EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Latent Salinity Stress Detection in Opuntia ficus-indica Using Hyperspectral Imaging and a 3D-CNN Framework

Juan Arredondo-Valdez, Horacio Abdiel Rodríguez-Garza, Héctor Flores-Breceda, Zayd Eliud Rangel-Nava iD, Néstor Everardo Aranda-Ledesma, Jesús Rodolfo Valenzuela-García, Moisés Hinojosa-Rivera, Ajay Kumar iD, Urbano Luna-Maldonado, Alejandro Isabel Luna-Maldonado iD

Sensors · 07.06.2026 · 26 (12) · 3641

DOI: 10.3390/s26123641 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.06.2026. Verfasst von Juan Arredondo-Valdez und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Agricultural and Food Engineering, Faculty of Agronomy, Autonomous University of Nuevo Leon, Francisco Villa S/N, Ex-Hacienda El Canadá…. Hauptthemen laut MEDLINE: Opuntia, Salt Stress, Hyperspectral Imaging, Imaging, Three-Dimensional. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Autónoma de Nuevo León.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Salinity stress remains a major bottleneck for agriculture in arid regions. While Opuntia ficus-indica is known for its resilience, its young cladodes maintain a misleadingly healthy visual appearance and stable biomass even under heavy saline pressure, making traditional vegetation indices and standard statistics unreliable for early diagnosis. The objective of this study was to develop a non-destructive phenotyping framework for the early detection of latent salinity stress in young Opuntia cladodes. Controlled experiments were conducted using hyperspectral data cubes (400–1000 nm) acquired from plants exposed to six distinct salinity levels ranging from 2 to 21 dS m−1. Our methodology integrates these high-dimensional spatial–spectral data with a tailor-made 3D Convolutional Neural Network (3D-CNN). Seven physiological vegetation indices—NDVI, PRI, WI, PSRI, MCARI, SIPI, and NDRE were extracted to track sub-clinical shifts and processed as a volumetric depth dimension within the network to preserve spatial–spectral integrity. The optimized 3D-CNN framework achieved a validation accuracy of 99.7% and a weighted F1-score of 99.1%, delivering 100% precision at critical stress thresholds (13 and 21 dS m−1). Spatial confidence maps (Softmax > 0.95) further confirmed the high reliability of the diagnostic output. Requiring a training duration of approximately 8 s, this framework provides a robust basis for precision early-warning irrigation systems to sustain Opuntia cultivation in challenging environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OpuntiaSalt StressHyperspectral ImagingImaging, Three-DimensionalConvolutional Neural NetworksSalinity

Stichwörter der Autor:innen

3D-CNNOpuntia ficus-indicahyperspectral imagingnon-destructive phenotypingprecision agriculturesalinity stress

Autor:innen und Institutionen

  • Department of Agricultural and Food Engineering, Faculty of Agronomy, Autonomous University of Nuevo Leon, Francisco Villa S/N, Ex-Hacienda El Canadá, General Escobedo 66050, Nuevo Leon, Mexico.
  • Department of Agricultural Machinery, Antonio Narro Autonomous Agricultural University, Calzada Antonio Narro 1923, Buenavista, Saltillo 25280, Coahuila, Mexico.
  • Faculty of Mechanical and Electrical Engineering, Autonomous University of Nuevo Leon, Pedro de Alba S/N, Ciudad Universitaria, San Nicolás de los Garza 66455, Nuevo Leon, Mexico.
  • Department of Biosystems and Agricultural Engineering, Oklahoma State University, Stillwater, OK 74078, USA.

ORCID-Profile: Zayd Eliud Rangel-Nava, Ajay Kumar, Alejandro Isabel Luna-Maldonado

Förderung

  • Universidad Autónoma de Nuevo León

Zitieren

APA

Arredondo-Valdez, J., Rodríguez-Garza, H. A., Flores-Breceda, H., Rangel-Nava, Z. E., Aranda-Ledesma, N. E., Valenzuela-García, J. R., Hinojosa-Rivera, M., Kumar, A., Luna-Maldonado, U., & Luna-Maldonado, A. I. (2026). Latent Salinity Stress Detection in Opuntia ficus-indica Using Hyperspectral Imaging and a 3D-CNN Framework. Sensors, 26(12), 3641. https://doi.org/10.3390/s26123641

Vancouver

Arredondo-Valdez J, Rodríguez-Garza HA, Flores-Breceda H, Rangel-Nava ZE, Aranda-Ledesma NE, Valenzuela-García JR, et al. Latent Salinity Stress Detection in Opuntia ficus-indica Using Hyperspectral Imaging and a 3D-CNN Framework. Sensors. 2026;26(12):3641. doi:10.3390/s26123641

BibTeX
@article{ArredondoValdez2026,
  author = {Arredondo-Valdez, Juan and Rodríguez-Garza, Horacio Abdiel and Flores-Breceda, Héctor and Rangel-Nava, Zayd Eliud and Aranda-Ledesma, Néstor Everardo and Valenzuela-García, Jesús Rodolfo and Hinojosa-Rivera, Moisés and Kumar, Ajay and Luna-Maldonado, Urbano and Luna-Maldonado, Alejandro Isabel},
  title = {Latent Salinity Stress Detection in Opuntia ficus-indica Using Hyperspectral Imaging and a 3D-CNN Framework},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3641},
  doi = {10.3390/s26123641}
}
Kostenlos starten →