基于多模态数据表型特征提取的番茄生长高度预测方法

doi:10.12133/j.smartag.SA202410032

Smart Agriculture ›› 2025, Vol. 7 ›› Issue (1): 97-110.doi: 10.12133/j.smartag.SA202410032

• 专题--农业知识智能服务和智慧无人农场（下） • 上一篇下一篇

基于多模态数据表型特征提取的番茄生长高度预测方法

宫宇¹^,², 王玲¹^,², 赵荣强¹^,²^,⁴(), 尤海波³, 周沫³, 刘劼¹^,²^,⁴

^1. 哈尔滨工业大学计算机科学与技术学院，黑龙江哈尔滨 150006，中国
^2. 智能农业技术与系统国家重点实验室，黑龙江哈尔滨 150080，中国
^3. 黑龙江省农业科学院园艺分院，黑龙江哈尔滨 150040，中国
^4. 哈尔滨工业大学人工智能研究院有限公司，黑龙江哈尔滨 150000，中国

收稿日期:2024-10-20 出版日期:2025-01-30
基金项目:
中央高校基本科研业务费专项资金(2023FRFK06013); 黑龙江省重点研发计划项目(2023ZX01A24); 哈尔滨工业大学横向项目(MH20240081)
作者简介:
宫宇，硕士研究生，研究方向为深度学习。E-mail：2419336982@qq.com
通信作者:
赵荣强，博士，副教授，研究方向为智能感知技术、图像及光谱图像处理、压缩感知、智慧农业、具身智能等。E-mail：zhaorq@hit.edu.cn

Tomato Growth Height Prediction Method by Phenotypic Feature Extraction Using Multi-modal Data

GONG Yu¹^,², WANG Ling¹^,², ZHAO Rongqiang¹^,²^,⁴(), YOU Haibo³, ZHOU Mo³, LIU Jie¹^,²^,⁴

^1. Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150006, China
^2. National Key Laboratory of Smart Farming Technology and Systems, Harbin 150080, China
^3. Horticultural Branch, Heilongjiang Academy of Agricultural Sciences, Harbin 150040, China
^4. Harbin Institute of Technology Research Institute for Artificial Intelligence Inc. , Harbin 150000, China

Received:2024-10-20 Online:2025-01-30
Foundation items:The Fundamental Research Funds for the Central Universities in China(2023FRFK06013); The Key Research and Development Program of Heilongjiang Province(2023ZX01A24); Harbin Institute of Technology Horizontal Project(MH20240081)
About author:
GONG Yu, E-mail: 2419336982@qq.com
Corresponding author:
ZHAO Rongqiang, E-mail: zhaorq@hit.edu.cn

摘要/Abstract

摘要：

【目的/意义】 准确预测番茄的生长高度对优化智能农业中的生产环境至关重要。然而，目前的预测方法大多依赖于经验模型、机制模型或基于学习的模型，这些模型主要利用图像数据或环境数据，未能充分利用多模态数据，无法全面捕捉植物生长的各个方面。 【方法】 为了解决这一限制，本研究提出了一种基于深度学习算法的两阶段表型特征提取（Phenotypic Feature Extraction, PFE）模型，该模型结合了番茄植物的环境信息和植物本身的信息，提供了对生长过程的全面理解。PFE模型采用表型特征和时间特征提取器，综合捕捉两类特征，从而深入理解番茄植物与环境之间的相互作用，最终实现对生长高度的高精度预测。 【结果和讨论】 实验结果表明，该模型具有显著效果：在基于过去五天数据预测接下来的两天时，PFE-RNN（Phenotypic Feature Extraction with Recurrent Neural Network）模型和PFE-LSTM（Phenotypic Feature Extraction with Long Short-Term Memory）模型的平均绝对百分比误差（Mean Absolute Percentage Error, MAPE）分别为0.81%和0.40%，显著低于大语言模型（Large language model, LLM）模型的8.00%和基于Transformer的模型的6.72%。在较长期预测中，PFE-RNN模型在10天预测4天后和30天预测12天后的表现持续优于其他两个基准模型，MAPE分别为2.66%和14.05%。 【结论】 所提出的基于表型-时间协同的预测方法展示了其在智能化、数据驱动的番茄种植管理中的巨大潜力，是提升智能番茄种植管理效率和精准度的一种有前景的方法。

关键词: 番茄生长预测, 深度学习, 表型特征提取, 多模态数据, 递归神经网络, 长短期记忆网络, 大语言模型

Abstract:

