Assessment of Convolution Neural Networks for Wetland Mapping with Landsat in the Central Canadian Boreal Forest Region

Methods for effective wetland monitoring are needed to understand how ecosystem services may be altered from past and present anthropogenic activities and recent climate change. The large extent of wetlands in many regions suggests remote sensing as an effective means for monitoring. Remote sensing approaches have shown good performance in local extent studies, but larger regional efforts have generally produced low accuracies for detailed classes. In this research we evaluate the potential of deep-learning Convolution Neural Networks (CNNs) for wetland classification using Landsat data to bog, fen, marsh, swamp, and water classes defined by the Canada Wetland Classification System (CWCS). The study area is the northern part of the forested region of Alberta where we had access to two reference data sources. We evaluated ResNet CNNs and developed a Multi-Size/Scale ResNet Ensemble (MSRE) approach that exhibited the best performance. For assessment, a spatial extension strategy was employed that separated regions for training and testing. Results were consistent between the two reference sources. The best overall accuracy for the CWCS classes was 62–68%. Compared to a pixel-based random forest implementation this was 5–7% higher depending on the accuracy measure considered. For a parameter-optimized spatial-based implementation this was 2–4% higher. For a reduced set of classes to water, wetland, and upland, overall accuracy was in the range of 86–87%. Assessment for sampling over the entire region instead of spatial extension improved the mean class accuracies (F1-score) by 9% for the CWCS classes and for the reduced three-class level by 6%. The overall accuracies were 69% and 90% for the CWCS and reduced classes respectively with region sampling. Results in this study show that detailed classification of wetland types with Landsat remains challenging, particularly for small wetlands. In addition, further investigation of deep-learning methods are needed to identify CNN configurations and sampling methods better suited to moderate spatial resolution imagery across a range of environments.

[1]  Suming Jin,et al.  Completion of the 2011 National Land Cover Database for the Conterminous United States – Representing a Decade of Land Cover Change Information , 2015 .

[2]  Aaron J. Smith,et al.  A Semi-Automated, Multi-Source Data Fusion Update of a Wetland Inventory for East-Central Minnesota, USA , 2015, Wetlands.

[3]  Julien Radoux,et al.  Sentinel-2's Potential for Sub-Pixel Landscape Feature Detection , 2016, Remote. Sens..

[4]  Jennifer N. Hird,et al.  Google Earth Engine, Open-Access Satellite Data, and Machine Learning in Support of Large-Area Probabilistic Wetland Mapping , 2017, Remote. Sens..

[5]  Xiangmin Xu,et al.  Single Image Super-Resolution Using Multi-Scale Convolutional Neural Network , 2017, PCM.

[6]  Atsuto Maki,et al.  A systematic study of the class imbalance problem in convolutional neural networks , 2017, Neural Networks.

[7]  Molly Reif,et al.  Satellite remote sensing of isolated wetlands using object-oriented classification of Landsat-7 data , 2009, Wetlands.

[8]  Geoffrey J. Hay,et al.  How wetland type and area differ through scale: A GEOBIA case study in Alberta's Boreal Plains , 2012 .

[9]  Marcelle Grenier,et al.  Object-based classification of a SPOT-4 image for mapping wetlands in the context of greenhouse gases emissions: the case of the Eastmain region, Québec, Canada , 2008 .

[10]  Longbing Cao,et al.  Training deep neural networks on imbalanced data sets , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[11]  Brian Brisco,et al.  Remote sensing for wetland classification: a comprehensive review , 2018 .

[12]  Junhua Li,et al.  A rule-based method for mapping Canada's wetlands using optical, radar and DEM data , 2005 .

[13]  Floyd M. Henderson,et al.  Radar detection of wetland ecosystems: a review , 2008 .

[14]  L. Monika Moskal,et al.  Harnessing the Temporal Dimension to Improve Object-Based Image Analysis Classification of Wetlands , 2018, Remote. Sens..

[15]  Ridha Touzi,et al.  Phase of Target Scattering for Wetland Characterization Using Polarimetric C-Band SAR , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Koreen Millard,et al.  On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping , 2015, Remote. Sens..

