Scholarlink

<p>The given paper introduces a multi-layer perceptron artificial neural network (MLP-ANN) framework to forecast river’s water quality and determine if it is acceptable for irrigation. The study concentrated on forecasting four important water quality parameters namely Total Dissolved Solids (TDS), pH, Sodium (Na), and Electrical Conductivity (EC), and the samples are taken at specific intervals from Kurnool district located in Andhra Pradesh region. Irrigation samples are analyzed for physio-chemical properties along with ionic constituents. The data obtained is used in MLP-ANN model to forecast characteristic values such as mean, median, standard deviation and many more. The proposed framework achieves the lowest root mean square error (RMSE) and is able to forecast water quality with highest accuracy (%). Thus, the framework acts as an important tool for researchers and policymakers in implementing best sustainable practices for water bodies.</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

Utilization and assessment of MLP-ANN framework to forecast quality of water for irrigation purposes

  • 期刊论文

  • 发表日期：

    2025年8月9日

查看全文
  • Deekshant Varshney,
  • Subhav Singh,
  • Ramandeep Singh,
  • Amit Kumar,
  • Phaneendra Babu Bobba,
  • K. V. Epifantsev,
  • Roopsi Rathee,
  • Muntadar Muhsen

摘要

The given paper introduces a multi-layer perceptron artificial neural network (MLP-ANN) framework to forecast river’s water quality and determine if it is acceptable for irrigation. The study concentrated on forecasting four important water quality parameters namely Total Dissolved Solids (TDS), pH, Sodium (Na), and Electrical Conductivity (EC), and the samples are taken at specific intervals from Kurnool district located in Andhra Pradesh region. Irrigation samples are analyzed for physio-chemical properties along with ionic constituents. The data obtained is used in MLP-ANN model to forecast characteristic values such as mean, median, standard deviation and many more. The proposed framework achieves the lowest root mean square error (RMSE) and is able to forecast water quality with highest accuracy (%). Thus, the framework acts as an important tool for researchers and policymakers in implementing best sustainable practices for water bodies.