Phase unwrapping, also known as ambiguity resolution, is an underdetermined problem in which assumptions must be made to obtain a result in SAR interferometry (InSAR) time series analysis. This problem is particularly acute for distributed scatterer InSAR, in which noise levels can be so large that they are comparable in magnitude to the signal of investigation. In addition, deformation rates can be highly nonlinear and orders of magnitude larger than neighboring point scatterers, which may be part of a more stable object. The combination of these factors has often proven too challenging for the conventional InSAR processing methods to successfully monitor these regions. We present a methodology which allows for additional environmental information to be integrated into the phase unwrapping procedure, thereby alleviating the problems described above. We show how problematic epochs that cause errors in the temporal phase unwrapping process can be anticipated by the machine learning algorithms which can create categorical predictions about the relative ambiguity level based on the readily available meteorological data. These predictions significantly assist in the interpretation of large changes in the wrapped interferometric phase and enable the monitoring of environments not previously possible using standard minimum gradient phase unwrapping techniques.

中文翻译：

---

上下文信息和人工智能引导的 InSAR 位移相位概率估计


相位展开，也称为模糊度解析，是一个待定问题，必须做出假设才能获得 SAR 干涉测量 (InSAR) 时间序列分析的结果。这个问题对于分布式散射体干涉合成孔径雷达 (InSAR) 来说尤其严重，其中噪声水平可能非常大，以至于其幅度与调查信号相当。此外，变形率可能是高度非线性的，并且比相邻点散射体大几个数量级，这可能是更稳定物体的一部分。事实证明，这些因素的结合往往对于传统 InSAR 处理方法来说很难成功监测这些区域。我们提出了一种方法，允许将额外的环境信息集成到相位展开过程中，从而减轻上述问题。我们展示了机器学习算法如何预测在时间相位展开过程中导致错误的有问题的时期，该算法可以根据容易获得的气象数据创建关于相对模糊度水平的分类预测。这些预测极大地有助于解释包裹干涉相位的巨大变化，并能够监测以前使用标准最小梯度相位展开技术不可能实现的环境。