[1]梁文香,张晓燕,罗仔秋,等.基于SAM_CSSAM模型的大豆耐盐性鉴定方法[J].江苏农业科学,2026,54(1):81-88.
 Liang Wenxiang,et al.The identification method for salt tolerance of soybean based on SAM_CSSAM model[J].Jiangsu Agricultural Sciences,2026,54(1):81-88.
点击复制

基于SAM_CSSAM模型的大豆耐盐性鉴定方法()

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第54卷
期数:
2026年第1期
页码:
81-88
栏目:
遗传育种与种质资源
出版日期:
2026-01-05

文章信息/Info

Title:
The identification method for salt tolerance of soybean based on SAM_CSSAM model
作者:
梁文香12张晓燕2罗仔秋1张浩淼1蒋东山1陈新2高尚兵1薛晨晨2
1.淮阴工学院计算机与软件工程学院,江苏淮安 223001; 2.江苏省农业科学院经济作物研究所,江苏南京 210014
Author(s):
Liang Wenxianget al
关键词:
大豆耐盐性种质资源鉴定注意力机制卷积神经网络
Keywords:
-
分类号:
S126;S565.101;TP391.41
DOI:
-
文献标志码:
A
摘要:
传统的大豆种质资源耐盐性鉴定方法存在鉴定周期长、鉴定效率低、精准度低等诸多缺陷,不符合现代高通量表型鉴定的需求,且极大地限制了大豆耐盐种质的挖掘与利用。研究以434份大豆材料为研究对象,设计对照和盐处理2个处理,采集大豆苗期的RGB图像,构建了基于结合通道选择和空间注意力机制的结构调整网络模型(structural adjustment network model with channel selection and spatial attention mechanism,简称SAM_CSSAM),首先使用改进的通道和空间注意力机制,学习通道和空间上的特征信息,并且结合通道权重选择模块进行去除背景冗余信息,最后提出结构权重选择模块减少下采样时特征信息的损失。在自建的大豆苗期耐盐性数据集上迭代训练500轮,模型的训练损失和验证准确率分别达到0.02、97.22%,精确率为97.24%,召回率为97.26%,F1分数为97.23%。相比于VGG16、MobileNet v2、ConvNext、ShuffleNet等模型均有明显提升。本研究基于深度学习建立了一种基于 SAM_CSSAM模型的大豆种质资源苗期耐盐性鉴定方法,可为耐盐大豆种质资源的挖掘提供理论依据和技术支撑。
Abstract:
-

参考文献/References:

[1]王广达. 不同类型钠盐对大豆幼苗生长的影响及作用机制[D]. 大庆:黑龙江八一农垦大学,2023.
[2]孙现军,胡正,姜雪敏,等. 大豆种质资源苗期耐盐性鉴定评价与筛选[J]. 作物学报,2024,50(9):2179-2186.
[3]王晓歌,高利英,邓永胜,等. 棉花萌发出苗期耐盐性鉴定和评价[J]. 山东农业科学,2025,57(2):29-37.
[4]胡炎,杨帆,杨宁,等. 盐碱地资源分析及利用研究展望[J]. 土壤通报,2023,54(2):489-494.
[5]Yao J P,Wang Z Y,de Oliveira R F,et al. A deep learning method for the long-term prediction of plant electrical signals under salt stress to identify salt tolerance[J]. Computers and Electronics in Agriculture,2021,190:106435.
[6]柏锡,吴芳芳,林凡敏,等. 大豆耐盐性鉴定体系的建立[J]. 东北农业大学学报,2013,44(4):8-13,161.
[7]邵桂花. 大豆种质资源耐盐性田间鉴定方法[J]. 作物杂志,1986(3):36-37.
[8]刘谢香,常汝镇,关荣霞,等. 大豆出苗期耐盐性鉴定方法建立及耐盐种质筛选[J]. 作物学报,2020,46(1):1-8.
[9]Behmann J,Steinrücken J,Plümer L. Detection of early plant stress responses in hyperspectral images[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2014,93:98-111.
[10]Moshou D,Pantazi X E,Kateris D,et al. Water stress detection based on optical multisensor fusion with a least squares support vector machine classifier[J]. Biosystems Engineering,2014,117:15-22.
[11]Zhuang S,Wang P,Jiang B R,et al. Early detection of water stress in maize based on digital images[J]. Computers and Electronics in Agriculture,2017,140:461-468.
[12]Deng Y X,Xin N,Zhao L G,et al. Precision detection of salt stress in soybean seedlings based on deep learning and chlorophyll fluorescence imaging[J]. Plants,2024,13(15):2089.
[13]Hao X,Jia J D,Gao W L,et al. MFC-CNN:an automatic grading scheme for light stress levels of lettuce (Lactuca sativa L.) leaves[J]. Computers and Electronics in Agriculture,2020,179:105847.
[14]Khotimah W N,Boussaid F,Sohel F,et al. SC-CAN:spectral convolution and channel attention network for wheat stress classification[J]. Remote Sensing,2022,14(17):4288.
[15]Hwang Y,Kim J,Ryu Y.Canopy structural changes explain reductions in canopy-level solar induced chlorophyll fluorescence in Prunus yedoensis seedlings under a drought stress condition[J]. Remote Sensing of Environment,2023,296:113733.
[16]Song W L,Xiang K Z,Lu Y Z,et al. Unlocking the secrets of corn:physiological responses and rapid forecasting in varied drought stress environments[J]. Remote Sensing,2024,16(22):4302.
[17]Gao S Y,Liang H,Hu D,et al. SAM-ResNet50:a deep learning model for the identification and classification of drought stress in the seedling stage of Betula luminifera[J]. Remote Sensing,2024,16(22):4141.
[18]文青青,李金星,王虎,等. 基于BERT的猕猴桃病虫害命名实体识别[J]. 计算机技术与发展,2025,35(5):214-220.
[19]Simonyan K,Zisserman A. Very deep convolutional networks for large-scale image recognition[C]//International Conference on Learning Representations.Computational and Biological Learning Society,2015.
[20]Sandler M,Howard A,Zhu M L,et al. MobileNet v2:inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:4510-4520.
[21]Liu Z,Mao H Z,Wu C Y,et al. A ConvNet for the 2020s[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans:IEEE,2022:11966-11976.
[22]Zhang X Y,Zhou X Y,Lin M X,et al. ShuffleNet:an extremely efficient convolutional neural network for mobile devices[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City:IEEE,2018:6848-6856.
[23]Huang G,Liu Z,van der Maaten L,et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu:IEEE,2017:2261-2269.
[24]Radosavovic I,Kosaraju R P,Girshick R,et al. Designing network design spaces[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle:IEEE,2020:10428-10436.

