AI based prediction of heavy metals in agricultural waste ashes using characterization for sustainable construction material
Year: 2026
Type: article
Abstract: In this study, an AI model for predicting the concentration of heavy metal (HM) present in the agricultural waste ashes (AWAs) such as sugarcane bagasse ash (SCBA) and rice husk ash (RHA) is developed from the physio-chemical properties of the ashes. Thirty-two (32) samples of SCBA and RHA were collected and characterized through detailed analysis by Fourier transform infrared spectroscopy (FTIR), X-ray fluorescence (XRF), scanning electron microscope (SEM), X-ray diffraction analysis (XRD), thermogravimetric analysis/differential scanning calorimetry (TGA/DSC), Energy dispersive X-ray (EDX) and atomic absorption spectroscopy (AAS). The study results indicate that AWAs are rich in HMs that can be categorized by loss on ignition, and have great potential as sustainable construction materials. The machine learning model built with deep neural networks has high prediction accuracy ( R 2 = 0.99) for HMs concentrations, which proves the model’ effectiveness. This research can be used to encourage the introduction of AWAs in the construction industry, which would result in a reduction of environmental hazards. Hence, current work aims to open new horizon for researchers to use chemical characterization for utilization of waste ashes for manufacturing of construction materials.
Authors: Wasim Abbass, Muneeb Ahmed, Ali Ahmed, Fahid Aslam, Abdulmoez Al Ismaeel, Hisham Jahangir Qureshi, Iram Aziz
Language: English
Subfield: Building and Construction
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,469
Funder: King Faisal University
OpenAlex ID: W7203974947