基于GIS的神经网络法在宗地地价评估中的应用  

Application of GIS-based Artificial Neural Network Method in Land Price Evaluation

作　　者：吴明发[1] 陈美球[2] 赵小汎[3] 周丙娟[2] 

机构地区：[1]广东海洋大学农学院,广东湛江524088 [2]江西农业大学国土学院,南昌330045 [3]中国科学院沈阳应用生态研究所

出　　处：《华南热带农业大学学报》2007年第1期65-69,共5页Journal of South China University of Tropical Agriculture

基　　金："南昌城市规划区土地定级及基准地价更新"项目资助。

摘　　要：为了对城市宗地地价进行评估,采用RS和GIS技术对宗地估价底图图层等资料进行更新和管理,建立GIS宗地估价信息系统并从中提取相似交易宗地,提出利用人工神经网络、结合特尔菲法建立宗地地价评估指标体系,以宗地地价为评估目标的宗地评估方法。本文在模型建立过程中,以南昌市22个商业用地资料中的18个为学习样本,以5个评估指标为输入,以宗地地价为输出,建立了三层BP人工神经网络,并以其余4个商业用地资料作为验证,取得了较好的模拟效果。有效地解决了一次大批量地价评估的难题,为宗地地价评估提出新的方向。Using RS technology to update evaluation base maps of parcels of land regularly, and using GIS to manage and analyze data of parcels of land, GIS evaluation Information System was established, and several similar lands were extracted. The paper introduced artificial neural network and Delphi approach to establish the evaluation index system of land evaluation——considering land price as its evaluation goal. The model of 3 layers of BP network was established based on the data sets of 18 of 22 commercial land of Nanchang city, inputting value of 5 evaluation index of cities and outputting value of land price. The simulation results were well validated by the data sets of another 4 commercial land. It showed that the model can effectively solve problems of numbers of land evaluation, thus pointing at new directions for land evaluation.

关 键 词：遥感 地理信息系统 神经网络模型评估法 宗地 南昌市 

分 类 号：F301.3[经济管理—产业经济]