Hou Yufei, Bao Huiyu, Rimi Tamanna Islam, Zhang Siyuan, Han Bangdong, Wang Yizhuo, Yu Ziyang, Chen Jianxin, Gao Hongxiu, Zhao Zhenqing, Wei Qiaorong, Chen Qingshan, Zhang Zhongchen
College of Agriculture, Northeast Agricultural University, Harbin 150030, China.
National Key Laboratory of Smart Farm Technologies and Systems, Harbin 150030, China.
Plants (Basel). 2025 Feb 1;14(3):424. doi: 10.3390/plants14030424.
This study aims to develop an effective and reliable method for estimating rice quality indices and yield, addressing the growing need for rapid, non-destructive, and accurate predictions in modern agriculture. Field experiments were conducted in 2018 at the Suiling Water Conservancy Comprehensive Experimental Station (47°27' N, 127°06' E), using Longqingdao 3 as the test variety. Measurements included the leaf area index (LAI), chlorophyll content (SPAD), leaf nitrogen content (LNC), and leaf spectral reflectance during the tillering, jointing, and maturity stages. Based on these parameters, spectral indicators were calculated, and univariate linear regression models were developed to predict key rice quality indices. The results demonstrated that the optimal values for brown rice rate, moisture content, and taste value were 0.866, 0.913, and 0.651, with corresponding RMSE values of 0.122, 0.081, and 1.167. After optimizing the models, the values for the brown rice rate and taste value improved significantly to 0.95 (RMSE: 0.075) and 0.992 (RMSE: 0.179), respectively. Notably, the spectral index GM2 during the jointing stage achieved the highest accuracy for yield prediction, with an value of 0.822. These findings confirm that integrating multiple indicators across different growth periods enhances the accuracy of rice quality and yield predictions, offering a robust and intelligent solution for practical agricultural applications.
本研究旨在开发一种有效且可靠的方法来估算水稻品质指标和产量，以满足现代农业对快速、无损和准确预测的日益增长的需求。2018年在绥棱水利综合试验站（北纬47°27′，东经127°06′）进行了田间试验，使用龙庆稻3作为试验品种。测量内容包括分蘖期、拔节期和成熟期的叶面积指数（LAI）、叶绿素含量（SPAD）、叶片氮含量（LNC）和叶片光谱反射率。基于这些参数，计算光谱指标，并建立单变量线性回归模型来预测关键水稻品质指标。结果表明，糙米率、水分含量和食味值的最优值分别为0.866、0.913和0.651，相应的均方根误差（RMSE）值分别为0.122、0.081和1.167。模型优化后，糙米率和食味值分别显著提高到0.95（RMSE：0.075）和0.992（RMSE：0.179）。值得注意的是，拔节期的光谱指数GM2在产量预测方面达到了最高精度，值为0.822。这些发现证实，整合不同生育期的多个指标可提高水稻品质和产量预测的准确性，为实际农业应用提供了一种强大而智能的解决方案。
