Land cover dynamic change in the Napahai Basin using the optimized random forest model

Abstract. Based on the optimized random forest (ORF) model proposed in our research, data of the Landsat-OLI, Landsat-TM images, and digital elevation model were used by us to obtain the land cover maps during several periods in the Napahai Basin. Model performance testing results show that producer accuracy and kappa coefficient of the ORF approach are 0.916 and 0.903, which are higher than the traditional maximum likelihood method. Furthermore, we analyzed the characteristic of land cover dynamic change and seasonal variation of wetlands landscape in 2002 and 2017, and revealed their driving mechanisms and ecological response process. The conclusions are as follows: (1) Lake area expanded in the past 15 years because of increased glacial runoff generated from global warming. Construction land and farmland replaced wetland areas in the middle and downstream regions. Moreover, due to the limitation of hydrothermal conditions in the canyon, few forests in the northeastern basin transferred to shrubs. (2) Dam, which was constructed in northern Napahai lake, controls water storage and made the lake area stable after 2013, so, area change percentage in 2017 from wet to dry season is lower than 2002. The wetland region in the central and downstream basin was synthetically affected by climate change and drainage projects, so its environment condition becomes dryer, and vegetation communities’ succession shows a reversed process. (3) Ecological problems in the Napahai Basin were mainly reflected at aspects of agricultural nonpoint source pollution, overgrazing, and urbanization. These factors affected lake, soil, and groundwater in the Napahai Basin and destroyed the ecological health of wetland landscapes. Therefore, in order to realize sustainable development environmental resources, local government should propose the effective policies to restore the degraded ecosystem and protect natural wetland.

[1]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[2]  Balachandran Manavalan,et al.  Random Forest-Based Protein Model Quality Assessment (RFMQA) Using Structural Features and Potential Energy Terms , 2014, PloS one.

[3]  J. Zedler,et al.  Wetland resources : Status, trends, ecosystem services, and restorability , 2005 .

[4]  Min Wang,et al.  Land cover classification using random forest with genetic algorithm-based parameter optimization , 2016 .

[5]  P. Gong,et al.  Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery , 2006 .

[6]  Emma Izquierdo-Verdiguier,et al.  Evaluating the Performance of a Random Forest Kernel for Land Cover Classification , 2017, Remote. Sens..

[7]  George May,et al.  Landsat Large-Area Estimates for Land Cover , 1986, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Mary E. Kentula,et al.  Characterization of wetland hydrology using hydrogeomorphic classification , 1999, Wetlands.

[9]  Fabio Roli,et al.  Support vector machines for remote sensing image classification , 2001, SPIE Remote Sensing.

[10]  Zhao-Liang Li,et al.  Scale Issues in Remote Sensing: A Review on Analysis, Processing and Modeling , 2009, Sensors.

[11]  Rémi Cresson,et al.  A Framework for Remote Sensing Images Processing Using Deep Learning Techniques , 2018, IEEE Geoscience and Remote Sensing Letters.

[12]  Jian-rong Fan,et al.  Hydraulic properties of concentrated flow of a bank gully in the dry‐hot valley region of southwest China , 2015 .

[13]  Matthew D. Miller.  The impacts of Atlanta’s urban sprawl on forest cover and fragmentation , 2012 .

[14]  Jian Zheng,et al.  A K-Means Remote Sensing Image Classification Method Based On AdaBoost , 2008, 2008 Fourth International Conference on Natural Computation.

[15]  V. Klemas,et al.  Using Remote Sensing to Select and Monitor Wetland Restoration Sites: An Overview , 2013 .

[16]  Chen Lin,et al.  Typical Alpine Wetland System Changes on the Qinghai-Tibet Plateau in Recent 40 Years , 2007 .

[17]  V. K. Jayaraman,et al.  Feature selection and classification employing hybrid ant colony optimization/random forest methodology. , 2009, Combinatorial chemistry & high throughput screening.

[18]  Josef Strobl,et al.  What’s wrong with pixels? Some recent developments interfacing remote sensing and GIS , 2001 .

[19]  Iryna Dronova,et al.  Object-Based Image Analysis in Wetland Research: A Review , 2015, Remote. Sens..

[20]  Ma Ke,et al.  Landscape assessment on wetland degradation during thirty years in Jiansanjiang region of Sanjiang Plain,Northeast China , 2009 .

[21]  L. Durieux,et al.  Advances in Geographic Object-Based Image Analysis with ontologies: A review of main contributions and limitations from a remote sensing perspective , 2013 .

[22]  Bo Li,et al.  Study of SAR Image Texture Feature Extraction Based on GLCM in Guizhou Karst Mountainous Region , 2012 .

[23]  A. Pekkarinen,et al.  A method for the segmentation of very high spatial resolution images of forested landscapes , 2002 .

[24]  L. Zhen,et al.  Impacts of ecological restoration and human activities on habitat of overwintering migratory birds in the wetland of Poyang Lake, Jiangxi Province, China , 2015, Journal of Mountain Science.

[25]  Bor-Chen Kuo,et al.  A Kernel-Based Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[26]  Albert Y. Zomaya,et al.  Remote sensing big data computing: Challenges and opportunities , 2015, Future Gener. Comput. Syst..

