Predicting Species Cover of Marine Macrophyte and Invertebrate Species Combining Hyperspectral Remote Sensing, Machine Learning and Regression Techniques

In order to understand biotic patterns and their changes in nature there is an obvious need for high-quality seamless measurements of such patterns. If remote sensing methods have been applied with reasonable success in terrestrial environment, their use in aquatic ecosystems still remained challenging. In the present study we combined hyperspectral remote sensing and boosted regression tree modelling (BTR), an ensemble method for statistical techniques and machine learning, in order to test their applicability in predicting macrophyte and invertebrate species cover in the optically complex seawater of the Baltic Sea. The BRT technique combined with remote sensing and traditional spatial modelling succeeded in identifying, constructing and testing functionality of abiotic environmental predictors on the coverage of benthic macrophyte and invertebrate species. Our models easily predicted a large quantity of macrophyte and invertebrate species cover and recaptured multitude of interactions between environment and biota indicating a strong potential of the method in the modelling of aquatic species in the large variety of ecosystems.

[1]  Erik Bonsdorff,et al.  Small-scale spatial structure of Baltic Sea zoobenthos—inferring processes from patterns , 2002 .

[2]  P. Chambers,et al.  The interaction between water movement, sediment dynamics and submersed macrophytes , 2001, Hydrobiologia.

[3]  D. Rocchini.  Effects of spatial and spectral resolution in estimating ecosystem α-diversity by satellite imagery , 2007 .

[4]  L. Kautsky.  Life strategies of aquatic soft bottom macrophytes , 1988 .

[5]  J. Elith,et al.  Species Distribution Models: Ecological Explanation and Prediction Across Space and Time , 2009 .

[6]  J. Kotta,et al.  Influence of the local abiotic environment, weather and regional nutrient loading on macrobenthic invertebrate feeding groups in a shallow brackish water ecosystem. , 2009 .

[7]  Han Olff,et al.  Positive Feedbacks in Seagrass Ecosystems – Evidence from Large-Scale Empirical Data , 2011, PloS one.

[8]  G. Kendrick,et al.  Multi‐scale spatial patterns of three seagrass species with different growth dynamics , 2008 .

[9]  G. De’ath.  Boosted trees for ecological modeling and prediction. , 2007, Ecology.

[10]  J. Randerson,et al.  Primary production of the biosphere: integrating terrestrial and oceanic components , 1998, Science.

[11]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[12]  John M. Melack,et al.  Remote sensing of aquatic vegetation: theory and applications , 2008, Environmental monitoring and assessment.

[13]  T. Hamazaki.  SPATIOTEMPORAL PREDICTION MODELS OF CETACEAN HABITATS IN THE MID‐WESTERN NORTH ATLANTIC OCEAN (FROM CAPE HATTERAS, NORTH CAROLINA, U.S.A. TO NOVA SCOTIA, CANADA) , 2002 .

[14]  Martin Isaeus.  Factors structuring Fucus communities at open and complex coastlines in the Baltic Sea , 2004 .

[15]  Tore Söderqvist,et al.  Ecosystem Goods and Services from Swedish Coastal Habitats: Identification, Valuation, and Implications of Ecosystem Shifts , 2007, Ambio.

[16]  Fred A. Kruse,et al.  The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data , 1993 .

[17]  Tiit Kutser,et al.  Mapping coloured dissolved organic matter concentration in coastal waters , 2009 .

[18]  T. Kutser,et al.  Relating Remotely Sensed Optical Variability to Marine Benthic Biodiversity , 2013, PloS one.

[19]  John M. Melack,et al.  Spatial and temporal variability of macrophyte cover and productivity in the eastern Amazon floodplain: A remote sensing approach , 2010 .

[20]  M. Kleiber.  Body size and metabolism , 1932 .

[21]  R. Carignan,et al.  An evaluation of approaches used to determine the distribution and biomass of emergent and submerged aquatic macrophytes over large spatial scales , 2003 .

[22]  Sarah C. Goslee,et al.  Extending community ecology to landscapes , 2002 .

