Multiobjective fireworks optimization for variable-rate fertilization in oil crop production

• An evolutionary algorithm named MOFOA is proposed, which is the first study that extends the relatively new fireworks optimization heuristic for multiobjective optimization.
• Differential evolution operators are integrated into the algorithm to diversify the search.
• The algorithm is successfully applied to a number of oil crop variable-rate fertilization (VFR) problems, including a real-world application in east China.

Variable-rate fertilization (VRF) decision is a key aspect of prescription generation in precision agriculture, which typically involves multiple criteria and objectives. This paper presents a multiobjective optimization problem model for oil crop fertilization, which takes into consideration not only crop yield and quality but also energy consumption and environmental effects. For efficiently solving the problem, we propose a hybrid multiobjective fireworks optimization algorithm (MOFOA) that evolves a set of solutions to the Pareto optimal front by mimicking the explosion of fireworks. In particular, it uses the concept of Pareto dominance for individual evaluation and selection, and combines differential evolution (DE) operators to increase information sharing among the individuals. The experimental tests and real-world applications in oil crop production in east China demonstrate the effectiveness and practicality of the algorithm.

Figure optionsDownload as PowerPoint slide