Long-Term Annual Mapping of Four Cities on Different Continents by Applying a Deep Information Learning Method to Landsat Data

Urbanization is a substantial contributor to anthropogenic environmental change, and often occurs at a rapid pace that demands frequent and accurate monitoring. Time series of satellite imagery collected at fine spatial resolution using stable spectral bands over decades are most desirable for this purpose. In practice, however, temporal spectral variance arising from variations in atmospheric conditions, sensor calibration, cloud cover, and other factors complicates extraction of consistent information on changes in urban land cover. Moreover, the construction and application of effective training samples is time-consuming, especially at continental and global scales. Here, we propose a new framework for satellite-based mapping of urban areas based on transfer learning and deep learning techniques. We apply this method to Landsat observations collected during 1984–2016 and extract annual records of urban areas in four cities in the temperate zone (Beijing, New York, Melbourne, and Munich). The method is trained using observations of Beijing collected in 1999, and then used to map urban areas in all target cities for the entire 1984–2016 period. The method addresses two central challenges in long term detection of urban change: temporal spectral variance and a scarcity of training samples. First, we use a recurrent neural network to minimize seasonal urban spectral variance. Second, we introduce an automated transfer strategy to maximize information gain from limited training samples when applied to new target cities in similar climate zones. Compared with other state-of-the-art methods, our method achieved comparable or even better accuracy: the average change detection accuracy during 1984–2016 is 89% for Beijing, 94% for New York, 93% for Melbourne, and 89% for Munich, and the overall accuracy of single-year urban maps is approximately 96 ± 3% among the four target cities. The results demonstrate the practical potential and suitability of the proposed framework. The method is a promising tool for detecting urban change in massive remote sensing data sets with limited training data.

[1]  Osamu Higashi,et al.  A SVM-based method to extract urban areas from DMSP-OLS and SPOT VGT data , 2009 .

[2]  Arthur P. Cracknell,et al.  Towards the development of a regional version of MOD17 for the determination of gross and net primary productivity of oil palm trees , 2015 .

[3]  J. Townshend,et al.  Characterizing the magnitude, timing and duration of urban growth from time series of Landsat-based estimates of impervious cover , 2016 .

[4]  Stefano Ermon,et al.  Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping , 2015, AAAI.

[5]  Limin Yang,et al.  Development of a 2001 National land-cover database for the United States , 2004 .

[6]  Annabel McGilvray Sydney & Melbourne: A tale of two cities , 2016, Nature.

[7]  Nazmul Hossain,et al.  Change of impervious surface area between 2001 and 2006 in the conterminous United States , 2011 .

[8]  Sang Michael Xie,et al.  Combining satellite imagery and machine learning to predict poverty , 2016, Science.

[9]  Lichao Mou,et al.  Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection , 2016, Remote. Sens..

[10]  Henrik Meilby,et al.  Locally optimized separability enhancement indices for urban land cover mapping: Exploring thermal environmental consequences of rapid urbanization in Addis Ababa, Ethiopia , 2016 .

[11]  Nicu Sebe,et al.  Semisupervised learning of classifiers: theory, algorithms, and their application to human-computer interaction , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Giles M. Foody,et al.  Impervious Surface Change Mapping with an Uncertainty-Based Spatial-Temporal Consistency Model: A Case Study in Wuhan City Using Landsat Time-Series Datasets from 1987 to 2016 , 2017, Remote. Sens..

[13]  P. Gong,et al.  The use of structural information for improving land-cover classification accuracies at the rural-urban fringe. , 1990 .

[14]  M. Friedl,et al.  Mapping global urban areas using MODIS 500-m data: new methods and datasets based on 'urban ecoregions'. , 2010 .

[15]  Annemarie Schneider,et al.  Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach , 2012 .

[16]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[17]  Lu Liang,et al.  China’s urban expansion from 1990 to 2010 determined with satellite remote sensing , 2012 .

