|Table of Contents|

Evolution of Spatial and Temporal Patterns of Wetlands in Danjiang Reservoir Area of South-to-North Water Diversion Project, China with Multi-source and Multi-feature Integration(PDF)

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

Issue:
2024年第05期
Page:
569-583
Research Field:
环境与可持续发展
Publishing date:

Info

Title:
Evolution of Spatial and Temporal Patterns of Wetlands in Danjiang Reservoir Area of South-to-North Water Diversion Project, China with Multi-source and Multi-feature Integration
Author(s):
WANG Xiao-feng1; 2*;  MA Juan1;  ZHOU Ji-tao1;  YAO Wen-jie1;  TU You1;  WANG Xiao-xue1
(1. School of Land Engineering, Chang'an University, Xi'an 710054, Shaanxi, China; 2. Shaanxi Key Laboratory of Land Remediation Engineering, Xi'an 710054, Shaanxi, China)
Keywords:
remote sensing monitoring;  wetland classification;  feature selection;  random forest;  Landsat imagery;  spatial and temporal characteristics;  Danjiangkou reservoir;  South-to-North Water Diversion Project
PACS:
X87
DOI:
10.19814/j.jese.2024.02024
Abstract:
The Danjiangkou reservoir serves as a crucial water source area for China's South-to-North Water Diversion Project. With the progression of urbanization and the secondary construction of the dam, the wetland ecosystem within the reservoir area has undergone significant transformations, necessitating urgent ecological scientific monitoring. Utilizing the Danjiang reservoir area as a case study, the capabilities of the Google Earth Engine(GEE)platform was harnessed. Firstly, it adopts existing land cover datasets to generate a wetland sample set; secondly, it integrates Landsat imagery, digital elevation model(DEM), and other data sources to construct a multi-source feature collection, subsequently performing feature selection based on the Jeffries-Matusita(JM)distance; the Random Forest(RF)algorithm is then employed to achieve wetland mapping in Danjiang reservoir area from 1985 to 2023. The results show that ① the proposed sample collection process effectively enhances the quality of the samples, providing a reference for the acquisition of long-term time-series classification samples; ② after wetland classification feature selection, the number of features is reduced from 37 to 27, with minimal impact on the overall classification accuracy; the average overall accuracy and the QADI value of the selected features applied to wetland classification in Danjiang reservoir area are 89.53% and 0.080 2, respectively, demonstrating the efficacy of feature selection in reducing information redundancy and improving image classification efficiency; ③ from 1985 to 2023, the wetland area in Danjiang reservoir area exhibits a fluctuating increasing trend, expanding from 17 839.85 ha in 1985 to 28 872.48 ha in 2023, representing an area increase of 38.12%. In general, the wetland ecosystem in Danjiang reservoir area demonstrates a positive trend of gradual recovery and optimization.

References:

