Development of spectral-phenological features for deep learning to understand Spartina alterniflora invasion

Abstract Invasive Spartina alterniflora (S. alterniflora), a native riparian species in the U.S. Gulf of Mexico, has led to serious degradation to the ecosystem and biodiversity as well as economic losses since it was introduced to China in 1979. Although multi-temporal remote sensing offers unique capability to monitor S. alterniflora over large areas and long time periods, three major hurdle exist: (1) in the coastal zone where S. alterniflora occupies, frequent cloud coverage reduces the number of available images that can be used; (2) prominent spectral variations exist within the S. alterniflora due to phonological variations; (3) poor spectral separability between S. alterniflora and its co-dominant native species is often presented in the territories where S. alterniflora intruded in. To articulate these questions, we proposed a new pixel-based phenological feature composite method (Ppf-CM) based on Google Earth Engine. The Ppf-CM method was brainstormed to battle the aforementioned three hurdles as the basic unit for extracting phonological feature is individual pixel in lieu of an entire image scene. With the Ppf-CM-derived phenological feature as inputs, we took a step further to investigate the performance of the latest deep learning method as opposed to that of the conventional support vector machine (SVM); Lastly, we strive to understand how S. alterniflora has changed its spatial distribution in the Beibu Gulf of China from 1995 to 2017. As a result, we found (1) the developed Ppf-CM method can mitigate the phonological variation and augment the spectral separability between S. alterniflora and the background species regardless of the significant cloud coverage in the study area; (2) deep learning, compared to SVM, presented better potentials for incorporating the new phenological features generated from the Ppf-CM method; and (3) for the first time, we discovered a S. alterniflora invasion outbreak occurred during 1996–2001.

[1]  Mutlu Ozdogan,et al.  Large area cropland extent mapping with Landsat data and a generalized classifier , 2018, Remote Sensing of Environment.

[2]  Li-Quan Zhang,et al.  An experimental study on physical controls of an exotic plant Spartina alterniflora in Shanghai, China , 2008 .

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

[4]  Yuqi Bai,et al.  Mapping major land cover dynamics in Beijing using all Landsat images in Google Earth Engine , 2017 .

[5]  Giles M. Foody,et al.  A relative evaluation of multiclass image classification by support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Bo Li,et al.  Linear spectral mixture analysis of Landsat TM data for monitoring invasive exotic plants in estuarine wetlands , 2010 .

[7]  B. Bradley.  Remote detection of invasive plants: a review of spectral, textural and phenological approaches , 2014, Biological Invasions.

[8]  Runhe Shi,et al.  Integrating pan-sharpening and classifier ensemble techniques to map an invasive plant (Spartina alterniflora) in an estuarine wetland using Landsat 8 imagery , 2016 .

[9]  John C. Callaway,et al.  The introduction and spread of smooth cordgrass (Spartina alterniflora) in South San Francisco Bay , 1992 .

[10]  Sergey Levine,et al.  Deep spatial autoencoders for visuomotor learning , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Kaishan Song,et al.  Landsat-Based Estimation of Mangrove Forest Loss and Restoration in Guangxi Province, China, Influenced by Human and Natural Factors , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[12]  Guanghui Lin,et al.  Interactions between mangroves and exotic Spartina in an anthropogenically disturbed estuary in southern China. , 2012, Ecology.

[13]  P. Hostert,et al.  Mapping patterns of urban development in Ouagadougou, Burkina Faso, using machine learning regression modeling with bi-seasonal Landsat time series , 2018, Remote Sensing of Environment.

[14]  Yang Shao,et al.  An evaluation of time-series smoothing algorithms for land-cover classifications using MODIS-NDVI multi-temporal data , 2016 .

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

[16]  T. Esch,et al.  New dimensions of urban landscapes: The spatio-temporal evolution from a polynuclei area to a mega-region based on remote sensing data , 2014 .

[17]  J. Qiu.  China’s cordgrass plan is ‘overkill’ , 2013, Nature.

[18]  Le Wang,et al.  Landsat time series-based multiyear spectral angle clustering (MSAC) model to monitor the inter-annual leaf senescence of exotic saltcedar , 2018 .

[19]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[20]  D. Roy,et al.  Monitoring conterminous United States (CONUS) land cover change with Web-Enabled Landsat Data (WELD) , 2014 .

[21]  Zhe Zhu,et al.  Mapping forest change using stacked generalization: An ensemble approach , 2018 .

[22]  A. Huete,et al.  MODIS Vegetation Index Compositing Approach: A Prototype with AVHRR Data , 1999 .

[23]  P. Vitousek,et al.  INTRODUCED SPECIES: A SIGNIFICANT COMPONENT OF HUMAN-CAUSED GLOBAL CHANGE , 1997 .

