A new GIS-based data mining technique using an adaptive neuro-fuzzy inference system (ANFIS) and k-fold cross-validation approach for land subsidence susceptibility mapping

In this paper, we evaluate the predictive performance of an adaptive neuro-fuzzy inference system (ANFIS) using six different membership functions (MF). In combination with a geographic information system (GIS), ANFIS was used for land subsidence susceptibility mapping (LSSM) in the Marand plain, northwest Iran. This area is prone to droughts and low groundwater levels and subsequent land subsidence damages. Therefore, a land subsidence inventory database was created from an extensive field survey. Areas of land subsidence or areas showing initial signs of subsidence were used for training, while one-third of inventory database were reserved for testing and validation. The inventory database randomly divided into three different folds of the same size. One of the folds was chosen for testing and validation. Other two folds was used for training. This process repeated for every fold in the inventory dataset. Thereafter, land subsidence related factors, such as hydrological and topographical factors, were prepared as GIS layers. Areas susceptible to land subsidence were then analyzed using the ANFIS approach, and land subsidence susceptibility maps were created, whereby six different MFs were applied. Lastly, the results derived from each MF were validated with those areas of the land subsidence database that were not used for training. Receiver operating characteristics (ROC) curves were drawn for all LSSMs, and the areas under the curves were calculated. The ROC analyses for the six LSSMs yielded very high prediction values for two out of the six methods, namely the difference of DsigMF (0.958) and GaussMF (0.951). The integration of ANFIS and GIS generally led to high LSSM prediction accuracies. This study demonstrated that the choice of training dataset and the MF significantly affects the results.     

Landslide detection using deep learning and object-based image analysis

Landslides - Recent landslide detection studies have focused on pixel-based deep learning (DL) approaches. In contrast, intuitive annotation of landslides from satellite imagery is based on...     

Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran

The identification of landslide-prone areas is an essential step in landslide hazard assessment and mitigation of landslide-related losses.In this study,we applied two novel deep learning algorithms,the recurrent neural network(RNN)and convolutional neural network(CNN),for national-scale landslide susceptibility mapping of Iran.We prepared a dataset comprising 4069 historical landslide locations and 11 conditioning factors(altitude,slope degree,profile curvature,distance to river,aspect,plan curvature,distance to road,distance to fault,rainfall,geology and land-sue)to construct a geospatial database and divided the data into the training and the testing dataset.We then developed RNN and CNN algorithms to generate landslide susceptibility maps of Iran using the training dataset.We calculated the receiver operating characteristic(ROC)curve and used the area under the curve(AUC)for the quantitative evaluation of the landslide susceptibility maps using the testing dataset.Better performance in both the training and testing phases was provided by the RNN algorithm(AUC=0.88)than by the CNN algorithm(AUC=0.85).Finally,we calculated areas of susceptibility for each province and found that 6%and 14%of the land area of Iran is very highly and highly susceptible to future landslide events,respectively,with the highest susceptibility in Chaharmahal and Bakhtiari Province(33.8%).About 31%of cities of Iran are located in areas with high and very high landslide susceptibility.The results of the present study will be useful for the development of landslide hazard mitigation strategies.     

A probabilistic model for the evaluation of strong column-weak beam provision for flexible-base buildings subjected to pulse-like ground motions

Bulletin of Earthquake Engineering - The main objective of this study is to employ a probabilistic approach to determine the appropriate value of the strong column-weak beam ratio (SCWBR) for three...     

Monitoring hawksbill turtle nesting sites in some protected areas from the Persian Gulf

Iranian nesting populations of the critically endangered hawksbill turtle(Eretmochelys imbricate) are some of the most important in the Indian Ocean. In this study, four of the most important hawksbill nesting grounds in the Persian Gulf, situated within three Iranian marine protected areas, were surveyed during nesting season,including Nakhiloo, Ommolgorm and Kharko Islands and the mainland beaches of the Naiband Marine-Coastal National Park(NMCNP). We present GIS maps of these key nesting grounds and describe sand texture of key nesting zones, along with conservation recommendations. About 9.2(28.3%) out of 32.5 km of all shores surveyed in this study were used by nesting hawksbill turtles follows: Nakhiloo: 1.4 km(52% of potential nesting area);Ommolgorm: 1.94 km(40%); Kharko: 3.4 km(28%), and NMCNP: 2.46 km(18.9%). The average nesting density was calculated as 131 nests/km at Nakhiloo, 76 nests/km at Ommolgorm, 7 nests/km at Kharko, and 15 nests per km at NMCNP. Highest nesting density was observed in Nakhiloo and Ommolgorm. It is thought that high hawksbill nesting density in these islands seems likely a result of limiting adequate nesting shores rather than the size of population, and also low density in Kharko and NMCNP more related to past and current pressures and low population density. With the exception of Ommolgorm Island, sands at the nesting grounds were well sorted.Grain size indicated that female hawksbill turtles in the Iranian Persian Gulf nest in sands that are generally mixed, with mean grain size ranging from coarse sands(0.4Φ;～0.5–1 mm) to fine sands(2Φ;～0.25 mm). We provide and discuss conservation recommendations and suggestions for future.     

An interval matrix method used to optimize the decision matrix in AHP technique for land subsidence susceptibility mapping

The analytical hierarchy process (AHP) is one of the most effective methods for criteria ranking/weighting to have been successfully incorporated into GIS analyses. We present a new method for optimizing pairwise comparison decision-making matrices in AHP method, which has been developed on the basis of an interval pairwise comparison matrix (IPCM) derived from expert knowledge. The method has been used for criteria ranking in land subsidence susceptibility mapping (LSSM) as a practical test case, for which an interval matrix was generated by pairwise comparison. To compare the capability of the AHP method (a traditional approach) with that of the proposed IPCM method (a novel approach), 11 creations of LSSM were ranked using each approach in turn. The criteria weightings obtained were then used to produce LSSM maps based on each of these approaches. The results were tested against a data set of known land subsidence occurrences, indicating an improvement in accuracy of about 14% in the LSSM map that was developed using the IPCM method. This improvement was achieved by minimizing the uncertainty associated with criteria ranking/weighting in a traditional AHP and could form a basis for future research into minimizing the uncertainty in weightings derived using the AHP method. Our results will be of considerable importance for researchers involved in GIS-based multi-criteria decision analysis (MCDA) and those dealing with GIS-based spatial decision-making methods.