Colegio de Postgraduados, Campus Montecillo, Carretera Federal Mexico-Texcoco, km. 36.5, Montecillo, Texcoco 56230, State of Mexico, Mexico.
Colegio Mexicano de Especialistas en Recursos Naturales AC, De las Flores no. 8 s/n, San Luis Huexotla, Texcoco 56220, State of Mexico, Mexico.
Sensors (Basel). 2021 Dec 24;22(1):94. doi: 10.3390/s22010094.
The scarcity of water for agricultural use is a serious problem that has increased due to intense droughts, poor management, and deficiencies in the distribution and application of the resource. The monitoring of crops through satellite image processing and the application of machine learning algorithms are technological strategies with which developed countries tend to implement better public policies regarding the efficient use of water. The purpose of this research was to determine the main indicators and characteristics that allow us to discriminate the phenological stages of maize crops ( L.) in Sentinel 2 satellite images through supervised classification models. The training data were obtained by monitoring cultivated plots during an agricultural cycle. Indicators and characteristics were extracted from 41 Sentinel 2 images acquired during the monitoring dates. With these images, indicators of texture, vegetation, and colour were calculated to train three supervised classifiers: linear discriminant (LD), support vector machine (SVM), and k-nearest neighbours (kNN) models. It was found that 45 of the 86 characteristics extracted contributed to maximizing the accuracy by stage of development and the overall accuracy of the trained classification models. The characteristics of the Moran's local indicator of spatial association (LISA) improved the accuracy of the classifiers when applied to the Lab* colour model and to the near-infrared (NIR) band. The local binary pattern (LBP) increased the accuracy of the classification when applied to the red, green, blue (RGB) and NIR bands. The colour ratios, leaf area index (LAI), RGB colour model, Lab* colour space, LISA, and LBP extracted the most important intrinsic characteristics of maize crops with regard to classifying the phenological stages of the maize cultivation. The quadratic SVM model was the best classifier of maize crop phenology, with an overall accuracy of 82.3%.
农业用水短缺是一个严重的问题，由于干旱加剧、管理不善以及资源分配和应用不足，这一问题变得更加严重。通过卫星图像处理监测作物和应用机器学习算法是发达国家倾向于实施更好的公共政策以实现水资源高效利用的技术策略。本研究的目的是确定主要指标和特征，以便通过有监督分类模型从 Sentinel-2 卫星图像中区分玉米作物（ L.）的物候阶段。训练数据是通过在农业周期内监测种植地块获得的。从 41 张在监测日期获取的 Sentinel-2 图像中提取了指标和特征。利用这些图像，计算了纹理、植被和颜色的指标，以训练三个有监督分类器：线性判别（LD）、支持向量机（SVM）和 k-最近邻（kNN）模型。结果发现，在所提取的 86 个特征中有 45 个特征有助于最大限度地提高各发育阶段和训练分类模型的整体精度。Moran's 局部空间关联（LISA）特征的应用提高了分类器在 Lab颜色模型和近红外（NIR）波段的精度。局部二值模式（LBP）应用于红、绿、蓝（RGB）和 NIR 波段时提高了分类精度。颜色比、叶面积指数（LAI）、RGB 颜色模型、Lab颜色空间、LISA 和 LBP 提取了与玉米作物分类物候阶段最相关的内在特征。二次 SVM 模型是玉米作物物候最佳分类器，整体精度为 82.3%。
