Bonfring International Journal of Industrial Engineering and Management Science
Online ISSN: 2277-5056 | Print ISSN: 2250-1096 | Frequency: 4 Issues/Year
Impact Factor: 0.541 | International Scientific Indexing(ISI) calculate based on International Citation Report(ICR)
A Centralized Knowledge-Sharing Framework for Smart Water Scarcity Management Using GIS and Machine Learning
Abstract:
Rising water scarcity has become a major global issue confronting humanity due to various factors such as the rapid increase in the population, the alternating climate, the migration to cities, and the bad management of water resources which all have environmental and socio-economic impacts of different severity. Smart water monitoring systems are among the recent technologies that have made it possible to collect data in real-time, but the solutions that have been developed so far mostly concentrate on the detection and analysis aspect of the problem and provide very little to knowledge dissemination, community involvement, and informed decision-making. To overcome these shortcomings, this article proposes a central knowledge sharing platform for smart water scarcity management integrated with machine learning, GIS drought visualization, and community collaboration. The suggested system gives domain experts and users the chance to collaborate, get access to and retrieve the unified digital interface consisting of the quality of water conservation strategies, educational materials, and multimedia resources. K-Means clustering is used to analyze spatial and drought data to classify the areas according to their drought intensity, while GIS-based mapping offers easy-to-understand visualization to facilitate planning and intervention that are appropriate and specific. To achieve high analytical precision and system productivity, data preprocessing techniques are utilized including cleaning, normalization, and feature reduction. Also, a content-based recommendation mechanism facilitates the dissemination of water-saving techniques that are specific to the location and aware of the context thereby maximizing user engagement and practical adoption. The experimental evaluation shows that drought classification is accurate, system reliability is high, and responsiveness is enhanced. To sum up, the proposed framework not only leads to sustainable water use but also raises public consciousness, and supports through a data-driven approach decision-making which makes it appropriate.
Keywords: Water Scarcity Management, Centralized Knowledge-Sharing Platform, Smart Water Systems, Machine Learning, GIS-Based Drought Mapping, Water Conservation
Volume: 16 | Issue: 1
Pages: 13-20
Issue Date: April , 2026
DOI: 10.9756/BIJIEMS/V16I1/BIJ26003
 |
|