English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Among natural hazards, land subsidence (LS) is considered to be one of the most significant natural disasters which occur in populated and inhabited regions of Iran. The Varamin aquifer, as one of the regions near the capital of Iran, where this geo-hazard has occurred widely and extensively, requires conducting comprehensive researches on LS. In this research, for LS risk assessment, the combination of a GIS-based hybrid model of the fuzzy-support vector machine (FSVM) as a new approach in the LS hazard assessment and an index model of vulnerability for LS vulnerability assessment were employed. From the hazard assessment viewpoint and according to the review of literature, fifteen factors affecting subsidence were arranged, and these parameters were normalized with the fuzzy membership functions based on their type of impact on LS. Moreover, for overlapping the parameters, the support vector machine (SVM) model and its three main kernels functions were used. Then, seventy percent (2919 pixels) of the data were used for the train and thirty percent (1251 pixels) were used for the test. The results of hazard model verification using receiver operating characteristic (ROC) showed the RBF kernel has the best performance result. From the vulnerability assessment viewpoint, an index model was developed using nine factors that can be damaged and affected by the LS, based on the literature review. In this regard, the Saaty’s paired comparison method was used to assign a weight to each of the vulnerability parameters, and then the parameters were aggregated to build the vulnerability map. Considering the vulnerability, 21% of the Varamin aquifer was classified as high and very high. Lastly, the risk map was obtained with the overlay of the hazard and vulnerability maps. The resulting map can be used by risk managers to make decisions that lead to reducing injuries and damages of LS.

Subsidence risk assessment based on a novel hybrid form of a tree-based machine learning algorithm and an index model of vulnerability