基于多种算法的果树果实生长模型研究—以云南昭通苹果为例

doi:10.3864/j.issn.0578-1752.2021.17.015

Abstract

Abstract:

【Objective】 Meteorological factors are closely related to fruit diameter during growth process, but this relationship between them tends to be non-linear and non-stationary, thus making it hard to monitor the fruit and trunk diameter continuously. Comparing the simulation capabilities of various growth models for fruit diameter could provide scientific support for fruit growth monitoring and predicting, timely irrigation and fertilization, and the regulation of growth environment. 【Method】 Taking apples in Zhaotong, Yunan Province as an example, this study first analyzed the characteristics of diameter change during apple growth in 2019 and 2020 and its relationship with environmental and climate factors. Subsequently, a deep learning method of Long Short-Term Memory (LSTM) model was adopted to simulate and predict the fruit diameter by integrating these factors, which was evaluated with the multi-linear regression (MLR) model and machine learning methods including Decision Tree (DT) and Random Forests (RF) using three sampling methods. 【Result】 The apple diameter had obvious diurnal cycle characteristics, which shrunk in the daytime and expanded in the nighttime. The maximum diameter was in the morning, while the minimum diameter was near the sunset. The growth rate of apple diameter was higher in the early growth period than near mature. The hourly and daily mean apple diameters were moderately or highly-positive correlated with soil temperature and soil moisture, while there was a highly-negative correlation with UVI. The daily mean increase (FMDG), daily increase (FDG), and maximum daily shrinkage (MDFS) of apple diameter had a weak negative correlation with 60 cm soil temperature as well as 20 and 40 cm soil moisture (-0.5≤R<-0.3). The simulation accuracy of the LSTM model was significantly higher than that of MLR, DT and RF model. The correlation coefficient (R) of LSTM model increased (3% -20%) compared with MLR, and the RMSE and MAE were approximately decreased by 50%-75%. The machine learning methods showed relatively poor performance in apple diameter simulation and might have overfitting problems. 【Conclusion】 Compared to statistics and machine learning approaches, the LSTM model demonstrated higher accuracy and robust performance because of the incapability of considering the complex non-linear correlations in the fruit growth simulation.

Key words: apple diameter, growth model, meteorological factors, deep learning, Long Short-Term Memory (LSTM)

SUN Qing,ZHAO YanXia,CHENG JinXin,ZENG TingYu,ZHANG Yi. Fruit Growth Modelling Based on Multi-Methods - A Case Study of Apple in Zhaotong, Yunnan[J].Scientia Agricultura Sinica, 2021, 54(17): 3737-3751.

0
/ / Recommend

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: https://www.chinaagrisci.com/EN/10.3864/j.issn.0578-1752.2021.17.015