[Objective] Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming. However, current prediction methods predominantly rely on empirical, mechanistic, or learning-based models that utilize either images data or environmental data. These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively. [Methods] To address this limitation, a two-stage phenotypic feature extraction (PFE) model based on deep learning algorithm of recurrent neural network (RNN) and long short-term memory (LSTM) was developed. The model integrated environment and plant information to provide a holistic understanding of the growth process, emploied phenotypic and temporal feature extractors to comprehensively capture both types of features, enabled a deeper understanding of the interaction between tomato plants and their environment, ultimately leading to highly accurate predictions of growth height. [Results and Discussions] The experimental results showed the model's effectiveness: When predicting the next two days based on the past five days, the PFE-based RNN and LSTM models achieved mean absolute percentage error (MAPE) of 0.81% and 0.40%, respectively, which were significantly lower than the 8.00% MAPE of the large language model (LLM) and 6.72% MAPE of the Transformer-based model. In longer-term predictions, the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead, the PFE-RNN model continued to outperform the other two baseline models, with MAPE of 2.66% and 14.05%, respectively. [Conclusions] The proposed method, which leverages phenotypic-temporal collaboration, shows great potential for intelligent, data-driven management of tomato cultivation, making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.

Key words: tomato growth prediction, deep learning, phenotypic feature extraction, multi-modal data, recurrent neural network, long short-term memory, large language model

中图分类号:

TP181

宫宇, 王玲, 赵荣强, 尤海波, 周沫, 刘劼. 基于多模态数据表型特征提取的番茄生长高度预测方法[J]. 智慧农业(中英文), 2025, 7(1): 97-110.

GONG Yu, WANG Ling, ZHAO Rongqiang, YOU Haibo, ZHOU Mo, LIU Jie. Tomato Growth Height Prediction Method by Phenotypic Feature Extraction Using Multi-modal Data[J]. Smart Agriculture, 2025, 7(1): 97-110.

