Investigation on Perceptron Learning for Water Region Estimation Using Large-Scale Multispectral Images

Land cover classification and investigation of temporal changes are considered to be common applications of remote sensing. Water/non-water region estimation is one of the most fundamental classification tasks, analyzing the occurrence of water on the Earth’s surface. However, common remote sensing practices such as thresholding, spectral analysis, and statistical approaches are not sufficient to produce a globally adaptable water classification. The aim of this study is to develop a formula with automatically derived tuning parameters using perceptron neural networks for water/non-water region estimation, which we call the Perceptron-Derived Water Formula (PDWF), using Landsat-8 images. Water/non-water region estimates derived from PDWF were compared with three different approaches—Modified Normalized Difference Water Index (MNDWI), Automatic Water Extraction Index (AWEI), and Deep Convolutional Neural Network—using various case studies. Our proposed method outperforms all three approaches, showing a significant improvement in water/non-water region estimation. PDWF performance is consistently better even in cases of challenging conditions such as low reflectance due to hill shadows, building-shadows, and dark soils. Moreover, our study implemented a sunglint correction to adapt water/non-water region estimation over sunglint-affected pixels.

[1]  Mark A. Trigg,et al.  Development of a global ~90m water body map using multi-temporal Landsat images , 2015, Remote Sensing of Environment.

[2]  Wenying Su,et al.  Observations of reflectance distribution around sunglint from a coastal ocean platform. , 2002, Applied optics.

[3]  Kenton Lee,et al.  Landsat 8 Operational Land Imager On-Orbit Geometric Calibration and Performance , 2014, Remote. Sens..

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

[5]  Tri Dev Acharya,et al.  Application of J48 Decision Tree for the Identification of Water Bodies using Landsat 8 OLI Sensor , 2015, ECSA 2015.

[6]  B. Rundquist,et al.  Remote Detection of Prairie Pothole Ponds in the Devils Lake Basin, North Dakota , 2005 .

[7]  Venkatesh Raghavan,et al.  Satellite-Derived Bathymetry using Adaptive Geographically Weighted Regression Model , 2016 .

[8]  G. S. Dwarakish,et al.  Automatic Shoreline Detection and Change Detection Analysis of Netravati-GurpurRivermouth Using Histogram Equalization and Adaptive Thresholding Techniques☆ , 2015 .

[9]  Ali Selamat,et al.  Water Feature Extraction and Change Detection Using Multitemporal Landsat Imagery , 2014, Remote. Sens..

[10]  Wojciech Czarnecki,et al.  On Loss Functions for Deep Neural Networks in Classification , 2017, ArXiv.

[11]  Rasmus Fensholt,et al.  Automated Water Extraction Index: A new technique for surface water mapping using Landsat imagery , 2014 .

[12]  E. Work,et al.  Utilization of satellite data for inventorying prairie ponds and lakes , 1976 .

[13]  Bruno Smets,et al.  Dynamic Water Surface Detection Algorithm Applied on PROBA-V Multispectral Data , 2016, Remote. Sens..

[14]  Fred J. Tanis,et al.  Multispectral bathymetry using a simple physically based algorithm , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Werner Alpers,et al.  The role of the critical angle in brightness reversals on sunglint images of the sea surface , 2010 .

[16]  Stefan Dech,et al.  Results of the Global WaterPack: a novel product to assess inland water body dynamics on a daily basis , 2015 .

[17]  S. K. McFeeters.  The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features , 1996 .

[18]  L. Lymburner,et al.  Water observations from space: Mapping surface water from 25 years of Landsat imagery across Australia , 2016 .

[19]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[20]  K. Shadan,et al.  Available online: , 2012 .

[21]  D. Rundquist,et al.  THE RELATIONSHIP BETWEEN SUMMER‐SEASON RAINFALL EVENTS AND LAKE‐SURFACE AREA , 1987 .

[22]  Haruma Ishida,et al.  Development of an unbiased cloud detection algorithm for a spaceborne multispectral imager , 2009 .

[23]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[24]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Rajiv Kumar Nath,et al.  Water-Body Area Extraction from High Resolution Satellite Images-An Introduction , Review , and Comparison , 2010 .

[26]  Laurence C. Smith,et al.  Automated Image Registration for Hydrologic Change Detection in the Lake-Rich Arctic , 2008, IEEE Geoscience and Remote Sensing Letters.

[27]  C. Woodcock,et al.  Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4–7, 8, and Sentinel 2 images , 2015 .

[28]  C. Verpoorter,et al.  Automated mapping of water bodies using Landsat multispectral data , 2012 .

[29]  Jiaping Wu,et al.  Water body delineation using index composition and HIS transformation , 2012 .

[30]  Yu Oishi,et al.  Development of an Automatic Dynamic Global Water Mask Using Landsat-8 Images , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[31]  Li Shen,et al.  Water body extraction from Landsat ETM+ imagery using adaboost algorithm , 2010, 2010 18th International Conference on Geoinformatics.

[32]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[33]  Samantha J. Lavender,et al.  Sun Glint Correction of High and Low Spatial Resolution Images of Aquatic Scenes: a Review of Methods for Visible and Near-Infrared Wavelengths , 2009, Remote. Sens..

[34]  J. Pekel,et al.  High-resolution mapping of global surface water and its long-term changes , 2016, Nature.

[35]  Santiago Yepez,et al.  Retrieval of suspended sediment concentrations using Landsat-8 OLI satellite images in the Orinoco River (Venezuela) , 2017 .

[36]  Monica Rivas Casado,et al.  Automated Identification of River Hydromorphological Features Using UAV High Resolution Aerial Imagery , 2015, Sensors.

[37]  W. Munk,et al.  Measurement of the Roughness of the Sea Surface from Photographs of the Sun’s Glitter , 1954 .

[38]  Takeo Tadono,et al.  PRECISE GLOBAL DEM GENERATION BY ALOS PRISM , 2014 .

[39]  S. Shalev-Shwartz,et al.  Stochastic Gradient Descent , 2014 .

[40]  Markus Metz,et al.  GRASS GIS: A multi-purpose open source GIS , 2012, Environ. Model. Softw..

[41]  Shihong Du,et al.  Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[42]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[43]  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.

[44]  Min Feng,et al.  A global, high-resolution (30-m) inland water body dataset for 2000: first results of a topographic–spectral classification algorithm , 2016, Int. J. Digit. Earth.

[45]  Xiaogang Wang,et al.  Deeply learned face representations are sparse, selective, and robust , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Kenta Oono,et al.  Chainer : a Next-Generation Open Source Framework for Deep Learning , 2015 .

[47]  Jin Chen,et al.  Comparison and improvement of methods for identifying waterbodies in remotely sensed imagery , 2012 .

[48]  Bryan A. Franz,et al.  Sentinel-2 MultiSpectral Instrument (MSI) data processing for aquatic science applications: Demonstrations and validations , 2017 .