Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Plant Sci.

Sec. Sustainable and Intelligent Phytoprotection

Volume 16 - 2025 | doi: 10.3389/fpls.2025.1666619

SegFormer-Based Nectar Source Segmentation in Remote Sensing Imagery

Provisionally accepted
  • Anhui Science and Technology University, Bengbu, China

The final, formatted version of the article will be published soon.

Beekeepers often face challenges in accurately obtaining the spatial distribution of nectar-producing plants, which is critical for scientific decision-making and efficient beekeeping. In this study, we present an efficient method for automatically identifying nectar-producing plants using remote sensing imagery. High-resolution satellite images were collected and preprocessed, and an improved segmentation approach based on the SegFormer model was developed. This model incorporates the CBAM attention mechanism, deep residual structures, and a spatial feature enhancement module to improve segmentation performance. Experimental results on rapeseed flower images in Wuyuan County demonstrate that the improved model significantly outperformed the baseline SegFormer model, with mIoU increasing from 89.31% to 91.05%, mPA from 94.15% to 95.02%, and both mPrecision and mRecall reaching 95.40% and 95.02%, respectively. The proposed method significantly enhances the efficiency and accuracy of nectar plant identification, providing real-time and reliable technical support for precision beekeeping management, the development of smart agriculture, and ecological monitoring and resource surveys, particularly playing a crucial role in optimizing bee colony migration, improving collection efficiency, and regulating honey quality.

Keywords: remote sensing, SegFormer, Nectar-producing plants, Bees, Semantic segmentation, deep learning

Received: 17 Jul 2025; Accepted: 25 Aug 2025.

Copyright: © 2025 Dong, Cao, Zhao and Zhao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Hao Cao, Anhui Science and Technology University, Bengbu, China

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.