Open Access

ARTICLE

Enhanced Plant Species Identification through Metadata Fusion and Vision Transformer Integration

Hassan Javed¹, Labiba Gillani Fahad¹, Syed Fahad Tahir^2,*, Mehdi Hassan², Hani Alquhayz³

1 Department of Computer Science, National University of Computer & Emerging Sciences, Islamabad, 44000, Pakistan
2 Department of Computer Science, Air University, Islamabad, 44000, Pakistan
3 Department of Computer Science and Information, College of Science in Zulfi, Majmaah University, Al-Majmaah, 11952, Saudi Arabia

* Corresponding Author: Syed Fahad Tahir. Email:

Computers, Materials & Continua 2025, 85(2), 3981-3996. https://doi.org/10.32604/cmc.2025.064359

Received 13 February 2025; Accepted 29 May 2025; Issue published 23 September 2025

Abstract

Accurate plant species classification is essential for many applications, such as biodiversity conservation, ecological research, and sustainable agricultural practices. Traditional morphological classification methods are inherently slow, labour-intensive, and prone to inaccuracies, especially when distinguishing between species exhibiting visual similarities or high intra-species variability. To address these limitations and to overcome the constraints of image-only approaches, we introduce a novel Artificial Intelligence-driven framework. This approach integrates robust Vision Transformer (ViT) models for advanced visual analysis with a multi-modal data fusion strategy, incorporating contextual metadata such as precise environmental conditions, geographic location, and phenological traits. This combination of visual and ecological cues significantly enhances classification accuracy and robustness, proving especially vital in complex, heterogeneous real-world environments. The proposed model achieves an impressive 97.27% of test accuracy, and Mean Reciprocal Rank (MRR) of 0.9842 that demonstrates strong generalization capabilities. Furthermore, efficient utilization of high-performance GPU resources (RTX 3090, 18 GB memory) ensures scalable processing of high-dimensional data. Comparative analysis consistently confirms that our metadata fusion approach substantially improves classification performance, particularly for morphologically similar species, and through principled self-supervised and transfer learning from ImageNet, the model adapts efficiently to new species, ensuring enhanced generalization. This comprehensive approach holds profound practical implications for precise conservation initiatives, rigorous ecological monitoring, and advanced agricultural management.

---

Keywords

---