Near-infrared spectroscopy integrated machine learning techniques for viable seed identification

MONIKA  SINGH; ANU  SHARMA; K K  CHATURVEDI; SANJEEV  KUMAR; DWIJESH CHANDRA  MISHRA; ALKA  ARORA; RAKESH  BHARDWAJ; MRINMOY  RAY; MAMATHA  Y S; SAMARTH  GODARA

doi:10.56093/ijas.v95i7.160183

Authors

MONIKA SINGH ICAR-Indian Agricultural Research Institute, New Delhi
ANU SHARMA ICAR-Indian Agricultural Statistics Research Institute, New Delhi
K K CHATURVEDI ICAR-Indian Agricultural Statistics Research Institute, New Delhi
SANJEEV KUMAR ICAR-Indian Agricultural Statistics Research Institute, New Delhi
DWIJESH CHANDRA MISHRA ICAR-Indian Agricultural Statistics Research Institute, New Delhi
ALKA ARORA ICAR-Indian Agricultural Statistics Research Institute, New Delhi
RAKESH BHARDWAJ ICAR-National Bureau of Plant Genetic Resources, New Delhi
MRINMOY RAY ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
MAMATHA Y S ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India
SAMARTH GODARA ICAR-Indian Agricultural Statistics Research Institute, New Delhi 110 012, India

https://doi.org/10.56093/ijas.v95i7.160183

Keywords:

Classification, Machine learning, Near-infrared (NIR) spectroscopy, Sustainable conservation, Viable seed

Abstract

The evaluation of seed viability is pivotal in agriculture, biodiversity conservation, and ecological research. Traditional methods used for testing the seed viability are often destructive and pose challenges regarding labour intensity and seed wastage. The study was carried out during 2022–23 at ICAR-Indian Agricultural Statistics Research Institute, New Delhi with the aim of collecting the seed genotypes and NIR spectroscopic instrument and computational approaches and appropriate hardware and software resources. A diverse dataset of NIR spectral data from various seed species was used and analysed using three sophisticated ML models, namely Linear Discriminant Analysis (LDA), Random Forest (RF), and Artificial Neural Networks (ANN). The performance of the developed models was evaluated based on accuracy, precision, recall, and F1 score metrics. Furthermore, the experimental results demonstrated that NIR spectroscopy and ML could effectively classify viable seed. The integration of artificial neural networks (ANNs) has demonstrated significant potential in capturing intricate patterns within spectral data, achieving an approximate accuracy of 95%. This highlights their effectiveness in precise classification tasks. Additionally, machine learning (ML)-based approaches have shown promise in conserving valuable seed resources by offering scalable solutions adaptable to large-scale agricultural and conservation applications. To enhance model transparency, Local Interpretable Model-Agnostic Explanations (LIME) has been employed, providing deeper insights into the ANN’s decision-making process by identifying key spectral features that influence classification outcomes. It was observed that ML-based approaches have the potential to enable continuous monitoring, contributing to the conservation of valuable seed resources. Additionally, these methods may offer a scalable solution that can be adapted for large-scale agricultural and conservation applications.

Downloads

Download data is not yet available.

References

Agelet L E, Gowen A A, Hurburgh Jr C R and ODonell C P. 2012. Feasibility of conventional and Roundup Ready soybeans discrimination by different near infrared reflectance technologies. Food Chemistry 134: 1165–72.

Akkem Y, Biswas S K and Varanasi A. 2024. A comprehensive review of synthetic data generation in smart farming by using variational autoencoder and generative adversarial network. Engineering Applications of Artificial Intelligence 131: 10788.

Al-Amery M, Geneve R L, Sanches M F, Armstrong, P R, Maghirang E B, Lee C, Vieira R D and Hildebrand D F. 2018. Near-infrared spectroscopy used to predict soybean seed germination and vigour. Seed Science Research 28(3): 245–52.

Ambrose A, Lohumi S, Lee W H and Cho B K. 2016. Comparative non-destructive measurement of corn seed viability using Fourier transform near-infrared (FT-NIR) and Raman spectroscopy. Sensors and Actuators B: Chemical 224: 500–06

Baek I, Kusumaningrum D, Kandpal LM, Lohumi S, Mo C, Kim MS and Cho B K. 2019. Rapid measurement of soybean seed viability using kernel-based multispectral image analysis.

Sensors 19(2): 271. https://doi.org/10.3390/s19020271 Barnes R J, Dhanoa M S and Lister S J. 1989. Standard normal

variate transformation and de-trending of near-infrared diffuse reflectance spectra. Applied Spectroscopy 43(5): 772–77.

