Author(s): Manatsawee Nawik; Suwatthana Chitthaladakorn; Sitang Pilailar

Linked Author(s):

Keywords: Area characteristic index; Infrastructure value index; Machine learning; Pipe replacement; Risk index; Systemic decision process

Abstract: This study aims to identify the optimal algorithm for enhancing the systematic decision-making process in pipe management within specified investment constraints, utilizing risk assessment and asset valuation. The objective is to implement this refined approach by applying it to the field datasets of MWA, thereby examining the correlation between prediction results and the corresponding action plan. The findings highlight the Random Forest regression model and the Random Forest classification model as the most effective algorithms for predicting RI and allocating measures to specific areas. The comparison reveals that MWA's action plan surpasses the necessary in terms of pipe management within the defined budget constraints.

DOI: https://doi.org/10.64697/HIC2024_P290

Year: 2024