Research progress of hyperspectral imaging technology in the in-situ sensing of crop quality and safety

doi:10.3969/j.issn.1004-1524.20250318

Acta Agriculturae Zhejiangensis ›› 2026, Vol. 38 ›› Issue (5): 1035-1047.DOI: 10.3969/j.issn.1004-1524.20250318

• Review • Previous Articles Next Articles

Research progress of hyperspectral imaging technology in the in-situ sensing of crop quality and safety

ZHANG Hao(), TAN Feng, ZHOU Yu, WANG Dachen, ZHOU Hongping, JIANG Hongzhe^*()

College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China

Received:2025-04-22 Online:2026-05-25 Published:2026-06-02

Abstract

Abstract:

Traditional hyperspectral imaging technology has been widely used in the nondestructive detection of crops in recent years. However, laboratory conditions can not fully simulate the field environment in which crops grow, leading to poor extrapolation performance of models. In contrast, in-situ sensing based on hyperspectral imaging technology directly collects spectral information from crops in the field without damaging samples, thereby preserving their state in real environments. This approach yields data that aligns more closely with actual agricultural production scenarios, enabling the development of more practical predictive models. Consequently, hyperspectral imaging technology holds great potential for in-situ sensing of crop quality and safety. This review briefly introduces the fundamental principles and processes of in-situ sensing based on hyperspectral imaging technology, focusing on its research progress in crop quality and safety. It further summarizes major challenges such as insufficient model generalization, difficulties in field deployment, and substantial environmental interference. Future research directions are discussed from the perspectives of hardware advancement, algorithmic innovation, and technological integration, aiming to support continued progress in this field.

Key words: hyperspectral imaging, in-situ sensing, quality sensing, safety sensing, non-destructive testing

CLC Number:

S123

ZHANG Hao, TAN Feng, ZHOU Yu, WANG Dachen, ZHOU Hongping, JIANG Hongzhe. Research progress of hyperspectral imaging technology in the in-situ sensing of crop quality and safety[J]. Acta Agriculturae Zhejiangensis, 2026, 38(5): 1035-1047.

