Electrical Engineering & Computer Science Department, UC Berkeley, USA.
Global Policy Laboratory, Goldman School of Public Policy, UC Berkeley, USA.
Nat Commun. 2021 Jul 20;12(1):4392. doi: 10.1038/s41467-021-24638-z.
Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its accessibility and use. We show that a single encoding of satellite imagery can generalize across diverse prediction tasks (e.g., forest cover, house price, road length). Our method achieves accuracy competitive with deep neural networks at orders of magnitude lower computational cost, scales globally, delivers label super-resolution predictions, and facilitates characterizations of uncertainty. Since image encodings are shared across tasks, they can be centrally computed and distributed to unlimited researchers, who need only fit a linear regression to their own ground truth data in order to achieve state-of-the-art SIML performance.
卫星图像与机器学习相结合（SIML）有可能通过远程估计数据匮乏地区的社会经济和环境条件来应对全球挑战，但 SIML 的资源要求限制了它的可访问性和使用。我们表明，卫星图像的单一编码可以在不同的预测任务中进行泛化（例如，森林覆盖、房价、道路长度）。我们的方法以低几个数量级的计算成本实现了与深度神经网络相竞争的精度，具有全球可扩展性，提供标签超分辨率预测，并有助于不确定性的描述。由于图像编码在任务之间是共享的，因此可以集中计算并分发给无限数量的研究人员，这些研究人员只需将线性回归拟合到自己的地面实况数据，就可以实现最先进的 SIML 性能。
