Speaker: Anupam Bhar, ECpE Graduate Student
Advisor: Ratnesh Kumar
Title: Sensor Data-Driven Agricultural Modeling and Decision Making for Optimum Fertigation
Abstract: To feed the increasing population, fields are now more intensively cultivated. Yield from field has increased by developing and breeding high yielding variety of crops, applying more fertilizer, pesticide, and water. These increased inputs, apart from their input costs, are the cause of environmental pollution. The current trend in farm is to apply fertilizer and water as recommended by general guidelines, e.g apply 150kg N per Hectare of maize field, with most of the fertilizer application occurring during middle and start of the growing season. These recommendations are for large geographic area and not localized to specific field conditions. Our goal of this study is to come up with a decision making strategy that would prescribe when and how much fertilizer and irrigation needs to be applied so that yield and profit to farmer is maximized as well as environmental pollution caused by agriculture activities is minimized. The temporal dynamics of the agriculture ecosystem is captured through agriculture model and sensor data. We begin our study by understanding and calibrating an integrated agroecosystem model named RZWQM (Root Zone Water Quality Model) to a field in Greeley, Colorado. We then use the calibrated model to come up with Fertilizer and Irrigation recommendation that would maximize farm profit. We then compare the Carbon-Nitrogen sub-model of RZWQM with a simpler model. We observe that the simpler model improves on execution time by sacrificing accuracy negligibly. Finally, a model-predictive real-time fertilization and irrigation decision-making is being proposed and formulated using the model, where the optimization steps are repeated each day, and the recommendations for only the current application period are actually applied.