Barocco Rebecca L, Clohessy James W, O'Brien G Kelly, Dufault Nicholas S, Anco Daniel J, Small Ian M
North Florida Research and Education Center, Department of Plant Pathology, University of Florida Institute of Food and Agricultural Sciences, Quincy, FL 32351.
Department of Plant Pathology, University of Florida Institute of Food and Agricultural Sciences, Gainesville, FL 32611.
Plant Dis. 2024 Feb;108(2):416-425. doi: 10.1094/PDIS-05-23-0847-RE. Epub 2024 Feb 18.
Early leaf spot () and late leaf spot () are two of the most economically important foliar fungal diseases of peanut, often requiring seven to eight fungicide applications to protect against defoliation and yield loss. Rust () may also cause significant defoliation depending on season and location. Sensor technologies are increasingly being utilized to objectively monitor plant disease epidemics for research and supporting integrated management decisions. This study aimed to develop an algorithm to quantify peanut disease defoliation using multispectral imagery captured by an unmanned aircraft system. The algorithm combined the Green Normalized Difference Vegetation Index and the Modified Soil-Adjusted Vegetation Index and included calibration to site-specific peak canopy growth. Beta regression was used to train a model for percent net defoliation with observed visual estimations of the variety 'GA-06G' (0 to 95%) as the target and imagery as the predictor (train: pseudo- = 0.71, test k-fold cross-validation: = 0.84 and RMSE = 4.0%). The model performed well on new data from two field trials not included in model training that compared 25 ( = 0.79, RMSE = 3.7%) and seven ( = 0.87, RMSE = 9.4%) fungicide programs. This objective method of assessing mid-to-late season disease severity can be used to assist growers with harvest decisions and researchers with reproducible assessment of field experiments. This model will be integrated into future work with proximal ground sensors for pathogen identification and early season disease detection.[Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY 4.0 International license.
早叶斑病（）和晚叶斑病（）是花生两种在经济上最重要的叶部真菌病害，通常需要喷施七到八次杀菌剂来防止落叶和产量损失。锈病（）也可能根据季节和地点导致严重落叶。传感器技术越来越多地被用于客观监测植物病害流行情况，以用于研究和支持综合管理决策。本研究旨在开发一种算法，利用无人机系统拍摄的多光谱图像来量化花生病害落叶情况。该算法结合了绿色归一化植被指数和修正土壤调节植被指数，并针对特定地点的冠层生长峰值进行了校准。使用贝塔回归训练了一个净落叶百分比模型，以品种“GA - 06G”的视觉观测估计值（0至95%）为目标，图像为预测变量（训练：伪 = 0.71，测试k折交叉验证： = 0.84，均方根误差 = 4.0%）。该模型在模型训练未包含的两个田间试验的新数据上表现良好，这两个试验比较了25种（ = 0.79，均方根误差 = 3.7%）和七种（ = 0.87，均方根误差 = 9.4%）杀菌剂方案。这种评估花生生长中后期病害严重程度的客观方法可用于帮助种植者做出收获决策，并帮助研究人员对田间试验进行可重复评估。该模型将被整合到未来与近端地面传感器的合作中，用于病原体识别和早期病害检测。[公式：见正文] 版权所有© 2024作者。本文是一篇根据知识共享署名4.0国际许可协议分发的开放获取文章。
