All Issue

2026 Vol.53, Issue 2 Preview Page

Engineering

Development of cold damage classifiers for peach flowers using hyperspectral imagery
Ji Won Choi1
,
Soo Been Cho1
,
Myeong Jin Jo2
,
Taegil Lee2
,
Chae Eun Kim3
,
Mi Hee Shin4
,
Hye-Young Lee45
,
Jin Gook Kim45
,
Byoung-Kwan Cho6
,
Taehwan Shin7
,
Geonwoo Kim14*
1Department of Biosystems Engineering, College of Agricultural and Life Sciences, Gyeongsang National University, Jinju 52828, Korea
2Department of Bio-industrial Machinery Engineering, Gyeongsang National University, Jinju 52828, Korea
3Division of Applied Life Science, Graduate School of Gyeongsang National University, Jinju 52828, Korea
4Institute of Agriculture and Life Sciences, Gyeongsang National University, Jinju 52828, Korea
5Division of Horticultural Science, College of Agriculture & Life Science, Gyeongsang National University, Jinju 52828, Korea
6Department of Biosystem Machinery Engineering, Chungnam National University, Daejeon 34134, Korea
7Agricultural Researcher, Fruit Research Division, National Institute of Horticultural & Herbal Science, Wanju 55365, Korea
*Corresponding Author
1 June 2026. pp. 111-130
PDF XML Citation
Abstract

This study proposes a hyperspectral imaging-based analytical framework and artificial intelligence (AI) classification models for the early, non-destructive detection of cold injury in peach flowers during the blooming stage. Peach flowers are highly vulnerable to low-temperature stress, yet conventional diagnosis relying on visual inspection or fruit-stage assessment limits timely response and cultivar selection. To address this, hyperspectral images covering 400 - 1,000 nm were acquired, region-of-interest spectra were extracted, and standardized preprocessing methods such as interquartile range (IQR) and standard normal variate (SNV) were applied. Machine learning and deep learning classification models were developed and evaluated under different temperature conditions. Among the tested configurations, the IQR - convolutional neural network (CNN) combination achieved the highest accuracy and reproducibility, indicating effective learning of subtle spectral responses to cold stress. Mean spectral analysis showed decreased reflectance below 3℃, likely associated with cell structural weakening and moisture reduction. Sensitivity analysis revealed notable responsiveness at 400 - 420 nm, 700 - 800 nm, and above 900 nm, and model-based feature importance highlighted 520 - 525 nm, 575 - 580 nm, 675 - 680 nm, 785 - 790 nm, 870 - 880 nm, 890 - 920 nm, and near 940 nm as discriminative regions. Among these, 675 - 680 nm, 785 - 790 nm, 870 - 880 nm, and 890 - 920 nm were interpreted as physiologically relevant to cold-injury responses. Overall, this study addresses limitations of fruit-stage assessments by presenting a blooming-stage, non-destructive detection framework with potential applications in cold-injury early warning, cold-tolerant cultivar development, and orchard management decision support.

Keywords
artificial intelligence
cold damage
hyperspectral imaging
peach flower
References
1

Alanazi A, Wahab NHA, Al-Rimy BAS. 2024. Hyperspectral imaging for remote sensing and agriculture: A comparative study of transformer-based models. In: Proceedings of the IEEE 14th Symposium on Computer Applications & Industrial Electronics. pp. 129-136. Piscataway, NJ: IEEE.

10.1109/ISCAIE61308.2024.10576233
2

Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamaría J, Fadhel MA, Al-Amidie M, Farhan L. 2021. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data 8:53.

10.1186/s40537-021-00444-833816053PMC8010506
3

Arús P, Verde I, Sosinski B, Zhebentyayeva T, Abbott AG. 2012. The peach genome. Tree Genetics & Genomes 8:531-547.

10.1007/s11295-012-0493-8
4

Bansal M, Goyal A, Choudhary A. 2022. A comparative analysis of k-nearest neighbor, genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning. Decision Analytics Journal 3:100071.

