方法与指标研究——Ⅰ鉴定方法与评价指标 [J]. 干旱地区农业研究, 2005, 23(3):33−36. doi: 10.3321/j.issn:1000-7601.2005.03.007 ZHANG C J, YAO Y Q, WANG Y H, et al. Study on resistance drought identify method and evaluation index of dry-land rice——Ⅰ Identify method and evaluation index [J]. Agricultural Research in the Arid Areas, 2005, 23(3): 33−36.(in Chinese) doi: 10.3321/j.issn:1000-7601.2005.03.007
[19]	张安宁, 王飞名, 余新桥, 等. 基于土壤水分梯度鉴定法的栽培稻抗旱标识品种筛选 [J]. 作物学报, 2008, 34(11):2026−2032. ZHANG A N, WANG F M, YU X Q, et al. Screening marker varieties with drought resistance in cultivated rice (Oryza sativa L.)/ using identification method with soil moisture gradient [J]. Acta Agronomica Sinica, 2008, 34(11): 2026−2032.(in Chinese)
[20]	LEE H, CHA J, CHOI C, et al. Rice WRKY11 plays a role in pathogen defense and drought tolerance [J]. Rice, 2018, 11(1): 1−12. doi: 10.1186/s12284-017-0196-8
[21]	王贺正, 马均, 李旭毅. 水稻开花期抗旱性鉴定指标的筛选 [J]. 作物学报, 2005, 31(11):1485−1489. doi: 10.3321/j.issn:0496-3490.2005.11.016 WANG H Z, MA J, LI X Y. Screening Identification Indexes of Drought Resistance at Flowering Stage in Rice [J]. Acta Agronomica Sinica, 2005, 31(11): 1485−1489.(in Chinese) doi: 10.3321/j.issn:0496-3490.2005.11.016
[22]	胡标林, 余守武, 万勇, 等. 东乡普通野生稻全生育期抗旱性鉴定 [J]. 作物学报, 2007, 33(3):425−432. doi: 10.3321/j.issn:0496-3490.2007.03.012 HU B L, YU S W, WAN Y, et al. Drought-resistance identification of Dongxiang common wild rice (Oryza rufipogon griff.)/ in whole growth period [J]. Acta Agronomica Sinica, 2007, 33(3): 425−432.(in Chinese) doi: 10.3321/j.issn:0496-3490.2007.03.012
[23]	周国雁, 伍少云, 隆文杰, 等. 云南省不同小麦资源种子萌发期抗旱性相关性状差异及与抗旱指数、抗旱系数的相关性 [J]. 华南农业大学学报, 2015, 36(2):13−18. doi: 10.7671/j.issn.1001-411X.2015.02.003 ZHOU G Y, WU S Y, LONG W J, et al. Drought resistant characters during germination of different wheat germplasm in Yunnan Province and their correlations with the index and coefficient of drought resistance [J]. Journal of South China Agricultural University, 2015, 36(2): 13−18.(in Chinese) doi: 10.7671/j.issn.1001-411X.2015.02.003
[24]	栗雨勤, 张文英, 王有增, 等. 作物抗旱性鉴定指标研究及进展 [J]. 河北农业科学, 2004, 8(1):58−61. doi: 10.3969/j.issn.1088-1631.2004.01.015 LI Y Q, ZHANG W Y, WANG Y Z, et al. Advances of studies on crop drought resistance identification [J]. Journal of Hebei Agricultural Sciences, 2004, 8(1): 58−61.(in Chinese) doi: 10.3969/j.issn.1088-1631.2004.01.015
[25]	王英. 利用回交导入系筛选水稻高产、抗旱和耐盐株系及选择导入系相关性状的QTL定位[D]. 北京: 中国农业科学院, 2013. WANG Y. Screening of High Yield, Drought and Salt Tolerant Plants from Backcross Introgression Lines and QTL Detectionfor Related Tranits in Rice[D]. Beijing: Chinese Academy of Agricultural Sciences, 2013. (in Chinese)
[26]	田又升, 谢宗铭, 王志军, 等. 水稻种子芽期抗旱性与产量抗旱系数关系分析 [J]. 作物杂志, 2014(5):148−153. TIAN Y S, XIE Z M, WANG Z J, et al. Relationship between the drought resistance of rice shoots and drought resistance coefficient of yield [J]. Crops, 2014(5): 148−153.(in Chinese)
[27]	安永平, 强爱玲, 张媛媛, 等. 渗透胁迫下水稻种子萌发特性及抗旱性鉴定指标研究 [J]. 植物遗传资源学报, 2006, 7(4):421−426. doi: 10.3969/j.issn.1672-1810.2006.04.009 AN Y P, QIANG A L, ZHANG Y Y, et al. Study on characteristics of germination and drought-resistance index by osmotic stress in rice [J]. Journal of Plant Genetic Resources, 2006, 7(4): 421−426.(in Chinese) doi: 10.3969/j.issn.1672-1810.2006.04.009
[28]	王贺正, 马均, 李旭毅, 等. 水稻种质芽期抗旱性和抗旱性鉴定指标的筛选研究 [J]. 西南农业学报, 2004, 17(5):594−599. doi: 10.3969/j.issn.1001-4829.2004.05.011 WANG H Z, MA J, LI X Y, et al. Study on drought resistance and screening of the drought resistance assessment indexes at germinating stage of rice [J]. Southwest China Journal of Agricultural Sciences, 2004, 17(5): 594−599.(in Chinese) doi: 10.3969/j.issn.1001-4829.2004.05.011
[29]	王贺正. 水稻抗旱性研究及其鉴定指标的筛选[D]. 雅安: 四川农业大学, 2007. WANG H Z. Study on Drought Resistance and Screening Identification Indexes of Drought Resistance in Rice[D]. Yaan: Sichuan Agricultural University, 2007. (in Chinese)
[30]	左付山, 李政原, 吕晓, 等. 基于BP神经网络的汽油机尾气排放预测 [J]. 江苏大学学报(自然科学版), 2020, 41(3):307−313. ZUO F S, LI Z Y, LYU X, et al. Prediction of gasoline engine exhaust emission based on BP neural network [J]. Journal of Jiangsu University (Natural Science Edition), 2020, 41(3): 307−313.(in Chinese)
[31]	梁春华. 人工神经网络在数据挖掘中的应用研究 [J]. 无线互联科技, 2019(22):17−18. doi: 10.3969/j.issn.1672-6944.2019.22.009 LIANG C H. Research on the application of artificial neural network in data mining [J]. Wireless Internet Technology, 2019(22): 17−18.(in Chinese) doi: 10.3969/j.issn.1672-6944.2019.22.009