Automated classification of A-DInSAR-based ground deformation by using random forest

被引:7
作者
Festa, Davide [1 ]
Casagli, Nicola [1 ,2 ]
Casu, Francesco [3 ]
Confuorto, Pierluigi [1 ]
De Luca, Claudio [3 ]
Del Soldato, Matteo [1 ]
Lanari, Riccardo [3 ]
Manunta, Michele [3 ]
Manzo, Mariarosaria [3 ]
Raspini, Federico [1 ]
机构
[1] Univ Firenze, Dept Earth Sci, Florence, Italy
[2] Natl Inst Oceanog & Appl Geophys OGS, Trieste, Italy
[3] IREA CNR, Naples, Italy
基金
欧盟地平线“2020”;
关键词
Ground deformation; A-DInSAR; machine learning; random forest; automated classification; SBAS APPROACH; ALGORITHM; INTERFEROMETRY; SCATTERERS; SERVICE; AREAS;
D O I
10.1080/15481603.2022.2134561
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
Wide-area ground motion monitoring is nowadays achievable via advanced Differential Interferometry SAR (A-DInSAR) techniques which benefit from the availability of large sets of Copernicus Sentinel-1 images. However, it is of primary importance to implement automated solutions aimed at performing integrated analysis of large amounts of interferometric data. To effectively detect high-displacement areas and classify ground motion sources, here we explore the feasibility of a machine learning-based approach. This is achieved by applying the random forest (RF) technique to large-scale deformation maps spanning 2015-2018. Focusing on the northern part of Italy, we train the model to identify landslide, subsidence, and mining-related ground motion with which to construct a balanced training dataset. The presence of noisy signals and other sources of deformation is also tackled within the model construction. The proposed approach relies on the use of explanatory variables extracted from the A-DInSAR datasets and from freely accessible informative layers such as Digital Elevation Model (DEM), land cover maps, and geohazard inventories. In general, the model performance is very promising as we achieved an overall accuracy of 0.97, a true positive rate of 0.94 and an F1-Score of 0.93. The obtained outcomes demonstrate that such transferable and automated approach may constitute an asset for stakeholders in the framework of geohazards risk management.
引用
收藏
页码:1749 / 1766
页数:18
相关论文
共 69 条
[1]   Application of Machine Learning to Classification of Volcanic Deformation in Routinely Generated InSAR Data [J].
Anantrasirichai, N. ;
Biggs, J. ;
Albino, F. ;
Hill, P. ;
Bull, D. .
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH, 2018, 123 (08) :6592-6606
[2]   Detecting Ground Deformation in the Built Environment Using Sparse Satellite InSAR Data With a Convolutional Neural Network [J].
Anantrasirichai, Nantheera ;
Biggs, Juliet ;
Kelevitz, Krisztina ;
Sadeghi, Zahra ;
Wright, Tim ;
Thompson, James ;
Achim, Alin Marian ;
Bull, David .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (04) :2940-2950
[3]   Study of Systematic Bias in Measuring Surface Deformation With SAR Interferometry [J].
Ansari, Homa ;
De Zan, Francesco ;
Parizzi, Alessandro .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (02) :1285-1301
[4]   A-DInSAR Performance for Updating Landslide Inventory in Mountain Areas: An Example from Lombardy Region (Italy) [J].
Antonielli, Benedetta ;
Mazzanti, Paolo ;
Rocca, Alfredo ;
Bozzano, Francesca ;
Dei Cas, Luca .
GEOSCIENCES, 2019, 9 (09)
[5]   InSAR full-resolution analysis of the 2017-2018 M > 6 earthquakes in Mexico [J].
Atzori, Simone ;
Antonioli, Andrea ;
Tolomei, Cristiano ;
De Novellis, Vincenzo ;
De Luca, Claudio ;
Monterroso, Fernando .
REMOTE SENSING OF ENVIRONMENT, 2019, 234
[6]   Landslide susceptibility mapping using GIS-based weighted linear combination, the case in Tsugawa area of Agano River, Niigata Prefecture, Japan [J].
Ayalew, Lulseged ;
Yamagishi, Hiromitsu ;
Ugawa, Norimitsu .
LANDSLIDES, 2004, 1 (01) :73-81
[7]   Synthetic aperture radar interferometry [J].
Bamler, R ;
Hartl, P .
INVERSE PROBLEMS, 1998, 14 (04) :R1-R54
[8]   A Methodology to Detect and Update Active Deformation Areas Based on Sentinel-1 SAR Images [J].
Barra, Anna ;
Solari, Lorenzo ;
Bejar-Pizarro, Marta ;
Monserrat, Oriol ;
Bianchini, Silvia ;
Herrera, Gerardo ;
Crosetto, Michele ;
Sarro, Roberto ;
Gonzalez-Alonso, Elena ;
Maria Mateos, Rosa ;
Liguerzana, Sergio ;
Lopez, Carmen ;
Moretti, Sandro .
REMOTE SENSING, 2017, 9 (10)
[9]   A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms [J].
Berardino, P ;
Fornaro, G ;
Lanari, R ;
Sansosti, E .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2002, 40 (11) :2375-2383
[10]   Landslide HotSpot Mapping by means of Persistent Scatterer Interferometry [J].
Bianchini, Silvia ;
Cigna, Francesca ;
Righini, Gaia ;
Proietti, Chiara ;
Casagli, Nicola .
ENVIRONMENTAL EARTH SCIENCES, 2012, 67 (04) :1155-1172