@article{Di2026, 
author = {Ruoyu Di and Pan Gao and Chengkai Li and Shiwei Ruan and Fei Tan and Weiping Yan and Zhihao Liang and Jingye Liu and Chu Zhang and Wei Xu},
title = {PlantSpecLab: A comprehensive open-source platform for high-throughput plant spectral data processing and phenotypic modeling},
year = {2026},
journal = {Plant Phenomics},
volume = {8},
number = {1},
pages = {100148},
keywords = {Hyperspectral imaging, Plant phenotyping, Open-source software, Fractional-order differencing, Image segmentation},
url = {https://www.sciopen.com/article/10.1016/j.plaphe.2025.100148},
doi = {10.1016/j.plaphe.2025.100148},
abstract = {High-throughput plant phenotyping with hyperspectral imaging (HSI) is pivotal for accelerating crop improvement to address global food security. Adoption is limited by a data-processing bottleneck, forcing a trade-off between costly, inflexible commercial software and programming-intensive open-source libraries. To overcome this barrier, we developed PlantSpecLab, an open-source, no-code platform that unifies the HSI workflow from image processing to modeling within a single interactive interface. The platform introduces spectrally guided segmentation strategies (Range Averaging, Difference Enhancement) and a spectral Fractional-Order Differencing (FOD) preprocessor to enhance extraction of subtle, physiologically relevant features. Across diverse in-house and public datasets, FOD-preprocessed spectra improved model performance over conventional pipelines, yielding a mean classification accuracy of 82.86 % for tomato maturity and average R2 = 0.8638 for fruit firmness. In cross-software benchmarks, PlantSpecLab matched the accuracy of ENVI and code-based Python pipelines while reducing end-to-end workflow time by over 90 % (from approximately 80 minutes to about 8 minutes). PlantSpecLab provides a transparent, efficient analytical environment that lowers the technical barrier to HSI analysis. This enables researchers to prioritize biological interpretation while minimizing computational overhead.}
}