Spectral Reconstruction Applied in Precision Agriculture: On-Field Solutions
Source abstract
Abstract
Over the past two decades, hyperspectral imaging (HSI) systems have shown significant potential in agriculture, from disease detection to the assessment of plant and fruit nutritional status. However, most applications remain confined to laboratory analyses under controlled conditions, with only a limited fraction implemented in field environments. In this scenario, spectral reconstruction techniques may serve as a bridge between the high accuracy of HSI and the challenges of on-field or even real-time applications. This review outlines the current state of the art of on-field HSI in the agrifood sector, highlighting existing limitations and potential advantages. It then introduces the problem of spectral reconstruction and reviews current techniques used to address it. Laboratory and on-field studies will be taken into account. The final section offers our perspective on the limitations of HSI and the promising potential of spectral super-resolution to overcome current barriers and enable broader adoption of hyperspectral technology in precision agriculture.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Spectroscopy and Chemometric Analyses · Remote Sensing in Agriculture · Smart Agriculture and AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Agricultural and Food Sciences, Alma Mater Studiorum, University of Bologna, 40126 Bologna, Italy
Department of Physics and Astronomy “Augusto Righi”, Alma Mater Studiorum, University of Bologna, 40126 Bologna, Italy
Funding
EU-NextGenerationEU-Piano Nazionale Ripresa e Resilienza (PNRR) Mission 4, Component 2, Investment 3.3
References (100+)
Show source-provided references
1. Zhang, J., Su, R., Fu, Q., Ren, W., Heide, F., and Nie, Y. (2022). A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging. Sci. Rep., 12.10.1038/s41598-022-16223-1 ↗
2. Fsian, A.N., Thomas, J.B., Hardeberg, J.Y., and Gouton, P. (2024). Spectral reconstruction from RGB imagery: A potential option for infinite spectral data?. Sensors, 24.10.3390/s24113666 ↗
3. Spectral super-resolution meets deep learning: Achievements and challenges10.1016/j.inffus.2023.101812 ↗
4. Lin, Y.T., and Finlayson, G.D. (2020). Physically Plausible Spectral Reconstruction. Sensors, 20.10.3390/s20216399 ↗
5. Reconstruction of hyperspectral data from RGB images with prior category information10.1109/TCI.2020.3000320 ↗
6. Arad, B., Timofte, R., Ben-Shahar, O., Lin, Y.T., and Finlayson, G.D. (2020, January 14–19). NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.
7. Arad, B., Timofte, R., Yahel, R., Morag, N., Bernat, A., Cai, Y., Lin, J., Lin, Z., Wang, H., and Zhang, Y. (2022, January 19–20). NTIRE 2022 Spectral Recovery Challenge and Data Set. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, LA, USA.
8. Strategies for analysing hyperspectral imaging data for food quality and safety issues—A critical review of the last 5 years10.1016/j.microc.2025.113994 ↗
9. A systematic review of hyperspectral imaging in precision agriculture: Analysis of its current state and future prospects10.1016/j.compag.2024.109037 ↗
10. Hyperspectral imaging and its applications: A review10.1016/j.heliyon.2024.e33208 ↗
11. Hyperspectral imaging for detection of plant diseases with deep learning
12. Mé rida-García, R., Gálvez, S., Solís, I., Martínez-Moreno, F., Camino, C., Soriano, J.M., Sansaloni, C., Ammar, K., Bentley, A.R., and Gonzalez-Dugo, V. (2024). High-throughput phenotyping using hyperspectral indicators supports the genetic dissection of yield in durum wheat grown under heat and drought stress. Front. Plant Sci., 15.10.3389/fpls.2024.1470520 ↗
13. Field Scanalyzer: An automated robotic field phenotyping platform for detailed crop monitoring10.1071/FP16163 ↗
14. Precision agriculture using hyperspectral imaging: Early results
15. Zhang, J., Pu, R., and Wang, J. (2012, January 22–27). Hyperspectral band selection for crop disease detection. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Munich, Germany.
