Species distribution models (SDMs) are widely used to gain ecological understanding and guide conservation decisions. These models are developed with a wide variety of algorithms - from statistic-based approaches to more recent machine learning algorithms - but one property they all have in common is the use of predictors that strongly simplify the temporal variability of driving factors. On the other hand, recent architectures of deep learning neural networks allow dealing with fully explicit spatiotemporal dynamics and thus fitting SDMs without the need to simplify the temporal and spatial dimension of predictor data. We present a deep learning-based SDM approach that uses time series of spatial data as predictors, and compare it with conventional modelling approaches, using five well known invasive species. Deep learning approaches provided consistently high performing models while also avoiding the use of pre-processed predictor sets, that can obscure relevant aspects of environmental variation.