eprintid: 10191466 rev_number: 10 eprint_status: archive userid: 699 dir: disk0/10/19/14/66 datestamp: 2024-04-30 09:27:03 lastmod: 2024-04-30 09:27:03 status_changed: 2024-04-30 09:27:03 type: article metadata_visibility: show sword_depositor: 699 creators_name: Ashraf, Waqar Muhammad creators_name: Dua, Vivek title: Data Information integrated Neural Network (DINN) algorithm for modelling and interpretation performance analysis for energy systems ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F43 keywords: Explainable AI; Model interpretation; Scientific machine learning; Artificial neural network; Loss function note: Copyright © 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/bync/4.0/). abstract: Developing a well-predictive machine learning model that also offers improved interpretability is a key challenge to widen the application of artificial intelligence in various application domains. In this work, we present a Data Information integrated Neural Network (DINN) algorithm that incorporates the correlation information present in the dataset for the model development. The predictive performance of DINN is also compared with a standard artificial neural network (ANN) model. The DINN algorithm is applied on two case studies of energy systems namely energy efficiency cooling (ENC) & energy efficiency heating (ENH) of the buildings, and power generation from a 365 MW capacity industrial gas turbine. For ENC, DINN presents lower mean RMSE for testing datasets (RMSE_test = 1.23 %) in comparison with the ANN model (RMSE_test = 1.41 %). Similarly, DINN models have presented better predictive performance to model the output variables of the two case studies. The input perturbation analysis following the Gaussian distribution for noise generation reveals the order of significance of the variables, as made by DINN, can be better explained by the domain knowledge of the power generation operation of the gas turbine. This research work demonstrates the potential advantage to integrate the information present in the data for the well-predictive model development complemented with improved interpretation performance thereby opening avenues for industry-wide inclusion and other potential applications of machine learning. date: 2024-05 date_type: published publisher: Elsevier BV official_url: http://dx.doi.org/10.1016/j.egyai.2024.100363 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2266048 doi: 10.1016/j.egyai.2024.100363 lyricists_name: Dua, Vivek lyricists_name: Ashraf, Waqar lyricists_id: VDUAX49 lyricists_id: WMAAS21 actors_name: Ashraf, Waqar actors_id: WMAAS21 actors_role: owner full_text_status: public publication: Energy and AI volume: 16 article_number: 100363 issn: 2666-5468 citation: Ashraf, Waqar Muhammad; Dua, Vivek; (2024) Data Information integrated Neural Network (DINN) algorithm for modelling and interpretation performance analysis for energy systems. Energy and AI , 16 , Article 100363. 10.1016/j.egyai.2024.100363 <https://doi.org/10.1016/j.egyai.2024.100363>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10191466/1/Ashraf_1-s2.0-S2666546824000296-main.pdf