Figures/Tables 9

References 61

[1]	李杰, 吴桂芳, 德雪红, 等. 农产品品质无损检测方法的研究进展[J]. 粮食与饲料工业, 2024(4): 70-76.
	LI J, WU G F, DE X H, et al. Research progress on nondestructive testing methods for agricultural products[J]. Cereal & Feed Industry, 2024(4): 70-76.
[2]	熊春晖, 佘永新, 焦逊, 等. 高光谱成像技术在农产品无损检测中的应用[J]. 粮油食品科技, 2023, 31(1): 109-122.
	XIONG C H, SHE Y X, JIAO X, et al. Application of hyperspectral imaging technology in nondestructive testing of agricultural products[J]. Science and Technology of Cereals, Oils and Foods, 2023, 31(1): 109-122.
[3]	BENELLI A, CEVOLI C, FABBRI A. In-field hyperspectral imaging: an overview on the ground-based applications in agriculture[J]. Journal of Agricultural Engineering, 2020, 51(3): 129-139.
[4]	王丹, 栾雨晴, 谭佐军, 等. 基于高光谱和卷积神经网络的西兰花农药残留检测[J]. 食品工业科技, 2025, 46(6): 1-8.
	WANG D, LUAN Y Q, TAN Z J, et al. Pesticide residue detection in broccoli based on hyperspectral technology and convolutional neural network[J]. Science and Technology of Food Industry, 2025, 46(6): 1-8.
[5]	章恺, 朱丽芳, 李入林, 等. 基于改进WOA-LSSVM和高光谱的猕猴桃糖度无损检测[J]. 食品与机械, 2024, 40(5): 107-112.
	ZHANG K, ZHU L F, LI R L, et al. Non destructive detection of kiwifruit sugar content based on improved WOA-LSSVM and hyperspectral analysis[J]. Food & Machinery, 2024, 40(5): 107-112.
[6]	张芳, 邓照龙, 田有文, 等. 基于高光谱成像技术的南果梨酸度无损检测方法[J]. 沈阳农业大学学报, 2024, 55(2): 231-239.
	ZHANG F, DENG Z L, TIAN Y W, et al. Non-destructive testing method for acidity of Nanguo pear based on hyperspectral imaging technology[J]. Journal of Shenyang Agricultural University, 2024, 55(2): 231-239.
[7]	周晨昕, 刘英, 夏海飞, 等. 基于高光谱数据的青梅成熟度分类方法[J]. 林业工程学报, 2025, 10(3): 146-153.
	ZHOU C X, LIU Y, XIA H F, et al. Maturity classification method of greengage based on hyperspectral data[J]. Journal of Forestry Engineering, 2025, 10(3): 146-153.
[8]	WIEME J, MOLLAZADE K, MALOUNAS I, et al. Application of hyperspectral imaging systems and artificial intelligence for quality assessment of fruit, vegetables and mushrooms: a review[J]. Biosystems Engineering, 2022, 222: 156-176.
[9]	丁世春, 马瑞峻, 陈瑜. 基于高光谱成像的水果品质检测研究进展[J]. 江苏农业科学, 2024, 52(15): 16-26.
	DING S C, MA R J, CHEN Y. Research progress on fruit quality detection based on hyperspectral imaging[J]. Jiangsu Agricultural Sciences, 2024, 52(15): 16-26.
[10]	袁伟东, 鞠皓, 姜洪喆, 等. 基于高光谱成像技术的油茶果不同成熟阶段判别[J]. 光谱学与光谱分析, 2023, 43(11): 3419-3426.
	YUAN W D, JU H, JIANG H Z, et al. Classification of different maturity stages of Camellia oleifera fruit using hyperspectral imaging technique[J]. Spectroscopy and Spectral Analysis, 2023, 43(11): 3419-3426.
[11]	FERNÁNDEZ-NOVALES J, TARDÁGUILA J, GUTIÉRREZ S, et al. On-the-go VIS+SW-NIR spectroscopy as a reliable monitoring tool for grape composition within the vineyard[J]. Molecules, 2019, 24(15): 2795.
[12]	FERNÁNDEZ-NOVALES J, BARRIO I, DIAGO M P. Non-invasive monitoring of berry ripening using on-the-go hyperspectral imaging in the vineyard[J]. Agronomy, 2021, 11(12): 2534.
[13]	BENELLI A, CEVOLI C, RAGNI L, et al. In-field and non-destructive monitoring of grapes maturity by hyperspectral imaging[J]. Biosystems Engineering, 2021, 207: 59-67.
[14]	YANG C, LEE W S, GADER P. Hyperspectral band selection for detecting different blueberry fruit maturity stages[J]. Computers and Electronics in Agriculture, 2014, 109: 23-31.
[15]	WENDEL A, UNDERWOOD J, WALSH K. Maturity estimation of mangoes using hyperspectral imaging from a ground based mobile platform[J]. Computers and Electronics in Agriculture, 2018, 155: 298-313.
[16]	GUTIÉRREZ S, WENDEL A, UNDERWOOD J. Spectral filter design based on in-field hyperspectral imaging and machine learning for mango ripeness estimation[J]. Computers and Electronics in Agriculture, 2019, 164: 104890.
[17]	GAO Z M, SHAO Y Y, XUAN G T, et al. Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning[J]. Artificial Intelligence in Agriculture, 2020, 4: 31-38.
[18]	SHAO Y Y, WANG Y X, XUAN G T. In-field and non-invasive determination of internal quality and ripeness stages of Feicheng peach using a portable hyperspectral imager[J]. Biosystems Engineering, 2021, 212: 115-125.
[19]	孙梦梦. 基于高光谱成像的油茶果成熟度及品质田间检测方法研究[D]. 南京: 南京林业大学, 2024.
	SUN M M. Study on field detection method of maturity and quality of Camellia oleifera fruit based on hyperspectral imaging[D]. Nanjing: Nanjing Forestry University, 2024.
[20]	黄华成. 基于高光谱技术的鲜椒成熟度及其损伤识别研究[D]. 贵阳: 贵州大学, 2022.
	HUANG H C. Study on maturity and damage identification of fresh pepper based on hyperspectral technology[D]. Guiyang: Guizhou University, 2022.
[21]	YUAN W D, ZHOU H P, ZHOU Y, et al. In-field and non-destructive determination of comprehensive maturity index and maturity stages of Camellia oleifera fruits using a portable hyperspectral imager[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2024, 315: 124266.
[22]	WU X J, WU X M, HUANG H C, et al. Characterization of pepper ripeness in the field using hyperspectral imaging (HSI) with back propagation (BP) neural network and kernel based extreme learning machine (KELM) models[J]. Analytical Letters, 2024, 57(3): 409-424.
[23]	ZHAO J, LI H, CHEN C, et al. Detection of water content in lettuce canopies based on hyperspectral imaging technology under outdoor conditions[J]. Agriculture, 2022, 12(11): 1796.
[24]	CHEN C, JIANG Y, ZHU X Q. Research on lettuce canopy image processing method based on hyperspectral imaging technology[J]. Plants, 2024, 13(23): 3403.
[25]	YANG F F, LIU T, WANG Q Y, et al. Rapid determination of leaf water content for monitoring waterlogging in winter wheat based on hyperspectral parameters[J]. Journal of Integrative Agriculture, 2021, 20(10): 2613-2626.
[26]	SHU M Y, DONG Q Z, FEI S P, et al. Improved estimation of canopy water status in maize using UAV-based digital and hyperspectral images[J]. Computers and Electronics in Agriculture, 2022, 197: 106982.
[27]	CEVOLI C, DI CECILIA L, FERRARI L, et al. Evaluation of cut alfalfa moisture content and operative conditions by hyperspectral imaging combined with chemometric tools: in-field application[J]. Biosystems Engineering, 2022, 222: 132-141.
[28]	LOGGENBERG K, STREVER A, GREYLING B, et al. Modelling water stress in a Shiraz vineyard using hyperspectral imaging and machine learning[J]. Remote Sensing, 2018, 10(2): 202.
[29]	GAO J L, MENG B P, LIANG T G, et al. Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau, China[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 147: 104-117.