16. Detection of weeds in maize fields using hyperspectral imaging
17. Active learning system for weed species recognition based on hyperspectral sensing10.1016/j.biosystemseng.2016.01.014 ↗
18. Williams, M., Verhoeven, S., and Roelofs, J. (2017, January 16–20). Hyperspectral weed detection using tractor-mounted imaging. Proceedings of the European Conference on Precision Agriculture (ECPA), Edinburgh, UK.
19. Horstrand, P., Guerra, R., and Aranda, J. (2019). Deep learning for weed detection in UAV-based hyperspectral imagery. Remote Sens., 11.
20. On-board hyperspectral data processing with UAVs for real-time applications
21. Sousa, J.J., Pádua, L., and Adão, T. (2022). Hyperspectral UAV imaging for vineyard monitoring. Remote Sens., 14.
22. Feng, L., Wu, B., He, Y., and Zhang, C. (2021). Hyperspectral Imaging Combined With Deep Transfer Learning for Rice Disease Detection. Front. Plant Sci., 12.10.3389/fpls.2021.693521 ↗
23. Lu, B., Dao, P., Liu, J., He, Y., and Shang, J. (2020). Recent advances of hyperspectral imaging technology and applications in agriculture. Remote Sens., 12.10.3390/rs12162659 ↗
24. Perspectives for hyperspectral sensing in precision agriculture10.1016/j.tplants.2018.11.007 ↗
25. Chen, Y., An, X., Gao, S., Li, S., and Kang, H. (2021). A Deep Learning-Based Vision System Combining Detection and Tracking for Fast On-Line Citrus Sorting. Front. Plant Sci., 12.10.3389/fpls.2021.622062 ↗
26. Machine learning approaches for hyperspectral weed detection
27. Ground-level hyperspectral imagery for detecting weeds in wheat fields10.1007/s11119-013-9321-x ↗
28. Advances in hyperspectral band selection for crop monitoring
29. Deep learning and computer vision in plant disease detection: A comprehensive review of techniques, models, and trends in precision agriculture10.1007/s10462-024-11100-x ↗
30. Zhang, X., Chen, Y., and Wang, Z. (2022). Generative adversarial networks for hyperspectral data augmentation in crop classification. Remote Sens., 14.
31. Zheng, H., Cheng, T., Li, D., Yao, X., Tian, Y., Cao, W., and Zhu, Y. (2018). Combining Unmanned Aerial Vehicle (UAV)-Based Multispectral Imagery and Ground-Based Hyperspectral Data for Plant Nitrogen Concentration Estimation in Rice. Front. Plant Sci., 9.10.3389/fpls.2018.00936 ↗
32. Hyperspectral and machine learning approaches for crop nutrient assessment
33. Assessment of crop water stress with UAV hyperspectral data
34. GPU implementation of endmember extraction algorithms for hyperspectral imagery
35. Aragón, M., González, J., and Plaza, A. (2019, January 22–25). Efficient hyperspectral PCA on embedded GPU platforms for precision agriculture. Proceedings of the IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.
36. Scalable architectures for real-time hyperspectral unmixing
37. A real-time FPGA accelerated stream processing for hyperspectral image classification10.1080/10106049.2020.1713231 ↗
38. Rosario, D., López, S., and Plaza, A. (2014, January 22–24). Real-time FPGA implementation of the Vertex Component Analysis algorithm for hyperspectral unmixing. Proceedings of the SPIE 9244, Image and Signal Processing for Remote Sensing XX, Amsterdam, The Netherlands.
