Velibor Spalevic

Bio: Velibor Spalevic is an academic researcher from University of Montenegro. The author has contributed to research in topics: Erosion & Drainage basin. The author has an hindex of 16, co-authored 113 publications receiving 767 citations. Previous affiliations of Velibor Spalevic include Technical University of Cluj-Napoca.

Twentieth century land resilience in Montenegro and consequent hydrological response

Abstract: To study the magnitude of land degradation, desertification or resilience in Montenegro throughout the 20th and early-21st centuries, we rephotographed the landscapes recorded on 48 historical photographs dating back to between 1890 and 1985, and analysed in a semi-quantitative way the land use and cover changes that had occurred using an expert rating system (six correspondents). Time-series of hydrology and population density were analysed for the period since 1948 and were compared with the changes observed using repeat photography. Overall, vegetation cover has strongly increased, and barren areas occupy less space. The industrialisation that expanded in the 1950s led to strong urbanisation. Despite steadily increasing population (with the notable exception of the mountain region), the vegetation cover has increased markedly everywhere. This denser vegetation has led to higher infiltration of rainfall. Partitioning of water led, on one hand, to deep infiltration and better low flows and to increased evapo-transpiration at the boundary layer, leading to decreased total runoff coefficients. In the mountain region, runoff coefficients have increased, which may be related to earlier snowmelt. Overall, the findings of this study are in line with observations elsewhere in the former Socialist Federal Republic of Yugoslavia and suggest that, as a result of erosion control and significant vegetation regrowth, the changes observed over a century there has been land resilience and not degradation. Copyright © 2012 John Wiley & Sons, Ltd.

Comparison of Groundwater Level Models Based on Artificial Neural Networks and ANFIS.

Abstract: Water table forecasting plays an important role in the management of groundwater resources in agricultural regions where there are drainage systems in river valleys. The results presented in this paper pertain to an area along the left bank of the Danube River, in the Province of Vojvodina, which is the northern part of Serbia. Two soft computing techniques were used in this research: an adaptive neurofuzzy inference system (ANFIS) and an artificial neural network (ANN) model for one-month water table forecasts at several wells located at different distances from the river. The results suggest that both these techniques represent useful tools for modeling hydrological processes in agriculture, with similar computing and memory capabilities, such that they constitute an exceptionally good numerical framework for generating high-quality models.

Soil Erosion Intensity and Runoff on the Djuricka River Basin (North of Montenegro)

Abstract: Ecological factors, which are the basis for the calculation of soil erosion, are included in the simulation model. Social aspects, such as the attitude of farmers towards practising environmentally sustainable land use techniques, are difficult to analyse because of lack of data and the level of difficulty inherent in connecting natural, economic, and social data together. At the level of the river basin, the use of an IntErO model allowed the quantification of the environmental effects of erosion and the land use planning measures. Maximal outflow (incidence of 100 years) from the river basin Q max , is 240 m 3 /s suggests the possibility of a large flood. The strength of the erosion process was medium, and the erosion type was mixed erosion. The predicted soil losses were 645 m³/km 2 per year. To support the faster renewal of the vegetation and slow down the erosion processes, biological protection measures need to be applied, together with technical ones, notably by using shoulders and ditches to partition water fluxes at the land surface. These would reduce runoff velocity and further support reforestation and the renewal of grass, shrubs and trees.

Estimation of Sediment Yield and Maximum Outflow Using the IntErO Model in the Sarada River Basin of Nepal

Abstract: Soil erosion is a severe environmental problem worldwide as it washes away the fertile topsoil and reduces agricultural production. Nepal, being a hilly country, has significant erosion disputes as well. It is important to cognise the soil erosion processes occurring in a river basin to manage the erosion severity and plan for better soil conservation programs. This paper seeks to calculate the sediment yield and maximum outflow from the Sarada river basin located in the western hills of Nepal using the computer-graphic Intensity of Erosion and Outflow (IntErO) model. Asymmetry coefficient of 0.63 was calculated, which suggests a possibility of large floods to come in the river basin in the future whereas the maximum outflow from the river basin was 1918 m³ s−1. An erosion coefficient value of 0.40 was obtained, which indicates surface erosion of medium strength prevails in the river basin. Similarly, the gross soil loss rate of 10.74 Mg ha−1 year−1 was obtained with the IntErO modeling which compares well with the soil loss from the erosion plot measurements. The IntErO model was used for the very first time to calculate soil erosion rates in the Nepalese hills and has a very good opportunity to be applied in similar river basins.

Climate Change 2007: Impacts, Adaptation and Vulnerability.

Abstract: Impatti, adattamento e vulnerabilita Le cause e le responsabilita dei cambiamenti climatici sono state trattate sul numero di ottobre della rivista Cda. Approfondiamo l’argomento presentando il documento: “Cambiamenti climatici 2007: impatti, adattamento e vulnerabilita” votato ad aprile 2007 dal secondo gruppo di lavoro del Comitato Intergovernativo sui Cambiamenti Climatici (Intergovernmental Panel on Climate Change). Si tratta del secondo di tre documenti che compongono il quarto rapporto sui cambiamenti climatici.

Applications of soil physics.

Abstract: Keywords: Mecanique des sols ; Drainage ; Ecoulement souterrain Reference Record created on 2004-09-07, modified on 2016-08-08

A spatially explicit deep learning neural network model for the prediction of landslide susceptibility

Abstract: With the increasing threat of recurring landslides, susceptibility maps are expected to play a bigger role in promoting our understanding of future landslides and their magnitude. This study describes the development and validation of a spatially explicit deep learning (DL) neural network model for the prediction of landslide susceptibility. A geospatial database was generated based on 217 landslide events from the Muong Lay district (Vietnam), for which a suite of nine landslide conditioning factors was derived. The Relief-F feature selection method was employed to quantify the utility of the conditioning factors for developing the landslide predictive model. Several performance metrics demonstrated that the DL model performed well both in terms of the goodness-of-fit with the training dataset (AUC = 0.90; accuracy = 82%; RMSE = 0.36) and the ability to predict future landslides (AUC = 0.89; accuracy = 82%; RMSE = 0.38). The efficiency of the model was compared to the quadratic discriminant analysis, Fisher's linear discriminant analysis, and multi-layer perceptron neural network. A comparative analysis using the Wilcoxon signed-rank tests revealed a significant improvement of landslide prediction using the spatially explicit DL model over these other models. The insights provided from this study will be valuable for further development of landslide predictive models and spatially explicit assessment of landslide-prone regions around the world.