Modelling of extreme temperature and its correlation with ENSO : a case study in Perlis
Abstract
Extreme value (EV) theory has raised researcher's attention for modelling and forecasting the catastrophic or high-risk events. Since extreme environmental events may cause huge loss of properties and affect human life, therefore it is significant to
understand the behavior of such uncommon events and predict the upcoming. EV theory affords some understanding to the tail of a distribution where standard models have proved unreliable. The generalized extreme value (GEV) distribution is used to model
the extreme based on block maxima method. Inference of the extremes of environmental events is essential as a guideline in designing structures to survive under the utmost extreme condition. Extreme temperature caused various effect and can be
associated with human health and material damage. Meanwhile, El Nino Southern
Oscillation (ENSO), is a climate condition that happened all year round globally. The
EV theory is applied through GEV with two approaches, Maximum Likelihood
Estimate (MLE) and L-Moments (LM) to model the extreme temperature in Chuping,
Perlis and hence estimates the future extreme levels. The issue of block size is
discussed. The goodness of fit (GOF) test is done using root mean squared error
(RMSE) and Kolmogorov Smirnov (KS) test to determine the best approach. From the
results, it is found that MLE is better than LM for the yearly block but LM squared
things up for the monthly block. The return level is expected to exceed the maximum
value 40.1oC at certain return periods. The moderate correlation coefficient, r is
obtained in finding the relation between extreme temperature and ENSO. So, it is
proofed that ENSO events influences extreme temperature in Chuping, Perlis.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Injected fuel flow forecasting with Online Sequential Extreme Learning Machine
Zuraidi, Saad; Muhammad Khusairi, Osman; Mohd Yusoff, Mashor, Prof. Dr. (Universiti Malaysia Perlis (UniMAP), 2012-06-18)This study deals with Online Sequential Extreme Learning Machine (OS-ELM) modeling of a gasoline engine to predict the injected fuel flow of the engine. The single hidden layer feedforward networks (SLFN) trained by ... -
Investigation of vision impairments using pattern reversal VEPs and extreme learning machine
Vijean, Vikneswaran; Hariharan, Muthusamy; Sazali, Yaacob, Prof. Dr. (Universiti Malaysia Perlis (UniMAP), 2012-06-18)Analysis of vision impairment using pattern reversal visually evoked potentials (VEP) is gaining interest from researchers. The VEPs are collected using non-invasive EEG electrodes from the scalp overlaying the occipital ... -
Detection of tuberculosis bacilli in tissue slide images using HMLP network trained by Extreme Learning Machine
Muhammad Khusairi, Osman; Mohd Yusoff, Mashor, Prof. Dr.; Hasnan, Jaafar, Prof. (Kauno Technologijos Universitetas, 2012-04)This paper proposes an automated detection of tuberculosis bacilli in Ziehl-Neelsen-stained tissue slides using image processing and neural network. Image segmentation using CY-based colour filter and k-mean clustering ...