机器学习及其在农业中应用研究的展望

doi:10.13998/j.cnki.issn1002-1248.2019.09.19-0652

摘要/Abstract

摘要： 机器学习是一种面向机器的数据分析方法,自动化机器学习的研究促进了人工智能的发展。大数据的快速积累,促进了机器学习算法的井喷式发展。如何选择合适的机器学习算法解决行业问题,成为了当前应用的难点。笔者整理了机器学习新材料,对各种机器算法的特点和算法之间的差异,进行了仔细的梳理,总结了各种算法的需求背景和优缺点,以及主要的应用场合。在此基础上,分析了机器学习在农业应用的案例,综述了机器学习在农业应用,指出了目前存在的发展瓶颈,并提出了进一步研究应用的建议。

关键词: 机器学习, 算法, 可解释性, 自动化, 黑箱, 智能机器, 智能机器人

Abstract: Machine learning is a machine-oriented data analysis method, and the research of automated machine learning promotes the development of artificial intelligence. The rapid accumulation of big data has promoted the development of machine learning algorithms. How to choose the right one to solve industry problems has been difficult in its applications. The authors sort out the new materials in this area, and carefully analyzes the characteristics of various machine algorithms and the differences between them, summarizes the background, advantages and disadvantages of them. On this basis, this paper analyzes the case of machine learning in agricultural applications, and summarizes it, finally, this paper points out the current development bottlenecks and proposes further research and application.

Key words: machine learning, algorithm, interpretable, automation, black box, intelligent machine, intelligent robot

中图分类号:

G250

胡林, 刘婷婷, 李欢, 崔运鹏. 机器学习及其在农业中应用研究的展望[J]. 农业图书情报, 2019, 31(10): 12-22.

HU Lin, LIU Tingting, LI Huan, CUI Yunpeng. Prospects for Machine Learning Research and its Application in Agriculture[J]. Agricultural Library and Information, 2019, 31(10): 12-22.