[30]	YU F H, FENG S, DU W, et al. A study of nitrogen deficiency inversion in rice leaves based on the hyperspectral reflectance differential[J]. Frontiers in Plant Science, 2020, 11: 573272.
[31]	CHEN X K, LI F L, SHI B T, et al. Estimation of winter wheat plant nitrogen concentration from UAV hyperspectral remote sensing combined with machine learning methods[J]. Remote Sensing, 2023, 15(11): 2831.
[32]	LI Z H, JIN X L, YANG G J, et al. Remote sensing of leaf and canopy nitrogen status in winter wheat (Triticum aestivum L.) based on N-PROSAIL model[J]. Remote Sensing, 2018, 10(9): 1463.
[33]	YANG G J, ZHAO C J, PU R L, et al. Leaf nitrogen spectral reflectance model of winter wheat (Triticum aestivum) based on PROSPECT: simulation and inversion[J]. Journal of Applied Remote Sensing, 2015, 9(1): 095976.
[34]	VERHOEF W. Light scattering by leaf layers with application to canopy reflectance modeling: the SAIL model[J]. Remote Sensing of Environment, 1984, 16(2): 125-141.
[35]	YE X J, ABE S, ZHANG S H. Estimation and mapping of nitrogen content in apple trees at leaf and canopy levels using hyperspectral imaging[J]. Precision Agriculture, 2020, 21(1): 198-225.
[36]	LU J S, YANG T C, SU X, et al. Monitoring leaf potassium content using hyperspectral vegetation indices in rice leaves[J]. Precision Agriculture, 2020, 21(2): 324-348.
[37]	赵明蕊. 基于高光谱成像技术的加工番茄果实品质无损检测研究[D]. 石河子: 石河子大学, 2023.
	ZHAO M R. Study on nondestructive testing of fruit quality of processed tomato based on hyperspectral imaging technology[D]. Shihezi: Shihezi University, 2023.
[38]	SHAO Y Y, SHI Y K, QIN Y D, et al. A new quantitative index for the assessment of tomato quality using Vis-NIR hyperspectral imaging[J]. Food Chemistry, 2022, 386: 132864.
[39]	XU J J, FU G S, YAN L P, et al. Estimation of the relative chlorophyll content of Carya illinoensis leaves using fractional order derivative of leaf and canopy scale hyperspectral data[J]. Journal of Soil Science and Plant Nutrition, 2024, 24(1): 1407-1423.
[40]	VANBRABANT Y, TITS L, DELALIEUX S, et al. Multitemporal chlorophyll mapping in pome fruit orchards from remotely piloted aircraft systems[J]. Remote Sensing, 2019, 11(12): 1468.
[41]	XIAO B, LI S Z, DOU S Q, et al. Comparison of leaf chlorophyll content retrieval performance of citrus using FOD and CWT methods with field-based full-spectrum hyperspectral reflectance data[J]. Computers and Electronics in Agriculture, 2024, 217: 108559.
[42]	ZHAO R M, TANG W J, LIU M J, et al. Spatial-spectral feature extraction for in-field chlorophyll content estimation using hyperspectral imaging[J]. Biosystems Engineering, 2024, 246: 263-276.
[43]	GAO D H, QIAO L, SONG D, et al. In-field chlorophyll estimation based on hyperspectral images segmentation and pixel-wise spectra clustering of wheat canopy[J]. Biosystems Engineering, 2022, 217: 41-55.
[44]	ALMOUJAHED M B, APOLO-APOLO O E, WHETTON R L, et al. Field-based hyperspectral imaging for detection and spatial mapping of Fusarium head blight in wheat[J]. European Journal of Agronomy, 2025, 164: 127485.
[45]	WHETTON R L, WAINE T W, MOUAZEN A M. Hyperspectral measurements of yellow rust and Fusarium head blight in cereal crops: Part 2: on-line field measurement[J]. Biosystems Engineering, 2018, 167: 144-158.
[46]	MA H Q, HUANG W J, DONG Y Y, et al. Using UAV-based hyperspectral imagery to detect winter wheat Fusarium Head blight[J]. Remote Sensing, 2021, 13(15): 3024.
[47]	LIU L Y, DONG Y Y, HUANG W J, et al. Monitoring wheat Fusarium head blight using unmanned aerial vehicle hyperspectral imagery[J]. Remote Sensing, 2020, 12(22): 3811.
[48]	YAO Z F, LEI Y, HE D J. Early visual detection of wheat stripe rust using visible/near-infrared hyperspectral imaging[J]. Sensors, 2019, 19(4): 952.
[49]	GUO A T, HUANG W J, DONG Y Y, et al. Wheat yellow rust detection using UAV-based hyperspectral technology[J]. Remote Sensing, 2021, 13(1): 123.
[50]	KHAN I H, LIU H Y, LI W, et al. Early detection of powdery mildew disease and accurate quantification of its severity using hyperspectral images in wheat[J]. Remote Sensing, 2021, 13(18): 3612.
[51]	ABDULRIDHA J, MIN A, ROUSE M N, et al. Evaluation of stem rust disease in wheat fields by drone hyperspectral imaging[J]. Sensors, 2023, 23(8): 4154.
[52]	LA PAROLA C M. Comparison of multispectral and hyperspectral UAV imagery for late blight (phytophtora infestans) detection in a potato (Solanum tuberosum) field[D]. LISBOA: Instituto Superior D AGRONOMIA, Patrian Uniwersidade de Lisboa, 2022.
[53]	SHI Y, HAN L X, KLEEREKOPER A, et al. Novel CropdocNet model for automated potato late blight disease detection from unmanned aerial vehicle-based hyperspectral imagery[J]. Remote Sensing, 2022, 14(2): 396.
[54]	WANG Y X, XING M F, ZHANG H G, et al. Rice false smut monitoring based on band selection of UAV hyperspectral data[J]. Remote Sensing, 2023, 15(12): 2961.
[55]	AN G Q, XING M F, HE B B, et al. Extraction of areas of rice false smut infection using UAV hyperspectral data[J]. Remote Sensing, 2021, 13(16): 3185.
[56]	IMAI N N, TOMMASELLI A M G, et al. Detection and mapping of trees infected with Citrus gummosis using UAV hyperspectral data[J]. Computers and Electronics in Agriculture, 2021, 188: 106298.
[57]	FRANCESCHINI M H D, BREDE B, KAMP J, et al. Detection of a vascular wilt disease in potato (‘Blackleg’) based on UAV hyperspectral imagery: can structural features from LiDAR or SfM improve plant-wise classification accuracy[J]. Computers and Electronics in Agriculture, 2024, 227: 109527.
[58]	ABDULRIDHA J, BATUMAN O, AMPATZIDIS Y. UAV-based remote sensing technique to detect citrus canker disease utilizing hyperspectral imaging and machine learning[J]. Remote Sensing, 2019, 11(11): 1373.
[59]	DENG X L, ZHU Z H, YANG J C, et al. Detection of citrus Huanglongbing based on multi-input neural network model of UAV hyperspectral remote sensing[J]. Remote Sensing, 2020, 12(17): 2678.
[60]	PANSY D L, MURALI M. UAV hyperspectral remote sensor images for mango plant disease and pest identification using MD-FCM and XCS-RBFNN[J]. Environmental Monitoring and Assessment, 2023, 195(9): 1120.
[61]	郭伟, 乔红波, 赵恒谦, 等. 基于比值导数法的棉花蚜害无人机成像光谱监测模型研究[J]. 光谱学与光谱分析, 2021, 41(5): 1543-1550.
	GUO W, QIAO H B, ZHAO H Q, et al. Cotton aphid damage monitoring using UAV hyperspectral data based on derivative of ratio spectroscopy[J]. Spectroscopy and Spectral Analysis, 2021, 41(5): 1543-1550.