https://www.chinaagrisci.com/EN/Y2021/V54/I17/3737

Figures/Tables 8

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

References 35

[1]	王顺富, 张丹, 夏敏, 王成轶, 刘毅, 邓芳, 杨艳群, 郎平勇, 全勇, 李云国. 昭通苹果产业助推脱贫攻坚的经验及成效. 云南农业大学学报(社会科学版), 2020, 14(6): 36-41.
	WANG S F, ZHANG D, XIA M, WANG C Y, LIU Y, DENG F, YANG Y Q, LANG P Y, QUAN Y, LI Y G. The experience and effectiveness of apple industry in promoting poverty alleviation program in Zhaotong. Journal of Yunnan Agricultural University (Social Science), 2020, 14(6): 36-41. (in Chinese)
[2]	周桂华, 吴惠标. 2016年云南主要自然灾害特点及减灾对策研究. 灾害学, 2017, 32(3): 112-119.
	ZHOU G H, WU H B. 2016 Yunnan major natural disasters and the characteristics of the mitigation measures research. Journal of Catastrophology, 2017, 32(3): 112-119. (in Chinese)
[3]	CONEJERO W, ALARCÓN J J, GARCÍA-ORELLANA Y, ABRISQUETA J M, TORRECILLAS A. Daily sap flow and maximum daily trunk shrinkage measurements for diagnosing water stress in early maturing peach trees during the post-harvest period. Tree Physiology, 2007, 27(1): 81-88. doi: 10.1093/treephys/27.1.81
[4]	陈毓瑾, 陈立, 娄玉穗, 秦泽冠, 董肖, 马超, 苗玉彬, 张才喜, 许文平, 王世平. 基于新梢直径和果粒投影面积变化确定‘巨峰’葡萄果实发育期的灌溉阈值. 果树学报, 2019, 36(5): 612-620.
	CHEN Y J, CHEN L, LOU Y S, QIN Z G, DONG X, MA C, MIAO Y B, ZHANG C X, XU W P, WANG S P. Determination of thresholds to trigger irrigation of ‘Kyoho’ grapevine during berry development periods based on variations of shoot diameter and berry projected area. Journal of Fruit Science, 2019, 36(5): 612-620. (in Chinese)
[5]	王国栋, 肖元松, 彭福田, 张亚飞, 郜怀峰, 孙希武, 贺月. 尿素配施不同用量纳米碳对桃幼树生长及氮素吸收利用的影响. 中国农业科学, 2018, 51(24): 4700-4709.
	WANG G D, XIAO Y S, PENG F T, ZHANG Y F, GAO H F, SUN X W, HE Y. Effects of urea application combined with different amounts of nano-carbon on plant growth along with nitrogen absorption and utilization in young peach trees. Scientia Agricultura Sinica, 2018, 51(24): 4700-4709. (in Chinese)
[6]	王晓森, 孟兆江, 段爱旺, 刘祖贵. 基于茎直径变化监测番茄水分状况的机理与方法. 农业工程学报, 2010, 26(12): 107-113.
	WANG X S, MENG Z J, DUAN A W, LIU Z G. Mechanism and methodology for monitoring tomato water content based on stem diameter variation. Transactions of the Chinese Society of Agricultural Engineering, 2010, 26(12): 107-113. (in Chinese)
[7]	林琭, 汤昀, 闫万丽, 张纪涛, 籍增顺. 基于茎直径变化的精准灌溉技术研究进展. 农业工程学报, 2016, 32(5): 1-13.
	LIN L, TANG Y, YAN W L, ZHANG J T, JI Z S. Overview of precise irrigation scheduling based on stem diameter variations. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(5): 1-13. (in Chinese)
[8]	贺琦琦, 郭向红, 杨凯, 石美娟, 马娟娟, 孙西欢, 雷涛, 刘艳武. 滴灌灌施磷钾肥对矮砧苹果树生理生长和产量的影响. 节水灌溉, 2019(8): 24-27.
	HE Q Q, GUO X H, YANG K, SHI M J, MA J J, SUN X H, LEI T, LIU Y W. Effects of phosphorus and potassium fertilizer on physiological growth and yield of dwarf rootstock apple trees under drip irrigation. Water Saving Irrigation, 2019(8): 24-27. (in Chinese)
[9]	高木旺, 聂佩显, 孙滢, 姜远茂, 张金春, 张继祥. 避雨环境下苹果幼树水分状态指标对干旱胁迫的响应. 应用生态学报, 2016, 27(8): 2459-2466.
	GAO M W, NIE P X, SUN Y, JIANG Y M, ZHANG J C, ZHANG J X. Response of water status indicators in apple saplings to drought stress under shelter from rain. Chinese Journal of Applied Ecology, 2016, 27(8): 2459-2466. (in Chinese)
[10]	夏桂敏, 孙媛媛, 王玮志, 吴奇, 迟道才. ‘寒富’苹果树茎流特征及其对环境因子的响应. 中国农业科学, 2019, 52(4): 701-714.