参考文献

[1] 陈春霞. 浅析机器学习的发展与应用[J]. 信息系统工程, 2017(8):99-100.
[2] Yildiz B, Bilbao J I, Sproul A B.A review and analysis of regression and machine learning models on commercial building electricity load forecasting[J]. RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2017, 73: 1104-1122.
[3] Jordan M I, Mitchell T M.Machine learning: Trends, perspectives, and prospects[J]. SCIENCE, 2015, 349(6245, SI): 255-260.
[4] 焦嘉烽, 李云. 大数据下的典型机器学习平台综述[J]. 计算机应用, 2017(11):7-15+20.
[5] 余殷博. 基于人工智能下的机器学习历史及展望[J]. 电子技术与软件工程, 2017(4):129-129.
[6] 崔运鹏,王健,刘娟. 基于深度学习的自然语言处理技术的发展及其在农业领域的应用[J]. 农业大数据学报,2019,1(1):38-44.
[7] Wayne Thompson, Hui Li and Alison Bolen. Artificial intelligence, machine learning, deep learning and beyond Understanding AI technologies and how they lead to smart applications[J/OL].[2019-03-12].https://www.sas.com/zh_cn/insights/articles/big-data/artificial-intelligence-machine-learning-deep-learning-and-beyond.html.
[8] MathWorks. 什么是机器学习?您需要知道的三件事[EB/OL]. [2019-02-01].https://ww2.mathworks.cn/discovery/machine-learning.html?s_tid=srchtitle.
[9] 陈嘉博. 机器学习算法研究及前景展望[J]. 信息通信, 2017(6).
[10] 夏天. 机器学习及其算法与应用研究[J]. 电脑知识与技术, 2017, 13(15):156-157.
[11] 张素芳, 翟俊海, 王聪,等. 大数据与大数据机器学习[J]. 河北大学学报(自然科学版), 2018, v.38(3):81-90+118.
[12] 师翊,耿楠,胡少军,张志毅,张晶.基于随机森林回归算法的苹果树冠层光照分布模型[J].农业机械学报,2019,50(05):214-222.
[13] 官赛萍,靳小龙,贾岩涛,王元卓,程学旗.面向知识图谱的知识推理研究进展[J].软件学报,2018,29(10):2966-2994.
[14] 张海波.基于正则化卷积神经网络的目标跟踪算法[J].信息技术,2019,43(06):82-86+90.
[15] 汤鲲, 蒋炳南, 彭艳兵. 基于决策树的多维属性自动推理识别[J]. 计算机与现代化, 2017(2):83-87.
[16] 李俊明. 中国PM_(2.5)污染时空趋势研究——基于贝叶斯时空统计视角[J].统计与信息论坛,2019,34(06):67-73.
[17] 章永来,周耀鉴.聚类算法综述[J/OL].计算机应用:1-14.[2019-07-11].http://kns.cnki.net/kcms/detail/51.1307.TP.20190415.1412.004.html.
[18] 李家辉,周忠眉.关联分类及其改进算法综述[J].科技通报,2018,34(08):140-144.
[19] 刘俊一. 基于人工神经网络的深度学习算法综述[J].中国新通信,2018,20(06):193-194.
[20] 李明旭. 基于人工神经网络的秀丽隐杆线虫趋温性行为建模[D].重庆邮电大学,2017.
[21] 王婷,崔运鹏,王健,刘婷婷,王末.认知计算及其在农业领域的应用研究[J].农业图书情报,2019,31(4):4-18.
[22] 鄂海红,张文静,肖思琪,程瑞,胡莺夕,周筱松,牛佩晴.深度学习实体关系抽取研究综述[J].软件学报,2019,30(06):1793-1818.
[23] 范玉涛. 空间数据挖掘中的降维算法研究[D].辽宁师范大学,2015.
[24] 张恩豪,陈晓红,刘鸿,朱玉莲.基于典型相关分析的多视图降维算法综述[J/OL].计算机工程:1-15.[2019-07-11].https://doi.org/10.19678/j.issn.1000-3428.0053147.
[25] 林思寒,黎静,薛龙,刘木华,陈金印,陈明,张一帆.基于时序高光谱的翠冠梨机械损伤的早期无损检测研究[J].江西农业大学学报,2018,40(04):835-842.
[26] 徐继伟,杨云.集成学习方法:研究综述[J].云南大学学报(自然科学版),2018,40(06):1082-1092.
[27] 王奕森,夏树涛.集成学习之随机森林算法综述[J].信息通信技术,2018,12(01):49-55.
[28] 于玲,吴铁军.集成学习:Boosting算法综述[J].模式识别与人工智能,2004,17(01):52-59.
[29] 蔡毅,朱秀芳,孙章丽,陈阿娇.半监督集成学习综述[J].计算机科学,2017,44(S1):7-13.
[30] 任涵. 基于遗传算法的猕猴桃组培苗变异监测研究[D].昆明理工大学,2017.
[31] Kumar M, Husian M, Upreti N, et al.Genetic algorithm: Review and application[J]. International Journal of Information Technology and Knowledge Management, 2010, 2(2): 451-454.
[32] 刘方园,王水花,张煜东.支持向量机模型与应用综述[J].计算机系统应用,2018,27(04):1-9.
[33] Mountrakis G, Im J, Ogole C.Support vector machines in remote sensing: A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(3): 247-259.
[34] Scholkopf B, Smola A J.Learning with kernels: support vector machines, regularization, optimization, and beyond[M]. MIT press, 2001.
[35] 赵彰. 机器学习研究范式的哲学基础及其可解释性问题[D].上海社会科学院,2018.
[36] He D, Xia Y, Qin T, et al.Dual learning for machine translation[C]//Advances in Neural Information Processing Systems. 2016: 820-828.
[37] 夏应策. 对偶学习的理论和实验研究[D].中国科学技术大学,2018.
[38] 吴宏杰,戴大东,傅启明,陈建平,陆卫忠.强化学习与生成式对抗网络结合方法研究进展[J].计算机工程与应用,2019,55(10):36-44.
[39] 邢恩旭,吴小勇,李雅娴.基于迁移学习的双层生成式对抗网络[J/OL].计算机工程与应用:1-11.[2019-07-11].http://kns.cnki.net/kcms/detail/11.2127.TP.20190308.0942.008.html.
[40] Bzdok D, Altman N, Krzywinski M.Points of significance: statistics versus machine learning[J]. 2018.
[41] Gu W, Foster K, Shang J, et al.A game-predicting expert system using big data and machine learning[J]. Expert Systems with Applications, 2019, 130: 293-305.
[42] Holzinger A, Kieseberg P, Weippl E, et al.Current advances, trends and challenges of machine learning and knowledge extraction: From machine learning to explainable ai[C]//International Cross-Domain Conference for Machine Learning and Knowledge Extraction. Springer, Cham, 2018: 1-8.
[43] Ahmad I, Basheri M, Iqbal M J, et al.Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection[J]. IEEE Access, 2018, 6: 33789-33795.
[44] González-Camacho J M, Ornella L, Pérez-Rodríguez P, et al. Applications of machine learning methods to genomic selection in breeding wheat for rust resistance[J]. The plant genome, 2018.
[45] Li B, Zhang N, Wang Y G, et al.Genomic prediction of breeding values using a subset of SNPs identified by three machine learning methods[J]. Frontiers in genetics, 2018, 9: 237.
[46] Odilbekov F, Armoniené R, Henriksson T, et al.Proximal phenotyping and machine learning methods to identify septoria tritici blotch disease symptoms in wheat[J]. Frontiers in plant science, 2018, 9: 685.
