Institute of Technology

Permanent URI for this communityhttps://etd.hu.edu.et/handle/123456789/66

The Institute of Technology focuses on education, research, and innovation in engineering, technology, and applied sciences to support sustainable development.

Browse

Filters

2018 - 201922020 - 202442

Settings

Has files: Yes

Search Results

Now showing 1 - 10 of 44
  • No Thumbnail Available
    Item
    FAILURE INVESTGATION OF EARTH FILL DAM, THE CASE OF ZANA DAM IN AMHARA RIGEN, ETHIOPIA
    (Hawassa University, 2020-07-03) DESTAW GASHAW ALEMU
    construction of dams serves a number of purposes such as water supply, irrigation, hydroelectric power generation, flood control and navigation etc.Zana dam is anEarth Fill Dam which islocated on Zana River used for irrigation purpose. The main problem of this dam is seepage and downstream slope failure.To address this problem evaluate the current dam conditionofdetermination of seepage and slope stability by Geo-studio software and identification of downstream slope failure and seepage through the body of the dam were assessed . Analysisofseepagewasdoneusingseepage and slope analysismethods which integrate Geo-studiosoftwareof Seep/w and slop/wtoolsatnormalandcurrentpoollevelcondition, the study was conducted mainly based on the laboratory investigation of materials used for construction. The result demonstrated that there wasa material property gap between what was stated in the design report and actually used in construction. The amount of seepage generated from the analysis was found to be1.406*10-7m3/s/mhowever from the actual constructed was found to be1.683 *10- 3 m3/s/m.Accordinglyfrom slope stability analysis the factor of safety of=1.335 and FS=1.193 for the designed and constructed sections respectivelywhich were less than 1.5.On the other handusing the newly proposed embankment section and the material property analyzed the seepage quantity through the embankment body found to be = 2.9218x10-7 m3/sec/m and the minimum factor of safety of = 2.127 and 2.285 with steady state condition upstream and downstream slop respectively, and factor of safety of =1.963 for using both horizontal and vertical seismic action. Similarly the major finding of the cause of failure is absence of proper filter and drainage materials. Result of gradation analysis of both base and shell materialsdemonstrated thatD15 (shell) =3 mm & D85 (core) =0.2mm this resulted 0.6mm>0.2mm which yielded that there was piping or internal erosion of the base material. Consequently the maximum and minimum bounds of filter materials obtained were: D60min=0.5mm, D15min=0.1 mm, D5min=0.075 mm, D100max=75 mm, D90max=20 mm, D60mm=2.5 mm & D15max=0.5mm obtained.Thereforecheminefilter material design and provision is mandatory for the safe life of the zoned type earth fill dam.
  • No Thumbnail Available
    Item
    EVALUATION OF THE IMPACTS OF CLIMATE CHANGE ON SEDIMENT YIELD FROM THE KATAR WATERSHED, CENTRAL RIFT-VALLEY BASIN, ETHIOPIA
    (Hawassa University, 2021-12-10) GELILA SAMUEL
    Climate change is one of the issues that, the world facing today including Ethiopia and it is anticipated that climate change will impact sediment yield in watersheds. The purpose of this study was to investigate the impacts of climate change on sediment yield from the Katar watershed in the Eastern Lake Ziway Basin, Ethiopia. Here, used the coordinated regional climate downscaling experiment (CORDEX)-Africa data outputs of Hadley Global Environment Model 2-Earth System (HadGEM2-ES) under representative concentration pathway (RCP) scenarios (RCP4.5). The analysis was performed in two future projection of 2030’s and 2060’s under the reference of baseline period of 1987-2017 with their RCP correction. After assessment of missing, quality and consistency of data; bias, the coefficient of variation and correlation were used to evaluate the systematic error of precipitation amount, the degree of precipitation variability and bias-corrected before serving as input to the impact analysis A Soil and Water Assessment Tool (SWAT) model was constructed to simulate the hydrological and the sedimentological responses to climate change. The model performance was calibrated and validated using the coefficient of determination (R2 ) and Nash–Sutcliffe efficiency (NSE). The results of the calibration and the validation of the sediment yield R2 and NSE were 0.65 and 0.61, and 0.66 and 0.65, respectively. Climate change output from this research shows that the watershed will get warmer in the future. Both minimum and maximum temperature of the catchment have an increasing trend by 1.04 0C for 2030’s and 2.04 0C for 2060’s for minimum temperature and 0.90 0C for 2030’s and 1.56 0C for 