Faculty of Engineering
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4203
Browse
11 results
Search Results
Publication Open Access Regression-Based Prediction of Power Generation at Samanalawewa Hydropower Plant in Sri Lanka Using Machine Learning(Hindawi, 2021-07-31) Ekanayake, P; Wickramasinghe, L; Jayasinghe, J. M; Rathnayake, U. SThis paper presents the development of models for the prediction of power generation at the Samanalawewa hydropower plant, which is one of the major power stations in Sri Lanka. Four regression-based machine learning and statistical techniques were applied to develop the prediction models. Rainfall data at six locations in the catchment area of the Samanalawewa reservoir from 1993 to 2019 were used as the main input variables. The minimum and maximum temperature and evaporation at the reservoir site were also incorporated. The collinearities between the variables were investigated in terms of Pearson’s and Spearman’s correlation coefficients. It was found that rainfall at one location is less impactful on power generation, while that at other locations are highly correlated with each other. Prediction models based on monthly and quarterly data were developed, and their performance was evaluated in terms of the correlation coefficient (R), mean absolute percentage error (MAPE), ratio of the root mean square error (RMSE) to the standard deviation of measured data (RSR), BIAS, and the Nash number. Of the Gaussian process regression (GPR), support vector regression (SVR), multiple linear regression (MLR), and power regression (PR), the machine learning techniques (GPR and SVR) produced the comparably accurate prediction models. Being the most accurate prediction model, the GPR produced the best correlation coefficient closer to 1 with a very less error. This model could be used in predicting the hydropower generation at the Samanalawewa power station using the rainfall forecast.Publication Embargo A new hybrid fuzzy time series model with an application to predict PM10 concentration(www.elsevier.com/locate/ecoenv, 2021-10-28) Alyousifi, Y; Othman, M; Husin, A; Rathnayake, U. SFuzzy time series (FTS) forecasting models show a great performance in predicting time series, such as air pollution time series. However, they have caused major issues by utilizing random partitioning of the universe of discourse and ignoring repeated fuzzy sets. In this study, a novel hybrid forecasting model by integrating fuzzy time series to Markov chain and C-Means clustering techniques with an optimal number of clusters is presented. This hybridization contributes to generating effective lengths of intervals and thus, improving the model accuracy. The proposed model was verified and validated with real time series data sets, which are the benchmark data of actual trading of Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and PM10 concentration data from Melaka, Malaysia. In addition, a comparison was made with some existing fuzzy time series models. Furthermore, the mean absolute percentage error, mean squared error and Theil's U statistic were calculated as evaluation criteria to illustrate the performance of the proposed model. The empirical analysis shows that the proposed model handles the time series data sets more efficiently and provides better overall forecasting results than existing FTS models. The results prove that the proposed model has greatly improved the prediction accuracy, for which it outperforms several fuzzy time series models. Therefore, it can be concluded that the proposed model is a better option for forecasting air pollution parameters and any kind of random parameters.Publication Open Access Hydrologic utility of satellite-based and gauge-based gridded precipitation products in the Huai Bang Sai watershed of Northeastern Thailand(https://www.mdpi.com/journal/hydrology, 2021-11-01) Gunathilake, M; Zamri, M. N. M; Alagiyawanna, T; Samarasinghe, J; Baddewela, P; Babel, M; Jha, M; Rathnayake, U. SAccurate rainfall estimates are important in many hydrologic activities. Rainfall data are retrieved from rain gauges (RGs), satellites, radars, and re-analysis products. The accuracy of gauge-based gridded precipitation products (GbGPPs) relies on the distribution of RGs and the quality of rainfall data records obtained from these. The accuracy of satellite-based precipitation products (SbPPs) depends on many factors, including basin climatology, basin topography, precipitation mechanism, etc. The hydrologic utility of different precipitation products was examined in many developed regions; however, less focused on the developing world. The Huai Bang Sai (HBS) watershed in north-eastern Thailand is a less focused but an important catchment that significantly contributes to the water resources in Thailand. Therefore, this research presents the investigation results of the hydrologic utility of SbPPs and GbGPPs in the HBS watershed. The efficiency of nine SbPPs (including 3B42, 3B42-RT, PERSIANN, PERSIANN-CCS, PERSIANN-CDR, CHIRPS, CMORPH, IMERG, and MSWEP) and three GbGPPs (including