The estimation of an increase in sea level with sufficient warning time is important in low-lying regions, especially in the east coast of Peninsular Malaysia (ECPM). This study primarily aims to investigate the validity and effectiveness of the support vector machine (SVM) and genetic programming (GP) models for predicting the monthly mean sea level variations and comparing their prediction accuracies in terms of the model performances. The input dataset was obtained from Kerteh, Tioman Island, and Tanjung Sedili in Malaysia from January 2007 to December 2017 to predict the sea levels for five different time periods (1, 5, 10, 20, and 40 years). Further, the SVM and GP models are subjected to preprocessing to obtain optimal performance. The tuning parameters are generalized for the optimal input designs (SVM2 and GP2), and the results denote that SVM2 outperforms GP with R of 0.81 and 0.86 during the training and testing periods, respectively, at the study locations. However, GP can provide values of 0.71 and 0.79 for training and testing, respectively, at the study locations. The results show precise predictions of the monthly mean sea level, denoting the promising potential of the used models for performing sea level data analysis.

Development, operations and management of multi-objective reservoirs, is vital for timely water supply. Optimisation studies were done at the Klang Gate Dam (KGD) utilising standard optimisation and dynamic programming; according to the technology then. Taking it further, the KGD was studied using the nature-inspired meta-heuristic algorithms (MHAs). The Whale Optimisation Algorithm (WOA) solves complex technical issues. The Lévy flight and distribution (LFWOA) was incorporated to increase productivity at the KGD. The aim of this study to minimise KGD's water deficit with WOA and LFWOA. The study comprises of two sections. The first section examined observed monthly inflow, demand, and storage data from 2001 to 2019, whilst the second compares performances to established MHAs, from 1097 to 2008. In the first section, LFWOA and WOA reliability were 60.53 and 58.33 %,respectively. For 2010, both methods gave similar vulnerability value. The LFWOA scored 1.04 while the WOA scored 1. In second section, the LFWOA satisfied 69.70% of exact demand, while the WOA met 56.06%. LFWOA had attained the least shortage. The LFWOA algorithm was the most robust among the MHAs (1.88). In short, the LFWOA is better on the count of reliability, resilience, and scarcity scores.