Improving Crop Yields Through Optimized Planting Schedules

Systems Conversation with Jay Swaminathan, University of North Carolina at Chapel Hill

Agricultural yields tend to be low in developing countries. In this research they study how crop yields could be improved through optimized seed planting schedules. They utilize a seed growth model based on phytology literature and embed that in an optimal seed planting problem while considering seasonal rainfall uncertainty. They show that the optimal planting policy is a time dependent threshold-type policy and the optimal threshold is dependent on the soil water content and seeding capacity. This policy can be easily implemented by small scale farmers. For real large-scale problems, in their computational study, they demonstrate significant relative yield advantage of the optimal planting schedule over commonly used heuristics in practice in Africa. They show that the relative yield advantage of the optimal policy over commonly used heuristics increases as the climate condition becomes more severe for planting.