基于BP神经网络的工业生态安全动态评价及障碍因子诊断

赵杨秋; 何刚; 王莹莹; 阮君; 张朋

doi:10.13961/j.cnki.stbctb.2021.03.018

您当前的位置：

首页 >

文章列表页 >

基于BP神经网络的工业生态安全动态评价及障碍因子诊断

试验研究

- 基于BP神经网络的工业生态安全动态评价及障碍因子诊断
- Dynamic Assessment and Obstacle Factor Diagnosis of Industrial Ecological Safety Based on BP Neural Network
- 水土保持通报 2021年41卷第3期页码：127-136
- 作者机构：
  
  安徽理工大学经济与管理学院,安徽,淮南,232001
- 作者简介：
- 基金信息：
  
  安徽省哲学社会科学规划项目“淮河生态经济带产业转型升级与生态环境的耦合协调发展研究”（AHSKY2019D026）;安徽理工大学研究生创新资助项目“淮河生态经济带经济发展与生态环境的共生性研究”（2020CX2089），“淮河生态经济带新型城镇化对生态环境质量影响研究”（2019CX2075）
- DOI：10.13961/j.cnki.stbctb.2021.03.018
  中图分类号： F205;X826
- 纸质出版：2021
- 稿件说明：
移动端阅览
赵杨秋, 何刚, 王莹莹, 等. 基于BP神经网络的工业生态安全动态评价及障碍因子诊断[J]. 水土保持通报, 2021,41(3):127-136.

Zhao Yangqiu, He Gang, Wang Yingying, et al. Dynamic Assessment and Obstacle Factor Diagnosis of Industrial Ecological Safety Based on BP Neural Network[J]. Bulletin of Soiland Water Conservation, 2021, 41(3): 127-136.
赵杨秋, 何刚, 王莹莹, 等. 基于BP神经网络的工业生态安全动态评价及障碍因子诊断[J]. 水土保持通报, 2021,41(3):127-136. DOI： 10.13961/j.cnki.stbctb.2021.03.018.

Zhao Yangqiu, He Gang, Wang Yingying, et al. Dynamic Assessment and Obstacle Factor Diagnosis of Industrial Ecological Safety Based on BP Neural Network[J]. Bulletin of Soiland Water Conservation, 2021, 41(3): 127-136. DOI： 10.13961/j.cnki.stbctb.2021.03.018.

摘要

[目的] 对安徽省工业生态安全进行评价和预测，为安徽省工业生态安全可持续发展提供科学依据。[方法] 基于压力、状态、响应框架和生态、环境、经济、社会框架构建工业生态安全评价指标体系，采用聚类工具进行安全等级划分，结合熵权法和综合指数法评价2009—2018年安徽省工业生态安全水平，运用BP神经网络模型对2019—2025年工业生态安全水平进行科学预测。[结果] ①从总体上看，2009—2018年安徽省工业生态安全评价指数呈波动上升趋势，安全等级由“临界安全”上升为“较安全”；②从各子系统来看，2009—2018年压力子系统的评价指数呈上升态势，状态和响应子系统的评价指数呈先下降后上升态势；③BP神经网络预测结果显示：2019—2025年安徽省工业生态安全态势总体呈波动上升状态，处于“临界安全”向“较安全”转变态势；④影响安徽省工业生态安全的主要障碍因素包括第二产业从业人员比例、第二产业占GDP的比例、污水集中处理率、森林覆盖率和人口密度，是今后调控的方向。[结论] 研究期间安徽省工业生态安全波动明显，但总体上呈上升趋势，工业生态安全得到明显的改善。

Abstract

[Objective] The industrial ecological safety of Anhui Province was evaluated and predicted

in order to provide a scientific basis for the sustainable development of industrial ecological safety in Anhui Province. [Methods] Pressure

state

response framework and ecological

environmental

economic

and social framework were used to establish the industrial ecological safety evaluation index system. Clustering tools were used to classify safety levels

and combined the entropy weight method and the comprehensive index method to evaluate the industrial ecological safety level in Anhui Province from 2009 to 2018. A BP neural network model was employed to scientifically predict the industrial ecological safety level in Anhui Province from 2019 to 2025. [Results] ① From an overall perspective

the industrial ecological safety evaluation index of Anhui Province from 2009 to 2018 showed a fluctuating upward trend

and the safety level rose from “critical safety” to “safer”. ② From the perspective of each subsystem

the evaluation index of the pressure subsystem showed an upward trend from 2009 to 2018

and the evaluation indexes of the state and response subsystems first declined and then increased. ③ The overall situation of industrial ecological state in Anhui Province from 2019 to 2025 fluctuated and rose

and the safety level rose from “critical safety” to “safer”. ④ The main obstacles affecting the industrial ecological safety of Anhui Province included the ratio of employees in the secondary industry

the ratio of the secondary industry to GDP

and the ratio of centralized sewage treatment

forest coverage

and population density

which providing direction for future regulation. [Conclusion] The industrial ecological state in Anhui Province fluctuated noticeably during the study period

but showed an overall upward trend

and the industrial ecological state was significantly improved.

关键词

Keywords

references

崔馨月,方雷,王祥荣,等.基于DPSIR模型的长三角城市群生态安全评价研究[J].生态学报,2021,41(1):302-319.

杨兆青,陆兆华,刘丹,等.煤炭资源型城市生态安全评价:以锡林浩特市为例[J].生态学报,2021,41(1):280-289.

Pan Zhong, Liu Qianlong, Jiang Ronggen. Microplastic pollution and ecological risk assessment in an estuarine environment:The Dongshan Bay of China[J]. Chemosphere, 2021,262.

