Dynamics of evaporation from open water bodies can affect land–atmosphere exchanges. Prior studies mainly concentrated on estimating evaporation while accuracy in its details and dynamics posed a challenge. Knowing that changes in climatic drivers strongly influence the dynamics of evaporation, this study sought to reveal such profiles exposed to paired climate drivers in the presence of evaporation memory. The extraction of gradient patterns (dynamic) of evaporation was conducted at Ahvaz station in Iran. In addition to having a warm climate, as indicated by previous studies, Ahvaz city includes an intricate evaporation pattern. The combination of second-order partial derivations (PaD2) and artificial neural networks (ANN) was utilized to achieve evaporation dynamic patterns. Primarily, our findings indicate that the predominant factor influencing the rate of evaporation is ambient humidity, which can be sourced through various ways, with evaporation memory being the most crucial. Furthermore, the station exhibited a reversal in the rate of evaporation due to climate agent interactions.