样品 Sample	感知内容 Test items	建模方法 Modeling approach	性能评估 Result validation	参考文献 Reference
葡萄Grape	TSS	PLSR	${R}_{\mathrm{C}}^{2}$=0.92、${R}_{\mathrm{P}}^{2}$=0.95	[11]
	花青素含量Anthocyanin content	PLSR	${R}_{\mathrm{C}}^{2}$=0.75、${R}_{\mathrm{P}}^{2}$=0.79	[11]
	TP	PLSR	${R}_{\mathrm{C}}^{2}$=0.42、${R}_{\mathrm{P}}^{2}$=0.43	[11]
葡萄Grape	TSS	PLSR	${R}_{\mathrm{P}}^{2}$=0.82	[12]
	花青素含量Anthocyanin content	PLSR	${R}_{\mathrm{P}}^{2}$=0.88	[12]
	TP	PLSR	${R}_{\mathrm{P}}^{2}$=0.55	[12]
	TA	PLSR	${R}_{\mathrm{P}}^{2}$=0.81	[12]
葡萄Grape	TSS、成熟度Ripeness	PLS-DA	ACC=86%~91%	[13]
蓝莓Blueberry	成熟度Ripeness	KNN、SVM、AdaBoost	ACC=88%	[14]
杧果Mango	成熟度Ripeness	PLS-DA、CNN	F1>0.97	[15]
草莓Strawberry	成熟度Ripeness	SVM	ACC=98.6%	[17]
桃Peach	成熟度Ripeness	LIBSVM	ACC=91.7%	[18]
油茶果Camellia oleifera fruit	成熟度Ripeness	PLS-DA	ACC=93.82%	[19]
油茶果Camellia oleifera fruit	成熟度Ripeness	PLS-DA	ACC=88.6%	[21]
辣椒Pepper	成熟度Ripeness	SG-Der-SAM PCA-KELM	ACC=99.8% ACC=89.4%	[20] [20]
辣椒Pepper	成熟度Ripeness	PCA-KELM	ACC=97.3%	[22]

