Sustainable decision-making for contaminated site risk management: A decision tree model using machine learning algorithms
Sustainable decision-making for contaminated site risk management: A decision tree model using machine learning algorithms
The presence of contaminated land is an inevitable legacy of industrial activity, and the management decisions governing reclamation of this land are key in minimizing environmental risk and allowing safe and effective land reuse. In this context, to predict the optimal remediation options for future decision-making processes in sustainable site management, thus enhancing information communication between stakeholders, 17 decision sensitivity parameters are analyzed in this study and their influence on the management patterns of contaminated sites identified with three decision tree (DT) algorithms including C4.5 (successor of Iterative Dichotomiser 3/ID 3), CHAID (Chi-squared Automatic Interaction Detection), and CART (Classification and Regression Trees), which is the first attempt to use artificial intelligence technology to predict strategy-based decision-making for contaminated site management. Based on four performance metrics (accuracy, precision, recall ratio and F1 score), CART-based DT model shows the highest prediction accuracy at an average value of 78.57%, which indicates a relatively credible decision simulation to assist in more efficient contaminated site management. With regard to specific factors and influence mechanisms on contaminated site management, the results demonstrate 7 recognition rules corresponding to 6 driving factors which have the greatest influence on the decision-making process. Long-term monitoring time, the type of land reuse and ex-situ performance are the most important factors in determining field implementation of cleanup activities. The built decision tree model and induced decision rules, once well-trained, can be relied on for a sustainable site management strategy as data become available at a new site.
Contaminated site, Decision tree, Decision-making mode, Machine leaning, Risk-based sustainable management
Li, Xiaonuo
05e8eb6d-45b7-49bd-8eae-2e1d5d1b4800
Yi, Shiyi
30938b88-6ef5-456e-bd21-8135a1e331a8
Cundy, Andrew B.
994fdc96-2dce-40f4-b74b-dc638286eb08
Chen, Weiping
932395b9-a198-453f-af8a-4e63f8505f8b
15 October 2022
Li, Xiaonuo
05e8eb6d-45b7-49bd-8eae-2e1d5d1b4800
Yi, Shiyi
30938b88-6ef5-456e-bd21-8135a1e331a8
Cundy, Andrew B.
994fdc96-2dce-40f4-b74b-dc638286eb08
Chen, Weiping
932395b9-a198-453f-af8a-4e63f8505f8b
Li, Xiaonuo, Yi, Shiyi, Cundy, Andrew B. and Chen, Weiping
(2022)
Sustainable decision-making for contaminated site risk management: A decision tree model using machine learning algorithms.
Journal of Cleaner Production, 371, [133612].
(doi:10.1016/j.jclepro.2022.133612).
Abstract
The presence of contaminated land is an inevitable legacy of industrial activity, and the management decisions governing reclamation of this land are key in minimizing environmental risk and allowing safe and effective land reuse. In this context, to predict the optimal remediation options for future decision-making processes in sustainable site management, thus enhancing information communication between stakeholders, 17 decision sensitivity parameters are analyzed in this study and their influence on the management patterns of contaminated sites identified with three decision tree (DT) algorithms including C4.5 (successor of Iterative Dichotomiser 3/ID 3), CHAID (Chi-squared Automatic Interaction Detection), and CART (Classification and Regression Trees), which is the first attempt to use artificial intelligence technology to predict strategy-based decision-making for contaminated site management. Based on four performance metrics (accuracy, precision, recall ratio and F1 score), CART-based DT model shows the highest prediction accuracy at an average value of 78.57%, which indicates a relatively credible decision simulation to assist in more efficient contaminated site management. With regard to specific factors and influence mechanisms on contaminated site management, the results demonstrate 7 recognition rules corresponding to 6 driving factors which have the greatest influence on the decision-making process. Long-term monitoring time, the type of land reuse and ex-situ performance are the most important factors in determining field implementation of cleanup activities. The built decision tree model and induced decision rules, once well-trained, can be relied on for a sustainable site management strategy as data become available at a new site.
Text
Sustainable decision-making for contaminated site risk management
Restricted to Repository staff only until 14 August 2024.
Request a copy
More information
Accepted/In Press date: 9 August 2022
e-pub ahead of print date: 14 August 2022
Published date: 15 October 2022
Additional Information:
Funding Information:
This work was supported by the National Key R&D Program of China [grant number 2020YFC1807500 ]; and the National Natural Science Foundation of China [grant number 72104231 ]. We are grateful to Junjing Jie for his considerable contribution to the coding work and valuable feedback on the model building.
Publisher Copyright:
© 2022
Keywords:
Contaminated site, Decision tree, Decision-making mode, Machine leaning, Risk-based sustainable management
Identifiers
Local EPrints ID: 470333
URI: http://eprints.soton.ac.uk/id/eprint/470333
ISSN: 0959-6526
PURE UUID: ab9fc5a0-2cfa-4d0d-ac0c-fb74ca8d8410
Catalogue record
Date deposited: 06 Oct 2022 16:54
Last modified: 17 Mar 2024 03:38
Export record
Altmetrics
Contributors
Author:
Xiaonuo Li
Author:
Shiyi Yi
Author:
Weiping Chen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
