Hybrid machine learning approach integrating GMDH and SVR for heavy metal concentration prediction in dust samples
- 10 September 2024
- journal article
- advanced functional-materials-and-devices
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 32 (37) , 22082-22101
Abstract
In agricultural regions prone to dust storms, heavy metal contamination of soil and crops from airborne particulates poses significant risks to food safety and public health. This study has assessed the potential of machine learning models for predicting concentrations of toxic heavy metals like arsenic, chromium, and lead in dust from the agricultural Sistan region of southeastern Iran. This region experiences frequent dust storms mobilizing particulates from local dried lakes onto agricultural lands. The metals including nickel, copper, magnesium, cobalt, zinc, chromium, arsenic, and lead were measured in summer dust samples during 2012–2018 across 15 stations. Two hybrid models were developed combining group method of data handling (GMDH) and support vector regression (SVR) machine learning with harmony search optimization (H) so as to predict toxic metals arsenic, chromium, and lead using nickel, copper, magnesium, cobalt, and zinc inputs. Standard error maps were uncertainty higher in southern and western areas, and they are most impacted by dust storms. Results demonstrated that the hybrid GMDH + H and SVR + H models improved the accuracy of individual GMDH and SVR models in predicting heavy metals. The GMDH + H model performed the best for the lead with an agreement index (d-index) of 0.98, root mean square error (RMSE) of 2.87 ppm, normalized RMSE (NRMSE) of 0.12, and coefficient of determination (RR) of 0.96. The SVR + H model showed the highest accuracy for arsenic and chromium, obtaining d-index 0.96, RMSE 0.47 ppm, NRMSE 0.09, and RR 0.92 for arsenic, and d-index 0.96, RMSE 11.24 ppm, NRMSE 0.16, and RR 0.93 for chromium. Taylor’s diagram and heatmap analysis confirmed the superiority of the hybrid techniques. This work demonstrates the utility of state-of-the-art computing for addressing complex environmental health challenges.Keywords
This publication has 62 references indexed in Scilit:
- Assessment of response surface method and hybrid models to predict evaporation (case study: Chahnimeh and Pishein reservoirs in Sistan and Baluchestan Province of Iran)Arabian Journal of Geosciences, 2023
- Advanced Machine Learning Model for Prediction of Drought Indices using Hybrid SVR-RSMWater Resources Management, 2022
- Metal accumulation in relation to size and body condition in an all-alien species communityEnvironmental Science and Pollution Research, 2021
- A support vector regression (SVR)-based method for dynamic load identification using heterogeneous responses under interval uncertaintiesApplied Soft Computing, 2021
- ML-based group method of data handling: an improvement on the conventional GMDHComplex & Intelligent Systems, 2021
- Heavy Metals and Neurological Disorders: From Exposure to Preventive Interventions2021
- Dust storms in Iran – Distribution, causes, frequencies and impactsAeolian Research, 2021
- Extreme learning machines: a new approach for modeling dissolved oxygen (DO) concentration with and without water quality variables as predictorsEnvironmental Science and Pollution Research, 2017
- Heavy metal monitoring, analysis and prediction in lakes and rivers: state of the artEnvironmental Science and Pollution Research, 2017
- Adaptive neuro-fuzzy inference system for prediction of water level in reservoirAdvances in Water Resources, 2006