[24]  C. Justice,et al.  High-Resolution Global Maps of 21st-Century Forest Cover Change , 2013, Science.

[25]  A. Skidmore,et al.  Spectral discrimination of vegetation types in a coastal wetland , 2003 .

[26]  A. Kolker,et al.  Anthropogenic and climate-change impacts on salt marshes of Jamaica Bay, New York City , 2002, Wetlands.

[27]  P. Beckschäfer.  Obtaining rubber plantation age information from very dense Landsat TM & ETM + time series data and pixel-based image compositing , 2017 .

[28]  Nancy F. Glenn,et al.  Multitemporal spectral analysis for cheatgrass (Bromus tectorum) classification , 2009 .

[29]  Giorgos Mountrakis,et al.  Effect of classifier selection, reference sample size, reference class distribution and scene heterogeneity in per-pixel classification accuracy using 26 Landsat sites , 2018 .

[30]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[31]  Yoshihiko Mochizuki,et al.  Surface object recognition with CNN and SVM in Landsat 8 images , 2015, 2015 14th IAPR International Conference on Machine Vision Applications (MVA).

[32]  Ibon Galparsoro,et al.  Coastal and estuarine habitat mapping, using LIDAR height and intensity and multi-spectral imagery , 2008 .

[33]  Zhe Zhu,et al.  Cloud detection algorithm comparison and validation for operational Landsat data products , 2017 .

[34]  Jie Zhang,et al.  Monitoring the Invasion of Smooth Cordgrass Spartina alterniflora within the Modern Yellow River Delta Using Remote Sensing , 2019, Journal of Coastal Research.

[35]  Cheng Wang,et al.  Mapping mixed vegetation communities in salt marshes using airborne spectral data , 2007 .

[36]  Joanne C. White,et al.  Generation of dense time series synthetic Landsat data through data blending with MODIS using a spatial and temporal adaptive reflectance fusion model. , 2009 .

[37]  Jianbo Lu,et al.  Spatial distribution of an invasive plant Spartina alterniflora and its potential as biofuels in China. , 2013 .

[38]  Wiebe Nijland,et al.  Satellite remote sensing of canopy-forming kelp on a complex coastline: A novel procedure using the Landsat image archive , 2019, Remote Sensing of Environment.

[39]  E. Peterson.  Estimating cover of an invasive grass (Bromus tectorum) using tobit regression and phenology derived from two dates of Landsat ETM+ data , 2005 .

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

[41]  E. Bernhardt,et al.  River and Riparian Restoration in the Southwest: Results of the National River Restoration Science Synthesis Project , 2007 .

[42]  R. Congalton,et al.  Integrating cloud-based workflows in continental-scale cropland extent classification , 2018, Remote Sensing of Environment.

[43]  Mark A. Friedl,et al.  Linking near-surface and satellite remote sensing measurements of deciduous broadleaf forest phenology , 2012 .

[44]  Jefersson Alex dos Santos,et al.  Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[45]  Sunil Kumar,et al.  Mapping Invasive Tamarisk (Tamarix): A Comparison of Single-Scene and Time-Series Analyses of Remotely Sensed Data , 2009, Remote. Sens..

[46]  P. Shafroth,et al.  Dominance of non-native riparian trees in western USA , 2005, Biological Invasions.

[47]  S. Pennings,et al.  Biotic homogenization of wetland nematode communities by exotic Spartina alterniflora in China. , 2019, Ecology.

[48]  Congcong Li,et al.  Stacked Autoencoder-based deep learning for remote-sensing image classification: a case study of African land-cover mapping , 2016 .

[49]  A. Hastings,et al.  Use of lidar to study changes associated with Spartina invasion in San Francisco bay marshes , 2006 .

[50]  Mingming Jia,et al.  Rapid Invasion of Spartina alterniflora in the Coastal Zone of Mainland China: New Observations from Landsat OLI Images , 2018, Remote. Sens..

[51]  Huawei Wan,et al.  Monitoring the Invasion of Spartina alterniflora Using Very High Resolution Unmanned Aerial Vehicle Imagery in Beihai, Guangxi (China) , 2014, TheScientificWorldJournal.

[52]  Raymond F. Kokaly,et al.  Mapping changing distributions of dominant species in oil-contaminated salt marshes of Louisiana using imaging spectroscopy , 2016 .

[53]  Z. Quan,et al.  Effects of Spartina alterniflora invasion on the communities of methanogens and sulfate-reducing bacteria in estuarine marsh sediments , 2013, Front. Microbiol..

[54]  Lorenzo Bruzzone,et al.  The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas. , 2007 .

