Application of data driven modelling in prediction of future climate change on the solar powered water pumping production.
| dc.contributor.author | Mukasa, Robert | |
| dc.date.accessioned | 2026-06-18T07:38:28Z | |
| dc.date.available | 2026-06-18T07:38:28Z | |
| dc.date.issued | 2026 | |
| dc.description | Dissertation | |
| dc.description.abstract | This study investigated the impact of climate change on the performance of photovoltaic (PV) solar powered water pumping systems (SPWPS) and future prediction of their performance, with the aim of: (i) identifying the key meteorological and technological parameters governing water yield; (ii) developing a validated predictive model linking meteorological variables to daily water yield; and (iii) simulating future water yield under Intergovernmental Panel on Climate Change (IPCC) climate projections. Historical meteorological data including solar irradiance, ambient temperature, relative humidity, wind speed, rainfall, and dust deposition index were analyzed alongside ten years of system performance data (2014–2023) using descriptive statistics, Principal Component Analysis (PCA), and Pearson correlation analysis to identify dominant influencing variables. Three data driven predictive models were developed and evaluated: Multiple Linear Regression (MLR), an Artificial Neural Network (ANN), and a Hybrid GRU-LSTM Recurrent Neural Network. The Hybrid GRU-LSTM model achieved the highest predictive accuracy (R² = 0.95, NSE = 0.94, RMSE = 0.31 m³/day), significantly outperforming MLR (R² = 0.71, NSE = 0.68) and the ANN (R² = 0.83, NSE = 0.81). PCA revealed that solar irradiance and ambient temperature together account for approximately 67% of total system performance variance. Sensitivity analysis confirmed solar irradiance (34.1%) and ambient temperature (21.3%) as the most influential model inputs. Future climate scenario simulations using IPCC SSP2-4.5 (moderate emissions) and SSP5-8.5 (high emissions) projections indicated projected declines in mean daily water yield of 6.7% and 13.6% respectively by 2050–2060, with reductions reaching 9.1% (SSP2-4.5) and 21.4% (SSP5-8.5) by 2070–2080. The largest losses are projected during the hot dry season (June–August), precisely when domestic water demand is highest, presenting a critical water security risk. The study recommends incorporating a 10–20% climate adjustment factor in future SPWPS design standards and establishing structured monitoring and maintenance frameworks aligned with projected climate trajectories | |
| dc.description.sponsorship | Dr. Joseph Ddumba Lwanyaga : Mr. Bendicto S. Maseruka : Busitema University | |
| dc.identifier.citation | Mukasa, R. (2026). Application of data driven modelling in prediction of future climate change on the solar powered water pumping production. Busitema University. Unpublished dissertation. | |
| dc.identifier.uri | https://bdears.busitema.ac.ug/handle/123456789/6302 | |
| dc.language.iso | en | |
| dc.publisher | Busitema University | |
| dc.title | Application of data driven modelling in prediction of future climate change on the solar powered water pumping production. | |
| dc.type | Other |