Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques
Groundwater over-abstraction may cause land subsidence (LS), and the LS mapping suffers the subjectivity associated with expert judgment. The paper seeks to reduce the subjectivity associated with the hazard, vulnerability, and risk mapping by formulating an inclusive multiple modeling (IMM), which...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/19/2622 |
| _version_ | 1797515716034822144 |
|---|---|
| author | Ata Allah Nadiri Marjan Moazamnia Sina Sadeghfam Rahim Barzegar |
| author_facet | Ata Allah Nadiri Marjan Moazamnia Sina Sadeghfam Rahim Barzegar |
| author_sort | Ata Allah Nadiri |
| collection | DOAJ |
| description | Groundwater over-abstraction may cause land subsidence (LS), and the LS mapping suffers the subjectivity associated with expert judgment. The paper seeks to reduce the subjectivity associated with the hazard, vulnerability, and risk mapping by formulating an inclusive multiple modeling (IMM), which combines two common approaches of multi-criteria decision-making (MCDM) at Level 1 and artificial intelligence (AI) at Level 2. Fuzzy catastrophe scheme (FCS) is used as MCDM, and support vector machine (SVM) is employed as AI. The developed methodology is applied in Iran’s Tasuj plain, which has experienced groundwater depletion. The result highlights hotspots within the study area in terms of hazard, vulnerability, and risk. According to the receiver operating characteristic and the area under curve (AUC), significant signals are identified at both levels; however, IMM increases the modeling performance from Level 1 to Level 2, as a result of its multiple modeling capabilities. In addition, the AUC values indicate that LS in the study area is caused by intrinsic vulnerability rather than man-made hazards. Still, the hazard plays the triggering role in the risk realization. |
| first_indexed | 2024-03-10T06:49:15Z |
| format | Article |
| id | doaj.art-76ea907576ee4f6b8e81e4afa045b209 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T06:49:15Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-76ea907576ee4f6b8e81e4afa045b2092023-11-22T16:59:59ZengMDPI AGWater2073-44412021-09-011319262210.3390/w13192622Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence TechniquesAta Allah Nadiri0Marjan Moazamnia1Sina Sadeghfam2Rahim Barzegar3Department of Earth Sciences, Faculty of Natural Sciences, University of Tabriz, 29 Bahman Boulevard, Tabriz 5166616471, East Azerbaijan, IranDepartment of Earth Sciences, Faculty of Natural Sciences, University of Tabriz, 29 Bahman Boulevard, Tabriz 5166616471, East Azerbaijan, IranDepartment of Civil Engineering, University of Maragheh, Maragheh 5518183111, East Azerbaijan, IranDepartment of Bioresource Engineering, McGill University, 21111 Lakeshore, Ste Anne de Bellevue, QC H9X 3V9, CanadaGroundwater over-abstraction may cause land subsidence (LS), and the LS mapping suffers the subjectivity associated with expert judgment. The paper seeks to reduce the subjectivity associated with the hazard, vulnerability, and risk mapping by formulating an inclusive multiple modeling (IMM), which combines two common approaches of multi-criteria decision-making (MCDM) at Level 1 and artificial intelligence (AI) at Level 2. Fuzzy catastrophe scheme (FCS) is used as MCDM, and support vector machine (SVM) is employed as AI. The developed methodology is applied in Iran’s Tasuj plain, which has experienced groundwater depletion. The result highlights hotspots within the study area in terms of hazard, vulnerability, and risk. According to the receiver operating characteristic and the area under curve (AUC), significant signals are identified at both levels; however, IMM increases the modeling performance from Level 1 to Level 2, as a result of its multiple modeling capabilities. In addition, the AUC values indicate that LS in the study area is caused by intrinsic vulnerability rather than man-made hazards. Still, the hazard plays the triggering role in the risk realization.https://www.mdpi.com/2073-4441/13/19/2622land subsidencerisk realizationhazardvulnerability |
| spellingShingle | Ata Allah Nadiri Marjan Moazamnia Sina Sadeghfam Rahim Barzegar Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques Water land subsidence risk realization hazard vulnerability |
| title | Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques |
| title_full | Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques |
| title_fullStr | Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques |
| title_full_unstemmed | Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques |
| title_short | Mapping Risk to Land Subsidence: Developing a Two-Level Modeling Strategy by Combining Multi-Criteria Decision-Making and Artificial Intelligence Techniques |
| title_sort | mapping risk to land subsidence developing a two level modeling strategy by combining multi criteria decision making and artificial intelligence techniques |
| topic | land subsidence risk realization hazard vulnerability |
| url | https://www.mdpi.com/2073-4441/13/19/2622 |
| work_keys_str_mv | AT ataallahnadiri mappingrisktolandsubsidencedevelopingatwolevelmodelingstrategybycombiningmulticriteriadecisionmakingandartificialintelligencetechniques AT marjanmoazamnia mappingrisktolandsubsidencedevelopingatwolevelmodelingstrategybycombiningmulticriteriadecisionmakingandartificialintelligencetechniques AT sinasadeghfam mappingrisktolandsubsidencedevelopingatwolevelmodelingstrategybycombiningmulticriteriadecisionmakingandartificialintelligencetechniques AT rahimbarzegar mappingrisktolandsubsidencedevelopingatwolevelmodelingstrategybycombiningmulticriteriadecisionmakingandartificialintelligencetechniques |