[23]  John D. Hedley,et al.  A remote sensing method for resolving depth and subpixel composition of aquatic benthos , 2003 .

[24]  F. P. Ojeda,et al.  Effects of canopy removal on the understory algal community structure of coastal forests of Macrocystispyrifera from southern South America , 2006 .

[25]  J. Kotta,et al.  Field Measurements on the Variability in Biodeposition and Estimates of Grazing Pressure of Suspension-Feeding Bivalves in the Northern Baltic Sea , 2005 .

[26]  Stuart R. Phinn,et al.  Integrating Quickbird Multi-Spectral Satellite and Field Data: Mapping Bathymetry, Seagrass Cover, Seagrass Species and Change in Moreton Bay, Australia in 2004 and 2007 , 2011, Remote. Sens..

[27]  R. Mac Nally,et al.  Regression and model-building in conservation biology, biogeography and ecology: The distinction between – and reconciliation of – ‘predictive’ and ‘explanatory’ models , 2000 .

[28]  J. Heine.  Effects of ice scour on the structure of sublittoral marine algal assemblages of st. lawrence and st. matthew islands alaska usa , 1989 .

[29]  Wahl. Martin.  Marine Hard Bottom Communities , 2009 .

[30]  L. Håkanson,et al.  Suspended particulate matter (SPM) in the baltic Sea-New empirical data and models , 2005 .

[31]  A. C. Seijmonsbergen,et al.  Improved landsat-based forest mapping in steep mountainous terrain , 2003 .

[32]  Alberto Jiménez-Valverde,et al.  Not as good as they seem: the importance of concepts in species distribution modelling , 2008 .

[33]  S. Olenin,et al.  The comparative roles of suspension-feeders in ecosystems , 2005 .

[34]  Mathias J. M. Römkens,et al.  Wave formation on a shallow layer of flowing grains , 2000, Journal of Fluid Mechanics.

[35]  M. Pedersen,et al.  Nutrient control of algal growth in estuarine waters: Nutrient limitation and the importance of nitrogen requirements and nitrogen storage among phytoplankton and species of macroalgae. , 1996 .

[36]  W. Geyer,et al.  The importance of boundary‐layer flows in supplying phytoplankton to the benthic suspension feeder, Mytilus edulis L. , 1989 .

[37]  Georg Martin,et al.  Feasibility of hyperspectral remote sensing for mapping benthic macroalgal cover in turbid coastal waters—a Baltic Sea case study , 2006 .

[38]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[39]  Andrew R. Watkinson,et al.  Large‐scale ecology and hydrology: an introductory perspective from the editors of the Journal of Applied Ecology , 2000 .

[40]  F. P. Ojeda,et al.  Effects of canapy removal on the understory algal community structure of coastal forests of Macrocystis pyrifera from southern South America , 1984 .

[41]  U. Schiewer.  Ecology of Baltic coastal waters , 2008 .

[42]  I. Pinto,et al.  Temporal stability of European rocky shore assemblages : variation across a latitudinal gradient and the role of habitat-formers , 2012 .

[43]  David L.B. Jupp,et al.  On the possibility of mapping living corals to the species level based on their optical signatures , 2006 .

[44]  Jonne Kotta,et al.  Detecting patterns and changes in a complex benthic environment of the Baltic Sea , 2011 .

[45]  D. Hermus,et al.  Effects of water dynamics on Zostera marina: transplantation experiments in the intertidal Dutch Wadden Sea , 2000 .

[46]  G. Kendrick,et al.  Modelling distribution of marine benthos from hydroacoustics and underwater video , 2008 .

[47]  K. Herkül,et al.  Effects of physical disturbance, isolation and key macrozoobenthic species on community development, recolonisation and sedimentation processes , 2006 .

[48]  R. Lafortezza,et al.  Sensitivity of landscape measurements to changing grain size for fine-scale design and management , 2007, Landscape and Ecological Engineering.

[49]  Robert Aps,et al.  Field measurements of spectral backscattering coefficient of the Baltic Sea and boreal lakes , 2009 .