相似文献/References:

[1]赵银月,耿智德,王铁军.云南省大豆地方种质资源的籽粒特征特性分析及评价[J].江苏农业科学,2013,41(04):62.
[2]李葵花,高玉亮,吴京姬.转P5CS基因马铃薯“东农303”耐盐、抗旱性研究[J].江苏农业科学,2014,42(11):131.
 Li Kuihua,et al().Study on salt resistance and drought resistance of P5CS transgenic potato cultivar “Dongnong 303”[J].Jiangsu Agricultural Sciences,2014,42(1):131.
[3]朱倩,谢飒英,谢三刚,等.稀土LaCl3对大豆叶绿素含量及a/b值的影响[J].江苏农业科学,2013,41(06):81.
 Zhu Qian,et al.Effect of LaCl3 on chlorophyll content and the ratio of chlorophyll a to chlorophyll b in soybean[J].Jiangsu Agricultural Sciences,2013,41(1):81.
[4]王宗标,王幸,徐泽俊,等.植物保健剂对大豆产量及农艺性状的影响[J].江苏农业科学,2013,41(06):85.
 Wang Zongbiao,et al.Effects of plant health care agent on yield and agronomic traits of soybean[J].Jiangsu Agricultural Sciences,2013,41(1):85.
[5]孙洪助,李鹤,郭世荣,等.8个不同砧用南瓜品种萌芽期耐盐性比较[J].江苏农业科学,2013,41(06):130.
 Sun Hongzhu,et al.Salt tolerance comparison of eight pumpkin cultivars used as rootstock at germination stage[J].Jiangsu Agricultural Sciences,2013,41(1):130.
[6]徐明坤,胥义.冷冻干燥法制备快速制浆半成品大豆的工艺条件优化[J].江苏农业科学,2013,41(06):216.
 Xu Mingkun,et al.Optimization of technological conditions for preparation of semi-finished soybean products for quick soybean milk production by freeze-drying method[J].Jiangsu Agricultural Sciences,2013,41(1):216.
[7]郭文琦,张培通,李春宏,等.沿海滩涂绿化树种选择和耐盐性评价[J].江苏农业科学,2014,42(10):175.
 Guo Wenqi,et al.Selection and evaluation on salt tolerance of gardening tree species in coastal beach areas[J].Jiangsu Agricultural Sciences,2014,42(1):175.
[8]陈新,袁星星,崔晓艳,等.江苏省大豆生产发展布局与未来发展方向[J].江苏农业科学,2013,41(08):5.
 Chen Xin,et al.Layout and future direction of soybean production development in Jiangsu Province[J].Jiangsu Agricultural Sciences,2013,41(1):5.
[9]吴平,陈晓梅,丁宁.4种湿生植物苗期耐盐性综合评价[J].江苏农业科学,2014,42(09):148.
 Wu Ping,et al.Comprehensive evaluation of salt tolerance of four hygrophytes[J].Jiangsu Agricultural Sciences,2014,42(1):148.
[10]李丽丽,郎敬,杨洪一,等.大豆根际解磷菌的鉴定[J].江苏农业科学,2014,42(08):363.
 Li Lili,et al.Identification of phosphate-solubilizing bacteria in rhizosphere of soybean[J].Jiangsu Agricultural Sciences,2014,42(1):363.
[11]姚梦楠,王永强,周恩强,等.86份大豆种质成熟期耐盐性评价[J].江苏农业科学,2025,53(7):59.
 Yao Mengnan,et al.Evaluation of salt tolerance of 86 soybean germplasms at maturation stage[J].Jiangsu Agricultural Sciences,2025,53(1):59.

备注/Memo

备注/Memo:
收稿日期:2025-02-20
基金项目:国家重点研发计划(编号:2023YFD2300100);“生物育种钟山实验室”资助项目(编号:ZSBBL);江苏省种业振兴揭榜挂帅项目(编号:JBGS-2021-014)。
作者简介:梁文香(1997—),女,河南周口人,硕士研究生,研究方向为图像处理,E-mail:liangwx1211@163.com;共同第一作者:张晓燕(1988—),女,山东烟台人,博士,副研究员,研究方向为豆类作物种质创新与应用,E-mail:xyzhang@jaas.ac.cn。
通信作者:高尚兵,博士,教授,研究方向深度学习、图像处理,E-mail:11060036@hyit.edu.cn;薛晨晨,博士,副研究员,研究方向大豆功能育种与应用,E-mail:xuecc@jaas.ac.cn。
更新日期/Last Update: 2026-01-05