Prediction of Flyrock in Mine Blasting: A New Computational Intelligence Approach

Natural Resources Research - Blasting is the predominant rock fragmentation technique in civil constructions, underground and surface mines. Flyrock is the unwanted throw of rock fragments during...     

Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques

Improving the accuracy of flood prediction and mapping is crucial for reducing damage resulting from flood events. In this study, we proposed and validated three ensemble models based on the Best First Decision Tree (BFT) and the Bagging (Bagging-BFT), Decorate (Bagging-BFT), and Random Subspace (RSS-BFT) ensemble learning techniques for an improved prediction of flood susceptibility in a spatially-explicit manner. A total number of 126 historical flood events from the Nghe An Province (Vietnam) were connected to a set of 10 flood influencing factors (slope, elevation, aspect, curvature, river density, distance from rivers, flow direction, geology, soil, and land use) for generating the training and validation datasets. The models were validated via several performance metrics that demonstrated the capability of all three ensemble models in elucidating the underlying pattern of flood occurrences within the research area and predicting the probability of future flood events. Based on the Area Under the receiver operating characteristic Curve (AUC), the ensemble Decorate-BFT model that achieved an AUC value of 0.989 was identified as the superior model over the RSS-BFT (AUC = 0.982) and Bagging-BFT (AUC = 0.967) models. A comparison between the performance of the models and the models previously reported in the literature confirmed that our ensemble models provided a reliable estimate of flood susceptibilities and their resulting susceptibility maps are trustful for flood early warning systems as well as development of mitigation plans.     

Was There Savanna Corridor on the Exposed Sunda Shelf During the Last Glacial Period?

To date, it is still heatedly debated that whether the exposed Sunda Shelf was covered by savanna or rainforest in the Last Glacial Period (LGP). A lot of palynological evidences revealed that large increase of non-arboreal pollen did not occurred on the southern South China Sea (SCS), and lowland and montane rainforest pollen were still predominant. Most of the herb-predominated pollen records occurred on the northern Australia, possibly indicating dispersions of herbs from current distribution centers. As a result, we advocated that inland and connected exposed Sunda Shelf around the southern SCS were covered by tropical forests rather than savanna during the LGP, although climate was drier then. This conclusion is not only supported by palaeoclimate-vegetation modeling, but also corresponds with most of the palynological evidences from South America. Current palynological records also showed the lack of palaeoenviromental reconstruction in Southeast Asia, including less pollen records and ambiguous correlations between marine pollen assemblage and its catchment vegetation.     

Trophic status of the Iranian Caspian Sea based on water quality parameters and phytoplankton diversity

The present study attempted to test the applicability of the trophic index (TRIX) for assessing trophic status along the Iranian coast of the Caspian Sea (CS). In order to increase the sensitivity of the TRIX for this area, we defined the range (lower and upper limits) from data collected between 1994 and 2005 which have been used as a reference. Several biological and chemical water quality parameters were determined and compared with the TRIX in order to describe the water quality status of the area. Comparisons were also made on two temporarily and spatially varied trophic status at the study site. Sampling was carried out at 36 stations during Phase I (1996–1997: before the introduction of an alien species Mnemiopsis leidyi, as a background data) while 24 stations were sampled during Phase II in 2005 (after the introduction of the alien species). A Parallel Study (as supplementary data) from 16 smaller scale sampling at shallower sites was also included in the discussion (1994–2005 on 18 transects). The results show that nutrient concentration (DIN, DIP compounds), oxygen (as absolute %) deviation from saturation (aD%O), chlorophyll a and also the Caspian Sea Trophic Index (TRIXCS) increase significantly after the introduction of an alien species (p<0.01). During Phase I and the Parallel Study, the phytoplankton community was dominated (based on important species index) by Thalassionema nitzschioides, Skeletonema costatum (Chrysophyta) year round but during Phase II, Spirulina laxissma (Cyanophyta) dominated annually and in autumn, coinciding with the minimum Shannon–Weaver diversity and Evenness indices recorded. Several trophic status indices and indicators were applied and an overall analysis suggested that the area has low trophic level during Phase I and high trophic level during Phase II. During the Parallel Study, low trophic level was recorded during the pre-invasion period and high trophic level for the post-invasion period.     

Occurrence of bed load transport in the presence of stable clast

It is well-versed that transport occurrence is vital for in stream rehabilitation, river restoration and installment of sediment sampler on river beds. Current practice emulates the use of continuous pre-diction using reach-averaged approach. However, prediction of transport occurrence entails the use of binary model through the execution of logistic regression analysis. Bed load and turbulence data were physically measured at mountainous region with divergent surface bedform in its presence. The para-meterization and statistical approaches are treated in the similar fashion with multiple regression except for the test for model fit and model selection criterion. The parameters on near-bed turbulence char-acteristics at the entrainment threshold were assigned as independent variables containing 15 pre-dictors. Almost 80 models were generated by selecting the best possible combination in accordance with the statistical precaution of alleviating multicollinearity issue. It is postulated that the model containing shields stress in the form of turbulent kinetic energy (TKE) at vertical direction and fractional time for second quadrant provides better estimation of potential location for greatest sediment-entrainment;hence a high possibility for transport occurrence.