APHRODITE_V1801, APHRODITE_V1901, and GPCC) was examined by simulating streamflow of the HBS watershed through the Soil & Water Assessment Tool (SWAT), hydrologic model. Subsequently, the streamflow simulation capacity of the hydrological model for different precipitation products was compared against observed streamflow records by using the same set of calibrated parameters used for an RG simulated scenario. The 3B42 product outperformed other SbPPS with a higher Nash–Sutcliffe Efficiency (NSEmonthly>0.55), while APHRODITE_V1901 (NSEmonthly>0.53) performed fairly well in the GbGPPs category with closer agreements with observed streamflow. In addition, the CMORPH precipitation product has not performed well in capturing observed rainfall and subsequently in simulating streamflow (NSEmonthly<0) of the HBS. Furthermore, MSWEP and CHIRPS products have performed fairly well during calibration; however, they showcased a lowered performance for validation. Therefore, the results suggest that accurate precipitation data is the major governing factor in streamflow modeling performances. The research outcomes would capture the interest of all stakeholders, including farmers, meteorologists, agriculturists, river basin managers, and hydrologists for potential applications in the tropical humid regions of the world. Moreover, 3B42 and APHRODITE_V1901 precipitation products show promising prospects for the tropical humid regions of the world for hydrologic modeling and climatological studies.Publication Open Access Trend analysis and change point detection of air pollution index in Malaysia(Springer Berlin Heidelberg, 2021-11-21) Alyousifi, Y; Ibrahim, K; Zin, W. Z. W; Rathnayake, U. SParametric methods are commonly used to conduct the trend analysis of air pollution. These methods require certain statistical assumptions, such as stationarity and normality of the data. However, such assumptions are usually not applicable to trends in Air pollution index (API). In addition, the change points in the time series have not been taken into consideration by most of the analysis of API. Therefore, this study presents a comprehensive investigation of the trend analysis and change point detection of the mean and maximum of API series in Malaysia. The hourly, daily, weekly, monthly, seasonal, and annual API data series were considered in the analysis. The fner time intervals were used to detect any signifcant increasing or decreasing trends of the API series for Malaysia. The API data were collected from 37 air monitoring stations in Peninsular Malaysia. The nonparametric tests, including Mann–Kendall test, Pettitt test, and innovative trend analysis were used to examine the contribution presented herein. Various aspects of API data were studied, including upward trends, downward trends, and change points. Several signifcant monotonic trends and changing points in some of the API measuring stations were found from the Mann–Kendall test results. Signifcant increasing trends of the monthly and seasonal mean, as well as maximum API, were found in the years 2013 and 2014 for some stations. In addition, the magnitudes of the increasing trends in maximum API are larger than the mean API. The detection points captured by the Pettitt test are possibly related to the El-Nino events. In general, the results of the study provide comprehensive information on air quality trends and their atmospheric aspects, which can help in developing strategies to address air quality problems and provide meaningful opportunities to mitigate air pollution problems in Peninsular Malaysia.Publication Open Access Projected Moisture Index (MI) for tropical Sri Lanka(Hindawi, 2021-12) Wickramarachchi, C; Samarasinghe, T; Alyousifi, Y; Rathnayake, U. SAtmospheric moisture loading can cause a great impact on the performance and integrity of building exteriors in a tropical climate. Buildings can be highly impacted due to the changing climate conditions over the world. Therefore, it is important to incorporate the projected changes of moisture loads in structural designs under changing climates. The moisture index (MI) is widely used in many countries as a climate-based indicator to guide the building designs for their durability performance. However, this was hardly considered in structural designs in Sri Lanka, even though the country is one of the most affected countries under climate change. Therefore, this study investigates future climate change impacts on the environmental moisture in terms of MI, which can be used in climate zoning, investigating indoor air quality, understanding thermal comfort and energy consumption, etc. The moisture index was found as a function of the drying index (DI) and wetting index (WI) to the whole country for its four rainfall seasons. The temporal and spatial distributions were plotted as MI maps and showcased under two categories; including historical MI maps (1990–2004) and future projected MI maps (2021–2040, 2041–2070, and 2071–2100). Future projected MI maps were constructed using bias-corrected climatic data for two RCP climatic scenarios (RCP4.5 and RCP8.5). Results