The issue of gully erosion is of major concern in the south-eastern part of Nigeria. This study adopts Geographic Information Systems (GIS) as a tool to identify and study gully erosion hazards in Abia state. 171 gully erosion sites were coordinated using GPS receivers and overlaid on the soil and geological maps of the study area. Spatial database for erosion sites was created using relational database model. Additional 35 gully erosion sites were identified from the processed digital elevation model (DEM) and ground verification carried out. Result shows that gully erosion sites were well dispersed around false bedded sand stone geological formation. The slope characteristic was ascertained to be greater than 15 o which encourages gully erosion activities. An erosion hazard map was produced showing risk and vulnerability of settlements and infrastructure. This study shows that GIS is an efficient and effective tool in the study and mapping of gully erosions.
The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in remote sensing is the ability to develop classifiers that can substantially discern the different classes inherent in natural and man-made targets. Emphasis has shifted from the use of conventional classifiers to modern non-parametric classifiers such as the Artificial Neural Network (ANN) and Support Vector Machine (SVM); and most recently the hybrid Deep Neural Network (DNN) which is a fusion of Deep Learning (DL) and ANN. This research therefore presents the novel application of Deep Support Vector Machine (DSVM) which is a fusion of DL and SVM to PolSAR image classification. Two PolSAR images of Flevoland region in Netherlands, and Winnipeg in Canada are used as test beds for the experiment. The Lee filter is used to filter the images to suppress the speckle noise in the images. The Pauli decomposition is applied to decompose the images into |ππ π»π»π»π» + ππ ππππ |, |ππ π»π»π»π» β ππ ππππ |, |ππ π»π»ππ | polarimetric channels. Then the Gray Level Co-occurrence Matrix (GLCM) texture feature for |ππ π»π»π»π» + ππ ππππ |, |ππ π»π»π»π» β ππ ππππ |, |ππ π»π»ππ | are extracted based on correlation, contrast, energy, and homogeneity statistics, using GLCM directions 0 0 , 45 0 , 90 0 , and 135 0 with an offset distance of 60. To enhance the efficiency of the model 8, 16, 32, 64, 128, and 256 quantization levels are explored. The DSVM classifier is implemented with four kernel function: Exponential Radial Basis Function (ERBF), Gaussian Radial Basis Function (GRBF), neural, and polynomial. The first set of results is a comparison of the DSVM and SVM.
Estimating runoff and understanding of the relationship between rainfall and runoff are of great importance in the management of flood. Several computer based hydrological models have been developed and used in simulating runoff in various watersheds in different parts of the world and in water resource studies. This study focuses on the combination of Geographic Information System (GIS) with Hydrologic Engineering Center βHydrologic Modelling System (HEC-HMS) hydrological model to simulate runoff process of the adjoining areas of the Lagos Island and Eti-Osa Local Government Areas (LGAs). The study makes use of LIDAR Digital Elevation Model (DEM), drainage data and land use map for catchment delineation and hydrological modelling, using HECGeoHMS and ArcGIS 10.2. In HEC-HMS 4.2.1, the delineated catchment with all hydrological parameters and average daily rainfall data, are used to simulate and compute rainfall runoff volume, peak discharges for 10 months (between Jan to October) and a total of three years (2012, 2015 and 2017) were considered. Direct runoff volume and depth estimation for the years under review were determined. Results show that the peak discharge occurred on the 2nd of July 2012 at a rate of 14m3/s with an estimated runoff volume at the basin outlet of 39,669.70 x 103m3 (this date tallies with the severe flood events that occurred in that year). The study shows that estimating hydrological outputs is possible with the use of HEC-HMS and GIS. It recommends the application of such technologies in the prediction and development of basic flood warning systems for the area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citationsβcitations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright Β© 2024 scite LLC. All rights reserved.
Made with π for researchers
Part of the Research Solutions Family.