图/表 21

参考文献 31

1	QUINET M, ANGOSTO T, YUSTE-LISBONA F J, et al. Tomato fruit development and metabolism[J]. Frontiers in plant science, 2019, 10: ID 1554.
2	PASLEY H, BROWN H, HOLZWORTH D, et al. How to build a crop model. A review[J]. Agronomy for sustainable development, 2022, 43(1): ID 2.
3	JONES J W, DAYAN E, ALLEN L H, et al. A dynamic tomato growth and yield model (tomgro)[J]. Transactions of the ASAE, 1991, 34(2): 663-672.
4	AMTHOR J S. After photosynthesis, what then: Importance of respiration to crop growth and yield[J]. Field crops research, 2025, 321: ID 109638.
5	HAN KUNLIN, WANG ZHAOYING, YANG HUIMIN, et al. Prediction model of tomato fruit diameter in greenhouse based on PCA-BPNN[J]. Xinjiang agricultural sciences, 2022, 59(2): 485-492.
6	ZHANG M, LI T, JI Y H, et al. Optimization of CO₂ enrichment strategy based on BPNN for tomato plants in greenhouse[J]. Transactions of the Chinese society for agricultural machinery, 2015, 46(8): 239-245.
7	CHEN B, OUYANG Z. Prediction of winter wheat evapotranspiration based on BP neural networks[J]. Transactions of the Chinese society of agricultural engineering, 2010, 26(4): 81-86.
8	HAN L, LI R, ZHU H L. Comprehensive evaluation model of soil nutrient based on BP neural network[J]. Transactions of the Chinese society for agricultural machinery, 2011, 42(7): 109-115.
9	TIAN X Q, ZHU X J. Loop control stategies of CO₂ concentration based on BPNN for Pleurotus eryngii in a factory farm[J]. Edible fungi of China, 2016, 35(2): 46-49, 53.
10	CHEN D J, SHI R L, PAPE J M, et al. Predicting plant biomass accumulation from image-derived parameters[J]. GigaScience, 2018, 7(2): ID giy001.
11	YANG H, HUANG C, LIU X R, et al. Convolutional neural networksed feature extraction for non-destructive lettuce growth monitoring[J]. Computer technology and development, 2023, 33(8): 137-143.
12	CHANDEL N S, CHAKRABORTY S K, RAJWADE Y A, et al. Identifying crop water stress using deep learning models[J]. Neural computing and applications, 2021, 33(10): 5353-5367.
13	YALCIN H. An approximation for A relative crop yield estimate from field images using deep learning[C]// 2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics). Piscataway, New Jersey, USA: IEEE, 2019.
14	BALI N S, SINGLA A. Deep learning based wheat crop yield prediction model in punjab region of north India[J]. Applied artificial intelligence, 2021, 35(15): 1304-1328.
15	NIGAM A, GARG S, AGRAWAL A, et al. Crop yield prediction using machine learning algorithms[C]// 2019 Fifth International Conference on Image Information Processing (ICIIP). Piscataway, New Jersey, USA: IEEE, 2019.
16	ELAVARASAN D, DURAIRAJ VINCENT P M. Crop yield prediction using deep reinforcement learning model for sustainable agrarian applications[J]. IEEE access, 2020, 8: 86886-86901.
17	DE ALWIS S, ZHANG Y S, NA M, et al. Duo attention with deep learning on tomato yield prediction and factor interpretation[M]// PRICAI 2019: Trends in Artificial Intelligence. Cham: Springer International Publishing, 2019: 704-715.
18	ZHOU X H, LIU Q Z, KATZIN D, et al. Boosting the prediction accuracy of a process-based greenhouse climate-tomato production model by particle filtering and deep learning[J]. Computers and electronics in agriculture, 2023, 211: ID 107980.
19	OIKONOMIDIS A, CATAL C, KASSAHUN A. Deep learning for crop yield prediction: A systematic literature review[J]. New Zealand journal of crop and horticultural science, 2023, 51(1): 1-26.
20	WANG P X, TIAN H R, ZHANG Y, et al. Crop growth monitoring and yield estimation based on deep learning: State of the art and beyond[J]. Transactions of the Chinese society for agricultural machinery, 2022, 53(2): 1-14.
21	GONG L Y, YU M, JIANG S Y, et al. Deep learning based prediction on greenhouse crop yield combined TCN and RNN[J]. Sensors, 2021, 21(13): ID 4537.
22	XING H M, XU X G, LI Z H, et al. Global sensitivity analysis of the AquaCrop model for winter wheat under different water treatments based on the extended Fourier amplitude sensitivity test[J]. Journal of integrative agriculture, 2017, 16(11): 2444-2458.
23	MAIMAITIJIANG M, SAGAN V, SIDIKE P, et al. Soybean yield prediction from UAV using multimodal data fusion and deep learning[J]. Remote sensing of environment, 2020, 237: ID 111599.
24	YANG Y, WEI X B, WANG J, et al. Prediction of seedling oilseed rape crop phenotype by drone-derived multimodal data[J]. Remote sensing, 2023, 15(16): ID 3951.
25	LIN Z X, FU R M, REN G Q, et al. Automatic monitoring of lettuce fresh weight by multi-modal fusion based deep learning[J]. Frontiers in plant science, 2022, 13: ID 980581.
26	TAN K. Large language models for crop yield prediction[EB/OL]. [2025-10-11].
27	ANAMI B S, MALVADE N N, PALAIAH S. Deep learning approach for recognition and classification of yield affecting paddy crop stresses using field images[J]. Artificial intelligence in agriculture, 2020, 4: 12-20.
28	JIANG H H, ZHANG C Y, QIAO Y L, et al. CNN feature based graph convolutional network for weed and crop recognition in smart farming[J]. Computers and electronics in agriculture, 2020, 174: ID 105450.
29	SHARMA R, DAS S, GOURISARIA M K, et al. A model for prediction of paddy crop disease using CNN[M]// Progress in Computing, Analytics and Networking. Singapore: Springer Singapore, 2020: 533-543.
30	TANG Q, LIANG J, ZHU F Q. A comparative review on multi-modal sensors fusion based on deep learning[J]. Signal processing, 2023, 213: ID 109165.
31	YU Y, SI X S, HU C H, et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural computation, 2019, 31(7): 1235-1270.

	KNO₃/g	NH₄H₂PO₄/g	KH₂PO₄/g	K₂SO₄/g	MgSO₄·7H₂O/g	CaCl₂/g	CaNO₃·4H₂O/g
CK	0.0	0.0	27.2	52.3	24.6	44.4	0.0
T₁	13.4	7.7	0.0	34.8	24.6	44.4	0.0
T₂	26.9	7.7	0.0	17.4	24.6	44.4	0.0
T₃	40.4	7.7	0.0	0.0	24.6	44.4	0.0
T₄	40.4	7.7	0.0	0.0	24.6	29.6	11.8
T₅	40.4	7.7	0.0	0.0	24.6	14.8	23.6
T₆	40.4	7.7	0.0	0.0	24.6	0.0	35.4

