Abstract

Accurate estimation of above-ground biomass (AGB) plays a significant role in characterizing crop growth status. In precision agriculture area, a widely-used method for measuring AGB is to develop regression relationships between AGB and agronomic traits extracted from multi-source remotely sensed images based on unmanned aerial vehicle (UAV) systems. However, such approach requires expert knowledges and causes the information loss of raw images. The objectives of this study are to (i) determine how multi-source images contribute to AGB estimation in single and whole growth stages; (ii) evaluate the robustness and adaptability of deep convolutional neural networks (DCNN) and other machine learning algorithms regarding AGB estimation. To establish multi-source image datasets, this study collected UAV red-green-blue (RGB), multispectral (MS) images and constructed the raster data for crop surface models (CSMs). Agronomic features were derived from the above-mentioned images and interpreted by the multiple linear regression, random forest, and support vector machine models. Then, a DCNN model was developed via an image-fusion architecture. Results show that the DCNN model provides the best estimation of maize AGB when a single type of image is considered, while the performance of DCNN degrades when sufficient agronomic features are used. Besides, the information of above three image datasets changes with various growth stages. The structure information derived from CSM images are more valuable than spectrum information derived from RGB and MS images in the vegetative stage, but less useful in the reproductive stage. Finally, a data fusion strategy was proposed according to the onboard sensors (or cost).

中文翻译：

---

使用多源无人机图像估计玉米地上生物量的深度卷积神经网络：与传统机器学习算法的比较

摘要

地上生物量 (AGB) 的准确估计在表征作物生长状态方面起着重要作用。在精准农业领域，广泛使用的 AGB 测量方法是建立 AGB 与基于无人机（UAV）系统的多源遥感图像提取的农艺性状之间的回归关系。然而，这种方法需要专业知识并导致原始图像的信息丢失。本研究的目的是 (i) 确定多源图像如何有助于单个和整个生长阶段的 AGB 估计；(ii) 评估深度卷积神经网络 (DCNN) 和其他机器学习算法在 AGB 估计方面的鲁棒性和适应性。为了建立多源图像数据集，本研究收集了无人机红绿蓝（RGB），多光谱 (MS) 图像并为作物表面模型 (CSM) 构建栅格数据。农艺特征来源于上述图像，并通过多元线性回归、随机森林和支持向量机模型进行解释。然后，通过图像融合架构开发了 DCNN 模型。结果表明，当考虑单一类型的图像时，DCNN 模型提供了对玉米 AGB 的最佳估计，而当使用足够的农艺特征时，DCNN 的性能会下降。此外，上述三个图像数据集的信息随着不同的成长阶段而变化。从 CSM 图像得到的结构信息在营养阶段比从 RGB 和 MS 图像得到的光谱信息更有价值，但在繁殖阶段用处不大。最后，