Agricultural industry is crucial for the economy; agricultural transportation is an integrated part of that industry. Optimization of the transportation and logistics costs is an important part of the transportation economics. This study focuses on the minimization of the total cost of transportation logistics. Sugar-beet is one of the important crops in the state of North Dakota and there has been sporadic research in the sugar-beet transportation economic modeling. Therefore, this research focuses on the transportation economic modeling of the sugar-beet including yield forecasting to reduce the uncertainty in this process. This study begins with developing a yield forecasting model which is presented as a way to sustain the agricultural transportation under stochastic environments. The stochastic environment includes variation in weather conditions, precipitation, soil type, and randomness of natural disasters. The yield forecasting model developed uses Normalized Difference Vegetation Index (NDVI), Geographical Information System (GIS), and statistical analysis. The second part of this study focuses on economic model to calculate the total cost associated with the sugar-beet transportation. This model utilizes the GIS analysis to calculate the distances travelled from member coop farms during harvest and transport to processing facilities in various locations. This model sheds light on the critical cost factors associated with the total economic analysis of sugar-beet harvest, transportation, and production. Since the sugar-beet yield varies significantly based on different factors, it provides for a variable optimal harvesting time based on the plant maturity and sugar content. Sub-optimized pilers location result in the high transportation and utilization costs. The third part of this research focuses on minimizing the sum of transportation costs to and from pilers and the piler utilization cost. A two-step algorithm, based on the GIS with global optimization method, is used to solve this problem. In conclusion, this research will provide a primary stepping stone for farmers, planners, and engineers to develop a data driven analytical tool which will help to minimize the total logistics cost of the sugar-beet crop while at the same time keeping the sugar content intact and predict the sugar yield and truck volume.