Molecular	Molecular weight standard concentration/（mg/L）
FeSO₄·7H₂O	13.206
EDTA·H₂O	17.679
EDTA·3H₂O	20.000
MnSO₄·H₂O	1.614
MnSO₄· 4H₂O	2.130
H₃BO₃	2.860
ZnSO₄·7H₂O	0.220
CuSO₄·5H₂O	0.080
Na₂MO₄·2H₂O	0.020

Network Structure	Parameters
Convolutional kernel	3×3
Convolutional stride	1
Convolutional padding	1
Pooling kernel	2×2
Pooling stride	2
Fully connected input	16×300×300
Fully connected output	16

Network structure	Parameters
Input features	34
RNN hidden size	30
RNN layers	2
Learning rate	0.001
Loss function	MSE_Loss
Optimizer	Adam

RNN network layers	Hidden layer size	Prediction scenario
		Short-term prediction		Mid-term prediction		Long-term prediction
		MSE	MAPE/%	MSE	MAPE/%	MSE	MAPE/%
2	15	6.89	2.16	55.21	6.03	113.17	6.74
	20	1.89	1.25	68.13	6.87	288.93	10.81
	25	2.11	1.11	56.51	5.41	297.91	10.85
	30	3.09	1.87	56.78	4.83	236.51	10.12
3	15	6.03	2.01	21.09	2.82	388.68	11.26
	20	1.52	1.07	27.53	4.11	180.16	7.14
	25	3.07	1.74	46.15	6.36	165.09	6.51
	30	2.49	1.50	60.96	6.71	203.26	8.26

基于多模态数据表型特征提取的番茄生长高度预测方法

Tomato Growth Height Prediction Method by Phenotypic Feature Extraction Using Multi-modal Data

在线阅读

知网下载

本地下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 21

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价

Prediction scenario	Average accuracy/%	Last day accuracy/%	Average percentage error/%	Last day average percentage error/%	R ²
Short-term prediction	91.67	91.67	0.81	0.83	0.999 678
Mid-term prediction	88.54	87.50	2.66	3.11	0.991 119
Long-term prediction	70.37	66.67	14.05	16.63	-0.041 393

Network structure	Parameters
Input features	34
LSTM hidden size	30
LSTM layers	2
Learning rate	0.001
Loss function	MSE_Loss
Optimizer	Adam

LSTM network layers	Hidden layer size	Prediction scenario
		Short-term prediction		Mmid-term prediction		Long-term prediction
		MSE	MAPE/%	MSE	MAPE/%	MSE	MAPE/%
2	15	1.48	0.96	121.90	8.44	153.98	7.61
	20	3.27	1.33	104.02	7.99	204.30	8.82
	25	0.57	0.88	88.01	6.63	254.83	9.67
	30	3.85	2.24	119.26	8.42	188.33	8.56
3	15	0.21	0.54	81.72	7.60	547.96	15.03
	20	1.56	1.44	105.02	8.89	286.87	10.56
	25	0.91	0.99	87.00	7.09	286.13	8.62
	30	0.34	0.73	98.91	7.16	172.19	6.54

Prediction scenario	Average accuracy/%	Last day accuracy/%	Average percentage error/%	Last day average percentage error/%	R ²
Short-term prediction	97.92	97.92	0.40	0.38	0.999 901
Mid-term prediction	53.13	41.67	6.36	7.72	0.965 263
Long-term prediction	50.93	33.33	14.49	19.48	-0.277 455

Model	Prediction scenario	MAPE/%	MSE	Last day MAPE/%
PFE-RNN	Short-term prediction	0.81	0.56	0.83
	Mid-term prediction	2.66	17.04	3.11
	Long-term prediction	14.05	651.35	16.63
PFE-LSTM	Short-term prediction	0.40	0.12	0.38
	Mid-term prediction	6.36	82.54	7.72
	Long-term prediction	14.49	696.22	19.48
Transformer	Short-term prediction	6.72	74.71	6.33
Transformer	Mid-term prediction	10.29	144.62	9.65
LLM	Short-term prediction	8.00	588.26	7.90
LLM	Mid-term prediction	27.43	4 067.70	28.93

