Assessing below-ground carbon and nitrogen accumulation of green infrastructure using machine learning methods, targeting sub-tropical bioretention basins. Issue 1 (June 2020)

• Record Type: Journal Article
• Authors: Kavehei, Emad; Karim, Abdul; Jenkins, Graham; Adame, Fernanda; Sattar, Abdul; Desha, Cheryl
• Is Part Of: IOP conference series. Volume 509:Issue 1(2020)
• Publication Date: 2020-06
• Subjects: Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/509/1/012029
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: This study presents an assessment of below-ground carbon dynamics of green infrastructure using artificial intelligence, targeting sub-tropical bioretention basins in South East Queensland, Australia. This extended abstract describes the context for the study and the significance of the work, which was recognised and enabled through the international Microsoft Artificial Intelligence (AI) for Earth Grants (2018 Grant winner). Four different scenarios were tested with three different approaches for modelling of the regression values. The three different machine learning methods were applied to predict belowground carbon and nitrogen, based on soil physical characteristics data entry. The neural network model performed better in predicting both the carbon and nitrogen concentration in all the scenarios. The implication of this study provides a profound shift in the type of platform that can be used, wherein machine learning methods can assist decision-makers in finding low-cost proxies for measuring carbon and nitrogen capture in bioretention basins.