本文为加拿大韦仕敦大学（作者：HwangLee）的硕士论文，共118页。

由于氮肥施用对环境和经济的影响，如何优化作物氮肥施用量，使氮肥供应量与作物需氮量准确匹配，一直是人们研究的热点。过量的氮会渗入农田周围的水源，造成农民不必要的支出。了解作物状况的详细空间信息被称为精确农业（precision agriculture），这一农业管理技术使农民能够最大限度地提高产量和利润，同时减少化肥、农药、水和杀虫剂的投入。

本研究的目的是记录和测试使用无人机（UAV）预测安大略省西南部小麦和玉米田中氮重的适用性和可行性。通过调查使用各种统计建模技术，以达到最佳精度。机器学习技术如随机森林和支持向量回归被用来提供比传统线性回归模型更稳健的模型。研究结果表明，大部分光谱指标与冠层氮重呈非线性关系，各变量之间具有高度的多重共线性。本文利用无人机遥感影像，给出了小麦和玉米田氮素最终预测图和模型。

The optimization of crop nitrogenfertilization to accurately predict and match the nitrogen (N) supply to thecrop N demand is the subject of intense research due to the environmental andeconomic impact of N fertilization. Excess N could seep into the water suppliesaround the field and cause unnecessary spending by farmers. Understanding thedetailed spatial information about a crop status is known as a farmingmanagement technique called precision agriculture, which allows farmers tomaximize their yield and profit while reducing the inputs of fertilizers,pesticides, water, and insecticides. The goal of this study is to document andtest the applicability and feasibility of using Unmanned Aerial Vehicle (UAV)to predict nitrogen weight of wheat and corn fields in south-west Ontario. Thisis investigated using various statistical modelling techniques to achieve thebest accuracy. Machine learning techniques such as Random Forests and SupportVector Regression are used, which provide more robust models than traditionallinear regression models. The results demonstrate that most spectral indiceshave a non-linear relationship with canopy nitrogen weight and show high degreeof multicollinearity among the variables. In this thesis, the final nitrogenprediction maps of wheat and corn fields using UAV images and the derivedmodels are provided.

1.  引言

2. 基于无人机图像的小麦和玉米田冠层氮素反演

3. 利用线性回归、随机森林和支持向量机结合无人机多光谱图像预测玉米冠层氮含量

4. 结论与展望

更多精彩文章请关注公众号：