 We developed a data-driven multi-layer perceptron, MLP, model that simultaneously predicted the land suitability of multiple crops in Canada. The MLP model was trained using available crop yields from 2013 to 2020, downscaled to the farm level, and incorporating soil climate landscape variables obtained from Google Earth Engine. The incorporation of a crop indicator function allowed us to train a multi-crop model that captured the interdependences and correlations between various crops, resulting in more accurate predictions. Compared to single-crop models, our multi-crop model produced up to a 2.82-fold reduction in mean absolute error for any particular crop. Our results suggest that barley, oats, and mixed grains are more tolerant to soil climate landscape variations and could be grown in many regions of Canada, while non-grain crops are more sensitive to environmental factors. Furthermore, predicted crop suitability was associated with a region's growing season length, supporting climate change projections that regions of northern Canada will become more suitable for agricultural use. This article was authored by Amandjot Bullock, Karam Nadine, and our Ayesha Ali. We are article.tv, links in the description below.