当前位置: X-MOL 学术Precision Agric. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Detecting the attack of the fall armyworm (Spodoptera frugiperda) in cotton plants with machine learning and spectral measurements
Precision Agriculture ( IF 6.2 ) Pub Date : 2021-08-31 , DOI: 10.1007/s11119-021-09845-4
Ana Paula Marques Ramos 1, 2 , Felipe David Georges Gomes 1 , Mayara Maezano Faita Pinheiro 1 , Danielle Elis Garcia Furuya 1 , Wesley Nunes Gonçalvez 3 , José Marcato Junior 3 , Mirian Fernandes Furtado Michereff 4 , Maria Carolina Blassioli-Moraes 4 , Miguel Borges 4 , Raúl Alberto Alaumann 4 , Veraldo Liesenberg 5 , Lúcio André de Castro Jorge 6 , Lucas Prado Osco 7
Affiliation  

The Spodoptera frugiperda (i.e., fall armyworm) causes irreversible damage in cotton cultivars, and its visual inspection on plants is a burdensome task for humans. A recent strategy to automatically do similar tasks is processing hyperspectral reflectance measurements with machine learning algorithms. Herein, its proposed a framework for modeling the spectral response of cotton plants under the fall armyworm attacks using machine learning algorithms, culminating in a theoretical model creation based on the band simulation process. A controlled experiment was conducted to collect hyperspectral radiance measurements from health and damage cotton plants over eight days. A hand-held spectroradiometer operating from 350 to 2500 nm was used. Several algorithms were evaluated, and a ranking approach was adopted to identify the most contributive wavelengths for detecting the damage. The Self-Organizing Map method was applied to organize the spectral wavelengths into groups, favoring the theoretical model creation for two sensors: OLI (Landsat-8) and MSI (Sentinel-2). It was found that the Random Forest algorithm produced the most suitable model, and the last day of analysis was better to separate healthy and damaged plants (F-measure: 0.912). The best spectral regions range from the red to near-infrared (650 to 1350 nm) and the shortwave infrared (1570 to 1640 nm). The theoretical model returned accurate results using both sensors (OLI, F-Measure = 0.865, and MSI, F-Measure = 0.886). In conclusion, the proposed framework contributes to accurately identifying cotton plants under the Spodoptera frugiperda attack for both hyperspectral and multispectral scales.



中文翻译:

通过机器学习和光谱测量检测棉花植株中秋粘虫(草地贪夜蛾)的攻击

草地夜蛾(即秋粘虫)对棉花品种造成不可逆转的损害,其对植物的目视检查对人类来说是一项繁重的任务。最近自动执行类似任务的一种策略是使用机器学习算法处理高光谱反射率测量。在此,它提出了一个框架,用于使用机器学习算法对秋粘虫攻击下棉花植物的光谱响应进行建模,最终基于波段模拟过程创建了理论模型。进行了一项受控实验,以在八天内从健康和损坏的棉花植株中收集高光谱辐射测量值。使用在 350 至 2500 nm 范围内操作的手持式光谱辐射计。评估了几种算法,并采用排序方法来确定最有助于检测损坏的波长。自组织映射方法用于将光谱波长组织成组,有利于为两个传感器创建理论模型:OLI (Landsat-8) 和 MSI (Sentinel-2)。发现随机森林算法产生了最合适的模型,分析的最后一天更好地分离了健康和受损植物(F-measure:0.912)。最佳光谱区域范围从红色到近红外(650 到 1350 nm)和短波红外(1570 到 1640 nm)。理论模型使用两种传感器(OLI,F-Measure = 0.865 和 MSI,F-Measure = 0.886)返回准确结果。总之,拟议的框架有助于准确识别棉花植物 自组织映射方法用于将光谱波长组织成组,有利于为两个传感器创建理论模型:OLI (Landsat-8) 和 MSI (Sentinel-2)。发现随机森林算法产生了最合适的模型,分析的最后一天更好地分离了健康和受损植物(F-measure:0.912)。最佳光谱区域范围从红色到近红外(650 到 1350 nm)和短波红外(1570 到 1640 nm)。理论模型使用两种传感器(OLI,F-Measure = 0.865 和 MSI,F-Measure = 0.886)返回准确结果。总之,拟议的框架有助于准确识别棉花植物 自组织映射方法用于将光谱波长组织成组,有利于为两个传感器创建理论模型:OLI (Landsat-8) 和 MSI (Sentinel-2)。发现随机森林算法产生了最合适的模型,分析的最后一天更好地分离了健康和受损植物(F-measure:0.912)。最佳光谱区域范围从红色到近红外(650 到 1350 nm)和短波红外(1570 到 1640 nm)。理论模型使用两种传感器(OLI,F-Measure = 0.865 和 MSI,F-Measure = 0.886)返回准确结果。总之,拟议的框架有助于准确识别棉花植物 OLI (Landsat-8) 和 MSI (Sentinel-2)。发现随机森林算法产生了最合适的模型,分析的最后一天更好地分离了健康和受损植物(F-measure:0.912)。最佳光谱区域范围从红色到近红外(650 到 1350 nm)和短波红外(1570 到 1640 nm)。理论模型使用两种传感器(OLI,F-Measure = 0.865 和 MSI,F-Measure = 0.886)返回准确结果。总之,拟议的框架有助于准确识别棉花植物 OLI (Landsat-8) 和 MSI (Sentinel-2)。发现随机森林算法产生了最合适的模型,分析的最后一天更好地分离了健康和受损植物(F-measure:0.912)。最佳光谱区域范围从红色到近红外(650 到 1350 nm)和短波红外(1570 到 1640 nm)。理论模型使用两种传感器(OLI,F-Measure = 0.865 和 MSI,F-Measure = 0.886)返回准确结果。总之,拟议的框架有助于准确识别棉花植物 最佳光谱区域范围从红色到近红外(650 到 1350 nm)和短波红外(1570 到 1640 nm)。理论模型使用两种传感器(OLI,F-Measure = 0.865 和 MSI,F-Measure = 0.886)返回准确结果。总之,拟议的框架有助于准确识别棉花植物 最佳光谱区域范围从红色到近红外(650 到 1350 nm)和短波红外(1570 到 1640 nm)。理论模型使用两种传感器(OLI,F-Measure = 0.865 和 MSI,F-Measure = 0.886)返回准确结果。总之,拟议的框架有助于准确识别棉花植物Spodoptera frugiperda攻击高光谱和多光谱尺度。

更新日期:2021-09-01
down
wechat
bug