Department of Agronomy and Plant Breeding, Faculty of Agricultural Sciences, University of Guilan, Rasht, Iran.
Department of Biosystems Engineering, Faculty of Agricultural Sciences, University of Guilan, Rasht, Iran.
PLoS One. 2022 Jul 11;17(7):e0271201. doi: 10.1371/journal.pone.0271201. eCollection 2022.
Plant leaf area (LA) is a key metric in plant monitoring programs. Machine learning methods were used in this study to estimate the LA of four plum genotypes, including three greengage genotypes (Prunus domestica [subsp. italica var. claudiana.]) and a single myrobalan plum (prunus ceracifera), using leaf length (L) and width (W) values. To develop reliable models, 5548 leaves were subjected to experiments in two different years, 2019 and 2021. Image processing technique was used to extract dimensional leaf features, which were then fed into Linear Multivariate Regression (LMR), Support Vector Regression (SVR), Artificial Neural Networks (ANN), and the Adaptive Neuro-Fuzzy Inference System (ANFIS). Model evaluation on 2019 data revealed that the LMR structure LA = 0.007+0.687 L×W was the most accurate among the various LMR structures, with R2 = 0.9955 and Root Mean Squared Error (RMSE) = 0.404. In this case, the linear kernel-based SVR yielded an R2 of 0.9955 and an RMSE of 0.4871. The ANN (R2 = 0.9969; RMSE = 0.3420) and ANFIS (R2 = 0.9971; RMSE = 0.3240) models demonstrated greater accuracy than the LMR and SVR models. Evaluating the models mentioned above on data from various genotypes in 2021 proved their applicability for estimating LA with high accuracy in subsequent years. In another research segment, LA prediction models were developed using data from 2021, and evaluations demonstrated the superior performance of ANN and ANFIS compared to LMR and SVR models. ANFIS, ANN, LMR, and SVR exhibited R2 values of 0.9971, 0.9969, 0.9950, and 0.9948, respectively. It was concluded that by combining image analysis and modeling through ANFIS, a highly accurate smart non-destructive LA measurement system could be developed.
植物叶面积（LA）是植物监测计划中的一个关键指标。本研究使用机器学习方法来估算四个李基因型的 LA，包括三个青梅基因型（Prunus domestica [subsp. italica var. claudiana.]) 和一个单种西洋李（prunus ceracifera），使用叶长（L）和叶宽（W）值。为了开发可靠的模型，在 2019 年和 2021 年两个不同的年份中对 5548 片叶子进行了实验。使用图像处理技术提取叶片尺寸特征，然后将其输入到线性多元回归（LMR）、支持向量回归（SVR）、人工神经网络（ANN）和自适应神经模糊推理系统（ANFIS）中。对 2019 年数据的模型评估表明，在各种 LMR 结构中，LA = 0.007+0.687 L×W 结构最为准确，R2 = 0.9955，根均方误差（RMSE）= 0.404。在这种情况下，基于线性核的 SVR 产生的 R2 为 0.9955，RMSE 为 0.4871。ANN（R2 = 0.9969；RMSE = 0.3420）和 ANFIS（R2 = 0.9971；RMSE = 0.3240）模型的准确性均高于 LMR 和 SVR 模型。在 2021 年对不同基因型的数据评估上述模型表明，它们可以在后续年份中以高精度估算 LA。在另一个研究部分中，使用 2021 年的数据开发了 LA 预测模型，评估结果表明，ANN 和 ANFIS 模型的性能优于 LMR 和 SVR 模型。ANN、ANFIS、LMR 和 SVR 的 R2 值分别为 0.9971、0.9969、0.9950 和 0.9948。因此，可以得出结论，通过结合图像分析和通过 ANFIS 进行建模，可以开发出一种高度精确的智能非破坏性 LA 测量系统。
