School of Built Environment (SBE) Collections

Permanent URI for this collection

http://10.29.1.53:4000/handle/10570/179

Browse

Recent Submissions

Now showing 1 - 5 of 448
  • Item
    Artificial neural networks in solving accuracy challenges of short-term rainfall forecasting in the Lake Victoria Basin
    (Makerere University, 2025) Sserwadda, George
    Accurate rainfall prediction is crucial for effective water resource management, disaster risk reduction, and agricultural planning in Uganda's Lake Victoria Basin. This study focused on Kampala as a representative case to address this need. Given that agriculture in the region is predominantly rain-fed and employs 68% of Uganda’s population, reliable forecasts are vital for economic stability and food security. However, achieving accuracy is challenging in this region because rainfall patterns are complex and non-linear, exhibiting high spatial-temporal variability. These patterns are influenced by large-scale climatic phenomena, including the Inter-Tropical Convergence Zone, El Niño/La Niña events, and the Indian Ocean Dipole, which often cause traditional forecasting models to struggle. This study investigated the use of Artificial Neural Networks (ANNs) to enhance shortterm (1-10 hours lead time) rainfall forecasting using Kampala as a case study within the Lake Victoria basin. A hybrid model, combining Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks was developed to address the region's prediction challenges. The model was trained using 80% of a dataset of hourly weather data from the Uganda National Meteorological Authority and the Trans-African HydroMeteorological Observatory (TAHMO) while 20% of the data was reserved for testing. The model outputs a quantitative prediction of precipitation (in mm) for a 10-hour horizon Additionally, the study incorporated lightning data, a parameter often overlooked in traditional models but essential for accurately forecasting the convective rainfall prevalent in the study area. The results of the study show that the proposed CNN-LSTM model significantly improves forecasting accuracy over traditional approaches. Notably, it achieved a reduction in Mean Absolute Error (MAE) of up to 95.30% against the one-dimensional CNN model and 89.28% against the standalone LSTM model when used for point predictions. The model also consistently outperformed Random Forest and Vector Autoregression (VAR) models. Consequently, integrating such machine learning models into forecasting frameworks for areas within the Lake Victoria Basin, such as Kampala can directly improve disaster management, agricultural decisions, and water resource planning Keyword: Artificial neural networks
  • Item
    An assessment of property rates as an alternative local revenue generation : a case study of Kawempe Division, Kampala City
    (Makerere University, 2025) Epieu, Emmanuel
    Kawempe Division lies right within the heart of Kampala City and yet revenue collections from property rates is always lagging below other divisions. Property rates has a very big potential of eccelerating revenue potential of the division. Its in the background of this that the auther set out to establish the magic potential of property rates as an alternative revenue generation source for Kawempe Divition.
  • Item
    Improvement and renovation of existing warehouse on plots 238 & 264 block no. 424, Kyagwe, Mukono District
    (Makerere University, 2025-12-05) Baguma, Borice
    This report thoroughly explains the construction practices that the author participated in as consultant’s Quantity Surveyor during the execution of construction works for the improvement and renovation of existing warehouse on plots 238 & 264 block no. 424, kyagwe, Mukono district. The project whose total cost was Uganda Shillings seven billion one hundred sixty-one million nine hundred thirty-six thousand twenty only (UGX. 7,161,936,020) VAT inclusive was implemented by Gisa Consortium Limited as the main contractor from 11th November 2024 up to 26th may 2025. The project consisted of improving and remodeling of three ware house blocks, construction of a new toilet block, mechanical and electrical works, air conditioning, ICT installations and external works of paving, landscaping, building gate house and boundary wall. It is a requirement that a student of Post Graduate Diploma in Construction Project Management of Makerere University relates his participation in a construction project with the knowledge obtained in this course. On this project, the author was assigned a number of duties including tender evaluation, measurements of work on site, preparing valuations and payment certificates, preparing procurement schedules, preparing construction work programs and schedule management, Throughout the execution of these tasks, the author was able to apply the various construction project management skills and knowledge obtained during the course as expounded in this report. This report discusses the project background and details, procurement and execution of works, challenges encountered, solutions and lessons learnt, conclusion and recommendations drawn by the author.
  • Item
    Investigation of the impact of design changes on project success; A case study of the Kikuube District Administration Block
    (Makerere University, 2025-06-19) Muhumuza, John
    This study explores the impact of design changes on the success of infrastructure projects, focusing on the Kikuube District Administration Block. It highlights a significant deviation from the ideal project delivery scenario of timeline, budget adherence, and high-quality standards. The study aims to analyze the causes of design variations and assess their effects on project outcomes. A series of targeted inquiries were conducted to identify common factors contributing to project variations and their subsequent influence on costs, timelines, and deliverables. Furthermore, the study evaluates the effectiveness of supervisory interventions in managing these challenges. Quantitative data analysis was performed using SPSS software, employing both descriptive and inferential statistics. The findings reveal that inadequate initial site investigations, particularly insufficient geotechnical surveys, were significant contributors to project complications. These oversights led to unforeseen subsoil conditions during construction, necessitating a shift from planned strip foundations to reinforced pad and column foundations, ground beams resulting in budget overruns and an approximate delay of 3.5 weeks. The research also identifies the adverse effects of late stakeholder engagement, which prompted changes in functional requirements, such as the inclusion of an ICT hub and expansions to boardroom and archive facilities. Vulnerabilities in the material supply chain emerged due to reliance on a limited number of suppliers, causing further delays. The study quantified the impacts of variations, recording significant cost escalations, timeline delays, and reduced construction quality. Recommendations include the implementation of a structured change-approval process to minimize delays and enhance evaluation thoroughness, alongside improving communication and fostering stakeholder dialogue to strengthen collaboration. Lastly, transparent accountability measures for contractors are proposed to align expectations and enhance overall project performance.
  • Item
    Construction project delays: implications on time and cost in Government Construction Projects in Uganda: a case study of the JLOS house project for the Ministry of Justice and Constitutional Affairs.
    (Makerere University, 2025) Migadde, Hamuza
    This report presents a comprehensive assessment of construction delays, time-cost implications, and contractor acceleration strategies on the JLOS House Phase 01 Project, a flagship justice sector infrastructure development in Uganda. The study evaluates the project’s performance against three progressively revised baselines, with the original completion date of 7 May 2024 now extended to 31 December 2025, reflecting over 600 days of cumulative delay. Using a combination of field observations, impacted work program analysis, progress reports, Minutes of site meetings, other project records and stakeholder websites, the research identifies critical delay causation factors including late design approvals, scope changes, institutional bottlenecks, equipment breakdowns, and material shortages. Delay categorisation and EOT claim analysis were supported by tools such as Gantt chart overlays, timeline simulations, and FIDIC-based contractual frameworks. Despite funded acceleration efforts such as manpower scaling, phased trade deployment, and site re-organization, the contractor was unable to recover schedule slippage due to unresolved external dependencies and fragmented coordination The study offers practical insights into delay mitigation and project control in complex public infrastructure projects by integrating academic knowledge from construction management, contract law, risk analysis, and scheduling techniques (e.g., CPM, delay causation modelling). The report concludes with actionable recommendations aimed at improving scope definition, approval workflows, digital project monitoring, and institutional capacity within Uganda’s public construction sector.