Agricultural research is essential for increasing food production to meet the requirements of an increasing population in the coming decades. Recently, satellite technology has been improving rapidly and deep learning has seen much success in generic computer vision tasks and many application areas which presents an important opportunity to improve analysis of agricultural land. Here we present a systematic review of 150 studies to find the current uses of deep learning on satellite imagery for agricultural research. Although we identify 5 categories of agricultural monitoring tasks, the majority of the research interest is in crop segmentation and yield prediction. We found that, when used, modern deep learning methods consistently outperformed traditional machine learning across most tasks; the only exception was that Long Short-Term Memory (LSTM) Recurrent Neural Networks did not consistently outperform Random Forests (RF) for yield prediction. The reviewed studies have largely adopted methodologies from generic computer vision, except for one major omission: benchmark datasets are not utilised to evaluate models across studies, making it difficult to compare results. Additionally, some studies have specifically utilised the extra spectral resolution available in satellite imagery, but other divergent properties of satellite images - such as the hugely different scales of spatial patterns - are not being taken advantage of in the reviewed studies.

翻译：农业研究对于在未来几十年满足日益增长人口的粮食需求至关重要。近年来，卫星技术快速发展，深度学习在通用计算机视觉任务及诸多应用领域取得了显著成功，这为改善农业用地分析提供了重要机遇。本文对150项研究进行了系统综述，以探索深度学习在卫星图像农业研究中的当前应用。尽管我们识别出5类农业监测任务，但研究兴趣主要集中在作物分割和产量预测方面。研究发现，在大多数任务中，现代深度学习方法始终优于传统机器学习；唯一的例外是，在产量预测任务中，长短期记忆（LSTM）循环神经网络并未始终优于随机森林（RF）方法。被综述的研究很大程度上借鉴了通用计算机视觉的方法，但存在一个重大不足：未使用基准数据集跨研究评估模型，导致结果难以比较。此外，部分研究专门利用了卫星图像中额外的光谱分辨率，但卫星图像的其他差异性特征（如空间模式尺度悬殊）并未在被综述的研究中得到充分利用。