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

[56]  Jiaping Wu,et al.  Monitoring the Invasion of Spartina alterniflora from 1993 to 2014 with Landsat TM and SPOT 6 Satellite Data in Yueqing Bay, China , 2015, PloS one.

[57]  Michael Sawada,et al.  A comparison of classification algorithms using Landsat-7 and Landsat-8 data for mapping lithology in Canada’s Arctic , 2015 .

[58]  Adriaan Van Niekerk,et al.  Evaluation of a rule-based compositing technique for Landsat-5 TM and Landsat-7 ETM+ images , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[59]  Elijah W. Ramsey,et al.  Marsh dieback, loss, and recovery mapped with satellite optical, airborne polarimetric radar, and field data , 2014 .

[60]  Xiaolin Zhu,et al.  An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions , 2010 .

[61]  A. Gitelson,et al.  Non‐destructive optical detection of pigment changes during leaf senescence and fruit ripening , 1999 .

[62]  Mingming Jia,et al.  Monitoring the Invasion of Spartina alterniflora Using Multi-source High-resolution Imagery in the Zhangjiang Estuary, China , 2017, Remote. Sens..

[63]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[64]  D. Lobell,et al.  Landsat-based classification in the cloud: An opportunity for a paradigm shift in land cover monitoring , 2017 .

[65]  Bin Zhao,et al.  Spectral Discrimination of the Invasive Plant Spartina alterniflora at Multiple Phenological Stages in a Saltmarsh Wetland , 2013, PloS one.

[66]  Joanne C. White,et al.  Pixel-Based Image Compositing for Large-Area Dense Time Series Applications and Science , 2014 .

[67]  Li Wang,et al.  The Tidal Marsh Inundation Index (TMII): An inundation filter to flag flooded pixels and improve MODIS tidal marsh vegetation time-series analysis , 2017 .

[68]  Johan Oszwald,et al.  Use of bi-Seasonal Landsat-8 Imagery for Mapping Marshland Plant Community Combinations at the Regional Scale , 2015, Wetlands.

[69]  George L. Geissler,et al.  Mapping the dynamics of eastern redcedar encroachment into grasslands during 1984–2010 through PALSAR and time series Landsat images , 2017 .

[70]  Patrick Hostert,et al.  A Pixel-Based Landsat Compositing Algorithm for Large Area Land Cover Mapping , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[71]  M. Marconcini,et al.  Normalized Difference Flood Index for rapid flood mapping: Taking advantage of EO big data , 2018 .

[72]  Stephen V. Stehman,et al.  Global bare ground gain from 2000 to 2012 using Landsat imagery , 2017 .

[73]  Wei Gao,et al.  Phenology-based Spartina alterniflora mapping in coastal wetland of the Yangtze Estuary using time series of GaoFen satellite no. 1 wide field of view imagery , 2017 .

[74]  Le Wang,et al.  Incorporating plant phenological trajectory in exotic saltcedar detection with monthly time series of Landsat imagery , 2016 .

[75]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[76]  Zongming Wang,et al.  A New Vegetation Index to Detect Periodically Submerged Mangrove Forest Using Single-Tide Sentinel-2 Imagery , 2019, Remote. Sens..

[77]  C. Hladik,et al.  Salt Marsh Elevation and Habitat Mapping Using Hyperspectral and LIDAR Data , 2013 .

[78]  Chen Shi,et al.  Comparison of UAV and WorldView-2 imagery for mapping leaf area index of mangrove forest , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[79]  Alfred Stein,et al.  Quantification of the Effects of Land-Cover-Class Spectral Separability on the Accuracy of Markov-Random-Field-Based Superresolution Mapping , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[80]  Le Wang,et al.  Phenology-guided saltcedar (Tamarix spp.) mapping using Landsat TM images in western U.S. , 2016 .

[81]  H. Mooney,et al.  Disruption of ecosystem processes in western North America by invasive species , 2004 .

[82]  Pei Qin,et al.  The positive and negative effects of exotic Spartina alterniflora in China , 2009 .

[83]  P. Mather,et al.  Classification Methods for Remotely Sensed Data , 2001 .

[84]  J. Mustard,et al.  Green leaf phenology at Landsat resolution: Scaling from the field to the satellite , 2006 .

[85]  D. Roy,et al.  Web-enabled Landsat Data (WELD): Landsat ETM+ composited mosaics of the conterminous United States , 2010 .

[86]  Nicholas C. Coops,et al.  Mass data processing of time series Landsat imagery: pixels to data products for forest monitoring , 2016, Int. J. Digit. Earth.

[87]  Bo Du,et al.  Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art , 2016, IEEE Geoscience and Remote Sensing Magazine.