Prediction of Cultivated Land Area and Importance of Influencing Factors Based on Random Forest Algorithm—A Case Study of Qingyang City, Gansu Province

WANG Quanxi; SUN Pengju; LIU Xuelu; LI Shangze; GAO Jiancun

doi:10.13961/j.cnki.stbctb.2018.05.054

您当前的位置：

首页 >

文章列表页 >

Prediction of Cultivated Land Area and Importance of Influencing Factors Based on Random Forest Algorithm—A Case Study of Qingyang City, Gansu Province

- Prediction of Cultivated Land Area and Importance of Influencing Factors Based on Random Forest Algorithm—A Case Study of Qingyang City, Gansu Province
- Bulletin of Soiland Water Conservation Vol. 38, Issue 5, Pages: 341-346(2018)
- 作者机构：
  
  1. 甘肃农业大学管理学院,甘肃,兰州,730070
  2. 甘肃农业大学资源与环境学院,甘肃,兰州,730070
  3. 甘肃省国土资源规划研究院,甘肃,兰州,730000
  4. 中国地质大学(武汉) 公共管理学院,湖北,武汉,430074
- 作者简介：
- 基金信息：
- DOI：10.13961/j.cnki.stbctb.2018.05.054
  CLC： F301.24
- Published：2018
- 稿件说明：
移动端阅览
WANG Quanxi, SUN Pengju, LIU Xuelu, et al. Prediction of Cultivated Land Area and Importance of Influencing Factors Based on Random Forest Algorithm—A Case Study of Qingyang City, Gansu Province[J]. Bulletin of Soiland Water Conservation, 2018, 38(5): 341-346.
DOI：

WANG Quanxi, SUN Pengju, LIU Xuelu, et al. Prediction of Cultivated Land Area and Importance of Influencing Factors Based on Random Forest Algorithm—A Case Study of Qingyang City, Gansu Province[J]. Bulletin of Soiland Water Conservation, 2018, 38(5): 341-346. DOI： 10.13961/j.cnki.stbctb.2018.05.054.

摘要

[目的

]

分析耕地面积变化影响因素的重要性，以便科学预测耕地资源数量，为保护耕地资源服务。[方法

]

以属于黄土高原地区的甘肃省庆阳市为例，尝试采用随机森林算法构建耕地面积预测模型，与BP神经网络模型的预测结果进行对比，并对耕地面积变化影响因素重要性进行排序。[结果

]

随机森林算法预测结果的相对误差和均方根误差均小于BP神经网络的，预测精度高，结果稳定。它预测出2020，2025，2030年的耕地面积分别为4.515×10

，4.513×10

，4.512×10

，呈现减少的趋势；主要影响因素重要程度排序为：农业机械总动力 > 农业人口 > 地区生产总值 > 固定资产投资额。[结论

]

随机森林算法适合于耕地面积预测，且能够测度耕地面积变化影响因素的重要程度。

Abstract

[Objective] To analyze the importance of the factors that influence the change of cultivated land area in order to predict the amount of cultivated land area resources

and to service the protection of cultivated land.[Methods] Taking Qingyang City of Gansu Province as a case study

the random forest algorithm was used to construct the prediction model of cultivated land area. The results were compared with those of BP neural network model

and the importance of the factors that influencing cultivated land area change was sorted.[Results] The relative error and root mean square error of the prediction results of the random forest algorithm were smaller than that of BP neural network

and the prediction accuracy was high and the results were stable. The cultivated land area in 2020

2025 and 2030 was predicted to be 4.515×105

4.513×105 and 4.512×105 hm2

respectively

showing a decreasing trend. The importance of the main influencing factors was ranked as:agricultural machinery general dynamics > agricultural population > GDP > fixed asset investment.[Conclusion] The random forest algorithm is suitable for the prediction of cultivated land area and can measure the importance of factors that influence the change of cultivated land area.

关键词

Keywords

references

蔡文春,杨德刚.新疆耕地变化及驱动力分析[J].干旱区资源与环境,2006,20(2):146-151.

陈素平,张乐勤.安徽省1995-2013年粮食生产与耕地压力动态变化特征及驱动因素[J].水土保持通报,2017,37(3):167-173.

项灵志,熊华,王海军.湖北省耕地面积变化与各产业发展的关系[J].水土保持通报,2017,37(3):125-130.