Timothy M. Lenton. What early warning systems are there for environmental shocks?[J]. Environmental Science & Policy, 2013,27:60-75.

Joern Birkmann, Denis Chang Seng, Neysa Setiadi. Enhancing early warning in the light of migration and environmental shocks[J]. Environmental Science & Policy, 2013,27:76-88.

Hans J P Marvin, Gijs A Kleter, Maryvon Y Noordam, et al. Proactive systems for early warning of potential impacts of natural disasters on food safety:Climate-change-induced extreme events as case in point[J]. Food Control, 2013,34(2):444-456.

Bai Xiaorui, Tang Jingchun. Ecological security assessment of Tianjin by PSR model[J]. Procedia Environmental Sciences, 2010,2:881-887.

Lu Shasha, Qin Fan, Chen Ni, et al. Spatiotemporal differences in forest ecological security warning values in Beijing:Using an integrated evaluation index system and system dynamics model[J]. Ecological Indicators, 2019,104:549-558.

Zhou Bin, Zhong Linsheng, Chen Tian, et al. Ecological security early-warning in Zhoushan Islands based on variable weight model[J]. Journal of Applied Ecology, 2015,26(6):1854-1862.

Ke Xiaoling, Amal Mougharbel, Guo Haixiang, et al. Early warning simulation of urban ecological security in the Yangtze River Economic Belt:A case study of Chongqing, Wuhan, and Shanghai[J]. Journal of Environmental Planning and Management, 2020,63(10):1811-1833.

郭中伟.建设国家生态安全预警系统与维护体系:面对严重的生态危机的对策[J].科技导报,2001,(1):54-56.

陈英,孔喆,路正,等.基于RBF神经网络模型的土地生态安全预警:以甘肃省张掖市为例[J].干旱地区农业研究,2017,35(1):264-270.

徐美,刘春腊,李丹,等.基于改进TOPSIS-灰色GM(1,1)模型的张家界市旅游生态安全动态预警[J].应用生态学报,2017,28(11):3731-3739.

赵艳萍.农田生态安全预警研究[D].安徽合肥:安徽农业大学,2007.

何焰,由文辉.水环境生态安全预警评价与分析:以上海市为例[J].安全与环境工程,2004,11(4):1-4.

田欣.星海湖湿地生态安全评估与预警研究[D].宁夏银川:宁夏大学,2018.

Li Yangfan, Sun Xiang, Zhu Xiaodong, et al. An early warning method of landscape ecological security in rapid urbanizing coastal areas and its application in Xiamen, China[J]. Ecological Modelling, 2010,221(19):2251-2260.

彭新沙,田大伦.国内工业生态安全研究述评[J].生态学报,2016,36(23):7538-7550.

Lu Shinli. Integrating heuristic time series with modified grey forecasting for renewable energy in Taiwan[J]. Renewable Energy, 2019,133:1436-1444.

熊建华,唐将伟.基于情景分析法的城市土地生态安全预警研究:以深圳为例[J].安全与环境学报,2018,18(3):1215-1219.

吴艳霞,邓楠.基于RBF神经网络模型的资源型城市生态安全预警:以榆林市为例[J].生态经济,2019,35(5):111-118.

潘真真,苏维词,王建伟.基于可拓-马尔科夫模型的贵州省生态安全预警[J].山地学报,2016,34(5):580-590.

苏学能,刘天琪,曹鸿谦,等.基于Hadoop架构的多重分布式BP神经网络的短期负荷预测方法[J].中国电机工程学报,2017,37(17):4966-4973,5216.

余文波,蔡海生,张莹,等.湖北省土地生态安全预警评价及调控[J].环境科学与技术,2018,41(2):189-196.

周彬,虞虎,钟林生,等.普陀山岛旅游生态安全发展趋势预测[J].生态学报,2016,36(23):7792-7803.

高家骥,李雪铭,张峰,等.南四湖湖泊湿地生态环境预警研究[J].地理科学,2016,36(8):1219-1226.

马世五,谢德体,张孝成,等.三峡库区生态敏感区土地生态安全预警测度与时空演变:以重庆市万州区为例[J].生态学报,2017,37(24):8227-8240.

王国萍,闵庆文,丁陆彬,等.基于PSR模型的国家公园综合灾害风险评估指标体系构建[J].生态学报,2019,39(22):8232-8244.

周燕妃.江苏省工业化与生态环境耦合协调度评价研究[D].安徽淮南:安徽理工大学,2019.

喻锋,李晓兵,王宏,等.皇甫川流域土地利用变化与生态安全评价[J].地理学报,2006,61(6):645-653.

杨嘉怡,曾旗.基于组合模型的煤炭城市生态安全预警研究:以焦作市为例[J].地域研究与开发,2018,37(3):113-119.

赵李明.基于遗传算法和BP神经网络的广州市空气质量预测与时空分布研究[D].江西赣州:江西理工大学,2016.

范胜龙,杨玉珍,陈训争,等.基于PSR和无偏GM(1,1)模型的福建省耕地生态安全评价与预测[J].中国土地科学,2016,30(9):19-27.

李旭军.BP神经网络在经济预测中的应用[D].湖北武汉:华中师范大学,2008.

浏览量

786

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于PSR-TOPSIS模型的陇中陇东黄土高原土地生态安全评价及障碍因子诊断

安徽省1949-2003年洪旱灾害时序分形特征研究

安徽省土地利用格局演变及其预测研究

安徽省几种主要土壤有机碳含量及其组分研究

安徽省城镇化演进边际生态环境效应的测度与分析