样品 Sample	感知内容 Test items	建模方法 Modeling approach	性能评估 Result validation	参考文献 Reference
葡萄Grape	TSS	PLSR	${R}_{\mathrm{C}}^{2}$=0.92、${R}_{\mathrm{P}}^{2}$=0.95	[11]
	花青素含量Anthocyanin content	PLSR	${R}_{\mathrm{C}}^{2}$=0.75、${R}_{\mathrm{P}}^{2}$=0.79	[11]
	TP	PLSR	${R}_{\mathrm{C}}^{2}$=0.42、${R}_{\mathrm{P}}^{2}$=0.43	[11]
葡萄Grape	TSS	PLSR	${R}_{\mathrm{P}}^{2}$=0.82	[12]
	花青素含量Anthocyanin content	PLSR	${R}_{\mathrm{P}}^{2}$=0.88	[12]
	TP	PLSR	${R}_{\mathrm{P}}^{2}$=0.55	[12]
	TA	PLSR	${R}_{\mathrm{P}}^{2}$=0.81	[12]
葡萄Grape	TSS、成熟度Ripeness	PLS-DA	ACC=86%~91%	[13]
蓝莓Blueberry	成熟度Ripeness	KNN、SVM、AdaBoost	ACC=88%	[14]
杧果Mango	成熟度Ripeness	PLS-DA、CNN	F1>0.97	[15]
草莓Strawberry	成熟度Ripeness	SVM	ACC=98.6%	[17]
桃Peach	成熟度Ripeness	LIBSVM	ACC=91.7%	[18]
油茶果Camellia oleifera fruit	成熟度Ripeness	PLS-DA	ACC=93.82%	[19]
油茶果Camellia oleifera fruit	成熟度Ripeness	PLS-DA	ACC=88.6%	[21]
辣椒Pepper	成熟度Ripeness	SG-Der-SAM PCA-KELM	ACC=99.8% ACC=89.4%	[20] [20]
辣椒Pepper	成熟度Ripeness	PCA-KELM	ACC=97.3%	[22]

