A Simulation and Genetic Optimization Framework for Optimizing Nitrogen Fertilization for Rice Crop


Precision agriculture is a technique that can enhance the current agricultural production system dramatically. Optimizing Nitrogen fertilization for rice crop is one of important research issues in Precision agriculture because it can decrease the cost of rice farming, reduce environmental pollution and increase grain yield. The optimal amount of N and schedules depend on several factors such as soil conditions, cultural practices, varieties of rice, and etc. For traditional approaches of fertilizer optimization, may costly and take a long time.Therefore, a new simulation and Genetic optimization framework for searching for the optimal fertilizer schedules and the optimal amount of N for rice crop is proposed. The proposed framework is based on genetic algorithm and Oryza 2000 Model. Firstly, the Oryza 2000 Model is calibrated and validated using field experimental data. Secondly, the calibrated Oryza 2000 model is utilized as simulation model in searching for the optimal fertilizer allocations during the crop growing period and the optimal amount of N. To validate the proposed framework, field experiments are conducted in Chachoengsao Province of Thailand. From the experiments, the total yield of rice crop significantly increases after applying the optimal fertilizer schedules and the optimal amount of N provided from the proposed simulation-optimization framework. The results of the study suggest that by employing a calibrated crop growth model combined with genetic algorithm can lead to achieve maximum yield.

Author Information
Pannavich Ariyatanakatawong, King Mongkut’s Institute of Technology Ladkrabang, Thailand

Paper Information
Conference: ACSS2013
Stream: Social Sciences

This paper is part of the ACSS2013 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

Comments & Feedback

Place a comment using your LinkedIn profile


Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by amp21