39. Benelli, A., Cevoli, C., and Fabbri, A. (2020, January 4–6). In-field Vis/NIR hyperspectral imaging to measure soluble solids content of wine grape berries during ripening. Proceedings of the 2020 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), Trento, Italy.10.1109/MetroAgriFor50201.2020.9277621 ↗
40. In-field and non-destructive monitoring of grapes maturity by hyperspectral imaging10.1016/j.biosystemseng.2021.04.006 ↗
41. Gutiérrez, S., Fernández-Novales, J., Diago, M.P., and Tardaguila, J. (2018). On-The-Go hyperspectral imaging under field conditions and machine learning for the classification of grapevine varieties. Front. Plant Sci., 9.10.3389/fpls.2018.01102 ↗
42. Fernández-Novales, J., Tardáguila, J., Gutiérrez, S., and Diago, M.P. (2019). On The Go VIS SW NIR spectroscopy as a reliable monitoring tool for grape composition within the vineyard. Molecules, 24.10.3390/molecules24152795 ↗
43. The prediction of ripening parameters in Primitivo wine grape cultivar using a portable NIR device10.1016/j.jfca.2022.104836 ↗
44. On the go hyperspectral imaging for the in field estimation of grape berry soluble solids and anthocyanin concentration
45. Hyperspectral imaging applications in agriculture and agro-food product quality and safety control: A review10.1080/05704928.2012.705800 ↗
46. In-field hyperspectral imaging: An overview on the ground-based applications in agriculture10.4081/jae.2020.1030 ↗
47. Efficient in-field plant phenomics for row-crops with an autonomous ground vehicle10.1002/rob.21728 ↗
48. Jiang, Y., Li, C., Robertson, J.S., Sun, S., Xu, R., and Paterson, A.H. (2018). GPhenoVision: A ground mobile system with multi-modal imaging for field-based high throughput phenotyping of cotton. Sci. Rep., 8.10.1038/s41598-018-19142-2 ↗
49. Maturity estimation of mangoes using hyperspectral imaging from a ground based mobile platform10.1016/j.compag.2018.10.021 ↗
50. Wang, B., Zhang, X., Dong, Y., Zhang, J., Zhang, J., and Zhou, X. (2018, January 6–9). Retrieval of leaf chlorophyll content of paddy rice with extracted foliar hyperspectral imagery. Proceedings of the 2018 7th International Conference on Agro-Geoinformatics (Agro-Geoinformatics), Hangzhou, China.10.1109/Agro-Geoinformatics.2018.8476024 ↗
51. Field monitoring of wheat seedling stage with hyperspectral imaging
52. Estimating leaf chlorophyll content in sugar beet canopies using millimeter- to centimeter-scale reflectance imagery10.1016/j.rse.2017.06.008 ↗
53. Nitrogen prediction model of rice plant at panicle initiation stage using ground-based hyperspectral imaging: Growing degree-days integrated model10.1007/s11119-015-9394-9 ↗
54. Potential of field hyperspectral imaging as a non destructive method to assess leaf nitrogen content in Wheat10.1016/j.fcr.2011.02.003 ↗
55. Hyperspectral measurements of yellow rust and fusarium head blight in cereal crops: Part 2: On-line field measurement10.1016/j.biosystemseng.2018.01.004 ↗
56. Zhao, J., Zhang, D., Huang, L., Zhang, Q., Liu, W., and Yang, H. (2016, January 18–20). Vertical features of yellow rust infestation on winter wheat using hyperspectral imaging measurements. Proceedings of the 2016 5th International Conference on Agro-Geoinformatics, Tianjin, China.10.1109/Agro-Geoinformatics.2016.7577620 ↗
57. Early drought stress detection in cereals: Simplex volume maximisation for hyperspectral image analysis10.1071/FP12060 ↗
58. Glyphosate-resistant and glyphosate-susceptible Palmer amaranth (Amaranthus palmeri S. Wats.): Hyperspectral reflectance properties of plants and potential for classification10.1002/ps.3755 ↗
59. Chen, W., Li, H., Niu, Q., and Hongnan, H. (2017, January 16–19). Hyperspectral image segmentation for maize stubble in no-till field. Proceedings of the 2017 ASABE Annual International Meeting. American Society of Agricultural and Biological Engineers, Spokane, WA, USA.10.13031/aim.201700963 ↗
60. A review of machine learning in hyperspectral imaging for food safety10.1016/j.vibspec.2025.103828 ↗
61. An overview of regression methods in hyperspectral and multispectral imaging
62. Huang, W.; Bao, Y.; He, Y. Application of near-infrared hyperspectral imaging for variety identification of coated maize kernels with deep learning10.1016/j.infrared.2020.103550 ↗
63. Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M.S., Hasan, M., Van Essen, B.C., Awwal, A.A.S., and Asari, V.K. (2019). A state-of-the-art survey on deep learning theory and architectures. Electronics, 8.10.3390/electronics8030292 ↗
64. Khanna, R., Sa, I., Nieto, J., and Siegwart, R. (June, January 29). On Field Radiometric Calibration for Multispectral Cameras. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Singapore.
