A machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction

Land subsidence is a worldwide threat that may cause irreversible damage to the environment and the infrastructures. Thus, identifying and mapping areas prone to land subsidence with accurate methods such as Land Subsidence Susceptibility Index (LSSI) mapping is crucial for mitigating the adverse im...

Full description

Saved in:
Bibliographic Details
Main Authors: Diana Orlandi, Esteban Díaz, Roberto Tomás, Federico A. Galatolo, Mario G.C.A. Cimino, Carolina Pagli, Nicola Perilli
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Applied Computing and Geosciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590197424000545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850065551949299712
author Diana Orlandi
Esteban Díaz
Roberto Tomás
Federico A. Galatolo
Mario G.C.A. Cimino
Carolina Pagli
Nicola Perilli
author_facet Diana Orlandi
Esteban Díaz
Roberto Tomás
Federico A. Galatolo
Mario G.C.A. Cimino
Carolina Pagli
Nicola Perilli
author_sort Diana Orlandi
collection DOAJ
description Land subsidence is a worldwide threat that may cause irreversible damage to the environment and the infrastructures. Thus, identifying and mapping areas prone to land subsidence with accurate methods such as Land Subsidence Susceptibility Index (LSSI) mapping is crucial for mitigating the adverse impacts of this geohazard. Also, Machine Learning (ML) is now becoming a powerful tool to analyze vast and different datasets such as those necessary for LSSI mapping. In this study, we use the conventional Frequency Ratio (FR) method and ML models to generate LSSI maps of the region of Murcia (Spain) where land subsidence occurred in the past due to groundwater overdraft. A LSSI map was initially generated with known FR. Then, additional Conditioning Factors (CFs) with increased spatial resolution were used to train several ML models and generate a new LSSI map. The Extra-Trees Classifier (ETC) outperformed the other approaches, achieving the best performance with a weighted average precision and F1-Score of 0.96, after optimizing its hyperparameters. Then, a third LSSI map was calculated using the FR method and observations of land subsidence from InSAR (Interferometric Synthetic Aperture Radar). This study shows that the effectiveness of using several CFs depends on the added information of each layer. Moreover, the comparison between the different LSSI maps and InSAR data highlights the crucial role of the spatial resolution for accurate mapping, thus enhancing land subsidence risk assessment.
format Article
id doaj-art-852867c967ef41d0b81c2c0fe2e3a8a3
institution DOAJ
issn 2590-1974
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Applied Computing and Geosciences
spelling doaj-art-852867c967ef41d0b81c2c0fe2e3a8a32025-08-20T02:48:58ZengElsevierApplied Computing and Geosciences2590-19742024-12-012410020710.1016/j.acags.2024.100207A machine learning approach for mapping susceptibility to land subsidence caused by ground water extractionDiana Orlandi0Esteban Díaz1Roberto Tomás2Federico A. Galatolo3Mario G.C.A. Cimino4Carolina Pagli5Nicola Perilli6Dept. of Information Engineering, University of Pisa, Pisa, 56122, Italy; Corresponding author. Dept. of Information Engineering, University of Pisa, via G. Caruso 16, Pisa, 56122, Italy.Dept. of Civil Engineering, University of Alicante, Alicante, 03080, SpainDept. of Civil Engineering, University of Alicante, Alicante, 03080, SpainDept. of Information Engineering, University of Pisa, Pisa, 56122, ItalyDept. of Information Engineering, University of Pisa, Pisa, 56122, ItalyDept. of Earth Sciences, University of Pisa, Pisa, 56126, ItalyDept. of Civil and Industrial Engineering, University of Pisa, Pisa, 56122, ItalyLand subsidence is a worldwide threat that may cause irreversible damage to the environment and the infrastructures. Thus, identifying and mapping areas prone to land subsidence with accurate methods such as Land Subsidence Susceptibility Index (LSSI) mapping is crucial for mitigating the adverse impacts of this geohazard. Also, Machine Learning (ML) is now becoming a powerful tool to analyze vast and different datasets such as those necessary for LSSI mapping. In this study, we use the conventional Frequency Ratio (FR) method and ML models to generate LSSI maps of the region of Murcia (Spain) where land subsidence occurred in the past due to groundwater overdraft. A LSSI map was initially generated with known FR. Then, additional Conditioning Factors (CFs) with increased spatial resolution were used to train several ML models and generate a new LSSI map. The Extra-Trees Classifier (ETC) outperformed the other approaches, achieving the best performance with a weighted average precision and F1-Score of 0.96, after optimizing its hyperparameters. Then, a third LSSI map was calculated using the FR method and observations of land subsidence from InSAR (Interferometric Synthetic Aperture Radar). This study shows that the effectiveness of using several CFs depends on the added information of each layer. Moreover, the comparison between the different LSSI maps and InSAR data highlights the crucial role of the spatial resolution for accurate mapping, thus enhancing land subsidence risk assessment.http://www.sciencedirect.com/science/article/pii/S2590197424000545Land subsidenceSusceptibility mappingMachine learningInSAR
spellingShingle Diana Orlandi
Esteban Díaz
Roberto Tomás
Federico A. Galatolo
Mario G.C.A. Cimino
Carolina Pagli
Nicola Perilli
A machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction
Applied Computing and Geosciences
Land subsidence
Susceptibility mapping
Machine learning
InSAR
title A machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction
title_full A machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction
title_fullStr A machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction
title_full_unstemmed A machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction
title_short A machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction
title_sort machine learning approach for mapping susceptibility to land subsidence caused by ground water extraction
topic Land subsidence
Susceptibility mapping
Machine learning
InSAR
url http://www.sciencedirect.com/science/article/pii/S2590197424000545
work_keys_str_mv AT dianaorlandi amachinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT estebandiaz amachinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT robertotomas amachinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT federicoagalatolo amachinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT mariogcacimino amachinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT carolinapagli amachinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT nicolaperilli amachinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT dianaorlandi machinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT estebandiaz machinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT robertotomas machinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT federicoagalatolo machinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT mariogcacimino machinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT carolinapagli machinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction
AT nicolaperilli machinelearningapproachformappingsusceptibilitytolandsubsidencecausedbygroundwaterextraction