showed that the temporal and spatial variations of MIs are justifiable to the country’s rainfall patterns and seasons. However, notable increases of MIs can be observed for future projected MIs in two seasons, and thus a careful investigation of their impacts should be assessed in terms of the construction of buildings and various agricultural activities. Therefore, the outcome of this research can be essentially used in policy implementation in adapting to the ongoing climate changes in Sri Lanka.Publication Open Access Development of wind power prediction models for Pawan Danavi wind farm in Sri Lanka(Hindawi, 2021-05) Peiris, A. T; Jayasinghe, J. M. J. W.; Rathnayake, U. SThis paper presents the development of wind power prediction models for a wind farm in Sri Lanka using an artificial neural network (ANN), multiple linear regression (MLR), and power regression (PR) techniques. Power generation data over five years since 2015 were used as the dependent variable in modeling, while the corresponding wind speed and ambient temperature values were used as independent variables. Variation of these three variables over time was analyzed to identify monthly, seasonal, and annual patterns. The monthly patterns are coherent with the seasonal monsoon winds exhibiting little annual variation, in the absence of extreme meteorological changes during the period of 2015–2020. The correlation within each pair of variables was also examined by applying statistical techniques, which are presented in terms of Pearson’s and Spearman’s correlation coefficients. The impact of unit increase (or decrease) in the wind speed and ambient temperature around their mean values on the output power was also quantified. Finally, the accuracy of each model was evaluated by means of the correlation coefficient, root mean squared error (RMSE), bias, and the Nash number. All the models demonstrated acceptable accuracy with correlation coefficient and Nash number closer to 1, very low RMSE, and bias closer to 0. Although the ANN-based model is the most accurate due to advanced features in machine learning, it does not express the generated power output in terms of the independent variables. In contrast, the regression-based statistical models of MLR and PR are advantageous, providing an insight into modeling the power generated by the other wind farms in the same region, which are influenced by similar climate conditions.Publication Open Access Ecosystem-Based Adaptation for the Impact of Climate Change and Variation in the Water Management Sector of Sri Lanka(Hindawi, 2021-02-25) Khaniya, B; Gunathilake, M. B; Rathnayake, U. SThe climate of Sri Lanka has been fluctuating at an alarming rate during the recent past. These changes are reported to have pronounced impacts on the livelihoods of the people in the country. Water is central to the sustainable functioning of ecosystems and wellbeing of mankind. It is evident that pronounced variations in the climate will negatively impact the availability and the quality of water resources. The ecosystem-based adaptation (EbA) approach has proved to be an effective strategy to address the impact of climate change on water resources in many parts of the world. The key aim of this paper is to elaborate the wide range of benefits received through implementation of EbAs in field level, watershed scale, and urban and coastal environments in the context of Sri Lanka. In addition, this paper discusses the benefits of utilizing EbA solutions over grey infrastructure-based solutions to address the issues related to water management. The wide range of benefits received through implementation of EbAs can be broadly classified into three categories: water supply regulation, water quality regulation, and moderation of extreme events. This paper recommends the utilization of EbAs over grey infrastructure-based solutions in adaptation to climate change in the water management sector for the developing region due its cost effectiveness, ecofriendliness, and multiple benefits received on long-term scales. The findings of this study will unequivocally contribute to filling existing knowledge and research gaps in the context of EbAs to future climate change in Sri Lanka. The suggestions and opinions of this study can be taken into account by decision makers and water resources planning agencies for future planning of actions related to climate change adaptation in Sri Lanka.Publication Open Access Artificial Neural Network based PERSIANN data sets in evaluation of hydrologic utility of precipitation estimations in a tropical watershed of Sri Lanka(AIMS Geosciences, 2021-09) Gunathilake, M; Senarath, T; Rathnayake, U. SThe developments of satellite technologies and remote sensing (RS) have provided a way forward with potential for tremendous progress in estimating precipitation in many regions of the world. These products are especially useful in developing countries and regions, where ground-based rain gauge (RG) networks are either sparse or do not exist. In the present study the hydrologic utility of three satellite-based precipitation