样品Sample	建模方法Modeling approach	性能评估Result validation	参考文献Reference
生菜Lettuce	MC-UVE-CARS-PLS	R_C=82.71%,R_P=84.67%	[23]
生菜Lettuce	PCA	AVG=0.952 6、0.047 7	[24]
冬小麦Winter wheat	BPNN	${R}_{\mathrm{C}}^{2}$=0.889,${R}_{\mathrm{P}}^{2}$=0.891	[25]
玉米Corn	LR	R²>0.6	[26]
紫花苜蓿Alfalfa	PLS	R²=0.86,RMSE=2.00%	[27]
葡萄藤Grapevine	RF	ACC=83.3%	[28]

样品Sample	建模方法Modeling approach	性能评估Result validation	参考文献Reference
生菜Lettuce	MC-UVE-CARS-PLS	R_C=82.71%,R_P=84.67%	[23]
生菜Lettuce	PCA	AVG=0.952 6、0.047 7	[24]
冬小麦Winter wheat	BPNN	${R}_{\mathrm{C}}^{2}$=0.889,${R}_{\mathrm{P}}^{2}$=0.891	[25]
玉米Corn	LR	R²>0.6	[26]
紫花苜蓿Alfalfa	PLS	R²=0.86,RMSE=2.00%	[27]
葡萄藤Grapevine	RF	ACC=83.3%	[28]

样品Sample	感知内容Test items	建模方法Modeling approach	性能评估Result validation	参考文献Reference
牧草Forage	磷含量Phosphorus content	FD-IB+SVM	R²=0.67,RMSE=0.047 2%	[29]
水稻Rice	氮含量Nitrogen content	GA-ELM	R²>0.68	[30]
水稻Rice	钾含量Potassium content	PROSPECT-5	R²=0.74	[36]
冬小麦Winter wheat	氮含量Nitrogen content	SVR	R²=0.88	[31]
		RFR	R²=0.91	[31]
冬小麦Winter wheat	氮含量Nitrogen content	N-PROSAIL	R²=0.75%,RMSE=0.38%	[32]
苹果树Apple tree	氮含量Nitrogen content	PLSR	R²=0.772 8	[35]
		MLR	R²=0.784 3	[35]

Research progress of hyperspectral imaging technology in the in-situ sensing of crop quality and safety

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 61

Related Articles 6

Recommended Articles

Metrics

Comments

样品 Sample	感知内容 Test items	建模方法 Modeling approach	性能评估 Result validation	参考文献 Reference
番茄Tomato	综合品质Comprehensive quality	RNN	${R}_{\mathrm{P}}^{2}$=0.649,RMSEP=0.56	[37]
番茄Tomato	综合品质Comprehensive quality	MLR	${R}_{\mathrm{V}}^{2}$=0.87,RMSEV=1.33,PRD=2.58	[38]
油茶果Camellia oleifera fruit	综合成熟度Composite maturity index	SPA-CNNR	R_P=0.839,RMSEP=0.261,RPD=1.849	[21]
油茶果Camellia oleifera fruit	综合品质Comprehensive quality	RF	R²=0.853 4,RMSE=0.052 6	[19]