2060’s for maximum temperature. Also, average annual rainfall shows increase by 4.8% for 2030’s and 1.6 % for 2060’s. The results of downscaled precipitation and temperature increased in both future period under RCP4.5 scenario. These climate variable increments were expected to result in intensifications in the mean annual sediment yield of 41.1% and 8.9% for RCP4.5 by the 2030s and the 2060s, respectively. The average annual sediment yield were 398 ton/km2 and 307 ton/km2 for the 2030’s and 2060’s, respectively. From this study, the results show that the sediment yield of the watershed is likely to increase under climate change scenarios. This will help water resources managers make informed decisions regarding the planning, management, and mitigation of the river basins.
  • No Thumbnail Available
    Item
    GROUNDWATER POTENTIAL MAPPING USING GIS AND REMOTE SENSING: A CASE STUDY IN WEYIB SUB-BASIN, GENALE-DAWA RIVER BASIN, SOUTHEAST ETHIOPIA
    (Hawassa University, 2021-08-12) ABDULGEFAR MUHIDIN MOHAMMED
    To fulfill the demand of a rapidly growing population in drought-prone areas with high rate of urbanization, identification and management of groundwater resources are required. In the Weyib Sub-basin, a search for an alternative source of water has been always a major issue. The current practice of groundwater potential zone (GWPZ) identification is time-consuming and uneconomical. Therefore, it is required to apply effective techniques for proper evaluation of groundwater resources. This study applied integration of GIS-Remote Sensing (RS) and Analytical Hierarchy Process (AHP) for mapping the GWPZ of Weyib Sub-basin, Southeast Ethiopia. For this purpose the physiographic, geology and climatic factors influencing GWPZ of the study area were characterized. The thematic maps of geomorphological landforms, lineament density, geology, rainfall distribution, drainage density, elevation, slope, LU/LC and soil texture were prepared. System for automated geoscientific analysis (SAGA) GIS, PCI Geomatics, Rockworks 16, IDRISI Selva and Surfer 17.1, were employed for landform classification, lineament extraction, rose diagram preparation, pairwise comparison of the factors and identification of groundwater flow direction, respectively. The AHP technique of Multi-criteria decision analysis (MCDA) was employed to determine the relative weight and influences of the thematic layers. Geomorphologic landform, lineament density, geology, and rainfall distribution were found to be the dominant factors sharing the highest weightage of 67%. A weighting overlay approach of GIS was utilized to overlay the thematic maps. The resulting GWPZ of the study area indicates five zones representing very high, high, moderate, poor and very poor GWPZ. The areal extent of very high and high GWPZ is 41 km2 and 2032 km2, respectively. Moderate, poor and very poor GWPZ covers 2088 km2, 252 km2 and 0.142 km2 areas. The particular direction of groundwater flow is towards the NE and SE, coinciding with the direction of surface water flow. It was controlled by NW-SE striking geologic structures. The delineated GWPZ map is verified by using the existing water point’s inventory data. It indicates a good prediction accuracy of 84%. Thus, the identification of GWPZ by using GIS and RS through AHP is reliable for conducting similar studies
  • No Thumbnail Available
    Item
    EVALUATION OF PROPOSED EMBANKMENT DAM FOR DODOTA IRRIGATION PROJECT
    (Hawassa University, 2018-08-10) DAWUD MANZA DOLLEMO
    Design and construction of embankment dam is increasing from to time in our country to help the utilization of water for multipurpose. Evaluation of propose embankment dam for Dodota Irrigation project as alternative design by introducing asphaltic concrete core or clay core vital form the stand point of safety, controlling seepage and very important structure in fault and Earthquake area. This study was aimed to evaluate a proposed embankment dam as alternative design and analysis for Dodota Irrigation Project. Address this objective proposing an embankment dam with an impermeable asphalt concrete core and analyzes it for seepage static and dynamic stability using Geo Studio 2012 numerical computer program. Based on computation the flux through the dam and foundation for asphaltic concrete case has been found to be 0.000059 m 3 /s and the flux through the dam and foundation for asphaltic concrete case has been found to be 0. 