[50]  P. Ralph,et al.  Impact of light limitation on seagrasses , 2007 .

[51]  T. Kutser,et al.  Spectral library of macroalgae and benthic substrates in Estonian coastal waters , 2006, Proceedings of the Estonian Academy of Sciences. Biology. Ecology.

[52]  Klaus Janke,et al.  Biological interactions and their role in community structure in the rocky intertidal of Helgoland (German Bight, North Sea) , 1990, Helgoländer Meeresuntersuchungen.

[53]  Gary A. Kendrick,et al.  Probabilistic large-area mapping of seagrass species distributions , 2007 .

[54]  Mike P. Austin,et al.  Continuum Concept, Ordination Methods, and Niche Theory , 1985 .

[55]  D. Schiel,et al.  Patterns Along Environmental Gradients , 2009 .

[56]  A. Ricciardi,et al.  Global patterns of macroinvertebrate biomass in marine intertidal communities , 1999 .

[57]  G. Kendrick,et al.  Changes in seagrass cover on Success and Parmelia Banks, Western Australia between 1965 and 1995 , 2000 .

[58]  T. Kutser,et al.  Assessment of AHS (Airborne Hyperspectral Scanner) sensor to map macroalgal communities on the Ría de vigo and Ría de Aldán coast (NW Spain) , 2012 .

[59]  E. Harvey,et al.  Combining environmental gradients to explain and predict the structure of demersal fish distributions , 2010 .

[60]  Ashutosh Kumar Singh,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2010 .

[61]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[62]  Henrik Madsen,et al.  Introduction to General and Generalized Linear Models , 2010 .

[63]  G. Foody.  GIS: biodiversity applications , 2008 .

[64]  Angela Lee,et al.  Perspectives on … Environmental Systems Research Institute, Inc , 1997 .

[65]  K. Herkül,et al.  Contribution of scale-dependent environmental variability on the biomass patterns of drift algae and associated invertebrates in the Gulf of Riga, northern Baltic Sea , 2008 .

[66]  Patrick Bogaert,et al.  An object-based change detection method accounting for temporal dependences in time series with medium to coarse spatial resolution , 2008 .

[67]  Chuanmin Hu,et al.  Use of In Situ and Airborne Reflectance for Scaling-Up Spectral Discrimination of Coral Reef Macroalgae from Species to Communities , 2004 .

[68]  J. Kotta,et al.  Regional-Scale Patterns , 2009 .

[69]  S. Díaz,et al.  Vive la différence: plant functional diversity matters to ecosystem processes , 2001 .

[70]  S. Phinn,et al.  Spectral unmixing of coral reef benthos under ideal conditions , 2004, Coral Reefs.

[71]  R. Macarthur.  The Problem of Pattern and Scale in Ecology: The Robert H. MacArthur Award Lecture , 2005 .

[72]  F. Tuya,et al.  A Meta-Analysis of Seaweed Impacts on Seagrasses: Generalities and Knowledge Gaps , 2012, PloS one.

[73]  Georg Martin,et al.  Gulf of Riga and Pärnu Bay , 2008 .

[74]  Georg Martin,et al.  Effect of observation method on the perception of community structure and water quality in a brackish water ecosystem , 2009 .

[75]  F. Volpe,et al.  The influence of principal component analysis on the spatial structure of a multispectral dataset , 1999 .

[76]  D. Rocchini,et al.  Does using species abundance data improve estimates of species diversity from remotely sensed spectral heterogeneity , 2010 .

[77]  Christopher O. Justice,et al.  Towards operational monitoring of terrestrial systems by moderate-resolution remote sensing , 2002 .

[78]  J. Kotta,et al.  Epiphytes and associated fauna on the brown alga Fucus vesiculosus in the Baltic and the North Seas in relation to different abiotic and biotic variables , 2011 .

[79]  T. Kutser,et al.  Mapping Bottom Type and Water Depth in Shallow Coastal Waters with Satellite Remote Sensing , 2024, Journal of Coastal Research.