Breiman L. 2001. Random Forests. Machine Learning 45(1): 5–32 Daneshvar A, Tigabu M, Karimidoost A and Oden P. 2015. Single seed near infrared spectroscopy discriminates viable and non- viable seeds of Juniperus polycarpos. Silva Fennica 49(5).

https://doi.org/10.14214/sf.1334

Gholamy Afshin, Kreinovich Vladik and Kosheleva Olga. 2018. Why 70/30 or 80/20 Relation Between Training and Testing Sets: A Pedagogical Explanation.

Grassi S, Casiraghi E and Alamprese C. 2018. Handheld NIR device: A non-target approach to assess authenticity of fish fillets and patties. Food Chemistry 243: 382–88.

Hornik K, Stinchcombe M and White H. 1989. Multilayer feedforward networks are universal approximators. Neural Networks 2: 359–66.

Kosmowski F and Worku T. 2018. Evaluation of a miniaturized NIR spectrometer for cultivar identification: The case of barley, chickpea and sorghum in Ethiopia. PLOS One 13(3): e0193620.

Machine Learning Models (n.d.). PCA: An Unsupervised Dimensionality Reduction Technique. https://machinelearningmodels.org/pca-an-unsupervised- dimensionality-reduction-technique/

Nicolai B M, Beullens K and Bobelyn E. 2007. Non-destructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review. Postharvest Biology Technology 46(2): 99–118.

Olesen M H, Shetty N, Gislum R and Boelt B. 2011. Classification of viable and non-viable spinach (Spinacia oleracea L.) seeds by single seed near infrared spectroscopy and extended canonical variates analysis. Journal of Near Infrared Spectroscopy 19(4): 285–86.

Ozturk S, Bowler A, Rady A and Watson N J. 2023. Near- infrared spectroscopy and machine learning for classification of food powders during a continuous process. Journal of Food Engineering 341: 111339. https://doi.org/10.1016/j. jfoodeng.2022.111339

Priyadarshi M B, Sharma A, Chaturvedi K, Bhardwaj R, Lal S, Kumar S, Mishra D and Singh M. 2022. Machine learning algorithms for protein physicochemical component prediction using near infrared spectroscopy in chickpea germplasm. Indian Journal of Plant Genetic Resources 35(1): 44–48.

Priyadarshi M B, Sharma A, Chaturvedi K K, Bhardwaj R and Singh M. 2022. Development and comparison of regression models for determination of starch in chickpea using NIR spectroscopy. International Journal of Agriculture Environment and Biotechnology 15(3): 683–91.

Rinnan A, Berg F V D and Engelsen S B. 2009. Review of the most common pre-processing techniques for near-infrared spectra. Trends in Analytical Chemistry 28(10): 1201–22.

Roger JM, Palagos B, Bertrand D and Fernandez-Ahumada E. 2011. CovSel: Variable selection for highly multivariate and multi-response calibration. Chemometrics and Intelligent Laboratory Systems 106(2): 216–23.

Saranya A and Subhashini R. 2023. A systematic review of explainable artificial intelligence models and applications: Recent developments and future trends. Decision Analytics Journal 7: 100230.

Savitzky A and Golay M J E. 1964. Smoothing and differentiation of data by simplified least squares procedures. Analytical Chemistry 36(8): 1627–39. doi:10.1021/ac60214a047

Shrestha S, Deleuran L C and Gislum R. 2017. Separation of viable and non-viable tomato (Solanum lycopersicum L.) seeds using single seed near-infrared spectroscopy. Computers and Electronics in Agriculture 142: 348–55.

Smith L N. 2018. A Disciplined Approach to Neural Network Hyper-Parameters: Part 1-Learning Rate, Batch Size, Momentum, and Weight Decay. ArXivabs/1803: 09820.

Tigabu M, Daneshvar A, Jingjing R, Wu P, Ma X and Oden P C. 2019. Multivariate discriminant analysis of single seed near infrared spectra for sorting dead-filled and viable seeds of three pine species: Does one model fit all species? Forests 10(6): 469.

Wei K, Chen B, Zhang J, Fan S, Wu K, Liu G and Chen D. 2022. Explainable deep learning study for leaf disease classification. Agronomy 12: 1035.

Wold S, Esbensen K and Geladi P. 1987. Principal component analysis. Chemometrics and Intelligent Laboratory Systems 2(1–3): 37–52.

Workman J and Weyer L. 2012. Practical Guide and Spectral Atlas for Interpretive Near-Infrared Spectroscopy, 2nd edn. CRC Press, Taylor & Francis Group.

Zhao B, Dong X, Guo Y, Jia X and Huang Y. 2021. PCA dimensionality reduction method for image classification. Neural Processing Letters 54: 347–68.