Search

A genetic-based neural network ensemble (GNNE) is applied for estimation of daily soil temperatures (DST) at distinct depths. A sequential genetic-based negative correlation learning algorithm (SGNCL) is adopted to train the GNNE parameters. CLMS algorithm is used to achieve the optimum weights of components. Recorded data for two different stations located in Iran are used for the development of the GNNE models. Furthermore, the GNNE predictions are compared with the existing machine-learning models. The results demonstrate that GNNE outperforms other methods for the prediction of DSTs. [ABSTRACT FROM AUTHOR]

Hydrogen is a clean energy source with a relatively low pollution footprint. However, hydrogen does not exist in nature as a separate element but only in compound forms. Hydrogen is produced through a process that dissociates it from its compounds. Several methods are used for hydrogen production, which first of all differ in the energy used in this process. Investigating the viability and exact applicability of a method in a specific context requires accurate knowledge of the parameters involved in the method and the interaction between these parameters. This can be done using top-down models relying on complex mathematically driven equations. However, with the raise of computational intelligence (CI) and machine learning techniques, researchers in hydrology have increasingly been using these methods for this complex task and report promising results. The contribution of this study is to investigate the state of the art CI methods employed in hydrogen production, and to identify the CI method(s) that perform better in the prediction, assessment and optimization tasks related to different types of Hydrogen production methods. The resulting analysis provides in-depth insight into the different hydrogen production methods, modeling technique and the obtained results from various scenarios, integrating them within the framework of a common discussion and evaluation paper. The identified methods were benchmarked by a qualitative analysis of the accuracy of CI in modeling hydrogen production, providing extensive overview of its usage to empower renewable energy utilization. [ABSTRACT FROM AUTHOR]