This study compared the established MaxEnt and a more novel deep learning approach for modelling the distribution of humpback whales (Megaptera novaeangliae) in north Iceland. It examined the mechanisms, structures, and optimisation techniques of both approaches, highlighting their differences and similarities. For this, monthly distribution models for Skjálfandi Bay were created, spanning from 2018 until 2021, using presence-only sighting data and satellite remote sensing data. Additionally, the trained models were used to create distribution projections for the year 2022, solely based on the available environmental data. The results were compared by using the established Area Under the Curve value. The findings indicate that both approaches have their limitations and advantages. MaxEnt does not allow continuous updating within a time series, yet it mitigates the risk of overfitting by employing the maximum entropy principle. The deep learning model is more likely to overfit, but the larger weight network increased the model’s capability to capture complex relationships and patterns. Ultimately, the results indicate that the deep learning model had a higher predictive performance in modelling both current and future humpback whale distributions. Both modelling approaches have inherent limitations, such as the low resolution of the input data, spatial biases, and the inability to fully capture the complexity of all natural processes. Despite this, deep learning in particular showed promising results in modelling the distribution of humpback whales and prompts further research in different study areas and applications for other mobile animal species.