Estimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, Yemen
Abstract Earth fissures are potential hazards that often cause severe damage and affect infrastructure, the environment, and socio-economic development. Owing to the complexity of the causes of earth fissures, the prediction of earth fissures remains a challenging task. In this study, we assess eart...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-26526-y |
| _version_ | 1797977451684429824 |
|---|---|
| author | Yousef A. Al-Masnay Nabil M. Al-Areeq Kashif Ullah Ali R. Al-Aizari Mahfuzur Rahman Changcheng Wang Jiquan Zhang Xingpeng Liu |
| author_facet | Yousef A. Al-Masnay Nabil M. Al-Areeq Kashif Ullah Ali R. Al-Aizari Mahfuzur Rahman Changcheng Wang Jiquan Zhang Xingpeng Liu |
| author_sort | Yousef A. Al-Masnay |
| collection | DOAJ |
| description | Abstract Earth fissures are potential hazards that often cause severe damage and affect infrastructure, the environment, and socio-economic development. Owing to the complexity of the causes of earth fissures, the prediction of earth fissures remains a challenging task. In this study, we assess earth fissure hazard susceptibility mapping through four advanced machine learning algorithms, namely random forest (RF), extreme gradient boosting (XGBoost), Naïve Bayes (NB), and K-nearest neighbor (KNN). Using Qa’ Jahran Basin in Yemen as a case study area, 152 fissure locations were recorded via a field survey for the creation of an earth fissure inventory and 11 earth fissure conditioning factors, comprising of topographical, hydrological, geological, and environmental factors, were obtained from various data sources. The outputs of the models were compared and analyzed using statistical indices such as the confusion matrix, overall accuracy, and area under the receiver operating characteristics (AUROC) curve. The obtained results revealed that the RF algorithm, with an overall accuracy of 95.65% and AUROC, 0.99 showed excellent performance for generating hazard maps, followed by XGBoost, with an overall accuracy of 92.39% and AUROC of 0.98, the NB model, with overall accuracy, 88.43% and AUROC, 0.96, and KNN model with general accuracy, 80.43% and AUROC, 0.88), respectively. Such findings can assist land management planners, local authorities, and decision-makers in managing the present and future earth fissures to protect society and the ecosystem and implement suitable protection measures. |
| first_indexed | 2024-04-11T05:07:07Z |
| format | Article |
| id | doaj.art-15372160b25a4c608072eca8f1fc6d01 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T05:07:07Z |
| publishDate | 2022-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-15372160b25a4c608072eca8f1fc6d012022-12-25T12:13:30ZengNature PortfolioScientific Reports2045-23222022-12-0112111810.1038/s41598-022-26526-yEstimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, YemenYousef A. Al-Masnay0Nabil M. Al-Areeq1Kashif Ullah2Ali R. Al-Aizari3Mahfuzur Rahman4Changcheng Wang5Jiquan Zhang6Xingpeng Liu7Institute of Natural Disaster Research, School of Environment, Northeast Normal UniversityDepartment of Geology and Environment, Thamar UniversityInstitute of Geophysics and Geomatics, China University of GeosciencesInstitute of Surface-Earth System Science, School of Earth System Science, Tianjin UniversityDepartment of Civil Engineering, International University of Business Agriculture and Technology (IUBAT)Department of Surveying and Remote Sensing, School of Geosciences and Info-Physics, Central South UniversityInstitute of Natural Disaster Research, School of Environment, Northeast Normal UniversityInstitute of Natural Disaster Research, School of Environment, Northeast Normal UniversityAbstract Earth fissures are potential hazards that often cause severe damage and affect infrastructure, the environment, and socio-economic development. Owing to the complexity of the causes of earth fissures, the prediction of earth fissures remains a challenging task. In this study, we assess earth fissure hazard susceptibility mapping through four advanced machine learning algorithms, namely random forest (RF), extreme gradient boosting (XGBoost), Naïve Bayes (NB), and K-nearest neighbor (KNN). Using Qa’ Jahran Basin in Yemen as a case study area, 152 fissure locations were recorded via a field survey for the creation of an earth fissure inventory and 11 earth fissure conditioning factors, comprising of topographical, hydrological, geological, and environmental factors, were obtained from various data sources. The outputs of the models were compared and analyzed using statistical indices such as the confusion matrix, overall accuracy, and area under the receiver operating characteristics (AUROC) curve. The obtained results revealed that the RF algorithm, with an overall accuracy of 95.65% and AUROC, 0.99 showed excellent performance for generating hazard maps, followed by XGBoost, with an overall accuracy of 92.39% and AUROC of 0.98, the NB model, with overall accuracy, 88.43% and AUROC, 0.96, and KNN model with general accuracy, 80.43% and AUROC, 0.88), respectively. Such findings can assist land management planners, local authorities, and decision-makers in managing the present and future earth fissures to protect society and the ecosystem and implement suitable protection measures.https://doi.org/10.1038/s41598-022-26526-y |
| spellingShingle | Yousef A. Al-Masnay Nabil M. Al-Areeq Kashif Ullah Ali R. Al-Aizari Mahfuzur Rahman Changcheng Wang Jiquan Zhang Xingpeng Liu Estimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, Yemen Scientific Reports |
| title | Estimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, Yemen |
| title_full | Estimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, Yemen |
| title_fullStr | Estimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, Yemen |
| title_full_unstemmed | Estimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, Yemen |
| title_short | Estimate earth fissure hazard based on machine learning in the Qa’ Jahran Basin, Yemen |
| title_sort | estimate earth fissure hazard based on machine learning in the qa jahran basin yemen |
| url | https://doi.org/10.1038/s41598-022-26526-y |
| work_keys_str_mv | AT yousefaalmasnay estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen AT nabilmalareeq estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen AT kashifullah estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen AT aliralaizari estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen AT mahfuzurrahman estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen AT changchengwang estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen AT jiquanzhang estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen AT xingpengliu estimateearthfissurehazardbasedonmachinelearningintheqajahranbasinyemen |