10.1016/j.dajour.2022.100071
5

Bazrafshan O, Ehteram M, Latif SDL, Huang YF, Teo FY, Ahmed ANA, El-Shafie A. 2022. Predicting crop yields using a new robust Bayesian averaging model based on multiple hybrid ANFIS and MLP models. Ain Shams Engineering Journal 13:101724.

10.1016/j.asej.2022.101724
6

Brown JD. 2008. Effect size and eta squared. Shiken: JALT Testing & Evaluation SIG Newsletter 12:38-43.

7

Byrne DH, Raseira MB, Bassi D, Piagnani MC, Gasic K, Reighard GL, Moreno MA, Pérez S. 2012. Peach. In Fruit Breeding edited by Badenes ML, Byrne DH. pp. 505-569. Springer, New York, NY.

10.1007/978-1-4419-0763-9_14
8

Caballero D, Calvini R, Amigo JM. 2019. Hyperspectral imaging in crop fields: Precision agriculture. In Hyperspectral Imaging (Data Handling in Science and Technology, Vol. 32) edited by Amigo JM. pp. 453-473. Elsevier, Netherlands.

10.1016/B978-0-444-63977-6.00018-3
9

Cai H, Chen T. 2020. Multi-dimension CNN for hyperspectral image classificaton. In: Proceedings of the IEEE International Geoscience and Remote Sensing Symposium. pp. 1275-1278. Piscataway, NJ: IEEE.

10.1109/IGARSS39084.2020.9323561
10

Cao K, Zhang S, Chen Y, Ye J, Wei Y, Jiang S, Shao X. 2023. ERF transcription factor PpRAP2.12 activates PpVIN2 expression in peach fruit and reduces tolerance to cold stress. Postharvest Biology and Technology 199:112276.

10.1016/j.postharvbio.2023.112276
11

Chen B, Shi S, Sun J, Chen B, Guo K, Du L, Yang J, Xu Q, Song S, Gong W. 2021. Using HSI color space to improve the multispectral lidar classification error caused by measurement geometry. IEEE Transactions on Geoscience and Remote Sensing 59:3567-3579.

10.1109/TGRS.2020.3006577
12

Choi JW, Hidayat MS, Cho SB, Hwang WH, Lee H, Cho BK, Kim MS, Baek I, Kim G. 2025. Recent trends in machine learning, deep learning, ensemble learning, and explainable artificial intelligence techniques for evaluating crop yields under abnormal climate conditions. Plants 14:2841.

10.3390/plants1418284141011993PMC12473817
13

Choi M, Ryu J, Ju JB, Lee S, Kim G, Kim HJ, Jo C. 2026. Predicting sensory characteristics of pork using physicochemical and VIS/NIR hyperspectral imaging data with machine learning. Food Control 180:111615.

10.1016/j.foodcont.2025.111615
14

Dolaptsis K, Pantazi XE, Paraskevas C, Arslan S, Tekin Y, Bantchina BB, Ulusoy Y, Gündoğdu KS, Qaswar M, Bustan D, et al. 2024. A hybrid LSTM approach for irrigation scheduling in maize crop. Agriculture 14:210.

10.3390/agriculture14020210
15

Gavahi K, Abbaszadeh P, Moradkhani H. 2021. DeepYield: A combined convolutional neural network with long short-term memory for crop yield forecasting. Expert Systems with Applications 184:115511.

10.1016/j.eswa.2021.115511
16

Gitelson A, Arkebauer T, Solovchenko A, Nguy-Robertson A, Inoue Y. 2022. An insight into spectral composition of light available for photosynthesis via remotely assessed absorption coefficient at leaf and canopy levels. Photosynthesis Research 151:47-60.

10.1007/s11120-021-00863-x
17

Gitelson AA, Merzlyak MN, Lichtenthaler HK. 1996. Detection of red edge position and chlorophyll content by reflectance measurements near 700 nm. Journal of Plant Physiology 148:501-508.

10.1016/S0176-1617(96)80285-9
18

Gowthami G, Priscila SS. 2024. Classification of intrusion using CNN with IQR (inter quartile range) approach. In Advancements in Smart Computing and Information Security edited by Rajagopal S, Popat K, Meva D, Bajeja S. pp. 259-269. Springer, Switzerland.

