Fluoride contamination in African groundwater: Predictive modeling using stacking ensemble techniques

Usman Sunusi Usman; Yousif Hassan Mohamed Salh; Bing Yan; Jean Pierre Namahoro; Qian Zeng; Ismaila Sallah

doi:10.1016/j.scitotenv.2024.177693

Fluoride contamination in African groundwater: Predictive modeling using stacking ensemble techniques

Sci Total Environ. 2024 Nov 20:177693. doi: 10.1016/j.scitotenv.2024.177693. Online ahead of print.

Authors

Usman Sunusi Usman¹, Yousif Hassan Mohamed Salh¹, Bing Yan², Jean Pierre Namahoro³, Qian Zeng¹, Ismaila Sallah¹

Affiliations

¹ School of Environmental Studies, China University of Geosciences Wuhan, 388 Lumo Road, Wuhan 430074, China.
² School of Environmental Studies, China University of Geosciences Wuhan, 388 Lumo Road, Wuhan 430074, China. Electronic address: yanbing@cug.edu.cn.
³ School of Economic and Management, China University of Geosciences Wuhan, China.

PMID: 39577590
DOI: 10.1016/j.scitotenv.2024.177693

Abstract

Fluoride contamination of groundwater is a severe public health problem in Africa due to natural factors that include geological weathering of fluoride-bearing minerals and climatic conditions characterized by high evaporation rates that highly elevate fluoride levels. Anthropogenic activities further aggravate the problem and have affected millions of people in countries such as; South Africa, Tanzania, Nigeria, Ethiopia, Ghana, Kenya, Mauritania, Botswana, and Egypt. High fluoride levels of up to 10 mg/L have been encountered in parts of the East African Rift Valley, above the WHO's recommended limit of 1.5 mg/L, causing serious dental and skeletal fluorosis among the affected people. In this study, the distributions of F^- in groundwater of Africa were forecast using an advanced stacking ensemble learning model based on 11 crucial groundwater physiochemical variables and 6270 accessible statistics of observed concentrations. The enhanced algorithm incorporates randomized trees, Tree-Bag, RF, DT, XGB, and ET Machine as base trainees, with a simple Naïve Bayes as the meta-analyzer. The model's AUC score of 0.86 accurately represented the uneven distributions of groundwater fluoride. The results showed that 20-35 % of the continent's eastern part and 10 % of its western region are at risk of having fluoride levels exceeding WHO limits, with an expected population of around 80 million. Regionally, fluoride contamination ranges from 0.1 to 3 mg/L in West Africa was range from 0.0 to 13.29 mg/L, 0.01-588 mg/L in East Africa, 0.04-65.9 mg/L in South Africa, and 0.1-10.5 mg/L in North and 0.01-1.9 mg/L in Central Africa. Na⁺ and HCO₃^- are Africa's leading primary causes of fluoride contamination, with Ca²⁺ and Cl^- contributing to fluoride influence in some parts of the continent. This study helped identify health concerns linked to groundwater fluoride and offered guidance on assessing health risks in areas with sparse sample sizes.

Keywords: Africa; Fluoride; Groundwater; Physiochemical parameters; Stacking ensemble learning.