昆明市土地利用变化趋势的多模型对比分析

许安泽; 张述清; 朱大明; 裘木兰; 保红

doi:10.13961/j.cnki.stbctb.2023.01.017

您当前的位置：

首页 >

文章列表页 >

昆明市土地利用变化趋势的多模型对比分析

试验研究

- 昆明市土地利用变化趋势的多模型对比分析
- Comparative Analysis of Three Land Use Transition Models in Kunming City
- 水土保持通报 2023年43卷第1期页码：141-148
- 作者机构：
  
  1. 昆明理工大学国土资源工程学院,云南,昆明,650093
  2. 云南省国土资源规划设计研究院,云南,昆明,650216
  3. 昆明市不动产权籍调查中心(昆明市国土规划勘察测绘研究院),云南,昆明,650200
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目“滇中城市群国土格局多尺度演化模拟及优化配置”(41761081)。
- DOI：10.13961/j.cnki.stbctb.2023.01.017
  中图分类号： F301.2
- 纸质出版：2023
- 稿件说明：
移动端阅览
许安泽, 张述清, 朱大明, 等. 昆明市土地利用变化趋势的多模型对比分析[J]. 水土保持通报, 2023,43(1):141-148.

Xu Anze, Zhang Shuqing, Zhu Daming, et al. Comparative Analysis of Three Land Use Transition Models in Kunming City[J]. Bulletin of Soiland Water Conservation, 2023, 43(1): 141-148.
许安泽, 张述清, 朱大明, 等. 昆明市土地利用变化趋势的多模型对比分析[J]. 水土保持通报, 2023,43(1):141-148. DOI： 10.13961/j.cnki.stbctb.2023.01.017.

Xu Anze, Zhang Shuqing, Zhu Daming, et al. Comparative Analysis of Three Land Use Transition Models in Kunming City[J]. Bulletin of Soiland Water Conservation, 2023, 43(1): 141-148. DOI： 10.13961/j.cnki.stbctb.2023.01.017.

摘要

[目的] 对比分析逻辑回归(LogReg)、多层神经网络(MLP)和相似度加权学习(SimWeight)3种土地利用变化趋势模型在多地类变化分析中的模拟效果与土地利用预测精度，为云贵高原地区的国土空间规划、水土保持和生态修复等提供参考。[方法] 以2000—2020年昆明市土地利用变化为例，分别采用3种模型对该区域建模，并使用受试者工作特征曲线、ROC曲线下面积和Kappa系数等多种方法评估精度。[结果] 对于大多数地类的变化趋势，MLP和SimWeight模型的模拟效果要好于LogReg模型，特别是在未利用地的变化分析中MLP和SimWeight模型的AUC值均大于0.9。在整体土地利用变化预测上，LogReg，MLP和SimWeight3种模型的Kappa值分别为0.9066，0.904 1，0.925 3，整体预测结果表现接近，但SimWeight模型略微优于其他模型。[结论] 对于昆明市LUCC建模的模型选择，若为追求更高精度可选择SimWeight模型，若更在意运算速度则优先选择MLP模型，若需要进一步分析驱动因子与土地变化的关系应选择LogReg模型。

Abstract

[Objective] The simulation effects and land use prediction accuracy of three land use transition models (LogReg

MLP

and SimWeight) for multi-land change analysis were compared and analyzed in order to provide a reference for land space planning

soil and water conservation

and ecological restoration in the Yunnan-Guizhou Plateau. [Methods] Three models were used to simulate land use changes for Kunming City from 2000 to 2020. Various methods such as ROC curve

AUC coefficient

and kappa coefficient were used to evaluate model performance. [Results] The simulations of change trends for most land use classes by MLP and SimWeight were better than the simulations by LogReg

especially with regard to the change analysis of unused land where the AUC values for MLP and SimWeight were greater than 0.9. The kappa values for LogReg

MLP

and SimWeight were 0.906 6

0.904 1

and 0.925 3

respectively. The overall prediction results for the three models were similar

and SimWeight was slightly better than the two other models. [Conclusion] For LUCC modeling of Kunming City

SimWeight is recommended when the user desires higher accuracy

MLP is recommended when the user cares more about calculation speed

and LogReg is recommended when the user wants to further analyze the relationship between driving factors and land use changes.

关键词

Keywords

references

Foley J A, Defries R, Asner G P, et al. Global consequences of land use [J]. Science, 2005,309(5734):570-574.

刘纪远,张增祥,张树文,等.中国土地利用变化遥感研究的回顾与展望: 基于陈述彭学术思想的引领[J].地球信息科学学报,2020,22(4):680-687.

肖宝玉.中国LUCC研究特征与趋势: 基于CiteSpace的分析[J].亚热带资源与环境学报,2020,15(1):61-70.

Verburg P H, Soepboer W, Veldkamp A, et al. Modeling the spatial dynamics of regional land use: The CLUE-S model [J]. Environmental Management, 2002,30(3):391-405.

张沐锋,刘万侠,王健恩,等.基于Clue-S模型的石马河流域东莞段生态系统服务价值变化情景模拟[J].水土保持通报,2021,41(1):152-160.