[1] MAO D H,WANG Z M,DU B J,et al.National Wetland Mapping in China:A New Product Resulting from Object-based and Hierarchical Classification of Landsat 8 Oli Images[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,164(6):11-25.
[2] MAO D H,YANG H,WANG Z M,et al.Reverse the Hidden Loss of China's Wetlands[J].Science,2022,376:1061.
[3] 包洪福,孙志禹,陈凯麒.南水北调中线工程对丹江口库区生物多样性的影响[J].水生态学杂志,2015,36(4):14-19.
BAO Hong-fu,SUN Zhi-yu,CHEN Kai-qi.Environmental Impact of the Middle Section of the South-to-North Water Transfer Project on Biological Diversity in the Danjiangkou Reservoir Area[J].Journal of Hy-droecology,2015,36(4):14-19.
[4] NASAR-U-MINALLAH M,HAASE D,QURESHI S,et al.Ecological Monitoring of Urban Thermal Field Variance Index and Determining the Surface Urban Heat Island Effects in Lahore,Pakistan[J].Environmental Monitoring and Assessment,2023,195(10):1212.
[5] RUNHONG L,SHICHU L,HONGYAN Z.Progress of Chinese Coastal Wetland Based on Remote Sensing[J].Remote Sensing Technology and Application,2018,32(6):998-1011.
[6] HAILU A,MAMMO S,KIDANE M.Dynamics of Land Use,Land Cover Change Trend and Its Drivers in Jimma Geneti District,Western Ethiopia[J].Land Use Policy,2020,99:105011.
[7] CHAI D F,NEWSAM S,ZHANG H K,et al.Cloud and Cloud Shadow Detection in Landsat Imagery Based on Deep Convolutional Neural Networks[J].Remote Sensing of Environment,2019,225:307-316.
[8] 刘瑞清,李加林,孙 超,等.基于Sentinel-2遥感时间序列植被物候特征的盐城滨海湿地植被分类[J].地理学报,2021,76(7):1680-1692.
LIU Rui-qing,LI Jia-lin,SUN Chao,et al.Classification of Yancheng Coastal Wetland Vegetation Based on Vegetation Phenological Characteristics Derived from Sentinel-2 Time-series[J].Acta Geographica Si-nica,2021,76(7):1680-1692.
[9] 黄玉玲,杨 刚,孙伟伟,等.多源多特征集成的南美洲典型地区湿地制图[J].遥感学报,2023,27(6):1300-1319.
HUANG Yu-ling,YANG Gang,SUN Wei-wei,et al.Wetlands Mapping in Typical Regions of South America with Multi-source and Multi-feature Integration[J].National Remote Sensing Bulletin,2023,27(6):1300-1319.
[10] 王安琪,周德民,宫辉力.基于雷达后向散射特性进行湿地植被识别与分类的方法研究[J].遥感信息,2012,27(2):15-19.
WANG An-qi,ZHOU De-min,GONG Hui-li.A Re-search on the Method of Wetland Vegetation Identification and Classification Based on Radar Backscatter Characteristics[J].Remote Sensing Information,2012,27(2):15-19.
[11] 宁晓刚,常文涛,王 浩,等.联合GEE与多源遥感数据的黑龙江流域沼泽湿地信息提取[J].遥感学报,2022,26(2):386-396.
NING Xiao-gang,CHANG Wen-tao,WANG Hao,et al.Extraction of Marsh Wetland in Heilongjiang Basin Based on GEE and Multi-source Remote Sensing Data[J].National Remote Sensing Bulletin,2022,26(2):386-396.
[12] DUBEAU P,KING D J,UNBUSHE D G,et al.Mapping the Dabus Wetlands,Ethiopia,Using Random Forest Classification of Landsat,Palsar and Topographic Data[J].Remote Sensing,2017,9(10):1056.
[13] ADELI S,QUACKENBUSH L J,SALEHI B,et al.The Importance of Seasonal Textural Features for Object-based Classification of Wetlands:New York State Case Study[C]∥ISPRS.The International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences.Nice:ISPRS,2022:471-477.
[14] CARLSON D F,VIVÓ-PONS A,TREIER U A,et al.Mapping Intertidal Macrophytes in Fjords in Southwest Greenland Using Sentinel-2 Imagery[J].Science of the Total Environment,2023,865:161213.
图9 不同阶段湿地面积变化及其差异
Fig.9 Changes of Wetland Area at Different Stages and Their Differences[15] SCHRATZ P,MUENCHOW J,ITURRITXA E,et al.Monitoring Forest Health Using Hyperspectral Imagery:Does Feature Selection Improve the Performan-ce of Machine-learning Techniques?[J].Remote Sen-sing,2021,13(23):4832.
[16] 霍轩琳,牛振国,张 波,等.高寒湿地分类的遥感特征优选研究[J].遥感学报,2023,27(4):1045-1060.
HUO Xuan-lin,NIU Zhen-guo,ZHANG Bo,et al.Remote Sensing Feature Selection for Alpine Wetland Classification[J].National Remote Sensing Bulletin,2023,27(4):1045-1060.