0.001334 m 3 /s. The factory of safety of the propose embankment dam for the alternative design of embankment at different construction stage and with different loading condition satisfied the minimum requirement of (USAC,2003). The stress deformation observed was much lower than the expected bearing capacity of the foundation rock. The static deformation analysis computed for the propose embankment dam shows the horizontal and vertical deformation that the dam may subject to were in the tolerable limit. The dynamic deformation also analysis computed for the propose embankment dam during the time of shaking the maximum vertical and horizontal deformations within allowable limit. Generally, application of asphaltic concrete core rick fill and rock fill clay core dam in the project can fulfill the basic requirement and minimum factor of safety under all loading condition. Over all analysis of the thesis aim is indicate the possibility of constructing dam for the Dodota Irrigation Project
  • No Thumbnail Available
    Item
    IMPACTS OF LAND USE LAND COVER CHANGE ON RESERVOIR SEDIMENTATION (THE CASE OF RIBB DAM, IN LAKE TANA SUB-BASIN, ETHIOPIA)
    (Hawassa University, 2020-10-06) MEBRATU ESUBALEW ENGIDA
    Land use land cover (LULC) change is the challenge and continuous drivers of environmental change. Understanding the rate and process of change is, therefore, basic for managing the water resources and the environment at large. This study was intended to analyze the LULC changes impacts on sediment load from 2000 to 2018 periods, and select critical (hot spot area) sub basins and recommend best management practice for Ribb watershed of Lake Tana sub basin, Ethiopia. Both climate and hydrometric (flow and sediment) data were collected and analyzed over the period 1990 to 2018. Two time satellite imageries of the Land sat product (2000 and 2018) were used for land use change detection. The hybrid classification technique for extracting thematic information from satellite images were employed by using ERDAS model for classification of LULC. The Soil and Water Assessment Tool (SWAT) model was calibrated and validated to estimate sediment load of the watershed during the period 1992 to 2001 and 2002 to 2007 respectively. To manage the sediment load best management practices (BMP) as a scenario (filter strip, grassed water way and contouring) were implemented on 2018 LU map. The land use change detection result indicate that cultivated land has expanded from 66.87% in 2000 to 75.53% in 2018. Between 2000 and 2018 periods, it was increased by 8.66 %. The rate of increment during 2000–2018 periods were 608.915 ha/year. Similarly, settlement area had also increased by 2.09% from 2000–2018 periods. Similarly, shrub land and bare land also decreased at a rate of 412.868 and 227.651 ha/year, respectively, between 2000 and 2018 periods. Also the water body decreased at a rate of 1.593 ha/year between 2000 and 2018. The SWAT model result depict that the model give reasonable fit of sediment flux with observation during calibration and validation as evaluated with ENS ( 0.63 ) , R2 ( 0.67) and percent bias (17%) during calibration and ENS ( 0.58) , R2 ( 0.71) and percent bias of (12%) during validation period. Moreover, the severity of soil loss rate was increased with the average of 26.89 ton/ha/year from 2000 to 2018 LULC, which indicates that the management practice, was weak within the watershed. The BMP scenarios depict that filter strip was significant amount of LULC conversions practice and soil loss rate had occurred in the watershed from 2000 to 2018 periods, and expected to continue in the future. Thus, appropriate conservation and management practice are very much crucial to safe guard the life of the reservoir
  • No Thumbnail Available
    Item
    DETECTION AND CLASSIFICATION OF INDIGENOUS ROCK MINERALS USING DEEP LEARNING TECHNIQUES
    (Hawassa University, 2023-03-08) HADIA BERKA WAKO
    Ethiopia is undoubtedly a place of riches, with a vast and diverse landmass that is rich in resources. However, less attention has been given in utilizing computing discipline like Artificial Intelligence to solve the current problems in the area of mineral mining in Ethiopia. GUJI Zone is one of Oromia 20 administrative zones blessed with different mineral resources. Despite the fact that mineral has lions share contribution to economy of Ethiopia, little work is done in modernizing the mining industry in Ethiopia especially in empowering small-scale Artisanal community. GUJI is one of the zones following outmoded techniques to identify minerals in mining industry. Rock mineral detection and classification employing conventional methods involves testing physical and chemical properties at both the micro- and macro-scale in the laboratory, which is expensive and time-consuming. Identifying tiny rock minerals and detecting its originality using traditional procedure and techniques takes too much time. Identification of minerals merely through visual