65. A Subband Radiometric Calibration Method for UAV-Based Multispectral Remote Sensing10.1109/JSTARS.2018.2842466 ↗
66. Simoneau, A., and Aubé, M. (2023). Methods to Calibrate a Digital Colour Camera as a Multispectral Imaging Sensor in Low Light Conditions. Remote Sens., 15.10.3390/rs15143634 ↗
67. Poncet, A.M., Knappenberger, T., Brodbeck, C., Fogle, M., Shaw, J.N., and Ortiz, B.V. (2019). Multispectral UAS Data Accuracy for Different Radiometric Calibration Methods. Remote Sens., 11.10.3390/rs11161917 ↗
68. Unmanned Aerial System multispectral mapping for low and variable solar irradiance conditions: Potential of tensor decomposition10.1016/j.isprsjprs.2019.06.017 ↗
69. Calibration of a Common Shortwave Multispectral Camera System for Quantitative Agricultural Applications10.1007/s11119-019-09701-6 ↗
70. An Illumination Estimation and Compensation Method for Radiometric Correction of Multispectral Images10.1109/TGRS.2022.3225291 ↗
71. Kitanovski, V., Thomas, J.B., and Hardeberg, J.Y. (2021, January 1–4). Reflectance Estimation from Snapshot Multispectral Images Captured under Unknown Illumination. Proceedings of the 29th Color and Imaging Conference Final Program and Proceedings, Online.10.2352/issn.2169-2629.2021.29.264 ↗
72. Illuminant Estimation in Multispectral Imaging10.1364/JOSAA.34.001085 ↗
73. Thomas, J.B. (2015, January 25–26). Illuminant Estimation from Uncalibrated Multispectral Images. Proceedings of the 2015 Colour and Visual Computing Symposium (CVCS), Gjovik, Norway.10.1109/CVCS.2015.7274900 ↗
74. Li, Y., Fu, Q., and Heidrich, W. (2021, January 10–17). Multispectral illumination estimation using deep unrolling network. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00267 ↗
75. Amziane, A., Losson, O., Mathon, B., Dumenil, A., and Macaire, L. (2020, January 9–12). Frame-based Reflectance Estimation from Multispectral Images for Weed Identification in Varying Illumination Conditions. Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP), Paris, France.10.1109/IPTA50016.2020.9286692 ↗
76. Practical Low-Cost Recovery of Spectral Power Distributions10.1111/cgf.12717 ↗
77. Calibration of Space-Multispectral Imaging Sensors: A Review10.1016/S0034-4257(98)00111-4 ↗
78. Light Source Calibration for Multispectral Imaging in Surgery10.1007/s11548-020-02195-y ↗
79. A new instrument for passive remote sensing Measurements of sunlight-induced chlorophyll fluorescence10.1016/j.rse.2004.02.012 ↗
80. Evaluation and unification of some methods for estimating reflectance spectra from RGB images10.1364/JOSAA.25.002444 ↗
81. Lin, Y.T., and Finlayson, G.D. (2019, January 13–17). Exposure Invariance in Spectral Reconstruction from RGB Images. Proceedings of the IS&T International Symposium on Electronic Imaging, Burlingame, CA, USA.
