Flood susceptibility modelling using advanced ensemble machine learning models

Floods are one of nature's most destructive disasters because of the immense damage to land,buildings,and human fatalities.It is difficult to forecast the areas that are vulnerable to flash flooding due to the dynamic and complex nature of the flash floods.Therefore,earlier identification of flash flood susceptible sites can be performed using advanced machine learning models for managing flood disasters.In this study,we applied and assessed two new hybrid ensemble models,namely Dagging and Random Subspace(RS)coupled with Artificial Neural Network(ANN),Random Forest(RF),and Support Vector Machine(SVM)which are the other three state-of-the-art machine learning models for modelling flood susceptibility maps at the Teesta River basin,the northern region of Bangladesh.The application of these models includes twelve flood influencing factors with 413 current and former flooding points,which were transferred in a GIS environment.The information gain ratio,the multicollinearity diagnostics tests were employed to determine the association between the occurrences and flood influential factors.For the validation and the comparison of these models,for the ability to predict the statistical appraisal measures such as Freidman,Wilcoxon signed-rank,and t-paired tests and Receiver Operating Characteristic Curve(ROC)were employed.The value of the Area Under the Curve(AUC)of ROC was above 0.80 for all models.For flood susceptibility modelling,the Dagging model performs superior,followed by RF,the ANN,the SVM,and the RS,then the several benchmark models.The approach and solution-oriented outcomes outlined in this paper will assist state and local authorities as well as policy makers in reducing flood-related threats and will also assist in the implementation of effective mitigation strategies to mitigate future damage.

Multi-media compartments for assessing ecological and health risks from concurrent exposure to multiple contaminants on Bhola Island,Bangladesh

In this study,a set of coupled multi-media compartments(i.e.,sediment,soil,water and vegetable)was used to assess ecological and health risks from the ingestion of 11 PTEs(Pb,Cd,Cr,As,Hg,Cu,Zn,Ni,Co,Fe,and Mn)and their transportation routes in the water-soil-plant system from the coastal Bhola Island,Bangladesh.The mean concentrations of Cd,Pb,and Co for soil and Cd,Co,and As for sediment were higher than their reference values.In contrast,Cd,Pb,and Ni concentrations in water surpassed the acceptable limits set by national and international laws and were considered unsuitable for drinking purposes.Vegetables demonstrated high Pb and Cd contents,demonstrating a potential food safety risk to the inhabitants.Results of principal component analysis(PCA)revealed that Cd,Pb,Hg,Cu,Ni and Zn sources were likely to be anthropogenic,especially agro-farming inputs,whereas the Fe,As,Cr,Mn,and Co sources were similar to natural origin.So,Cd,Pb and Co are the key contaminants in the study area and pose the elevated health and ecological risks in the coastal area.Cd and Pb exhibited higher ecological risks in soils and sediments,as Pb had the highest bio-accessibility(BA;0.02±0.003)and Cd possessed a high bioaccumulation factor(BCF;0.004±0.006).The self-organizing map analysis recognized three spatial patterns which are good agreement with PCA.The average hazard index(HI)values for soil were above the permissible level(HI>1)set by the respective agency;two times higher HI values were noticed for children than adults,suggesting children are highly susceptible to health risk.Continuous monitoring and source controls for Cd and Pb,along with agro-farming management practices,need to be implemented to reduce the risk of PTE contamination to the aquatic ecosystem and its inhabitants.