observation is often erroneous. To address these problems, a deep learning approach for the classification and detection of Rock Minerals is proposed. The design- science research methodology is followed to achieve the objectives of the research. To conduct this study, 2000 images were collected from Guji’s zone and Mindat.org website. After collecting the images, image pre-processing techniques such as image resizing, image segmentation using roboflow, and image annotation are performed. Moreover, data augmentation is applied to balance the dataset and increase the number of images. This research work focuses on classifying and detecting fifteen types of rock minerals. Based on YOLOv7 deep learning model we have used 70% of the dataset to train the model and 30 % of the dataset to test the performance of the model. Finally, the developed model is evaluated using accuracy, precision, recall, and mAP with other models. Experimental result shows that the accuracy obtained from YOLOv7 is 76%mAP for large objects comparing to other models. Consequently, the pretrained weight of yolov7 achieved a 97.3% accuracy in classifying and detecting with other images
  • No Thumbnail Available
    Item
    EXPLORING A BETTER FEATURE EXTRACTION METHOD FOR AMHARIC HATE SPEECH DETECTION
    (Hawassa University, 2021-10-08) YESUF MOHAMED YIMAM
    Hate speech is a speech that causes people to be attacked, discriminated, and hated because of their personal and collective identities. When hate speech grows, it will cause death and displacement of peoples from their homes and properties. Social media has the ability of widely spreading hate speech. To solve this problem, various researchers have studied many ways to detect social media hate speeches that are spreading in international and local languages. Because the problem is so serious, it needs to be carefully studied and better addressed in a variety of solutions. The previous studies detect a speech as hate speech, based on the frequency (occurrence) of a word in a given dataset; this means it does not consider the role of each word in a given sentence. The main purpose of this study is to design a method that can generate hate speech features from a given text by identifying the role of a word in a given sentence, so that hate speech can easily be distinguished from other forms of speech in a better way. To do this, various researches related to this study have been studied and reviewed. This study created a new feature extraction method for Amharic hate speech detection. The created model needs a training and testing dataset, so that posts and comments, which are posted on 25 popular Facebook pages, have been collected to build the dataset. Whether a speech is hateful or not, should be determined by the law that prohibits hate speech. So that, using different filtration methods, datasets that contain religious, ethnic, and hate words are collected and given to law experts, to annotate it manually. The law experts labeled 2590 datasets into three classes; Religion-hate, Ethnic-hate, and Non-hate. After dataset preparation, a new feature extraction method, which can distinguish hate speech from other speech, is developed. The new feature extraction method and other feature extraction methods that are used in other related studies are implemented and computed with three machine learning classification algorithms: SVM, NB, and RF. The result in different evaluation metrics shows that the new feature extraction method performed better in all combinations of classification algorithms. By using 80% of 2590 labeled datasets as a training set and the rest as a test set, 96.2% average accuracy is achieved using the combination of SVM with the new feature extraction method.
  • No Thumbnail Available
    Item
    DEVELOPING IMAGE-BASED ENSET PLANT DISEASE IDENTIFICATION USING CONVOLUTIONAL NEURAL NETWORK
    (Hawassa University, 2020-11-07) UMER NURI MOHAMMED
    Nowadays, decline in food plant productivity is a major problem causing food insecurity to which plant disease is one of the factors. Early identification and accurate diagnosis of the health status of food plants is hence critical to limit the spread of plant diseases and it should be in a technological manner rather than by the labor force. Traditional observation methods by farmers or domain experts is perhaps time-consuming, expensive and sometimes inaccurate. Based on the literature, the literature suggests that deep learning approaches are the most accurate models for the detection of plant disease. Convolutional Neural network (CNN) is one of the popular approaches that allows computational models that are composed of multiple processing layers to learn representations of image