	XIA G M, SUN Y Y, WANG W Z, WU Q, CHI D C. The characteristics of sap flow of Hanfu apple trees and its response to environmental factors. Scientia Agricultura Sinica, 2019, 52(4): 701-714. (in Chinese)
[11]	LI M, CHEN M X, ZHANG Y, FU C X, XING B, LI W Y, QIAN J P, LI S, WANG H, FAN X D, YAN Y J, WANG Y A, YANG X T. Apple fruit diameter and length estimation by using the thermal and sunshine hours approach and its application to the digital orchard management information system. PLoS ONE, 2015, 10(4): e0120124. doi: 10.1371/journal.pone.0120124
[12]	张海辉, 田世杰, 马敏娟, 赵娟, 张军华, 张佐经. 考虑直径影响的苹果霉心病透射光谱修正及检测. 农业机械学报, 2019, 50(1): 313-320.
	ZHANG H H, TIAN S J, MA M J, ZHAO J, ZHANG J H, ZHANG Z J. Detection method of moldy core in apples using modified transmission spectrum based on size of fruit. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(1): 313-320. (in Chinese)
[13]	张彪, 刘璇, 毕金峰, 吴昕烨, 金鑫, 李旋, 李潇. 基于BP人工神经网络算法的苹果制干适宜性评价. 中国农业科学, 2019, 52(1): 129-142.
	ZHANG B, LIU X, BI J F, WU X Y, JIN X, LI X, LI X. Suitability evaluation of apple for chips-processing based on BP artificial neural network. Scientia Agricultura Sinica, 2019, 52(1): 129-142. (in Chinese)
[14]	陈舒蕴. 基于LSTM多类型机组风电场等值建模研究. 山东农业大学学报(自然科学版), 2020, 51(2): 294-297.
	CHEN S Y. Study on the equivalent modeling of wind power farm based on LSTM multi-type wind turbine generators. Journal of Shandong Agricultural University (Natural Science Edition), 2020, 51(2): 294-297. (in Chinese)
[15]	王子文. 基于深度学习和模糊决策的苹果自动分拣方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2019.
	WANG Z W. Use of deep learning and fuzzy decision making in automated sorting of apple[D]. Harbin: Harbin Institute of Technology, 2019. (in Chinese)
[16]	SUN X D, WU P C, HOI S C H. Face detection using deep learning: an improved faster RCNN approach. Neurocomputing, 2018, 299: 42-50. doi: 10.1016/j.neucom.2018.03.030
[17]	XUE W D, CHAI Y, LI Q G, HONG Y Q, ZHENG G F. Short-term relay quality prediction algorithm based on long and short-term memory. Instrumentation, 2018, 5(4): 46-54.
[18]	LI P, LI X, PAN H, KHYAM O, NOOR-A-RAHIM M. Text-based indoor place recognition with deep neural network. Neurocomputing, 2020, 390: 239-247. doi: 10.1016/j.neucom.2019.02.065
[19]	沈利言, 姜海燕, 胡滨, 谢元澄. 水稻病虫草害与药剂实体关系联合抽取算法. 南京农业大学学报, 2020, 43(6): 1151-1161.
	SHEN L Y, JIANG H Y, HU B, XIE Y C. A study on joint entity recognition and relation extraction for rice diseases pests weeds and drugs. Journal of Nanjing Agricultural University, 2020, 43(6): 1151-1161. (in Chinese)
[20]	郑艳梅, 黄光耀, 芦碧波, 王永茂. 结合深度学习和引导滤波的苹果叶片图像分割. 中国农业大学学报, 2020, 25(9): 112-120.
	ZHENG Y M, HUANG G Y, LU B B, WANG Y M. An apple leaf image segmentation algorithm using deep learning and guided filtering. Journal of China Agricultural University, 2020, 25(9): 112-120. (in Chinese)
[21]	曲之琳. 深度学习网络在苹果表面病变图像识别中的应用[D]. 南京: 南京邮电大学, 2017.
	QU Z L. Application of deep learning network in recognition of apple surface lesions[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2017. (in Chinese)
[22]	MTIBAA F, NGUYEN K K, AZAM M, PAPACHRISTOU A, VENNE J S, CHERIET M. LSTM-based indoor air temperature prediction framework for HVAC systems in smart buildings. Neural Computing and Applications, 2020, 32(23): 17569-17585. doi: 10.1007/s00521-020-04926-3
