当前位置: X-MOL 学术GISci. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran
GIScience & Remote Sensing ( IF 6.7 ) Pub Date : 2021-10-19 , DOI: 10.1080/15481603.2021.1991689
Ali Radman 1 , Mehdi Akhoondzadeh 1 , Benyamin Hosseiny 1
Affiliation  

ABSTRACT

InSAR processing is vastly used for land deformation monitoring from the space. Machine learning methods are known as strong tools for data modeling as well as predicting. In this study, we are going to model and predict the future behavior of land subsidence by InSAR processing and leveraging deep learning methods over the lands in the vicinity of Lake Urmia (located in the northwest of Iran). Accordingly, Sentinel-1 data over 56 months from November 2014 to June 2019 and small baseline subsets (SBAS) InSAR methods were utilized. Several regions with a high rate of subsidence were identified (maximum monthly subsidence of 13.3 mm). Furthermore, environmental factors affecting subsidence were considered. Therefore, parameters such as rainfall, groundwater, and lake area variations were measured using TRMM, GRACE, and MODIS satellite data, respectively. In order to determine and assess the relation between land deformations and environmental variations, several machine learning methods were implemented. The environmental parameters were used as the input of models and ground deformations as the target to be predicted. Eventually, ground deformations were estimated using multi-layer perceptron (MLP), convolutional neural network (CNN), and long short-term memory (LSTM) networks, in which each network had strengths and weaknesses on different occasions. Thus, by blending the forecast of the three models, a weighted ensemble was constructed, which outperformed the single models and reached the root mean square error (RMSE), mean absolute error (MAE), and standard deviation (SD) of 8.2 mm, 6.4 mm, and ±5.2 mm, respectively. The result indicated that although each single model had proper accuracy, an ensemble model can improve land deformation anticipation using the strength of networks in various conditions.



中文翻译:

结合 InSAR 和深度学习对伊朗乌尔米亚湖附近地区的沉降进行建模和预测

摘要

InSAR 处理广泛用于从空间进行土地变形监测。机器学习方法被称为数据建模和预测的强大工具。在这项研究中,我们将通过 InSAR 处理并利用深度学习方法对乌尔米亚湖(位于伊朗西北部)附近的土地进行建模和预测未来的地面沉降行为。因此,使用了 2014 年 11 月至 2019 年 6 月超过 56 个月的 Sentinel-1 数据和小型基线子集 (SBAS) InSAR 方法。确定了几个下沉率高的地区(每月最大下沉量为 13.3 毫米)。此外,还考虑了影响沉降的环境因素。因此,使用TRMM、GRACE和MODIS卫星数据测量了降雨、地下水和湖泊面积变化等参数,分别。为了确定和评估土地变形与环境变化之间的关系,实施了几种机器学习方法。环境参数作为模型的输入,地面变形作为预测目标。最终,使用多层感知器 (MLP)、卷积神经网络 (CNN) 和长短期记忆 (LSTM) 网络来估计地面变形,其中每个网络在不同情况下各有优缺点。因此,通过混合三个模型的预测,构建了一个加权集合,其性能优于单个模型,并达到了 8.2 mm 的均方根误差 (RMSE)、平均绝对误差 (MAE) 和标准偏差 (SD),分别为 6.4 毫米和 ±5.2 毫米。

更新日期:2021-12-14
down
wechat
bug