products (SbPPs) namely, Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN), PERSIANN-Cloud Classification System (PERSIANN-CCS) and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Dynamic Infrared Rain Rate near real-time (PDIR-NOW) were examined by using them to drive the Hydrologic Engineering Center-Hydrologic Modeling System (HEC-HMS) hydrologic model for the Seethawaka watershed, a sub-basin of the Kelani River Basin of Sri Lanka. The hydrologic utility of SbPPs was examined by comparing the outputs of this modelling exercise against observed discharge records at the Deraniyagala streamflow gauging station during two extreme rainfall events from 2016 and 2017. The observed discharges were simulated considerably better by the model when RG data was used to drive it than when these SbPPs. The results demonstrated that PERSIANN family of precipitation products are not capable of producing peak discharges and timing of peaks essential for near-real time flood-forecasting applications in the Seethawaka watershed. The difference in performance is quantified using the Nash-Sutcliffe Efficiency, which was >0.80 for the model when driven by RGs, and <0.08 when driven by the SbPPs. Amongst the SbPPs, PERSIANN performed best. The outcomes of this study will provide useful insights and recommendations for future research expected to be carried out in the Seethawaka watershed using SbPPs. The results of this 479 AIMS Geosciences Volume 7, Issue 3, 478–489. study calls for the refinement of retrieval algorithms in rainfall estimation techniques of PERSIANN family of rainfall products for the tropical region.Publication Open Access Optimal control of combined sewer overflows(DAVID PUBLISHING, 2021) Rathnayake, U. S: Combined sewer networks carry wastewater and stormwater together. Capacity limitation of these sewer networks results in combined sewer overflows (CSOs) during high-intensity storms. Untreated CSOs when directly discharged to the nearby natural water bodies cause many environmental problems. Controlling existing urban sewer networks is one possible way of addressing the issues in urban wastewater systems. However, it is still a challenge, when considering the receiving water quality effects. This paper presents an evolutionary constrained multi-objective optimization approach to control the existing combined sewer networks. The control of online storage tanks was taken into account when controlling the combined sewer network. The developed multi-objective approach considers two important objectives, i.e. the pollution load to the receiving water from CSOs and the cost of the wastewater treatment. The proposed optimization algorithm is applied here to a realistic interceptor sewer system to demonstrate its effectiveness.Publication Open Access Hydrological models and Artificial Neural Networks (ANNs) to simulate streamflow in a tropical catchment of Sri Lanka(10.1155/2021/6683389, 2021-05) Gunathilake, M. B; Karunanayake, C; Gunathilake, A. S; Samarasinghe, T; Bandara, I. M; Rathnayake, U. SAccurate streamflow estimations are essential for planning and decision-making of many development activities related to water resources. Hydrological modelling is a frequently adopted and a matured technique to simulate streamflow compared to the data driven models such as artificial neural networks (ANNs). In addition, usage of ANNs is minimum to simulate streamflow in the context of Sri Lanka. Therefore, this study presents an intercomparison between streamflow estimations from conventional hydrological modelling and ANN analysis for Seethawaka River Basin located in the upstream part of the Kelani River Basin, Sri Lanka. The hydrological model was developed using the Hydrologic Engineering Centre-Hydrologic Modelling System (HEC-HMS), while the data-driven ANN model was developed in MATLAB. The rainfall and streamflows’ data for 2003–2010 period have been used. The simulations by HEC-HMS were performed by four types of input rainfall data configurations, including observed rainfall data sets and three satellite-based precipitation products (SbPPs), namely, PERSIANN, PERSIANN-CCS, and PERSIANN-CDR. The ANN model was trained using three well-known training algorithms, namely, Levenberg–Marquadt (LM), Bayesian regularization (BR), and scaled conjugate gradient (SCG). Results revealed that the simulated hydrological model based on observed rainfall outperformed those of based on remotely sensed SbPPs. BR algorithm-based ANN algorithm was found to be superior among the data-driven models in the context of ANN model simulations. However, none of the above developed models were able to capture several peak discharges recorded in the Seethawaka River. The results of this study indicate that ANN models can be used to simulate streamflow to an acceptable level, despite presence of intensive spatial and temporal data sets, which are often required for hydrologic software. Hence, the results of the current study provide valuable feedback for water resources’ planners in the developing region which lack multiple data sets for hydrologic software.