[17] CHATZIANTONIOU A,PETROPOULOS G P,PSOMIADIS E.Co-orbital Sentinel 1 and 2 for Lulc Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning[J].Remote Sensing,2017,9(12):1259.
[18] LIU J T,FENG Q L,GONG J H,et al.Land-cover Classification of the Yellow River Delta Wetland Ba-sed on Multiple End-member Spectral Mixture Analysis and a Random Forest Classifier[J].International Journal of Remote Sensing,2016,37(8):1845-1867.
[19] WANG S,FENG W,QUAN Y H,et al.A Heterogeneous Double Ensemble Algorithm for Soybean Planting Area Extraction in Google Earth Engine[J].Computers and Electronics in Agriculture,2022,197:106955.
[20] 罗逸臻,黄远程,王 涛.关中平原城市群生态环境质量时空变化特征及其驱动力[J].地球科学与环境学报,2023,45(6):1316-1329.
LUO Yi-zhen,HUANG Yuan-cheng,WANG Tao.Spatial-temporal Variation Characteristics of Ecological Environment Quality and Their Driving Forces in Guanzhong Plain Urban Agglomeration,China[J].Journal of Earth Sciences and Environment,2023,45(6):1316-1329.
[21] 李艺霖,赵先超.长株潭城市群生态环境与城镇化时空耦合协调关系:基于遥感生态指数和夜间灯光指数[J].地球科学与环境学报,2024,46(3):307-320.
LI Yi-lin,ZHAO Xian-chao.Spatio-temporal Coupling Coordination Relationship Between Ecological Environment and Urbanization in Changsha-Zhuzhou-Xiangtan Urban Agglomeration,China:Based on Remote Sensing Ecological Index and Nighttime Lighting Index[J].Journal of Earth Sciences and Environment,2024,46(3):307-320.
[22] 刘金宝,刘 轩,孙增慧,等.丹江口水库土地利用与水质变化响应关系研究[J].遥感技术与应用,2023,38(2):285-296.
LIU Jin-bao,LIU Xuan,SUN Zeng-hui,et al.Study on the Response Relationship Between Land Use and Water Quality Change in Danjiangkou Reservoir[J].Remote Sensing Technology and Application,2023,38(2):285-296.
[23] 董亚东,杨文宇,秦 赫.丹江口库区水域面积动态变化分析:基于长时间序列Landsat数据[J].安徽农业科学,2016,44(1):321-324.
DONG Ya-dong,YANG Wen-yu,QIN He.Dynamic Analysis of Water Area in Danjiangkou Reservoir:Ba-sed on Long-time Series Landsat Data[J].Journal of Anhui Agricultural Sciences,2016,44(1):321-324.
[24] 刘 海,武 靖,殷 杰,等.丹江口水库动库容估算及其变化[J].应用生态学报,2018,29(8):2658-2666.
LIU Hai,WU Jing,YIN Jie,et al.Evaluation and Change of Danjiangkou Reservoir Dynamic Capacity[J].Chinese Journal of Applied Ecology,2018,29(8):2658-2666.
[25] 段晋江,姜永涛,丁磊香,等.丹江口水库水域变化遥感监测研究[J].河南城建学院学报,2022,31(4):56-61.
DUAN Jin-jiang,JIANG Yong-tao,DING Lei-xiang,et al.Monitoring of Water Area Change in Danjiang-kou Reservoir Area Based on Remote Sensing Data[J].Journal of Henan University of Urban Construction,2022,31(4):56-61.
[26] ZHANG X,LIU L Y,CHEN X D,et al.GLC_FCS30:Global Land-cover Product with Fine Classification System at 30 m Using Time-series Landsat Imagery[J].Earth System Science Data,2021,13(6):2753-2776.
[27] 陈 军,陈 晋.GlobeLand30遥感制图创新与大数据分析[J].中国科学:地球科学,2018,48(10):1391-1392.
CHEN Jun,CHEN Jin.GlobeLand30:Operational Glo-bal Land Cover Mapping and Big-data Analysis[J].Science China:Earth Sciences,2018,48(10):1391-1392.
[28] XUE L Q.Land Cover Change Information Extraction of Danjiangkou Wetland Based on GF_1 Data and Softmax Algorithm[C]∥WANG L H,WU Y R,GONG J Y.Proceedings of the 8th China High Resolution Earth Observation Conference(CHREOC 2022).Berlin:Springer,2022:322-330.
[29] 冯 倩,张佳华,邓 帆,等.基于特征优选和时空融合算法的黄河三角洲湿地类别制图方法研究[J].自然资源遥感,2024,36(2):39-49.
FENG Qian,ZHANG Jia-hua,DENG Fan,et al.A Mapping Methodology for Wetland Categories of the Yellow River Delta Based on Optimal Feature Selection and Spatio-temporal Fusion Algorithm[J].Remote Sensing for Natural Resources,2024,36(2):39-49.
[30] 常文涛.基于哨兵影像特征分析和样本迁移的黑龙江流域沼泽湿地提取与时空变化研究[D].青岛:山东科技大学,2021.
CHANG Wen-tao.Study on Marsh Wetland Extraction and Spatiotemporal Change in Heilongjiang Basin Based on Sentinel Image Feature Analysis and Sample Migration[D].Qingdao:Shandong University of Science and Technology,2021.
[31] 张 猛,曾永年,朱永森.面向对象方法的时间序列MODIS数据湿地信息提取:以洞庭湖流域为例[J].遥感学报,2017,21(3):479-492.