82. Connah, D.R., and Hardeberg, J.Y. (2005, January 17–20). Spectral recovery using polynomial models. Proceedings of the Color Imaging X: Processing, Hardcopy, and Applications, Bellingham, WA, USA.10.1117/12.586315 ↗
83. Locally Linear Embedded Sparse Coding for Spectral Reconstruction From RGB Images10.1109/LSP.2017.2776167 ↗
84. A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution
85. Shi, Z., Chen, C., Xiong, Z., Liu, D., and Wu, F. (2018, January 18–22). HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.10.1109/CVPRW.2018.00139 ↗
86. Liu, P., and Zhao, H. (2020). Adversarial Networks for Scale Feature-Attention Spectral Image Reconstruction from a Single RGB. Sensors, 20.10.3390/s20082426 ↗
87. Alvarez-Gila, A., van de Weijer, J., and Garrote, E. (2017, January 22–29). Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB. Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy.10.1109/ICCVW.2017.64 ↗
88. Arad, B., Ben-Shahar, O., Timofte, R., Gool, L.V., Zhang, L., Yang, M., Xiong, Z., Chen, C., Shi, Z., and Liu, D. (2018, January 18–22). NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.10.1109/CVPRW.2018.00138 ↗
89. Chen, C., Wang, Y., Zhang, N., Zhang, Y., and Zhao, Z. (2023). A review of hyperspectral image super-resolution based on deep learning. Remote Sens., 15.10.3390/rs15112853 ↗
90. Arad, A., and Ben-Shahar, O. (2016, January 8–16). Sparse Recovery of Hyperspectral Signal from Natural RGB Images. Proceedings of the Computer Vision—ECCV 2016, Amsterdam, The Netherlands.10.1007/978-3-319-46478-7_2 ↗
91. Generalized Assorted Pixel Camera: Postcapture Control of Resolution, Dynamic Range, and Spectrum10.1109/TIP.2010.2046811 ↗
92. Chakrabarti, S., and Zickler, T. (2011, January 20–25). Statistics of Real-World Hyperspectral Images. Proceedings of the CVPR 2011, Colorado Springs, CO, USA.10.1109/CVPR.2011.5995660 ↗
93. Multi-manifold locality graph preserving analysis for hyperspectral image classification10.1016/j.neucom.2019.12.112 ↗
94. Ghamisi, P., Benediktsson, J.A., and Phinn, S. (2014, January 13–18). Fusion of Hyperspectral and LiDAR Data in Classification of Urban Areas. Proceedings of the 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, QC, Canada.10.1109/IGARSS.2014.6946386 ↗
95. Pacifici, F., Chanussot, J., and Du, Q. (2011, January 24–29). 2011 GRSS Data Fusion Contest: Exploiting WorldView-2 Multi-Angular Acquisitions. Proceedings of the 2011 IEEE International Geoscience and Remote Sensing Symposium, Vancouver, BC, Canada.10.1109/IGARSS.2011.6049404 ↗
96. Hyperspectral Image Data Analysis10.1109/79.974718 ↗
97. Katkovsky, L.V., Martinov, A.O., Siliuk, V.A., Ivanov, D.A., and Kokhanovsky, A.A. (2018). Fast Atmospheric Correction Method for Hyperspectral Data. Remote Sens., 10.10.20944/preprints201809.0119.v3 ↗
98. Imaging Spectroscopy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS)10.1016/S0034-4257(98)00064-9 ↗
99. WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF10.1016/j.rse.2020.112012 ↗
100. Koundinya, S., Sharma, H., Sharma, M., Upadhyay, A., Manekar, R., Mukhopadhyay, R., Karmakar, A., and Chaudhury, S. (2020, January 18–22). 2D-3D CNN based architectures for spectral reconstruction from RGB images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.