10.1007/978-3-031-59097-9_19
19

Grossman YL, DeJong TM. 1994. PEACH: A simulation model of reproductive and vegetative growth in peach trees. Tree Physiology 14:329-345.

10.1093/treephys/14.4.329
20

Gupta RK, Vijayan D, Prasad TS. 2003. Comparative analysis of red-edge hyperspectral indices. Advances in Space Research 32:2217-2222.

10.1016/S0273-1177(03)90545-X
21

Hussain SB, Karagiannis E, Manzoor M, Ziogas V. 2023. From stress to success: Harnessing technological advancements to overcome climate change impacts in citriculture. Critical Reviews in Plant Sciences 42:345-363.

10.1080/07352689.2023.2248438
22

Ige AO, Sibiya M. 2024. State-of-the-art in 1D convolutional neural networks: A survey. IEEE Access 12:144082-144105.

10.1109/ACCESS.2024.3433513
23

Iqbal N, Shahzad MU, Sherif ESM, Tariq MU, Rashid J, Le TV, Ghani A. 2024. Analysis of wheat-yield prediction using machine learning models under climate change scenarios. Sustainability 16:6976.

10.3390/su16166976
24

Jia Z, Bao Y, Zhao Y, Liu Y, Zheng Y, Feng Z, Jin P. 2023. Cold shock treatment enhances cold tolerance in peach fruit through modulating PpbZIP9 and PpVIP1-mediated respiratory metabolism. Postharvest Biology and Technology 204:112421.

10.1016/j.postharvbio.2023.112421
25

Jiang R, Qu D, Liu G, Xie S, Chen S, Peng Y. 2024. Hyperspectral detection technology in agriculture: A review. In: Proceedings of the International Conference on Image Processing, Computer Vision and Machine Learning. pp. 1716-1721. Piscataway, NJ: IEEE.

10.1109/ICICML63543.2024.10958046
26

Khatun R, Akter M, Islam MM, Uddin MA, Talukder MA, Kamruzzaman J, Azad AKM, Paul BK, Almoyad MAA, Aryal S, et al. 2023. Cancer classification utilizing voting classifier with ensemble feature selection method and transcriptomic data. Genes 14:1802.

10.3390/genes1409180237761941PMC10530870
27

Khonina SN, Kazanskiy NL, Oseledets IV, Nikonorov AV, Butt MA. 2024. Synergy between artificial intelligence and hyperspectral imagining—A review. Technologies 12:163.

10.3390/technologies12090163
28

Li B, Zhang C, Cao B, Qin G, Wang W, Tian S. 2012. Brassinolide enhances cold stress tolerance of fruit by regulating plasma membrane proteins and lipids. Amino Acids 43:2469-2480.

10.1007/s00726-012-1327-6
29

Li C, Czyż EA, Halitschke R, Baldwin IT, Schaepman ME, Schuman MC. 2023. Evaluating potential of leaf reflectance spectra to monitor plant genetic variation. Plant Methods 19:108.

10.1186/s13007-023-01089-937833725PMC10576306
30

Li J, Cui R, Li B, Song R, Li Y, Du Q. 2019. Hyperspectral image super-resolution with 1D–2D attentional convolutional neural network. Remote Sensing 11:2859.

10.3390/rs11232859
31

Li Y, Tan X, Zhang W, Jiao Q, Xu Y, Li H, Zou Y, Yang L, Fang Y. 2021. Research and application of several key techniques in hyperspectral image preprocessing. Frontiers in Plant Science 12:627865.

10.3389/fpls.2021.62786533679841PMC7935556
32

Li Y, Wang Y, Wang Z, Liu G, Chang R, Chen H, Li J, Tian Q. 2025. Metabolite analysis of peach (Prunus persica L. Batsch) branches in response to freezing stress. Plant Biology 27:92-101.

10.1111/plb.13727
33

Lurie S, Crisosto CH. 2005. Chilling injury in peach and nectarine. Postharvest Biology and Technology 37:195-208.

