At present, flood is the most significant environmental problem in the entire world. In this work, flood susceptibility (FS) analysis has been done in the Dwarkeswar River basin of Bengal basin, India. Fourteen flood causative factors extracted from different datasets like DEM, satellite images, geology, soil and rainfall data have been considered to predict FS. Three heuristic models and one statistical model fuzzy Logic (FL), frequency ratio (FR), multi-criteria decision analysis (MCDA) and logistic regression (LR) have been used. The validating datasets are used to validate these models. The result shows that 68.71%, 68.7%, 60.56% and 48.51% area of the basin is under the moderate to very high FS by the MCDA, FR, FL and LR, respectively. The ROC curve with AUC analysis has shown that the accuracy level of the LR model (AUC?=?0.916) is very much successful to predict the flood. The rest of the models like FL, MCDA and FR (AUC?=?0.893, 0.857 and 0.835, respectively) have lesser accuracy than the LR model. The elevation was the most dominating factor with coefficient value of 19.078 in preparation of the FS according to the LR model. The outcome of this study can be implemented by local and state authority to minimize the flood hazard.
相似文献The present study has tried to develop ecological insecurity model (EIM) in the growing stone quarrying and crushing dominated areas using robust machine learning techniques and attempted to link it with ecosystem service value (ESV). Satellite image-based landscape metrics have been used for developing machine learning-oriented EIM, and the global coefficient of Costanza et al. (Glob Environ Change 26:152–158, 2014) has been used for computing ESV. Field parameter-based ecological insecurity index (EII) has been developed for validating the EIMs along with the statistical methods. Applied Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN) revealed that 21.88 to 60.79% area has predicted as highly ecologically insecure in all the selected four stone quarrying and crushing dominated clusters and this is has inflated from 2000 to 2020. All the applied models are acceptable in terms of their performances, but the RF model is found to be the best representative in relation to EII. It causes considerable loss of ESV which ranges from 160,845.18 US$ to 757,445.17 US$ in all the clusters from 2000 to 2020. The findings of the study are useful for ecological management in this area. It further recommends applying such an approach in such similar fields to establish the general finding and provides knowledge to the state of arts.
相似文献