A novel GIS-based ensemble technique for flood susceptibility mapping using evidential belief function and support vector machine: Brisbane, Australia.

In this study, we propose and test a novel ensemble method for improving the accuracy of each method in flood susceptibility mapping using evidential belief function (EBF) and support vector machine (SVM). The outcome of the proposed method was compared with the results of each method. The proposed method was implemented four times using different SVM kernels. Hence, the efficiency of each SVM kernel was also assessed. First, a bivariate statistical analysis using EBF was performed to assess the correlations among the classes of each flood conditioning factor with flooding. Subsequently, the outcome of the first stage was used in a multivariate statistical analysis performed by SVM. A highest prediction accuracy of 92.11% was achieved by an ensemble EBF-SVM-radial basis function method; the achieved accuracy was 7% and 3% higher than that offered by the individual EBF method and the individual SVM method, respectively. Among all the applied methods, both the individual EBF and SVM methods achieved the lowest accuracies. The reason for the improved accuracy offered by the ensemble methods is that by integrating the methods, a more detailed assessment of the flooding and conditioning factors can be performed, thereby increasing the accuracy of the final map.

A comparative modeling study on non-climatic and climatic risk assessment on Asian Tiger Mosquito (Aedes albopictus).

Aedes albopictus, the Asian Tiger Mosquito, vector of Chikungunya, Dengue Fever and Zika viruses, has proven its hardy adaptability in expansion from its natural Asian, forest edge, tree hole habitat on the back of international trade transportation, re-establishing in temperate urban surrounds, in a range of water receptacles and semi-enclosures of organic matter. Conventional aerial spray mosquito vector controls focus on wetland and stagnant water expanses, proven to miss the protected hollows and crevices favoured by Ae. albopictus. New control or eradication strategies are thus essential, particular in light of potential expansions in the southeastern and eastern USA. Successful regional vector control strategies require risk level analysis. Should strategies prioritize regions with non-climatic or climatic suitability parameters for Ae. albopictus? Our study used current Ae. albopictus distribution data to develop two independent models: (i) regions with suitable non-climatic factors, and (ii) regions with suitable climate for Ae. albopictus in southeastern USA. Non-climatic model processing used Evidential Belief Function (EBF), together with six geographical conditioning factors (raster data layers), to establish the probability index. Validation of the analysis results was estimated with area under the curve (AUC) using Ae. albopictus presence data. Climatic modeling was based on two General Circulation Models (GCMs), Miroc3.2 and CSIRO-MK30 running the RCP 8.5 scenario in MaxEnt software. EBF non-climatic model results achieved a 0.70 prediction rate and 0.73 success rate, confirming suitability of the study site regions for Ae. albopictus establishment. The climatic model results showed the best-fit model comprised Coldest Quarter Mean Temp, Precipitation of Wettest Quarter and Driest Quarter Precipitation factors with mean AUC value of 0.86. Both GCMs showed that the whole study site is highly suitable and will remain suitable climatically, according to the prediction for 2055, for Ae. albopictus expansion.