[23]	BLANQUERO R, CARRIZOSA E, MOLERO-RIO C, MORALES D R. Sparsity in optimal randomized classification trees. 2020, 284(1): 255-272.
[24]	BREIMAN L. Random Forests. Machine Learning, 2001, 45(1): 5-32. doi: 10.1023/A:1010933404324
[25]	GISLASON P O, BENEDIKTSSON J A, SVEINSSON J R. Random Forests for land cover classification. Pattern Recognition Letters, 2006, 27(4): 294-300. doi: 10.1016/j.patrec.2005.08.011
[26]	DE ANDRADE C F, DELGADO R C, BARBOSA M L, TEODORO P E, DA SILVA J C A, WANDERLEY H S, CAPRISTO-SILVA G F. Fire regime in Southern Brazil driven by atmospheric variation and vegetation cover. Agricultural and Forest Meteorology, 2020, 295: 108194. doi: 10.1016/j.agrformet.2020.108194
[27]	MUKAKA M M. Statics corner: A guide to appropriate use of correlation coefficient in medical research. Malawi Medical Journal, 2012, 24(3): 69-71.
[28]	VAJSOVÁ B, FASBENDER D, WIRNHARDT C, LEMAJIC S, DEVOS W. Assessing spatial limits of Sentinel-2 data on arable crops in the context of checks by monitoring. Remote Sensing, 2020, 12(14): 2195. doi: 10.3390/rs12142195
[29]	LIU C W, KANG S Z, LI F S, LI S E, DU T S, TONG L. Relationship between environmental factor and maximum daily stem shrinkage in apple tree in arid region of northwest China. Scientia Horticulturae, 2011, 130(1): 118-125. doi: 10.1016/j.scienta.2011.06.022
[30]	ORTUNO M F, CONEJERO W, MORENO F, MORIANA A, INTRIGLIOLO D S, BIEL C, MELLISHO C D, PEREZ-PASTOR A, DOMINGO R, RUIZ-SANCHEZ M C, CASADESUS J, BONANY J, TORRECILLAS A. Could trunk diameter sensors be used in woody crops for irrigation scheduling? A review of current knowledge and future perspectives. Agricultural Water Management, 2010, 97(1): 1-11. doi: 10.1016/j.agwat.2009.09.008
[31]	EGEA G, PAGÁN E, BAILLE A, DOMINGO R, NORTES P A, PÉREZ-PASTOR A. Usefulness of establishing trunk diameter based reference lines for irrigation scheduling in almond trees. Irrigation Science, 2009, 27(6): 431-441. doi: 10.1007/s00271-009-0157-0
[32]	BERMAN M E, DEJONG T M. Seasonal patterns of vegetative growth and competition with reproductive sinks in peach (Prunus persica). The Journal of Horticultural Science and Biotechnology, 2003, 78(3): 303-309. doi: 10.1080/14620316.2003.11511622
[33]	孙红, 李松, 李民赞, 刘豪杰, 乔浪, 张瑶. 农业信息成像感知与深度学习应用研究进展. 农业机械学报, 2020, 51(5): 1-17.
	SUN H, LI S, LI M Z, LIU H J, QIAO L, ZHANG Y. Research progress of image sensing and deep learning in agriculture. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(5): 1-17. (in Chinese)
[34]	邵泽中, 姚青, 唐健, 李罕琼, 杨保军, 吕军, 陈轶. 面向移动终端的农业害虫图像智能识别系统的研究与开发. 中国农业科学, 2020, 53(16): 3257-3268.
	SHAO Z Z, YAO Q, TANG J, LI H Q, YANG B J, LV J, CHEN Y. Research and development of the intelligent identification system of agricultural pests for mobile terminals. Scientia Agricultura Sinica, 2020, 53(16): 3257-3268. (in Chinese)
[35]	刘慧芳, 贺正, 贾彪, 刘志, 李振洲, 付江鹏, 慕瑞瑞, 康建宏. 基于机器学习的滴灌玉米光合响应特征. 中国农业科学, 2019, 52(17): 2939-2950.
	LIU H F, HE Z, JIA B, LIU Z, LI Z Z, FU J P, MU R R, KANG J H. Photosynthetic response characteristics of maize under drip irrigation based on machine learning. Scientia Agricultura Sinica, 2019, 52(17): 2939-2950. (in Chinese)

