Convolutional Neural Network-Based Land Cover Classification Using 2-D Spectral Reflectance Curve Graphs With Multitemporal Satellite Imagery

Researchers constantly seek more efficient detection techniques to better utilize enhanced image resolution in accurately detecting and monitoring land cover. Recently, convolutional neural networks (CNNs) have shown high performances comparable to or even better than widely used and adopted machine learning techniques. The aim of this study is to investigate the application of CNNs for land cover classification by using two-dimensional (2-D) spectral curve graphs from multispectral satellite images. The land cover classification was conducted in Concord, New Hampshire, USA, and South Korea by using multispectral images acquired from 30-m Landsat-8 and 500-m Geostationary Ocean Color Imager images. For the construction of input data specific to CNNs, two seasons (winter and summer) of multispectral bands were transformed into 2-D spectral curve graphs for each class. Land cover classification results of CNNs were compared with the results of support vector machines (SVMs) and random forest (RFs). The CNNs model showed higher performance than RFs and SVMs in both study sites. The examination of land cover classification maps demonstrates a good agreement with reference maps, Google Earth images, and existing global scale land cover map, especially for croplands. Using the spectral curve graph could incorporate the phenological cycles on classifying the land cover types. This study shows that the use of a new transformation of spectral bands into a 2-D form for application in CNNs can improve land cover classification performance.

[1]  V. Brovkin,et al.  Effect of Anthropogenic Land-Use and Land-Cover Changes on Climate and Land Carbon Storage in CMIP5 Projections for the Twenty-First Century , 2013 .

[2]  Gang Fu,et al.  Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network , 2017, Remote. Sens..

[3]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[4]  Hongwei Liu,et al.  Convolutional Neural Network With Data Augmentation for SAR Target Recognition , 2016, IEEE Geoscience and Remote Sensing Letters.

[5]  Toby N. Carlson,et al.  The impact of land use — land cover changes due to urbanization on surface microclimate and hydrology: a satellite perspective , 2000 .

[6]  Hankui K. Zhang,et al.  Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data , 2013 .

[7]  Solomon W. Newete,et al.  Field spectroradiometer and simulated multispectral bands for discriminating invasive species from morphologically similar cohabitant plants , 2018 .

[8]  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 .

[9]  Christelle Vancutsem,et al.  GlobCover: ESA service for global land cover from MERIS , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[10]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[11]  Matthew L. Clark,et al.  One-Dimensional Convolutional Neural Network Land-Cover Classification of Multi-Seasonal Hyperspectral Imagery in the San Francisco Bay Area, California , 2017, Remote. Sens..

[12]  Le Yu,et al.  Detailed dynamic land cover mapping of Chile: Accuracy improvement by integrating multi-temporal data , 2016 .

[13]  P. Dirmeyer,et al.  University of Nebraska-Lincoln DigitalCommons @ University of Nebraska-Lincoln Papers in Natural Resources Natural Resources , School of 2014 Land cover changes and their biogeophysical effects on climate , 2016 .

[14]  Joanne C. White,et al.  Optical remotely sensed time series data for land cover classification: A review , 2016 .

[15]  R. Lunetta,et al.  Land-cover change detection using multi-temporal MODIS NDVI data , 2006 .

[16]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[17]  Jean-Christophe Castella,et al.  Combining top-down and bottom-up modelling approaches of land use/cover change to support public policies: Application to sustainable management of natural resources in northern Vietnam , 2007 .

[18]  Nataliia Kussul,et al.  Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[19]  Bruno Merz,et al.  At what scales do climate variability and land cover change impact on flooding and low flows? , 2007 .

[20]  S. Cecchi,et al.  Phytoremediation of Soil Polluted by Nickel Using Agricultural Crops , 2005, Environmental management.

[21]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[22]  J. Townshend,et al.  Detection of land cover changes using MODIS 250 m data , 2002 .

[23]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[24]  Soe W. Myint,et al.  A support vector machine to identify irrigated crop types using time-series Landsat NDVI data , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[25]  Damien Sulla-Menashe,et al.  MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets , 2010 .

[26]  Konrad Schindler,et al.  An Overview and Comparison of Smooth Labeling Methods for Land-Cover Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[27]  M. Bauer,et al.  Land cover classification and change analysis of the Twin Cities (Minnesota) Metropolitan Area by multitemporal Landsat remote sensing , 2005 .

[28]  Damien Sulla-Menashe,et al.  A parametric model for classifying land cover and evaluating training data based on multi-temporal remote sensing data , 2014 .

[29]  Bruce K. Wylie,et al.  Geospatial data mining for digital raster mapping , 2019, GIScience and Remote Sensing.

[30]  Rei Sonobe,et al.  Assessing the suitability of data from Sentinel-1A and 2A for crop classification , 2017 .

[31]  Martin Herold,et al.  Some challenges in global land cover mapping : An assessment of agreement and accuracy in existing 1 km datasets , 2008 .

[32]  Thomas Blaschke,et al.  Evaluation of Feature Selection Methods for Object-Based Land Cover Mapping of Unmanned Aerial Vehicle Imagery Using Random Forest and Support Vector Machine Classifiers , 2017, ISPRS Int. J. Geo Inf..

[33]  Jianjun Ge,et al.  Impacts of land use/cover classification accuracy on regional climate simulations , 2007 .

