Application of Neural Network Swarm Optimization for Paddy Field Classification from Remote Sensing Data

Monitoring changes in paddy area is important for economic and environment research since rice is staple food in Asia, and paddy agriculture is a major cropping system in Asia. Recently, remote sensing is used actively to observe the change of paddy area. However, monitoring paddy area by remote sensing is difficult due to the temporal changes of paddy and difference of spatiotemporal characteristics of paddy agriculture between countries or regions. In our previous research using MLP and spatiotemporal satellite sensor data, the proposed classifier yielded 90.8% correct classification rate. In this paper, we proposed a cooperative learning method using PSO as the global search method and MLP as the local search method in order to improve the classification accuracy for practical use.