Scholarlink

<p>Water informatics, a field of interest in the global warming context, integrates data from different sensors and technologies for efficient water resource management. Technologies like the Internet of Things (IoT), machine to machine (M2M) communications, and FoG networks have significantly enhanced this domain. The paper explores some important aspects of water informatics, specifically focusing on water level prediction, and water leakage monitoring. It highlights the importance of water level prediction for flood monitoring. The authors have used water level time series data from Venice Lagoon Telemareographic Network for the period 1983–2015 to analyze water level statistics, and have applied long short-term memory (LSTM) and random forest (RF) methods to create a predictive data model. The LSTM and RF model achieved an RMSE of 0.012 and 0.086 respectively, indicating superior performance of LSTM in computing both short-term fluctuations and long-term anomalies. In addition to this, the authors have also developed an IoT system for real-time water leakage monitoring, which is crucial for dynamic water level prediction and monitoring. A complementary IoT framework for water quality monitoring system that includes temperature, PH, turbidity, and other factors has also been proposed by the authors. This interdisciplinary study integrates machine learning prediction algorithms, and IoT-based monitoring systems, making it highly relevant for future water resources management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning Based In-Silico Water Level Prediction and IoT Based Monitoring System

  • 期刊论文

  • 发表日期：

    2026年1月10日

查看全文
  • Faruque Aziz,
  • Rudraneel Bhattacharya,
  • Arijit De,
  • Sukanta Ghosh,
  • Debashish Pal,
  • Subhajit Das

摘要

Water informatics, a field of interest in the global warming context, integrates data from different sensors and technologies for efficient water resource management. Technologies like the Internet of Things (IoT), machine to machine (M2M) communications, and FoG networks have significantly enhanced this domain. The paper explores some important aspects of water informatics, specifically focusing on water level prediction, and water leakage monitoring. It highlights the importance of water level prediction for flood monitoring. The authors have used water level time series data from Venice Lagoon Telemareographic Network for the period 1983–2015 to analyze water level statistics, and have applied long short-term memory (LSTM) and random forest (RF) methods to create a predictive data model. The LSTM and RF model achieved an RMSE of 0.012 and 0.086 respectively, indicating superior performance of LSTM in computing both short-term fluctuations and long-term anomalies. In addition to this, the authors have also developed an IoT system for real-time water leakage monitoring, which is crucial for dynamic water level prediction and monitoring. A complementary IoT framework for water quality monitoring system that includes temperature, PH, turbidity, and other factors has also been proposed by the authors. This interdisciplinary study integrates machine learning prediction algorithms, and IoT-based monitoring systems, making it highly relevant for future water resources management.