[47] Han X, Huettmann F, Guo Y, et al.Conservation prioritization with machine learning predictions for the black-necked crane Grus nigricollis, a flagship species on the Tibetan Plateau for 2070[J]. Regional environmental change, 2018, 18(7): 2173-2182.
[48] Qiu Z, Cheng Q, Song J, et al.Application of machine learning-based classification to genomic selection and performance improvement[C] //International Conference on Intelligent Computing. Springer, Cham, 2016: 412-421.
[49] Mohanty S P, Hughes D P, Salathé M.Using deep learning for image-based plant disease detection[J]. Frontiers in plant science, 2016, 7: 1419.
[50] Fuentes A, Yoon S, Kim S, et al.A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition[J]. Sensors, 2017, 17(9): 2022.
[51] Corrales D C, Corrales J C, Figueroa-Casas A.Towards detecting crop diseases and pest by supervised learning[J]. Ingeniería y Universidad, 2015, 19(1): 207-228.
[52] Hepworth P J, Nefedov A V., Muchnik I B.Broiler chickens can benefit from machine learning: Support vector machine analysis of observational epidemiological data[J]. Journal of the Royal Society Interface, 2012(9):1934-1942.
[53] Liakos K, Busato P, Moshou D, et al.Machine learning in agriculture: A review[J]. Sensors, 2018, 18(8): 2674.
[54] Schuster E W, Kumar S, Sarma S E, et al.Infrastructure for data-driven agriculture: identifying management zones for cotton using statistical modeling and machine learning techniques[C]//2011 8th International Conference & Expo on Emerging Technologies for a Smarter World. IEEE, 2011: 1-6.
[55] Dahikar S S, Rode S V.Agricultural crop yield prediction using artificial neural network approach[J]. International Journal of Innovative Research in Electrical, Electronics, Instrumentation and Control Engineering, 2014, 2(1): 683-686.
[56] Chlingaryan A, Sukkarieh S, Whelan B.Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review[J].Computers and electronics in agriculture, 2018, 151: 61-69.
[57] Sahoo S, Russo T A, Elliott J, et al.Machine learning algorithms for modeling groundwater level changes in agricultural regions of the US[J]. Water Resources Research, 2017, 53(5): 3878-3895.
[58] Bendre M R, Thool R C, Thool V R.Big data in precision agriculture: Weather forecasting for future farming[C]//2015 1st International Conference on Next Generation Computing Technologies (NGCT). IEEE, 2015: 744-750.
[59] Kussul N, Lavreniuk M, Skakun S, et al.Deep learning classification of land cover and crop types using remote sensing data[J]. IEEEGeoscience and Remote Sensing Letters, 2017, 14(5): 778-782.
[60] Zhong L, Hu L, Zhou H.Deep learning based multi-temporal crop classification[J]. Remote sensing of environment, 2019, 221: 430-443.
[61] Park S, Im J, Jang E, et al.Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions[J]. Agricultural and forest meteorology, 2016, 216: 157-169.
[62] Park S, Im J, Park S, et al.AMSR2 soil moisture downscaling using multisensor products through machine learning approach[C]//2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). IEEE, 2015: 1984-1987.
[63] De Vito S, Esposito E, Salvato M, et al.Calibrating chemical multisensory devices for real world applications: An in-depth comparison of quantitative machine learning approaches[J]. Sensors and Actuators B: Chemical, 2018, 255: 1191-1210.
[64] Wang J, Xie J, Zhao R, et al.A new probabilistic kernel factor analysis for multisensory data fusion: application to tool condition monitoring[J].IEEE Transactions on Instrumentation and Measurement, 2016, 65(11): 2527-2537.
[65] 裘炯良, 周力沛, 郑剑宁等. 机器学习技术与病媒生物种属鉴定[J]. 中华卫生杀虫药械, 2017,(5):436-439.
[66] 孙存一, 龚六堂. 大数据思维下的利率定价研究——以机器学习为视角的实证分析[J]. 金融理论与实践, 2017(7):1-5.
[67] 孙美卫. 一种基于机器学习的经济数据识别方法[J]. 佳木斯大学学报(自然科学版), 2018,36(3):137-140.
[68] Milacic L, Jovic S, Vujovic T, et al.Application of artificial neural network with extreme learning machine for economic growth estimation[J]. Physica A: Statistical Mechanics and its Applications, 2017, 465: 285-288.
[69] Malhotra A,Maloo M.了解印度的食品通货膨胀:一种机器学习方法[J].arXiv:机器学习,2017.
[70] Jean N, Burke M, Xie M, et al.Combining satellite imagery and machine learning to predict poverty[J]. Science, 2016, 353(6301): 790-794.
[71] Wang M, Cui Y, Wang X, et al.Machine learning for networking: Workflow, advances and opportunities[J]. IEEE Network, 2017, 32(2): 92-99.
[72] Qin S J, Chiang L H.Advances and opportunities in machine learning for process data analytics[J]. Computers & Chemical Engineering, 2019, 126: 465-473.
[73] Baydin A G, Pearlmutter B A, Radul A A, et al.Automatic differentiation in machine learning: a survey[J]. Journal of machine learning research, 2018, 18(153).