應用輻狀基底類神經網路推估颱風期間水稻損失

Abstract

台灣位於颱風行進路線上，經常受到颱風的侵襲，每年造成的農業損失巨大，即使農業生產管理技術進步或是品種改良仍無法完全避免每次颱風帶來的傷害，因此本論文欲研究颱風因子如何影響農業損失。台灣從日治時期就開始發展稻米產業，為台灣主要農作物之一，且台灣稻米一年兩穫，資料最多也最齊全，因此以稻米作為研究目標。本篇研究應用輻狀基底類神經網路建立模型，結合三種不同決定隱藏層神經元的方法，分別為K-means、自組特徵映射網路與垂直最小平方法，欲使模型估計值與真實值誤差達到最小，並比較三種不同中心點的模型效果。

Taiwan is located in the path of typhoon and there is huge agricultural losses caused by typhoons every year. Even though there are agricultural technological progress and variety improvement, we can’t completely avoid the damage. So, we want to discuss how typhoon factors affect agricultural loss. Taiwan has developed the rice industry since Japanese occupation period, and it becomes one of the most important crops in Taiwan. In this paper, we focus on the research of the losses of rice. We apply radial basis function neural network to build the model, combined with three different ways including K-means, self-organizing map network and orthogonal least squares to find the centers of neurons in the hidden layer. And then, we compare the effects of three different models.