Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Alexandria Engineeri...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Alexandria Engineering Journal
Article . 2022 . Peer-reviewed
License: CC BY NC ND
Data sources: Crossref
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Alexandria Engineering Journal
Article . 2022
Data sources: DOAJ
versions View all 2 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Deep Learning model and Classification Explainability of Renewable energy-driven Membrane Desalination System using Evaporative Cooler

Authors: Hanaa Salem; Ibrahim M. El-Hasnony; A.E. Kabeel; Emad M.S. El-Said; Omar M. Elzeki;

Deep Learning model and Classification Explainability of Renewable energy-driven Membrane Desalination System using Evaporative Cooler

Abstract

Recently, the scientific community has become more interested in solar-driven steam materials and systems for desalination and disinfection. Solar thermal energy for membrane distillation desalination provides a green and sustainable option for building settings where there is a strong connection between water constraint and high solar irradiation. Artificial intelligence (AI) is rapidly being used to optimize water treatments and saltwater desalination because of its high precision and accuracy. Explainable AI (XAI) enables people to better understand and trust a model's predictions and to detect and rectify inaccurate AI predictions. This study analyses recent advances in solar-driven steam materials engineering and the significant technological constraints that impede its wide-scale deployment. Using local interpretable model-agnostic explanations (LIME), our study provides an interpretable solution (in addition to the binary classification result of the developed black-box deep learning (DL) model) so that experts can understand why the machine thinks this way, providing critical insights for the decision-making process. The proposed XAI-DL model is based on a DL network consisting of three cascaded convolutional blocks for processing tabular data. Therefore, the XAI-DL classification model achieves a cooling quality accuracy of 82.64% during the validation stage, supporting the explaining capability. During the testing, the [inlet-cooling-water-temperature] pushes the model lower, whereas the [ambient-temperature], [feed-water-flow-rate], and the [inlet-feed-water-temperature] pushes the model higher. The LIME explanation result is consistent with the statistical analysis of the data. Consequently, the proposed explainer assists non-experts in comparing and improving the untrustworthy model through and clarifies the importance of each feature and its relationship to other features and its relationship to the class. Finally, the XAI-DL fits and supports the different manufacturers of membrane desalination system(s) to inspect cooling quality in their designed system and consistency of interpretability and trust.

Keywords

Water management, Artificial intelligence, Renewable energy, Deep Learning, Desalination, Water treatment, TA1-2040, Engineering (General). Civil engineering (General)

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    30
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Top 10%
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 10%
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
30
Top 10%
Top 10%
Top 10%
gold