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

Fruit Growth Modelling Based on Multi-Methods - A Case Study of Apple in Zhaotong, Yunnan

RichHTML

PDF

Abstract

Cite this article

share this article

Figures/Tables 8

References 35

Related Articles 13

Metrics

Comments

Recommended 0

[1]	FENG XiangQian,YIN Min,WANG MengJia,MA HengYu,CHU Guang,LIU YuanHui,XU ChunMei,ZHANG XiuFu,ZHANG YunBo,WANG DanYing,CHEN Song. Effects of Meteorological Factors on Quality of Late Japonica Rice During Late Season Grain Filling Stage Under ‘Early Indica and Late Japonica’ Cultivation Pattern in Southern China [J]. Scientia Agricultura Sinica, 2023, 56(1): 46-63.
[2]	YU WeiBao,LI Nan,KOU YiHong,CAO XinYou,SI JiSheng,HAN ShouWei,LI HaoSheng,ZHANG Bin,WANG FaHong,ZHANG HaiLin,ZHAO Xin,LI HuaWei. Study on the Quality Parameters of Strong Gluten Wheat and Analysis of Its Relationship with Meteorological Factors in Shandong Province [J]. Scientia Agricultura Sinica, 2022, 55(22): 4383-4397.
[3]	XIAO LiuJun,LIU LeiLei,QIU XiaoLei,TANG Liang,CAO WeiXing,ZHU Yan,LIU Bing. Testing the Responses of Low Temperature Stress Routine to Low Temperature Stress at Jointing and Booting in Wheat [J]. Scientia Agricultura Sinica, 2021, 54(3): 504-521.
[4]	ZHU Yan,TANG Liang,LIU LeiLei,LIU Bing,ZHANG XiaoHu,QIU XiaoLei,TIAN YongChao,CAO WeiXing. Research Progress on the Crop Growth Model CropGrow [J]. Scientia Agricultura Sinica, 2020, 53(16): 3235-3256.
[5]	LIU QingFei, ZHANG HongLi, WANG YanLing. Real-Time Pixel-Wise Classification of Agricultural Images Based on Depth-Wise Separable Convolution [J]. Scientia Agricultura Sinica, 2018, 51(19): 3673-3682.
[6]	LI ShuQin, ZHU YePing, LIU HaiLong, LI ShiJuan, LIU ShengPing, ZHANG HongYing, GAO Wei. 3D Shape Simulation of Winter Wheat after Turning Green Stage Based on Effective Accumulated Temperature [J]. Scientia Agricultura Sinica, 2017, 50(9): 1594-1605.
[7]	WANG Ying-1, 2 , 3 , WANG Liang-Gui-3, HUANG Cheng-Ming-4, LI Yu-Fan-1, 3 , YUAN Su-Xia-1, LIU Chun-1, MING Jun-1. Growth Regularity and Bulb Propagation Techniques of Lilies in Open Field [J]. Scientia Agricultura Sinica, 2014, 47(8): 1558-1566.
[8]	CAO Hong-Xin, ZHAO Suo-Lao, GE Dao-Kuo, LIU Yong-Xia, LIU Yan, SUN Jin-Ying, YUE Yan-Bin, ZHANG Zhi-You, CHEN Yu-Li. Discussion on Development of Crop Models [J]. Scientia Agricultura Sinica, 2011, 44(17): 3520-3528.
[9]	ZHAO Chun-jiang,LU Sheng-lian,GUO Xin-yu,XIAO Bo-xiang,WEN Wei-liang . Exploration of Digital Plant and Its Technology System [J]. Scientia Agricultura Sinica, 2010, 43(10): 2023-2030 .
[10]	CHEN Guo-qing,ZHANG Ji-wang,DONG Shu-ting. Visualization-Based Growth Simulation System for Super-Maize#br# [J]. Scientia Agricultura Sinica, 2009, 42(9): 3361-3367 .
[11]	,,. A Simulation Analysis on Geometrical Parameters of Rice Leaf Blade [J]. Scientia Agricultura Sinica, 2006, 39(05): 910-915 .
[12]	,,,. Analysis of Body Conformation and Fitting Growth Model in Tibetan Chicken Raised in Plain [J]. Scientia Agricultura Sinica, 2005, 38(05): 1065-1068 .
[13]	,,. Study on the Soil Erodibility Based on the Soil Particle-size [J]. Scientia Agricultura Sinica, 2004, 37(11): 1647-1653 .