Research Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194

This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.

Browse

Filters

2023 - 20243

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Time series

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    PublicationOpen Access
    Forecasting Global Annual Average CO2 Concentrations
    (Faculty of Humanities and Sciences, SLIIT, 2024-12-04) Rasanjali, R.P.B; Tharupathi, M.D.G; Dharmarathne, S.R.J.M; Weerakoon, M.M; Peris, T.S.G
    This study aims to enhance the accuracy of CO₂ level forecasts, compare the effi cacy of diff erent predicti ve models, and provide insights for policy development. Employing ti me series and regression analysis techniques, the study uses historical data from global monitoring stati ons (1979- 2022) to model the annual mean concentrati on of atmospheric CO2 The results reveal that the ARIMA (1,1,1) model outperforms the simple linear regression model in predicti ve accuracy. Nevertheless, the regression model came across a technical problem as residuals are signifi cantly autocorrelated. The Augmented Dickey-Fuller test was applied to ensure stati onarity of the fi rst diff erence of the original series. The model was trained using data from 1979 to 2022 and validated for 2023. The errors of the ARIMA(1,1,1) was found to be white noise. The ARIMA model projected CO₂ concentrati ons of 419.5, 421.8 and 424.2 for the years 2023, 2024, and 2025 respecti vely, with a percentage error of just 0.048% for the 2023. In contrast, the corresponding percentage of error for the simple linear regression model was -1.236%. These fi ndings underscore the ARIMA model’s superior performance in forecasti ng future CO₂ levels and its suitability for environmental monitoring and climate change miti gati on strategies. This research provides a valuable methodological framework for future atmospheric science studies and informs policy decisions aimed at addressing rising CO₂ concentrations.
  • Thumbnail Image
    PublicationOpen Access
    Assessing Statistical Methods for Generating Forecasts for COVID-19
    (Faculty of Humanities and Sciences, SLIIT, 2024-06-09) Siriwardena, S. M. D. G. A; Dharmaratne, G.; Amaratunga, D.
    The COVID-19 pandemic, a persistent global health emergency that has affected almost all facets of daily life, was initially discovered in Wuhan, China, in December 2019. Since that time, the virus has rapidly spread over the globe, causing serious social and economic upheavals necessitating the need for reliable forecasting methods. This study compares ten distinct models to predict the number of confirmed COVID-19 cases in Sri Lanka, aiming to assess the performance of statistical models using limited and volatile real-world data characterized by trends, random peaks, and autocorrelations. In addition to the classical ARIMA model, various smoothing and filtering techniques were explored to capture the unique characteristics of the data. The model consistencies in multiple-day predictions were demonstrated, and robust evaluation criteria, along with non-robust measures, were utilized to enhance the effectiveness of the evaluation process. The results highlight the effectiveness of traditional smoothing and filtering strategies such as Simple Exponential Smoothing, Holt’s Exponential Smoothing, and the Smoothing Splines technique coupled with the ARIMA model. This study also discovered that the ARIMA model, when applied directly to the original data without using any smoothing or filtering approaches, failed to forecast adequately, thereby demonstrating the insufficiency of the ARIMA model on its own to provide credible forecasts when given a volatile set of data.
  • Thumbnail Image
    PublicationOpen Access
    Data Smoothing and Other Methods for Generating Forecasts for COVID-19 Cases in Sri Lanka
    (Faculty of Humanities and Sciences, SLIIT, 2023-11-01) Siriwardena, G; Dharmaratne, G; Amaratunga, D
    The COVID-19 pandemic has significantly impacted global society, including Sri Lanka, necessitating the need for reliable forecasting methods. This study compares ten distinct models to predict the number of confirmed COVID-19 cases in Sri Lanka, aiming to assess the performance of statistical models using limited and volatile realworld data characterized by trends, random peaks, and autocorrelations. In addition to the classical ARIMA model, various smoothing and filtering techniques were explored to capture the unique characteristics of the data. The model consistencies in multiple-day predictions were demonstrated, and robust evaluation criteria, along with non-robust measures, were utilized to enhance the effectiveness of the evaluation process. The results highlight the effectiveness of traditional smoothing strategies such as Simple Exponential Smoothing, Holt’s Exponential Smoothing, and the Smoothing Splines technique coupled with the ARIMA model. Notably, applying the ARIMA model directly to the original data without smoothing or filtering approaches yielded inadequate forecasts, underscoring its limitations in volatile data settings.