Research Papers - Department of Civil Engineering

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/598

Browse

Filters

20202

Advanced Search

Filter by

Settings

Author: search.filters.author.Azamathulla, HSubject: search.filters.subject.Atmospheric temperature

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Comparison of different Artificial Neural Network (ANN) training algorithms to predict atmospheric temperature in Tabuk, Saudi Arabia
    (researchgate.net, 2020-06) Perera, A; Azamathulla, H; Rathnayake, U
    Use of Artificial neural network (ANN) models to predict weather parameters has become important over the years. ANN models give more accurate results in weather and climate forecasting among many other methods. However, different models require different data and these data have to be handled accordingly, but carefully. In addition, most of these data are from non-linear processes and therefore, the prediction models are usually complex. Nevertheless, neural networks perform well for non-linear data and produce well acceptable results. Therefore, this study was carried out to compare different ANN models to predict the minimum atmospheric temperature and maximum atmospheric temperature in Tabuk, Saudi Arabia. ANN models were trained using eight different training algorithms. BFGS Quasi Newton (BFG), Conjugate gradient with Powell-Beale restarts (CGB), Levenberg-Marquadt (LM), Scaled Conjugate Gradient (SCG), Fletcher-Reeves update Conjugate Gradient algorithm (CGF), One Step Secant (OSS), Polak-Ribiere update Conjugate Gradient (CGP) and Resilient Back-Propagation (RP) training algorithms were fed to the climatic data in Tabuk, Saudi Arabia. The performance of the different training algorithms to train ANN models were evaluated using Mean Squared Error (MSE) and correlation coefficient (R). The evaluation shows that training algorithms BFG, LM and SCG have outperformed others while OSS training algorithm has the lowest performance in comparison to other algorithms used.
  • Thumbnail Image
    PublicationOpen Access
    Recent Climatic Trends In Trinidad And Tobago, West Indies
    (Research and Technology Transfer Affairs Division,, 2020-02) Perera, A; Mudannyake, S; Azamathulla, H; Rathnayake, U. S
    Seawater level rise is one of the most prevalent adverse environmental impacts of the ongoing global warming process. Island nations are more vulnerable to the impact than the land masses. Two such islands impacted by global warming are Trinidad and Tobago, located in the Atlantic Ocean. However, there is minimal related research in this area in the context of the impact of climate variability. Therefore, it is timely and interesting to assess the climatic trends in islands that are extremely vulnerable like Trinidad and Tobago. This paper presents a detailed non-parametric statistical analysis for well-known climate gauges in Trinidad and Tobago, West Indies. Mann Kendall and Sen’s slope tests were carried out on two identified rain gauges in Trinidad and Tobago. Monthly climatic data including cumulative rainfall and the average of the minimum and maximum atmospheric temperatures were processed to identify the trend analysis using the above stated non-parametric tests. Important results are found from the analysis; most importantly, there is no significant impact on the rainfall in the area due to the climate variability over 30 years. However, the atmospheric temperature behaves in a different way and it has a rising pattern across the total 12 months studied. This can be seen for both the minimum and maximum atmospheric temperatures. Therefore, the warm months are becoming warmer and the cold months are becoming less cold. This is a critical finding that must be considered for any future planning processes.