The textile industry is a significant sector in the global economy, generating 1000 billion dollars in revenue. However, it has also caused ecological issues, particularly regarding water usage. With approximately 93 billion m3 of water consumed per year, the industry contributes to the depletion and contamination of this natural resource due to a lack of proper reusing and quality control practices. This study focuses on examining data from 12 Portuguese textile companies to determine if it is possible to predict water quality for reuse. Two automated machine learning tools were used to evaluate over 650 data models, aiming to obtain the best results from the available data. The analysis revealed that focusing on individual companies yielded the best outcomes, with a maximum R2 Score of 0.67, a mean absolute error of 0.32, and a root mean squared error of 0.36. These findings could have implications for improving water management practices in the textile industry.

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

Preliminary Study About the Water Quality Prediction Models: A Textile Case Study

  • Ana Raquel Silva,
  • Rita Miranda,
  • Filipe Portela

摘要

The textile industry is a significant sector in the global economy, generating 1000 billion dollars in revenue. However, it has also caused ecological issues, particularly regarding water usage. With approximately 93 billion m3 of water consumed per year, the industry contributes to the depletion and contamination of this natural resource due to a lack of proper reusing and quality control practices. This study focuses on examining data from 12 Portuguese textile companies to determine if it is possible to predict water quality for reuse. Two automated machine learning tools were used to evaluate over 650 data models, aiming to obtain the best results from the available data. The analysis revealed that focusing on individual companies yielded the best outcomes, with a maximum R2 Score of 0.67, a mean absolute error of 0.32, and a root mean squared error of 0.36. These findings could have implications for improving water management practices in the textile industry.