Methods of training a gamma mixture hurdle model for estimating corresponding food flows between regions

Embodiments described herein relate to training, by a computing system, a gamma mixture hurdle model. The model may characterize a functional relationship between: output data specifying food flows between zones, and input variables representing food production and food consumption in the zones. The training involves: (i) using binary logistic regression to estimate whether corresponding food flows exist between zone pairs, and (ii) for pairs in which corresponding food flows exist, using a gamma mixture model to estimate amounts of the corresponding food flows. Based on the gamma mixture hurdle model, the computing system can estimate, where each zone includes a respective set of regions: (i) whether corresponding food sub-flows exist between region pairs, and (ii) for pairs in which the corresponding food sub-flows are estimated to exist, potentials of the corresponding food sub-flows. The computing system can also determine, using a linear programming framework, values for the corresponding food sub-flows.