王琳,吴业,杨桂山,等.基于STIRPAT模型的耕地面积变化及其影响因素[J].农业工程学报,2008,24(12):196-200.

王海鸿,马琼,付士波,等.西北干旱半干旱区耕地面积变化与人口、经济发展的相关关系研究:以甘肃省为例[J].干旱区资源与环境,2011,25(1):74-79.

吴美琼,陈秀贵.基于主成分分析法的钦州市耕地面积变化及其驱动力分析[J].地理科学,2014,34(1):54-59.

巴哈尔古丽·吾甫尔,瓦哈甫·哈力克.基于主成分分析的巴州耕地变化趋势与驱动力[J].干旱区资源与环境,2012,26(3):105-110.

周晓艳,宋祯利,宋亚男,等.基于地理加权回归模型的长江中游地区人均耕地面积变化影响因素分析[J],水土保持通报,2016,36(1):136-142.

肖思思,吴春笃,储金宇.近15 a中国耕地驱动因素的空间差异分析[J].中国土地科学,2013,27(7):55-61.

孙国军,刘普幸,孙涛.乌拉特前旗耕地变化的驱动力研究及预测[J].水土保持通报,2011,31(1):207-210.

赵永,刘旭华,孙腾达.基于空间自回归模型的中国耕地面积变化预测[J].干旱区资源与环境,2013,27(8):1-5.

程文仕,曹春,黄鑫.趋势移动平均法在耕地面积预测中的应用研究:基于1985-2010年甘肃省耕地面积分析[J].干旱区资源与环境,2015,29(8):185-189.

曹银贵,王静,刘爱霞.基于BP神经网络的三峡库区开县耕地面积预测研究[J].中国农业资源与区划,2007,28(4):30-34.

王霞,王占岐,金贵,等.基于核函数支持向量回归机的耕地面积预测[J].农业工程学报,2014,30(4):204-211.

Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.

方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛,2012,26(3):32-38.

王盼,陆宝宏,张瀚文.基于随机森林模型的需水预测模型及其应用[J].水资源保护,2014,30(1):34-38.

余坤勇,姚雄,邱祈荣.基于随机森林模型的山体滑坡空间预测研究[J].农业机械学报,2016,47(10):338-345.

马玥,姜琦刚,孟治国,等.基于随机森林算法的农耕区土地利用分类研究[J].农业机械学报,2016,47(1):297-303.

陈元鹏,罗明,彭军还,等.基于网格搜索随机森林算法的工矿复垦区土地利用分类[J].农业工程学报,2017,33(14):250-257.

田义超,李晶,任志远.近300年来黄土高原耕地变化及时空格局分析[J].干旱区资源与环境,2012,26(2):94-101.

甄亿位,郝敏,陆宝宏,等.基于随机森林的中长期降水量预测模型研究[J].水电能源科学,2015,33(6):6-10.

王小川,史峰,郁磊,等.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.

车明亮,聂宜民,刘登民,等.区域耕地数量变化预测方法的对比研究[J].中国土地科学,2010,24(5):13-18.

卞德鹏,常庆瑞,柳艺博,等.黄土丘陵沟壑区耕地数量动态变化及其驱动力分析:以吴起为例[J].干旱地区农业研究,2009,27(3):245-248.

Views

1076

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Calculation on Effective Area of Cultivated Land in Naoli River Basin Based on Grey System Theory

Additional Soil Erosion Predication of Natural Gas Pipe Project from West to East in Shaanxi Province

Intelligent Evaluation of Loess Collapsibility

Research on Predicting Index of Phosphorus Leaching from Soil

A Study on Prediction of Boundary Angle of Surface Movement by BP Artificial Neural Network

Related Author

Zhou Hao

Chen Zhushu

Feng Xiaojuan

WANG Cun-rong

ZHANG Jian

KOU Quan

FU Liang-yong

LI Yingliang

Related Institution

Department of Resources and Environment, Hunan Normal University

Yiyang Tobacco Monopoly Administration

Songshan Shaolin Wushu College, Dengfeng

Xifeng Water and Soil Conservation Station of Huanghe River Conservancy Committee, Xifeng

Electronic Comprehensive Investigation and Surveying Institute of Ministry of Information Industry

⁰