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

[18]  Emanuele Della Valle,et al.  An Introduction to Information Retrieval , 2013 .

[19]  Yun Zhang,et al.  Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery , 2018, Remote. Sens..

[20]  K. Todd,et al.  Automated discrimination of upland and wetland using terrain derivatives , 2007 .

[21]  Xin Liu,et al.  Self-Error-Correcting Convolutional Neural Network for Learning with Noisy Labels , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[22]  Brian Brisco,et al.  The integration of optical, topographic, and radar data for wetland mapping in northern Minnesota , 2011 .

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[24]  Alisa L. Gallant,et al.  The Challenges of Remote Monitoring of Wetlands , 2015, Remote. Sens..

[25]  Fan Yang,et al.  Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  W Parkinson,et al.  Influence of sample distribution and prior probability adjustment on land cover classification , 2016 .

[27]  Rogério Schmidt Feris,et al.  A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection , 2016, ECCV.

[28]  Robert H. Fraser,et al.  Monitoring land cover change and ecological integrity in Canada's national parks , 2009 .

[29]  Joseph F. Knight,et al.  Influence of Multi-Source and Multi-Temporal Remotely Sensed and Ancillary Data on the Accuracy of Random Forest Classification of Wetlands in Northern Minnesota , 2013, Remote. Sens..

[30]  Jeffrey S. Evans,et al.  Using a multiscale, probabilistic approach to identify spatial-temporal wetland gradients , 2016 .

[31]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Jin Chen,et al.  Global land cover mapping at 30 m resolution: A POK-based operational approach , 2015 .

[33]  Eric S. Kasischke,et al.  Mapping boreal peatland ecosystem types from multitemporal radar and optical satellite imagery , 2017 .

[34]  S. Franklin,et al.  Classification of wetland habitat and vegetation communities using multi-temporal Ikonos imagery in southern Saskatchewan , 2002 .

[35]  J. Gibbs.  Wetland Loss and Biodiversity Conservation , 2000 .

[36]  Joanne C. White,et al.  Disturbance-Informed Annual Land Cover Classification Maps of Canada's Forested Ecosystems for a 29-Year Landsat Time Series , 2018 .

[37]  Matthew S. Nokleby,et al.  Learning Deep Networks from Noisy Labels with Dropout Regularization , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[38]  Richard A. Fournier,et al.  An object-based method to map wetland using RADARSAT-1 and Landsat ETM images: test case on two sites in Quebec, Canada , 2007 .

[39]  Rasim Latifovic,et al.  Circa 2010 Land Cover of Canada: Local Optimization Methodology and Product Development , 2017, Remote. Sens..

[40]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  James D. Wickham,et al.  Thematic accuracy assessment of the 2011 National Land Cover Database (NLCD). , 2017, Remote sensing of environment.

[42]  Luisa Verdoliva,et al.  Land Use Classification in Remote Sensing Images by Convolutional Neural Networks , 2015, ArXiv.

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

[44]  Keiji Yanai,et al.  Simultaneous estimation of food categories and calories with multi-task CNN , 2017, 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA).

[45]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Jitendra Malik,et al.  Beyond Skip Connections: Top-Down Modulation for Object Detection , 2016, ArXiv.

[47]  Laura L. Bourgeau-Chavez,et al.  Improving Wetland Characterization with Multi-Sensor, Multi-Temporal SAR and Optical/Infrared Data Fusion , 2009 .

[48]  Rasim Latifovic,et al.  Development and assessment of a 250 m spatial resolution MODIS annual land cover time series (2000–2011) for the forest region of Canada derived from change-based updating , 2014 .

[49]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[50]  Pheng-Ann Heng,et al.  SINet: A Scale-Insensitive Convolutional Neural Network for Fast Vehicle Detection , 2018, IEEE Transactions on Intelligent Transportation Systems.

[51]  Rick L. Lawrence,et al.  Change detection of wetland ecosystems using Landsat imagery and change vector analysis , 2007, Wetlands.

[52]  Fuchun Sun,et al.  HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[53]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[54]  J. Seibert,et al.  On the calculation of the topographic wetness index: evaluation of different methods based on field observations , 2005 .

[55]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.