ZHANG Meng,ZENG Yong-nian,ZHU Yong-sen.Wetland Mapping of Donting Lake Basin Based on Time-series MODIS Data and Object-oriented Method[J].Journal of Remote Sensing,2017,21(3):479-492.
[32] BREIMAN L.Random Forests[J].Machine Learning,2001,45:5-32.
[33] TATSUMI K,YAMASHIKI Y,TORRES M A C,et al.Crop Classification of Upland Fields Using Random Forest of Time-series Landsat 7 ETM+ Data[J].Computers and Electronics in Agriculture,2015,115:171-179.
[34] 冯 瑞,杨丽萍,侯成磊,等.基于随机森林的陕西省西安市近地表气温估算[J].地球科学与环境学报,2022,44(1):102-113.
FENG Rui,YANG Li-ping,HOU Cheng-lei,et al.Estimation of Near-surface Air Temperature in Xi'an City of Shaanxi Province,China Based on Random Forest[J].Journal of Earth Sciences and Environment,2022,44(1):102-113.
[35] RODRIGUEZ-GALIANO V F,GHIMIRE B,ROGAN J,et al.An Assessment of the Effectiveness of a Random Forest Classifier for Land-cover Classification[J].ISPRS Journal of Photogrammetry and Remote Sensing,2012,67:93-104.
[36] 陈 超,傅姣琪,随欣欣,等.面向灾后水体遥感信息提取的知识决策树构建及应用[J].遥感学报,2018,22(5):792-801.
CHEN Chao,FU Jiao-qi,SUI Xin-xin,et al.Construction and Application of Knowledge Decision Tree After Adisaster for Water Body Information Extraction from Remote Sensing Image[J].Journal of Remote Sensing,2018,22(5):792-801.
[37] MA H J,GAO X H,GU X T.Random Forest Classification of Landsat 8 Imagery for the Complex Terrain Area Based on the Combination of Spectral,Topographic and Texture Information[J].Journal of Geo-information Science,2019,21(3):359-371.
[38] TELUGUNTLA P,THENKABAIL P S,OLIPHANT A,et al.A 30-m Landsat-derived Cropland Extent Product of Australia and China Using Random Forest Machine Learning Algorithm on Google Earth Engine Cloud Computing Platform[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,144:325-340.
[39] JUN M J.A Comparison of a Gradient Boosting Decision Tree,Random Forests,and Artificial Neural Networks to Model Urban Land Use Changes:The Case of the Seoul Metropolitan Area[J].International Journal of Geographical Information Science,2021,35(11):2149-2167.
[40] SABAT-TOMALA A,RACZKO E,ZAGAJEWSKI B.Comparison of Support Vector Machine and Random Forest Algorithms for Invasive and Expansive Species Classification Using Airborne Hyperspectral Data[J].Remote Sensing,2020,12(3):516.
[41] LIU Q H,ZHANG Y L,LIU L S,et al.A Novel Landsat-Based Automated Mapping of Marsh Wetland in the Headwaters of the Brahmaputra,Ganges and Indus Rivers,Southwestern Tibetan Plateau[J].International Journal of Applied Earth Observation and Geoinformation,2021,103:102481.
[42] VALENTI V L,CARCELEN E C,LANGE K,et al.Leveraging Google Earth Engine User Interface for Semiautomated Wetland Classification in the Great Lakes Basin at 10 m with Optical and Radar Geospatial Datasets[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2020,13:6008-6018.
[43] FEIZIZADEH B,DARABI S,BLASCHKE T,et al.Qadi as a New Method and Alternative to Kappa for Accuracy Assessment of Remote Sensing-based Image Classification[J].Sensors,2022,22(12):4506.
[44] ZHANG X,YANG H,ZHANG W S,et al.Hydrolo-gic Impacts of Cascading Reservoirs in the Middle and Lower Hanjiang River Basin Under Climate Variability and Land Use Change[J].Journal of Hydrology:Regional Studies,2022,44:101253.
[45] WANG L T,WANG S X,ZHOU Y,et al.Landscape Pattern Variation,Protection Measures,and Land Use/Land Cover Changes in Drinking Water Source Protection Areas:A Case Study in Danjiangkou Re-servoir,China[J].Global Ecology and Conservation,2020,21:e00827.
[46] CAMPAGNOLO M L,CERDEIRA J O.Contextual Classification of Remotely Sensed Images with Integer Linear Programming[M]∥TAVARES J M R S,NATAL J R M.Computational Modelling of Objects Represented in Images:Fundamentals,Methods and Applications.London:CRC Press,2018:123-128.

Memo

Memo:
-
Last Update: 2024-10-01