样品 Sample	建模方法 Modeling approach	性能评估 Result validation	参考文献 Reference
山核桃 Pecan	XGboost	${R}_{\mathrm{P}}^{2}$=0.788, RMSEP=0.842	[39]
柑橘 Citrus	H-ELR、PLSR	R²=0.876, RMSE=3.447, RPD=2.601	[41]
植物Plants	3D-CNN-LSTM	${R}_{\mathrm{P}}^{2}$=0.87~0.97	[42]
小麦Wheat	K-means、PLSR	${R}_{\mathrm{P}}^{2}$>0.81	[43]

样品Sample	感知内容Test items	建模方法Modeling approach	性能评估Result validation	参考文献Reference
小麦Wheat	FHB	ETR	R²=0.94	[44]
小麦Wheat	FHB	SB+VI+WF	R²=0.88,RMSE=2.68%	[46]
小麦Wheat	FHB	BPNN	ACC=98%	[47]
小麦Wheat	条锈病Stripe rust	PCA-loadings-BPNN	${R}_{\mathrm{C}}^{2}$=0.921,${R}_{\mathrm{P}}^{2}$=0.918	[48]
小麦Wheat	条锈病Stripe rust	PLSR	R²=0.65、0.75、0.82	[49]
小麦Wheat	PM	PLSR	ACC=82.35%	[50]
小麦Wheat	SR	RFC	ACC=85%	[51]
马铃薯Potato	晚疫病Late blight	RFC	ACC=0.99±0.04	[52]
马铃薯Potato	晚疫病Late blight	CropdocNet	ACC=98.09%	[53]
水稻Rice	稻曲病False smut	GBDT	ACC=85.62%	[54]
水稻Rice	稻曲病False smut	RF	ACC=74.23%、85.19%	[55]
柑橘Citrus	流胶病Gummosis	SAM	ACC=94%	[56]

样品 Sample	感知内容 Test items	建模方法 Modeling approach	性能评估 Result validation	参考文献 Reference
马铃薯Potato	黑胫病Blackleg	SVM	BA=0.915	[57]
柑橘Citrus	溃疡病Citrus canker	RBF、KNN	ACC=100%	[58]
柑橘Citrus	黄龙病Huanglongbing disease	GA、SAE	ACC=99.72%	[59]
杧果Mango	虫害Insect pest	MD-FCM、XCS-RBFNN	ACC=97.02%	[60]
棉花Cotton	蚜害Aphid infestation	PLSR	R²=0.612,RMSE=0.89	[61]

[1]	YU Shuochen, ZHANG Jun, SONG Xinjie, ZHOU Jinyun. Research on 1D-DenseRNet-based classification and detection method for canned food vacuum data [J]. Acta Agriculturae Zhejiangensis, 2024, 36(12): 2846-2856.
[2]	YU Wenjie, WANG Caixia, QIAO Lu, WANG Songlei, HE Xiaoguang. Construction of PLSR prediction model for detecting color of Jingyuan yellow beef by hyperspectral technique [J]. , 2020, 32(3): 527-533.
[3]	MENG Qinglong, ZHANG Yan, SHANG Jing. Nondestructive recognition of surface defect on kiwifruits using hyperspectral imaging technology [J]. , 2019, 31(8): 1372-1378.
[4]	WANG Yanxiang, ZHANG Yan, YANG Chengya, MENG Qinglong, SHANG Jing. Advances in new nondestructive detection and identification techniques of crop diseases based on deep learning [J]. , 2019, 31(4): 669-676.
[5]	MENG Youqing, WENG Haiyong, CEN Haiyan, LI Hongye, HE Yong. Carbohydrate metabolism and near-infrared spectral characteristics in asymptomatic Huang-longbing infected leaves [J]. , 2019, 31(3): 428-435.
[6]	JIN Xiu, LU Jie, FU Yunzhi, WANG Shuai, XU Gaojian, LI Shaowen. A classification method for hyperspectral imaging of Fusarium head blight disease symptom based on deep convolutional neural network [J]. , 2019, 31(2): 315-325.