Author(s)

WenLiang Hou^*, ZhiPeng He, JieWen Gu, JiaLin Zhang, JiaoYing Li

Affiliation(s)

College of Information and Electrical Engineering, Heilongjiang Bayi Agricultural University, Daqing 163319, Heilongjiang, China.

Corresponding Author

WenLiang Hou

ABSTRACT

To address the issues of low soybean self-sufficiency and drought - related production constraints, multispectral imaging can non - invasively detect crop characteristics, while deep convolutional networks identify drought from multispectral images. However, large models face mobility limitations due to high computational requirements.This study presents a mobile detection approach integrating ReliefF feature screening and lightweight convolutional neural networks, and develops the "Early Acknowledgment for Soybean Drought" App. It embeds a lightweight model that optimizes 37 - dimensional soybean canopy multispectral features via ReliefF and uses a three - layer 1D convolutional network for drought identification.The model achieves 96.88% classification accuracy on the self - built dataset, with an inference time of 18 ms, a size under 30 MB, and less than 60 MB memory usage on mobile. The APP integrates the multispectral camera SDK and PyTorch inference engine, enabling real - time spectral analysis. Field tests show its one - button operation, low learning curve for farmers, and significant water - saving and yield - increasing effects, offering a lightweight, high - precision mobile solution for soybean drought management and promoting smart agriculture development.

KEYWORDS

Soybean drought; Multispectral image; Feature screening; Recognition model; Mobile app

CITE THIS PAPER

WenLiang Hou, ZhiPeng He, JieWen Gu, JiaLin Zhang, JiaoYing Li. Drought recognition for the soybean plant based on lightweight deep learning model. Journal of Computer Science and Electrical Engineering. 2025, 7(4): 17-24. DOI: https://doi.org/10.61784/jcsee3063.

REFERENCES

[1] Li Hefeng. Steady increase of domestic soybean production capacity and self-sufficiency. Economic Daily News, 2024-11-22(006). DOI: 10.28425/n.cnki.njjrb.2024.008771.

[2] Shen Panpan. Research on the calculation method of soybean canopy wilt index based on multispectral image processing. Heilongjiang Bayi Nongken University, 2023. DOI:10.27122/d.cnki.ghlnu.2023.000122.

[3] Haoxin Song. Research on citrus information extraction from UAV multispectral images based on deep learning. Guilin University of Technology, 2023. DOI: 10.27050/d.cnki.ghlgc.2023.001051.

[4] Gao Shijiao, Guan Haiou, Ma Xiaodan, et al. A multispectral image extraction method for soybean canopy. Spectroscopy and Spectral Analysis, 2022, 42(11): 3568-3574.

[5] Fu Hongyu, Wang Wei, Lu Jianning, et al. Estimation of physical and chemical traits of ramie based on multi-spectral remote sensing by unmanned aircraft and machine learning. Journal of Agricultural Machinery, 2023, 54(05): 194-200+347.

[6] Fan Xuexing, Zhang Huichun, Zou Yiping, et al. Inversion of plant chlorophyll content based on multispectral imaging and machine learning. Forestry Science, 2023, 59(07): 78-88.

[7] Han Wenting, Cui Jiawei, Cui Xin, et al. Research on salinity estimation of agricultural soil based on feature optimization and machine learning. Journal of Agricultural Machinery, 2023, 54(03): 328-337.

[8] Huang Linsheng, Shao Song, Lu Xianju, et al. Multispectral image segmentation and alignment of lettuce based on convolutional neural network. Journal of Agricultural Machinery, 2021, 52(09): 186-194.

[9] Pang Q. Research on the detection of obvious/hidden defects in apple epidermis based on deep learning and spectral imaging . Shanghai Ocean University, 2022. DOI:10.27314/d.cnki.gsscu.2022.000147.

[10] Bedi S R, Singh A. A Feature Selection Based Relief Algorithm with Fuzzy Logic for Software Effort Estimation.Research Cell: An International Journal of Engineering Sciences, 2018, 30(SP): 1-5.

[11] Jiang C, Sun X, Dai Y, et al. EEG Emotion Recognition Employing RGPCN-BiGRUAM: ReliefF-Based Graph Pooling Convolutional Network and BiGRU Attention Mechanism. Electronics, 2024, 13(13): 2530-2530.

[12] Mahbod A, Saeidi N, Hatamikia S, et al. Evaluating pre-trained convolutional neural networks and foundation models as feature extractors for content-based medical image retrieval. Engineering Applications of Artificial Intelligence, 2025: 150110571-110571.

[13] Yifan D, Chuanbo W, Zheng W. A motor bearing fault diagnosis method based on multi-source data and onedimensional lightweight convolution neural network. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 2023, 237(2): 272-283.

[14] Carmona A M ,Sautua J F, Pérez-Hernández O, et al. AgroDecisor EFC: First Android^TM app decision support tool for timing fungicide applications for management of late-season soybean diseases. Computers and Electronics in Agriculture, 2018: 144310-313.