Dynamic Change and Prediction of Land Use in Jinjiang City Based on LCM Model

doi:10.13466/j.cnki.lyzygl.2018.01.014

Abstract

Abstract:

The aim of the study was to explore the evolution law of land use and the future land use status in Jinjiang City.This paper analyzed the dynamic change of land use type with three remote sensing images in 1990,2000 and 2010.Based on the remote sensing interpretation data and the land use dynamic change influencing factors,this paper constructed the land use forecasting model(LCM).This model was used to forecast the quantity and distribution of land use in 2020 and 2030 in Jinjiang.The results are as follows:(1) The Kappa indices of LCM model in 2010 were all more than 80%.(2) The prediction results show that construction land will increase in the central and north parts of Jinjiang,and the decrease of cultivated land will be distributed in the central urban area of Jinjiang future zoning.The bare land will decrease in the LCM model prediction,mainly in the coastal area.While the forest land will decrease in 2020,but the growth trend will appear after 2020,and mainly in the coastal towns.This paper indicated that the accuracy and credibility of LCM prediction were high and provided a reasonable basis for the future planning of land use in Jinjiang City and the direction of regional economic development.

Key words: land use dynamics, MLP_ANN model, Marcov model, prediction, Jinjiang

CLC Number:

TP79

SU Yanqin, LAI Riwen, LUO Wenwei, YU Lili, LAI Chimin, LI Honglin. Dynamic Change and Prediction of Land Use in Jinjiang City Based on LCM Model[J]. FOREST RESOURCES WANAGEMENT, 2018, (1): 96-102.

Figures/Tables 10

Tab.1

Fig.1

Tab.2

Types and formulas of Kappa indexs

指数名称	公式	备注	公式序号
数量Kappa指数	$K 1 = P 0 - NQML) (1 - NQML))$	NQML:没有保持数量,而有中等保持空间位置能力的驱动力	(9)
标准Kappa指数	$K 3 = P 0 - MQNL) (1 - MQNL))$	MQNL:仅有中等保持数量,而没有保持空间位置能力的驱动力	(10)
随机Kappa指数	$K 4 = P 0 - NQNL) (1 - NQNL))$	NQNL:既没有保持数量,又没有保持空间位置能力的驱动力	(11)
位置Kappa指数	$K 2 = P 0 - NQNL) (MQPL - NQNL))$	MQPL:既有中等保持数量,又有完全保持空间位置能力的驱动力	(12)

Tab.2

Fig.2

Fig.3

Fig.4

Fig.5

Tab.3

Fig.6

Fig.7

References 12

[1]	闫化冰, 段红梅, 薛建春. 包头市土地利用动态变化研究[J]. 中国市场, 2009(13):61-63.
[2]	赵冬玲, 杜萌, 杨建宇, 等. 基于CA-Markov模型的土地利用演化模拟预测研究[J]. 农业机械学报, 2016(3):278-285.
[3]	刘淑燕, 余新晓, 李庆云, 等. 基于CA-Markov模型的黄土丘陵区土地利用变化[J]. 农业工程学报, 2010(11):297-303.
[4]	魏辽生. 基于IDRISI-LCM模型的土地利用变化与预测研究[D]. 大连:辽宁师范大学, 2015.
[5]	徐广才, 康慕谊, 李亚飞. 基于MLP-ANN与Markov Chain的土地利用变化预测方法——以锡林郭勒盟为例[J]. 生态环境学报, 2010(10):2386-2392.
[6]	Labs C. Species Distribution Modeling in IDRISI’s Land Change Modeler[EB/OL]. [2017-12-01]. http://clarklabs.org.
[7]	仕玉治, 黄继文, 刘海娇, 等. 基于LCM模型的黄河三角洲土地利用变化预测[J]. 人民黄河, 2014(2):68-70.
[8]	李刚, 陈莹. 我国东南沿海高速城市化地区土地利用动态变化及趋势——以福建省晋江市为例[J]. 经济地理, 2006(3):409-411.
[9]	杨俊, 单灵芝, 席建超, 等. 南四湖湿地土地利用格局演变与生态效应[J]. 资源科学, 2014(4):856-864.
[10]	Arsanjani J J H M. Integration of Logistic Regression,Markov Chain and Cellular Automata Models to simulate urban expansion[J]. International Journal of Applied Earth Observation and. 2013,1(21):265-275.
[11]	Islam M S A A. Land use change prediction in Dhaka City using GIS aided Markov Chain modelling[J]. Journal of Life and Earth Science, 2011,6(21):81-89. doi: 10.3329/jles.v6i0.9726
[12]	曹瑞娜. 基于GIS和CLUE-S模型的山区土地利用情景模拟研究[D]. 泰安:山东农业大学, 2014.