[18]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[19]  Xiao Xiang Zhu,et al.  Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources , 2017, IEEE Geoscience and Remote Sensing Magazine.

[20]  Yue Lin,et al.  Reconstructing Historical Land Cover Type and Complexity by Synergistic Use of Landsat Multispectral Scanner and CORONA , 2017, Remote. Sens..

[21]  E. Lambin,et al.  Dynamics of Land-Use and Land-Cover Change in Tropical Regions , 2003 .

[22]  Robert E. Wolfe,et al.  A Landsat surface reflectance dataset for North America, 1990-2000 , 2006, IEEE Geoscience and Remote Sensing Letters.

[23]  Zhe Zhu,et al.  Object-based cloud and cloud shadow detection in Landsat imagery , 2012 .

[24]  A. Tatem,et al.  Detecting Change in Urban Areas at Continental Scales with MODIS Data , 2015 .

[25]  Xiao Xiang Zhu,et al.  Deep Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[27]  Jun Yang,et al.  The first all-season sample set for mapping global land cover with Landsat-8 data. , 2017, Science bulletin.

[28]  P. Gong,et al.  A 30-year (1984–2013) record of annual urban dynamics of Beijing City derived from Landsat data , 2015 .

[29]  K. Arai A supervised Thematic Mapper classification with a purification of training samples , 1992 .

[30]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[31]  B. Turner,et al.  Remote sensing of the surface urban heat island and land architecture in Phoenix, Arizona: Combined effects of land composition and configuration and cadastral-demographic-economic factors , 2015 .

[32]  A. Luckman,et al.  Mapping urban change in the UK using satellite radar interferometry , 2003 .

[33]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[34]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[35]  Tim Futing Liao,et al.  Analysis of Multivariate Social Science Data , 2010 .

[36]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[37]  J. Townshend,et al.  Urban growth of the Washington, D.C.–Baltimore, MD metropolitan region from 1984 to 2010 by annual, Landsat-based estimates of impervious cover , 2013 .

[38]  Limin Yang,et al.  An approach for mapping large-area impervious surfaces: synergistic use of Landsat-7 ETM+ and high spatial resolution imagery , 2003 .

[39]  T. Pei,et al.  Quantitative estimation of urbanization dynamics using time series of DMSP/OLS nighttime light data: A comparative case study from China's cities , 2012 .

[40]  Hermann Ney,et al.  Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

[42]  Qingquan Li,et al.  Improving Land Use/Land Cover Classification by Integrating Pixel Unmixing and Decision Tree Methods , 2017, Remote. Sens..

[43]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[44]  S. Carpenter,et al.  Global Consequences of Land Use , 2005, Science.

[45]  Shauna J. Sweet,et al.  Analysis of Multivariate Social Science Data (2nd ed.) , 2011 .

[46]  N. Grimm,et al.  Global Change and the Ecology of Cities , 2008, Science.

[47]  Chaoqing Yu,et al.  Changing patterns of urban-rural nutrient flows in China: driving forces and options. , 2017, Science bulletin.

[48]  Dengsheng Lu,et al.  Regional mapping of human settlements in southeastern China with multisensor remotely sensed data , 2008 .

[49]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[50]  Jie Wang,et al.  Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery , 2014, Remote. Sens..

[51]  Bin Li,et al.  Building a Better Urban Picture: Combining Day and Night Remote Sensing Imagery , 2015, Remote. Sens..

[52]  Philip J. Howarth,et al.  Landsat digital enhancements for change detection in urban environments , 1983 .

[53]  Uwe Stilla,et al.  Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks , 2016, IEEE Geoscience and Remote Sensing Letters.

[54]  Arthur P. Cracknell,et al.  Evaluation of MODIS gross primary productivity and land cover products for the humid tropics using oil palm trees in Peninsular Malaysia and Google Earth imagery , 2013 .

[55]  Annemarie Schneider,et al.  Expansion and growth in Chinese cities, 1978–2010 , 2014 .