[27]  R. C. Frohn,et al.  Segmentation and object-oriented classification of wetlands in a karst Florida landscape using multi-season Landsat-7 ETM+ imagery , 2011 .

[28]  Francisco Alonso-Sarría,et al.  Modification of the random forest algorithm to avoid statistical dependence problems when classifying remote sensing imagery , 2017, Comput. Geosci..

[29]  Lei Deng,et al.  Analysis of wavelet packet and statistical textures for object-oriented classification of forest-agriculture ecotones using SPOT 5 imagery , 2012 .

[30]  Chad Hendrix,et al.  A Comparison of Urban Mapping Methods Using High-Resolution Digital Imagery , 2003 .

[31]  Yan Peng,et al.  Spectral-spatial multi-feature classification of remote sensing big data based on a random forest classifier for land cover mapping , 2017, Cluster Computing.

[32]  Emma Izquierdo-Verdiguier,et al.  Encoding Invariances in Remote Sensing Image Classification With SVM , 2013, IEEE Geoscience and Remote Sensing Letters.

[33]  Martin Kappas,et al.  Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery , 2017, Sensors.

[34]  Gabriele Moser,et al.  Multimodal Classification of Remote Sensing Images: A Review and Future Directions , 2015, Proceedings of the IEEE.

[35]  R. Parkinson.  Decelerating Holocene sea-level rise and its influence on Southwest Florida coastal evolution; a transgressive/regressive stratigraphy , 1989 .

[36]  S. Zhang,et al.  Feature Selection and Optimization of Random Forest Modeling , 2014, CIT 2014.

[37]  Yuming Yang,et al.  Distribution patterns and changes of aquatic plant communities in Napahai Wetland in northwestern Yunnan Plateau, China , 2008, Frontiers of Biology in China.

[38]  K. Clarke,et al.  Impact of Urban Sprawl on Water Quality in Eastern Massachusetts, USA , 2007, Environmental management.

[39]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[40]  唐明艳 Tang Mingyan,et al.  Analysis of vegetation and soil degradation characteristics under different human disturbance in lakeside wetland, Napahai , 2013 .

[41]  Clément Mallet,et al.  INVESTIGATING THE POTENTIAL OF DEEP NEURAL NETWORKS FOR LARGE-SCALE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE IMAGES , 2017 .

[42]  Robert A. Schowengerdt,et al.  A detailed comparison of backpropagation neural network and maximum-likelihood classifiers for urban land use classification , 1995, IEEE Trans. Geosci. Remote. Sens..

[43]  Onisimo Mutanga,et al.  Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers , 2014 .

[44]  Alexis J. Comber,et al.  Random forest classification of salt marsh vegetation habitats using quad-polarimetric airborne SAR, elevation and optical RS data , 2014 .

[45]  Caiyun Zhang,et al.  Combining object-based texture measures with a neural network for vegetation mapping in the Everglades from hyperspectral imagery , 2012 .

[46]  W. Mitsch.  Wetland creation, restoration, and conservation: A Wetland Invitational at the Olentangy River Wetland Research Park , 2005 .

[47]  Bing Zhang,et al.  Long-Term Changes of Lake Level and Water Budget in the Nam Co Lake Basin, Central Tibetan Plateau , 2014 .

[48]  Timothy A. Warner,et al.  Implementation of machine-learning classification in remote sensing: an applied review , 2018 .

[49]  Emma Izquierdo-Verdiguier,et al.  Correction: Zafari, A.; Zurita-Milla, R.; Izquierdo-Verdiguier, E. Evaluating the Performance of a Random Forest Kernel for Land Cover Classification. Remote Sensing 2019, 11, 575 , 2019, Remote. Sens..

[50]  Dookie Kim,et al.  An improved application technique of the adaptive probabilistic neural network for predicting concrete strength , 2009 .

[51]  Mohammad Firuz Ramli,et al.  Measuring Land Cover Change in Seremban, Malaysia Using NDVI Index , 2015 .

[52]  Claire Marais-Sicre,et al.  Effect of Training Class Label Noise on Classification Performances for Land Cover Mapping with Satellite Image Time Series , 2017, Remote. Sens..

[53]  Guoqing Zhou,et al.  Comparison of object-oriented and Maximum Likelihood Classification of land use in Karst area , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[54]  Qian Yu.  Object-based vegetation classification with high resolution remote sensing imagery , 2005 .

[55]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[56]  Hu Pengfei,et al.  Accuracy of TRMM precipitation data in the southwest monsoon region of China , 2017, Theoretical and Applied Climatology.

[57]  Yudong Zhang,et al.  Remote-Sensing Image Classification Based on an Improved Probabilistic Neural Network , 2009, Sensors.

[58]  Stuart R. Phinn,et al.  Hyperspectral Data for Mangrove Species Mapping: A Comparison of Pixel-Based and Object-Based Approach , 2011, Remote. Sens..

[59]  R. Englund.  The loss of native biodiversity and continuing nonindigenous species introductions in freshwater, estuarine, and wetland communities of Pearl Harbor, Oahu, Hawaiian Islands , 2002 .

[60]  Lei Shi,et al.  Mapping Vegetation and Land Use Types in Fanjingshan National Nature Reserve Using Google Earth Engine , 2018, Remote. Sens..