10.1016/j.postharvbio.2005.04.012
34

Meng X, Han J, Wang Q, Tian S. 2009. Changes in physiology and quality of peach fruits treated by methyl jasmonate under low temperature stress. Food Chemistry 114:1028-1035.

10.1016/j.foodchem.2008.09.109
35

Mutanga O, Skidmore AK. 2007. Red edge shift and biochemical content in grass canopies. ISPRS Journal of Photogrammetry and Remote Sensing 62:34-42.

10.1016/j.isprsjprs.2007.02.001
36

Muthuramalingam P, Shin H, Adarshan S, Jeyasri R, Priya A, Chen JT, Ramesh M. 2022. Molecular insights into freezing stress in peach based on multi-omics and biotechnology: An overview. Plants 11:812.

10.3390/plants1106081235336695PMC8954506
37

Nikzadfar M, Rashvand M, Zhang H, Shenfield A, Genovese F, Altieri G, Matera A, Tornese I, Laveglia S, Paterna G, et al. 2024. Hyperspectral imaging aiding artificial intelligence: A reliable approach for food qualification and safety. Applied Sciences 14:9821.

10.3390/app14219821
38

Niu R, Huang J, Zhang Y, Wang F, Wang C. 2025. Physiological response and comprehensive evaluation of cold-resistant peach varieties to low-temperature stress. Agronomy 15:182.

10.3390/agronomy15010182
39

Nur NB, Bachmann CM. 2023. Comparison of soil moisture content retrieval models utilizing hyperspectral goniometer data and hyperspectral imagery from an unmanned aerial system. Journal of Geophysical Research: Biogeosciences 128:e2023JG007381.

10.1029/2023JG007381
40

Peng J, Wang K, Ma C, Long J, Tu K, Pan L. 2021. Determination of anthocyanin and moisture content of purple sweet potatoes during drying process by their optical properties in the 400-1050 nm range. Food Chemistry 359:129811.

10.1016/j.foodchem.2021.129811
41

Penso GA, Citadin I, Scariotto S, dos Santos CEM, Junior AW, Bruckner CH, Rodrigo J. 2020. Development of peach flower buds under low winter chilling conditions. Agronomy 10:428.

10.3390/agronomy10030428
42

Perkov S, Cvjetinovic J, Sydygalieva A, Gorodkov S, Li G, Gorin D. 2025. Optical based methods for water monitoring in biological tissue. Journal of Biophotonics 18:e202400438.

10.1002/jbio.202400438
43

Qazi EUH, Almorjan A, Zia T. 2022. A one-dimensional convolutional neural network (1D-CNN) based deep learning system for network intrusion detection. Applied Sciences 12:7986.

10.3390/app12167986
44

Ray S, Lama A, Mishra P, Biswas T, Das SS, Gurung B. 2023. An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique. Applied Soft Computing 149:110939.

10.1016/j.asoc.2023.110939
45

Richardson JTE. 2011. Eta squared and partial eta squared as measures of effect size in educational research. Educational Research Review 6:135-147.

10.1016/j.edurev.2010.12.001
46

Saleem MH, Potgieter J, Arif KM. 2021. Automation in agriculture by machine and deep learning techniques: A review of recent developments. Precision Agriculture 22:2053-2091.

10.1007/s11119-021-09806-x
47

Shahhosseini M, Hu G, Khaki S, Archontoulis SV. 2021. Corn yield prediction with ensemble CNN-DNN. Frontiers in Plant Science 12:709008.

10.3389/fpls.2021.70900834408763PMC8364956
48

Shirazi MI, Khatir S, Boutchicha D, Wahab MA. 2024. Feature extraction and classification of multiple cracks from raw vibrational responses of composite beams using 1D-CNN network. Composite Structures 327:117701.

10.1016/j.compstruct.2023.117701
49

Siche R, Vejarano R, Aredo V, Velasquez L, Saldaña E, Quevedo R. 2016. Evaluation of food quality and safety with hyperspectral imaging (HSI). Food Engineering Reviews 8:306-322.