[1]	吴华瑞, 李静晨, 杨雨森. 基于大语言模型的个性化作物水肥管理智能决策方法[J]. 智慧农业(中英文), 2025, 7(1): 11-19.
[2]	许世卫, 李乾川, 栾汝朋, 庄家煜, 刘佳佳, 熊露. 农产品市场监测预警深度学习智能预测方法[J]. 智慧农业(中英文), 2025, 7(1): 57-69.
[3]	姜京池, 闫莲, 刘劼. 基于精准知识筛选及知识协同生成的农业大语言模型[J]. 智慧农业(中英文), 2025, 7(1): 20-32.
[4]	齐梓均, 牛当当, 吴华瑞, 张礼麟, 王仑峰, 张宏鸣. 基于双维信息与剪枝的中文猕猴桃文本命名实体识别方法[J]. 智慧农业(中英文), 2025, 7(1): 44-56.
[5]	吴华瑞, 赵春江, 李静晨. 基于多模态融合大模型架构Agri-QA Net的作物知识问答系统[J]. 智慧农业(中英文), 2025, 7(1): 1-10.
[6]	张辉, 胡军, 石航, 刘昶希, 吴淼. 融合远端深度学习识别模型的白菜株心精准对靶喷雾系统[J]. 智慧农业(中英文), 2024, 6(6): 85-95.
[7]	芦碧波, 梁迪, 杨洁, 宋爱青, 皇甫尚卫. 基于改进ENet的复杂背景下山药叶片图像分割方法[J]. 智慧农业(中英文), 2024, 6(6): 109-120.
[8]	赵春江, 李静晨, 吴华瑞, 杨雨森. 基于大语言模型推理的数字孪生平台蔬菜作物生长模型研究[J]. 智慧农业(中英文), 2024, 6(6): 63-71.
[9]	罗友璐, 潘勇浩, 夏顺兴, 陶友志. 基于改进YOLOv8的苹果叶病害轻量化检测算法[J]. 智慧农业(中英文), 2024, 6(5): 128-138.
[10]	刘伊, 张彦军. ReluformerN：轻量化高低频增强高光谱农业地物分类方法[J]. 智慧农业(中英文), 2024, 6(5): 74-87.
[11]	年悦, 赵凯旋, 姬江涛. 基于改进DeepLabCut模型的奶牛滑蹄检测方法[J]. 智慧农业(中英文), 2024, 6(5): 153-163.
[12]	张岩琪, 周硕, 张凝, 柴秀娟, 孙坦. 基于改进实例分割算法的区域养殖生猪计数系统[J]. 智慧农业(中英文), 2024, 6(4): 53-63.
[13]	翁智, 范琦, 郑志强. 基于多模态图像信息及改进实例分割网络的肉牛体尺自动测量方法[J]. 智慧农业(中英文), 2024, 6(4): 64-75.
[14]	侯依廷, 饶元, 宋贺, 聂振君, 王坦, 何豪旭. 复杂大田场景下基于改进YOLOv8的小麦幼苗期叶片数快速检测方法[J]. 智慧农业(中英文), 2024, 6(4): 128-137.
[15]	李豪, 杜雨秋, 肖星竹, 陈彦羲. 基于深度学习的四川盆地丘陵区县域耕地遥感识别研究[J]. 智慧农业(中英文), 2024, 6(3): 34-45.

RNN network layers	Hidden layer size	Prediction scenario
		Short-term prediction		Mid-term prediction		Long-term prediction
		MSE	MAPE/%	MSE	MAPE/%	MSE	MAPE/%
2	15	10.26	2.61	25.04	3.18	386.39	10.01
	20	10.82	2.62	126.04	7.70	354.20	8.61
	25	10.38	2.5	30.03	3.88	546.32	11.57
	30	12.99	2.36	18.98	2.99	425.85	11.87
3	15	6.83	1.64	37.67	3.79	405.23	10.71
	20	8.14	2.13	1 532.62	22.76	1 140.67	17.18
	25	31.33	5.41	144.03	8.28	432.18	10.94
	30	14.63	2.95	16.78	2.27	672.64	13.62

LSTM network layers	Hidden layer size	Prediction scenario
		Short-term prediction		Mid-term prediction		Long-term prediction
		MSE	MAPE/%	MSE	MAPE/%	MSE	MAPE/%
2	15	6.68	1.83	31.11	3.39	802.94	15.17
	20	2.99	1.40	18.01	2.56	378.78	9.44
	25	6.59	2.22	39.56	4.25	486.95	11.55
	30	5.15	1.52	30.60	3.43	358.90	9.49
3	15	3.79	1.37	37.67	3.79	870.38	15.67
	20	3.89	1.39	21.53	2.84	507.24	10.95
	25	3.41	1.40	30.07	3.58	485.04	11.79
	30	7.01	1.74	153.36	7.81	385.27	8.66