Spatial Modeling of COVID-19 Prevalence Using Adaptive Neuro-Fuzzy Inference System

This study is dedicated to modeling the spatial variation in COVID-19 prevalence using adaptive neuro-fuzzy inference system (ANFIS) when dealing with nonlinear relationships, especially useful for small areas or sample size problems. We compiled a broad range of socio-demographic, environmental, and climatic factors along potentially related urban land uses predict rural districts Golestan province northeast Iran very high-case fatality ratio (9.06%) during first year pandemic (2020–2021). also compared ANFIS principal component analysis (PCA)-ANFIS methods geographical information framework. Our results showed that combined PCA, accuracy significantly increased. The PCA-ANFIS model superior performance (R2 (determination coefficient) = 0.615, MAE (mean absolute error) 0.104, MSE square 0.020, RMSE (root mean 0.139) than 0.543, 0.137, 0.034, 0.185). sensitivity indicated migration rate, employment number days rainfall, residential apartment units were most contributing predicting province. findings ability parameters, particularly sizes. Identifying main spread may provide insights health policymakers effectively mitigate high disease.