A Methodological Approach to Environmental Modelling in Coastal Wetlands of Cameroon Using Geographically Weighted Regression and MaxEnt

This study presents a novel methodological approach to analyzing aggregated count data, specifically in the context of Acute Gastroenteritis (AGE) mapping and spatial regression. The research introduces new enhancements for selecting prior spatializations and addressing ecological bias. Our improvements include mutual standardization techniques, more refined selection processes for spatial models, and more robust specifications of prior distributions. By focusing on the application of Maximum Entropy (MaxEnt) modeling to AGE data in the coastal lowlands of Douala, Cameroon, we offer a fresh perspective on spatial modeling in the context of environmental health. The research draws on data collected from six health areas in the coastal lowlands of Douala, Cameroon, covering the period from 2010 to 2013. These data encompass both the chemical characteristics of well water and the prevalence of AGE, specifically focusing on AGE consultations and diagnostic characteristics. We performed comprehensive physico-chemical and bacteriological analyses of water samples from 40 wells distributed across the study area during both dry and rainy seasons. The collected data was analyzed using Geographically Weighted Regression (GWR) and Maximum Entropy (MaxEnt) modeling techniques. The hierarchical MaxEnt model provided robust estimates of area-level risk parameters and facilitated the assessment of sensitivity to different spatial models. Our findings indicate that while GWR is more susceptible to ecological bias, this limitation was effectively addressed using MaxEnt. Seven distinct MaxEnt models were generated, each illustrating the spatio-temporal dynamics of AGE about environmental variables. These models revealed variability in high AGE concentration areas across different years and seasons, with AGE rates in affected areas ranging from 0.50% to 0.76%. The relatively stable average AUC values (0.7) underscore the varied nature of AGE in the study area and its endemic characteristics, highlighting the effectiveness of MaxEnt in capturing the complex dynamics of AGE, and offering valuable insights into its spatial and temporal patterns.