Bakker M M, Alam S J, van Dijk J, et al. Land-use change arising from rural land exchange: An agent-based simulation model [J]. Landscape Ecology, 2015,30(2):273-286.

冯丽媛,米文宝,马国庆.基于CA-Markov模型的宁夏沿黄生态经济带土地利用变化及模拟研究[J].水土保持通报,2019,39(5):218-222.

Gemitzi A. Predicting land cover changes using a CA Markov model under different shared socioeconomic pathways in Greece [J]. GIScience & Remote Sensing, 2021,58(3):425-441.

Shen Qiping, Chen Qing, Tang B S, et al. A system dynamics model for the sustainable land use planning and development [J]. Habitat International, 2009,33(1):15-25.

Deng Xiangzheng, Su Hongbo, Zhan Jinyan. Integration of multiple data sources to simulate the dynamics of land systems [J]. Sensors (Basel,Switzerland), 2008,8(2):620-634.

田益多,梅昀,陈银蓉.基于Markov-DLS模型的江西省多情景下土地利用时空演变分析[J].水土保持通报,2021,41(3):218-227.

Rutherford G N, Guisan A, Zimmermann N E. Evaluating sampling strategies and logistic regression methods for modelling complex land cover changes [J]. Journal of Applied Ecology, 2007,44(2):414-424.

Lin Yingzhi, Deng Xiangzheng, Li Xing, et al. Comparison of multinomial logistic regression and logistic regression: Which is more efficient in allocating land use? [J]. Frontiers of Earth Science, 2014,8(4):512-523.

Ozturk D. Urban growth simulation of atakum (Samsun, Turkey) using cellular automata-Markov chain and multi-layer perceptron-Markov chain models [J]. Remote Sensing, 2015,7(5):5918-5950.

Guo Andong, Zhang Yuqing, Hao Qing. Monitoring and simulation of dynamic spatiotemporal land use/cover changes [J]. Complexity, 2020,2020:3547323.

Sangermano F, Eastman J R, Zhu Honglei. Similarity weighted instance-based learning for the generation of transition potentials in land use change modeling [J]. Transactions in GIS, 2010,14(5):569-580.

Mozumder C, Tripathi N K, Losiri C. Comparing three transition potential models: A case study of built-up transitions in North-East India [J]. Computers, Environment and Urban Systems, 2016,59:38-49.

Parsamehr K, Gholamalifard M, Kooch Y. Comparing three transition potential modeling for identifying suitable sites for REDD+ projects [J]. Spatial Information Research, 2020,28(2):159-171.

Allwein E, Schapire R, Singer Y. Reducing multiclass to binary: A unifying approach for margin classifiers [J]. Journal of Machine Learning Research, 2001,1(2):113-141.

李强,任志远.基于Logistic回归分析的土地利用变化空间统计与模拟[J].统计与信息论坛,2012,27(3):98-103.

Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors [J]. Nature, 1986,323(6088):533-536.

Chan J C W, Chan K P, Yeh A. Detecting the nature of change in an urban environment: A comparison of machine learning algorithms [J]. Photogrammetric Engineering and Remote Sensing, 2001,67(2):213-225.

Weinberger K, Saul L. Distance metric learning for large margin nearest neighbor classification [J]. Journal of Machine Learning Research, 2009,10:207-244.

Cramér H. Mathematical methods of statistics (PMS-9), volume 9[J]. Princeton, NJ,USA, 1946.

Bradley A P. The use of the area under the ROC curve in the evaluation of machine learning algorithms [J]. Pattern Recognition, 1997,30(7):1145-1159.

Hand D J, Till R J. A simple generalisation of the area under the ROC curve for multiple class classification problems [J]. Machine Learning, 2001,45(2):171-186.

Fawcett T. An introduction to ROC analysis [J]. Pattern Recognition Letters, 2006,27(8):861-874.

Pontius R. Quantification error versus location error in comparison of categorical maps [J]. Photogrammetric Engineering and Remote Sensing, 2000,66:1011-1016.

陈希孺.概率论与数理统计[M].安徽合肥:中国科学技术大学出版社,2009.

Buckley J J. The multiple judge,multiple criteria ranking problem: A fuzzy set approach [J]. Fuzzy Sets and Systems, 1984,13(1):25-37.

Eastman J R, Jin Weigen, Kyem P, et al. Raste procedure for multi-criteria/multi-objective decisions [J]. Photogrammetric Engineering and Remote Sensing, 1995,61(5):539-547.

张晓娟,周启刚,王兆林,等.基于MCE-CA-Markov的三峡库区土地利用演变模拟及预测[J].农业工程学报,2017,33(19):268-277.

浏览量

677

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

徐州市区的土地利用变化及其生态环境效应

基于PLUS-InVEST模型的江西省萍乡市碳储量时空演变与多情景模拟

西北地区生态产品价值实现成效评价——基于29个典型案例

黄河流域三大城市群城市土地绿色利用效率的空间关联网络与影响因素

干湿循环作用下易溶盐含量对伊犁黄土强度的影响