数据类型	时间	抽样数	正确数	评价精度	Kappa
Landsat5 TM	1990	130	117	90.00%	0.8601
Landsat5 TM	2000	130	122	93.85%	0.9144
Landsat7 ETM	2010	130	121	93.08%	0.8979

土地利用类型	2010		2020		2030
土地利用类型	面积/hm²	比例/%	面积/hm²	比例/%	面积/hm²	比例/%
建筑	26204.85	39.63	28051.97	45.31	30984.66	47.3
水域	1330.91	2.01	1039.41	1.68	992.18	1.51
林地	13360.14	20.2	11036.61	17.83	12221.23	18.66
园地	1697.47	2.57	1745.41	2.82	1763.72	2.69
耕地	22973.52	34.74	19591.92	31.65	19218.82	29.34
裸地	557.42	0.84	439.74	0.71	324.45	0.5

[1]	CHEN Xiaohua, CHEN Zongzhu, YANG Qingqing, LEI Jinrui, WU Tingtian, LI Yuanling, PAN Xiaoyan. Predicting the Probability of Tropical Forest Fires in Hainan Island Based on Random Forest Model [J]. Forest and Grassland Resources Research, 2024, 0(6): 140-145.
[2]	SHANG Naiyan, YANG Xiaobo, LI Donghai, LIU Rentong, SU Xin, SHI Jiaqi, DU Chunyan. Population Structure and Dynamic Characteristics of Heritiera parvifolia in Diaoluo Mountain of Hainan Tropical Rainforest National Park [J]. Forest and Grassland Resources Research, 2024, 0(5): 77-85.
[3]	CHEN Guofu, LI Chunhui, CHEN Zhenxiong. Application of Generalized Additive Model Based on Meteorological Factors in Forest Fire Prediction in Fujian Province [J]. Forest and Grassland Resources Research, 2024, 0(4): 94-102.
[4]	LIU Yan, NIU Xiang, WANG Bing. Spatial-Temporal Evolution of Habitat Quality and Its Prediction in Luoxiao Mountain Area in the Past 25 Years [J]. Forest and Grassland Resources Research, 2023, 0(6): 39-51.
[5]	BAI Xingwen, HU Sheng, BU Rigude, YANG Fan. Analysis and Research on the Docking Scheme of Forest Stock Data Between Continuous Inventory of Forest Resources and Forest Resource Planning and Design Investigation [J]. Forest and Grassland Resources Research, 2023, 0(5): 142-147.
[6]	JU Wenzhen, WEI Longbin, PENG Bolin, LI Changcheng, PAN Ting. Study on Driving Factors and Prediction Model of Forest Fire in Guangxi [J]. Forest and Grassland Resources Research, 2023, 0(5): 56-62.
[7]	YANG Xiaoyu, WANG Bing, ZHANG Pengjie. Estimation of Leaf Nitrogen of Betula Platyphylla in Burned Area of Daxing'anling,Inner Mongolia [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(6): 90-96.
[8]	FENG Yazhi, HU Yanrong, LIU Hongjiu. Study on Lasso-gray Prediction Model of Pecans Yield in Lin 'an [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(1): 94-102.
[9]	XU Ruijun, ZHOU Ruliang, LIU Qianfei, LI Wei, WANG Yanxia. Prediction and Simulation of the Suitable Habitat of Monochamus Alternatus under Climate Warming [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(4): 109-116.
[10]	LIU Hao, XU Dongmei. Study on the Dynamic Trend of Carbon Sinks in Arbor Forests in Shanxi Province [J]. FOREST RESOURCES WANAGEMENT, 2019, 0(6): 49-54.
[11]	ZHANG Dongyan, WANG Dongzhi, FAN Dongdong, ZHANG Jiandong, LI Dayong. Relationship Between Crown Width and DBH of Larix pricipis-rupperchtii with Different Site Types [J]. FOREST RESOURCES WANAGEMENT, 2019, 0(4): 69-73.
[12]	TONG Huiqin, LONG Fei, QI Huibo, ZHANG Zhe. Prediction and Simulation of the Potential Demand for Forest Carbon Sequestration in Seven Pilot Carbon Markets [J]. FOREST RESOURCES WANAGEMENT, 2019, 0(4): 10-17.
[13]	CHEN Dai. Prediction of Forest Fire Occurrence in Daxing’an Mountains Based on Logistic Regression Model [J]. FOREST RESOURCES WANAGEMENT, 2019, 0(1): 116-122.
[14]	HUANG Feng, XU Aijun, TANG Lihua. An Improved Hight Prediction Mixed Effect Model for Quercus variabilis [J]. FOREST RESOURCES WANAGEMENT, 2018, 0(5): 54-62.
[15]	ZENG Weisheng. Validation of Two-Variable Tree Volume Tables for Main Tree Species in China [J]. FOREST RESOURCES WANAGEMENT, 2018, 0(5): 35-41.