[34]  Hui Zhou,et al.  Joint Alternate Small Convolution and Feature Reuse for Hyperspectral Image Classification , 2018, ISPRS Int. J. Geo Inf..

[35]  Thilo Wehrmann,et al.  MAD-MEX: Automatic Wall-to-Wall Land Cover Monitoring for the Mexican REDD-MRV Program Using All Landsat Data , 2014, Remote. Sens..

[36]  Gui-Song Xia,et al.  Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery , 2015, Remote. Sens..

[37]  Qihao Weng,et al.  An evaluation of monthly impervious surface dynamics by fusing Landsat and MODIS time series in the Pearl River Delta, China, from 2000 to 2015 , 2017 .

[38]  Curt H. Davis,et al.  Fusion of Deep Convolutional Neural Networks for Land Cover Classification of High-Resolution Imagery , 2017, IEEE Geoscience and Remote Sensing Letters.

[39]  K. Patil.  Cochran's Q Test: Exact Distribution , 1975 .

[40]  Timothy A. Warner,et al.  A time series of annual land use and land cover maps of China from 1982 to 2013 generated using AVHRR GIMMS NDVI3g data , 2017 .

[41]  A. Belward,et al.  GLC2000: a new approach to global land cover mapping from Earth observation data , 2005 .

[42]  Huanxin Zou,et al.  Toward Fast and Accurate Vehicle Detection in Aerial Images Using Coupled Region-Based Convolutional Neural Networks , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[43]  Amy Loutfi,et al.  Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks , 2016, Remote. Sens..

[44]  J. Im,et al.  Drought monitoring using high resolution soil moisture through multi-sensor satellite data fusion over the Korean peninsula , 2017 .

[45]  Diego F. Cuadros,et al.  A Remote Sensing Data Based Artificial Neural Network Approach for Predicting Climate-Sensitive Infectious Disease Outbreaks: A Case Study of Human Brucellosis , 2017, Remote. Sens..

[46]  J. Paruelo,et al.  Land cover classification in the Argentine Pampas using multi-temporal Landsat TM data , 2003 .

[47]  Brian Brisco,et al.  Wetland classification in Newfoundland and Labrador using multi-source SAR and optical data integration , 2017 .

[48]  Sven Behnke,et al.  Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition , 2010, ICANN.

[49]  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..

[50]  H. Franklin Percival,et al.  Use of Unmanned Aircraft Systems to Delineate Fine-Scale Wetland Vegetation Communities , 2014, Wetlands.

[51]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[52]  Zhenwei Shi,et al.  Multilevel Cloud Detection in Remote Sensing Images Based on Deep Learning , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[53]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[54]  Angelo Cangelosi,et al.  Head pose estimation in the wild using Convolutional Neural Networks and adaptive gradient methods , 2017, Pattern Recognit..

[55]  Nikolaos A Patsopoulos,et al.  Critical interpretation of Cochran's Q test depends on power and prior assumptions about heterogeneity , 2010, Research synthesis methods.

[56]  Laurence Hubert-Moy,et al.  A Comparison of Parametric Classification Procedures of Remotely Sensed Data Applied on Different Landscape Units , 2001 .

[57]  Tao Liu,et al.  Comparing fully convolutional networks, random forest, support vector machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system , 2018 .

[58]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[59]  Giorgos Mountrakis,et al.  A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research , 2016 .

[60]  Rob Fergus,et al.  Stochastic Pooling for Regularization of Deep Convolutional Neural Networks , 2013, ICLR.

[61]  Y. Ryu,et al.  Characteristics of Landsat 8 OLI-derived NDVI by comparison with multiple satellite sensors and in-situ observations , 2015 .

[62]  Qihao Weng,et al.  Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends , 2012 .

[63]  D. Lu,et al.  Use of impervious surface in urban land-use classification , 2006 .

[64]  J. Im,et al.  Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest , 2013 .

[65]  Jungho Im,et al.  Arctic Sea Ice Thickness Estimation from CryoSat-2 Satellite Data Using Machine Learning-Based Lead Detection , 2016, Remote. Sens..

[66]  Zhilei Lin,et al.  A support vector machine classifier based on a new kernel function model for hyperspectral data , 2016 .

[67]  A. Henderson-Sellers,et al.  Possible climatic impacts of land cover transformations, with particular emphasis on tropical deforestation , 1984 .

[68]  Chaoyang Fang,et al.  Evaluation of Goddard’s LiDAR, hyperspectral, and thermal data products for mapping urban land-cover types , 2018 .

[69]  Xingrui Yu,et al.  Deep learning in remote sensing scene classification: a data augmentation enhanced convolutional neural network framework , 2017 .

[70]  Le Yu,et al.  Google Earth as a virtual globe tool for Earth science applications at the global scale: progress and perspectives , 2012 .

[71]  A. Gieske,et al.  Crop and land cover classification in Iran using Landsat 7 imagery , 2006 .

[72]  Kathleen Neumann,et al.  Challenges in using land use and land cover data for global change studies , 2011 .

[73]  Tong Xiao,et al.  An Automated Method for Extracting Rivers and Lakes from Landsat Imagery , 2014, Remote. Sens..

[74]  Mark H. Hansen,et al.  Using a land cover classification based on satellite imagery to improve the precision of forest inventory area estimates , 2002 .

[75]  Jungho Im,et al.  Deep learning-based monitoring of overshooting cloud tops from geostationary satellite data , 2018 .