4.7 Article

Improving field boundary delineation in ResUNets via adversarial deep learning

出版社

ELSEVIER
DOI: 10.1016/j.jag.2022.102877

关键词

Field boundaries; Adversarial learning; Semantic segmentation; Transfer learning; Boundary quality

资金

  1. NSF CAREER Award [1847334]
  2. USDA NIFA Foundational Program
  3. Advanced Research Projects Agency-Energy (ARPA-E) - US Department of Energy (DOE) [DOE DE-AR0001382]
  4. Div Of Chem, Bioeng, Env, & Transp Sys
  5. Directorate For Engineering [1847334] Funding Source: National Science Foundation

向作者/读者索取更多资源

Field boundary data is essential for digital agricultural services and research, and adversarial training can significantly improve the quality and performance of field boundary prediction.
Field boundary data is often required to access digital agricultural services and tools that assist with field-level assessment and monitoring. In addition, policy-makers and researchers need field boundaries to accurately assess food security and impacts on climate change. Thus, scalable and efficient automatic field boundary detection algorithms on satellite images have direct, important implications for many stakeholders. Deep learning is one approach that has been successfully applied in recent years to field boundary detection. Qualitatively however, these boundaries are often broken or malformed, necessitating a dependence on fine-tuned post-processing methods with arbitrary thresholds obtained through trial-and-error. Prior work has explored various architec-tures for predicting field boundaries, but little has been done beyond traditional supervised learning regimes. Thus, in this work, we propose a new approach to improving field boundary prediction by using an adversarial training framework. In particular, we investigated the effects of training a ResUNet model (a standard fully convolutional network architecture) as a generator in a traditional generative adversarial network (GAN) setup, on 30 meter resolution satellite imagery from 2017 over the state of Illinois. We then explored whether or not our methods can be transferred to label-scarce regions in Brazil. Overall, our results showed that adversarial training substantially improved boundary quality and performance, but had a lesser effect when transferred to unseen, low-data agricultural landscapes. Based on these findings, we conclude that adversarial training is a promising way to improve boundary quality during prediction time, and we suggest several ideas for future improvements that may make adversarial training more viable in transfer learning.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据