10.1007/s12393-015-9137-8
50

Srivastava R. 2021. Physicochemical, antioxidant properties of carotenoids and its optoelectronic and interaction studies with chlorophyll pigments. Scientific Reports 11:18365.

10.1038/s41598-021-97747-w34526535PMC8443628
51

Syeda IH, Alam MM, Illahi U, Su’ud MM. 2021. Advance control strategies using image processing, UAV and AI in agriculture: A review. World Journal of Engineering 18:579-589.

10.1108/WJE-09-2020-0459
52

Syu YR, Lin CH, Chi CY. 2019. An outlier-insensitive unmixing algorithm with spatially varying hyperspectral signatures. IEEE Access 7:15086-15101.

10.1109/ACCESS.2018.2890278
53

Tanou G, Minas IS, Scossa F, Belghazi M, Xanthopoulou A, Ganopoulos I, Madesis P, Fernie A, Molassiotis A. 2017. Exploring priming responses involved in peach fruit acclimation to cold stress. Scientific Reports 7:11358.

10.1038/s41598-017-11933-328900303PMC5595836
54

Thron M, Eichner K, Ziegleder G. 2001. The influence of light of different wavelengths on chlorophyll-containing foods. LWT 34:542-548.

10.1006/fstl.2001.0801
55

Walker C, Jha S, Chen K, Ewetz R. 2024. Integrated decision gradients: Compute your attributions where the model makes its decision. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. pp. 5289-5297. Washington, DC: AAAI.

10.1609/aaai.v38i6.28336
56

Wang B, Sun J, Xia L, Liu J, Wang Z, Li P, Guo Y, Sun X. 2023a. The applications of hyperspectral imaging technology for agricultural products quality analysis: A review. Food Reviews International 39:1043-1062.

10.1080/87559129.2021.1929297
57

Wang H, Li G, Wang Z. 2023b. Fast SVM classifier for large-scale classification problems. Information Sciences 642:119136.

10.1016/j.ins.2023.119136
58

Wang K, Shao X, Gong Y, Zhu Y, Wang H, Zhang X, Yu D, Yu F, Qiu Z, Lu H. 2013. The metabolism of soluble carbohydrates related to chilling injury in peach fruit exposed to cold stress. Postharvest Biology and Technology 86:53-61.

10.1016/j.postharvbio.2013.06.020
59

Witteveen M, Sterenborg HJCM, van Leeuwen TG, Aalders MCG, Ruers TJM, Post AL. 2022. Comparison of preprocessing techniques to reduce nontissue-related variations in hyperspectral reflectance imaging. Journal of Biomedical Optics 27:106003.

10.1117/1.JBO.27.10.10600336207772PMC9541333
60

Zhang G, Abdulla W. 2023. Optimizing hyperspectral imaging classification performance with CNN and batch normalization. Applied Spectroscopy Practica 1:1-16.

10.1177/27551857231204622
61

Zhang S, Cao K, Wei Y, Jiang S, Ye J, Xu F, Chen Y, Shao X. 2023. PpBZR1, a BES/BZR transcription factor, enhances cold stress tolerance by suppressing sucrose degradation in peach fruit. Plant Physiology and Biochemistry 202:107972.

10.1016/j.plaphy.2023.107972
62

Zhu Y, Huang Q, Pan Y, Zhang Z, Yuan R, Nie Y. 2022. Abnormal behavior of chilling injury in postharvest papaya fruit is associated with sugar metabolism. Journal of Food Science 87:919-928.

10.1111/1750-3841.16067
Information
  • Publisher :Institute of Agricultural Science, Chungnam National University
  • Publisher(Ko) :충남대학교 농업과학연구소
  • Journal Title :Korean Journal of Agricultural Science
  • Journal Title(Ko) :농업과학연구
  • Volume : 53
  • No :2
  • Pages :111-130
  • Received Date : 2026-02-04
  • Revised Date : 2026-03-10
  • Accepted Date : 2026-03-11
  • DOI :https://doi.org/10.7744/kjoas.530202
Journal Informaiton Korean Journal of Agricultural Science Korean Journal of Agricultural Science
Online Submission
  • NRF
  • KOFST
  • crossref funder-registry
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close