Xiao Yuxin, Zhai Yuanning, Zhou Lei, Yin Yiming, Qi Hengnian, Zhang Chu
School of Information Engineering, Huzhou University, Huzhou 313000, China.
College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China.
Foods. 2025 Jun 13;14(12):2091. doi: 10.3390/foods14122091.
Hyperspectral imaging (HSI) has broad applications for detecting the soluble solids content (SSC) of fruits. This study explores the integration of HSI with machine learning and deep learning to predict SSC in two mandarin varieties: Ponkan and Tianchao. Traditional machine learning models (support vector machines and partial least squares regression) and deep learning models (convolutional neural networks, long short-term memory, and Transformer architectures) were evaluated for SSC prediction performance. Combined models that integrated different deep learning architectures were also explored. Results revealed varietal differences in prediction performance. For Ponkan mandarins, the best SSC prediction model was achieved by partial least squares regression, outperforming deep learning models. In contrast, for Tianchao mandarins, the deep learning model based on convolutional neural network slightly surpassed the traditional model. SHapley Additive exPlanations (SHAP) analysis indicated that the influential wavelengths varied between varieties, suggesting differences in key spectral features for SSC prediction. These findings highlight the potential of combining HSI with advanced modeling for citrus SSC prediction, while emphasizing the need for variety-specific models. Future research should focus on developing more robust and generalized prediction models by incorporating a broader range of citrus varieties and exploring the impact of varietal characteristics on model performance.
高光谱成像（HSI）在检测水果可溶性固形物含量（SSC）方面具有广泛应用。本研究探索将HSI与机器学习和深度学习相结合，以预测椪柑和天草这两个柑橘品种的SSC。评估了传统机器学习模型（支持向量机和偏最小二乘回归）和深度学习模型（卷积神经网络、长短期记忆网络和Transformer架构）的SSC预测性能。还探索了整合不同深度学习架构的组合模型。结果显示预测性能存在品种差异。对于椪柑，偏最小二乘回归实现了最佳的SSC预测模型，优于深度学习模型。相比之下，对于天草柑橘，基于卷积神经网络的深度学习模型略优于传统模型。SHapley值相加解释（SHAP）分析表明，不同品种之间有影响的波长各不相同，这表明SSC预测的关键光谱特征存在差异。这些发现凸显了将HSI与先进建模方法相结合用于柑橘SSC预测的潜力，同时强调了针对特定品种模型的必要性。未来的研究应专注于通过纳入更广泛的柑橘品种并探索品种特征对模型性能的影响，来开发更稳健和通用的预测模型。
