Search

In this paper, we developed highly accurate ensemble machine learning models integrating Reduced Error Pruning Tree (REPT) as a base classifier with the Bagging (B), Decorate (D), and Random Subspace (RSS) ensemble learning techniques for spatial prediction of rainfall-induced landslides in the Uttarkashi district, located in the Himalayan range, India. To do so, a total of 103 historical landslide events were linked to twelve conditioning factors for generating training and validation datasets. Root Mean Square Error (RMSE) and Area Under the receiver operating characteristic Curve (AUC) were used to evaluate the training and validation performances of the models. The results showed that the single REPT model and its derived ensembles provided a satisfactory accuracy for the prediction of landslides. The D-REPT model with RMSE = 0.351 and AUC = 0.907 was identified as the most accurate model, followed by RSS-REPT (RMSE = 0.353 and AUC = 0.898), B-REPT (RMSE = 0.396 and AUC = 0.876), and the single REPT model (RMSE = 0.398 and AUC = 0.836), respectively. The prominent ensemble models proposed and verified in this study provide engineers and modelers with insights for development of more advanced predictive models for different landslide-susceptible areas around the world. [ABSTRACT FROM AUTHOR]

Dynamism of river bed morphology is continuous and an integrated process of mountain's natural outflow in Himalayan Foothill Rivers. In-stream seasonal sediment flux, bridge establishments, bridge scouring and railway-road construction have detrimental influence over the natural flow regime of the river thereby causing channel degradation in the piedmont zone of eastern Himalaya of India, specifically near the urban areas where river management strategies are very weak. Such extreme anthropogenic events have a distinctive influence in changing river bed morphology in the middle-lower part of river Chel in Darjeeling Himalayan piedmont zone of India. Huge sediment aggradation and transportation networks historically have affected River Chel and have caused channel avulsion which poses a serious threat to the physical and ecological environment of Chel. Aggradation and lifting of sediments from the river bed are fatal for the geomorphologic character of the river, though no studies have been undertaken yet, to analyse the situation quantitatively in this regard. This paper presents evidence that suggests the changing river bed morphology, the dynamic nature of the river, the poor health of the river which is principally the impact of the seasonal sediment flux and bridge construction and thus some methods of river restoration in the middle-lower part of the river have been explained. Agglomeration of sediment, flow bifurcation, the volume of seasonal water mass, bed elevation changes and scouring are a major dynamic disposition for change of river bed morphology. Point bar, sidebar, braided active channel, ripples, and rise in the bed elevation are rapid changes in upper to lower part of bridges that are examined in the present study. In the dry season (December to February), a huge amount of sediment lifting makes incommodious man-made holes and a number of emergent channels which principally control the formation of a new active channel in the next monsoon season. The avulsion of major intra-active channels and morphological changes of the river bed for the last 85 years have also been observed in this study. Unlabelled Image • This paper presents evidence that suggests that the changing river bed morphology, the dynamic nature of the river, the poor health of the river is principally the impact of the huge sediment aggradation and bridge construction and thus some methods of river restoration in the middle-lower part of river Chel. • Suspended sediment, aggradation and degradation, Scouring calculation for boulder agglomeration, Compare of satellite images and Topographical map for braided channel shifting are major methods for understanding of outcome results. • Agglomeration of sediment, flow bifurcation, volume of seasonal water mass, bed elevation change and scouring are major dynamic disposition for change of river bed morphology by bridge construction scouring. [ABSTRACT FROM AUTHOR]