data with multiple levels of abstraction. These models have dramatically improved the state-of-the-art in visual object recognition and image classification that makes it a good way for enset plant disease classification problems. For this purpose, we used an appropriate CNN based model for identifying and classifying the three most critical diseases of enset plants: - enset bacterial wilt, enset Leaf spot, and Root mealybug diseases. Enset is one of a major source of food in the South, Central and Southwestern parts of Ethiopia. A total of 14,992 images are used for conducting experiments including augmented images with four different categories; three diseased and a healthy class obtained from the different agricultural sectors stationed at Hawassa and Worabe Ethiopia, these images are provided as input to the proposed model. Under the 10-fold cross-validation strategy, the experimental results show that the proposed model can effectively detect and classify four classes of enset plant diseases with the best classification accuracy of 99.53%, which is higher than compared to other classical deep learning models such as MobileNet and Inception v3 deep learning models
  • No Thumbnail Available
    Item
    A MODEL TOWARDS PRICE PREDICTION FOR COMMODITIES USING DEEP LEARNING: CASE OF ETHIOPIAN COMMODITY EXCHANGE
    (Hawassa University, 2022-10-03) SOLEN GOBENA
    The development of information technology makes it possible to collect and store large amounts of data every second. Market Enterprises are generating large amounts of data, and it is difficult to use traditional data analysis methods to analyze and predict their future market price. Price predictions are an integral component of trade and policy analysis. The prices of agricultural commodities directly influence the real income of farmers and it also affects the national foreign currency. Haricot bean is produced in many areas of Ethiopia and it is rich in starch, protein, and dietary fiber, and is an excellent source of minerals and vitamins. Haricot bean is also the main agricultural commodity traded on the Ethiopian commodity exchange (ECX) market for the past 10 years. Though there are price prediction works for various crops in Ethiopia and abroad using machine learning and deep learning approaches, price prediction for Haricot bean has not been studied using machine learning as to the best of our knowledge,. The main objective of this study is to develop a price prediction model that can predict future prices of Haricot Bean traded at the ECX market based on time series data. Past 10 years, data has been obtained from the Ethiopian commodity exchange (ECX) with sample dataset size of 12272. Simple linear regression (SLR), multiple linear regression (MLR), and long short term memory (LSTM) were evaluated as predictive models. The results showed that LSTM outperformed other predictive models in all measures of model performance for predicting the Haricot Bean prices by achieving a coefficient of determination (R2 ) of 0.97, mean absolute percentage error (MAPE) of 0.015, and mean absolute error (MAE) of 0.032.
  • No Thumbnail Available
    Item
    FOR SIDAMA LANGUAGE USING THE HIDDEN MARKOV MODEL WITH VITERBI ALGORITHM
    (Hawassa University, 2022-04-07) BELACHEW KEBEDE ESHETU
    The Parts of Speech (POS) tagger is an essential low-level tool in many natural language processing (NLP) applications. POS tagging is the process of assigning a corresponding part of a speech tag to a word that describes how it is used in a sentence. There are different approaches to POS tagging. The most common approaches are rule-based, stochastic, and hybrid POS tagging. In this paper, the stochastic approach, particularly the Hidden Markov Model (HMM) approach with the Viterbi algorithm, was applied to develop the part of the speech tagger for Sidaama. The HMM POS tagger tags the words based on the most probable sequence of words. For training and testing the model, 9,660 Sidaama sentences containing 130,847 tokens (words, punctuation, and symbols) were collected, and 4 experts in the language undertook the POS annotation. Thirty-one (31) POS tags were used in the annotation. The source of the corpus is fables, news, reading passages, and some scripts from the Bible. 90% of the corpus is used for training and the remaining 10% is used for testing. The POS tagger was implemented using the Python programming language (python 3.7.0) and the Natural Language Toolkit (NLTK 3.0.0). The performance of the Sidaama POS tagger was tested and validated using a ten-fold cross-validation technique. In the performance analysis experiment, the model achieved an accuracy of 91.25% for HMM model and 98.46% with the Viterbi algorithm