REMAP: An online remote sensing application for land cover classification and monitoring

Recent assessments of progress towards global conservation targets have revealed a paucity of indicators suitable for assessing the changing state of ecosystems. Moreover, land managers and planners are often unable to gain timely access to maps they need to support their routine decision-making. This deficiency is partly due to a lack of suitable data on ecosystem change, driven mostly by the considerable technical expertise needed to make ecosystem maps from remote sensing data. We have developed a free and open-access online remote sensing and environmental modelling application, REMAP (the remote ecosystem monitoring and assessment pipeline; https://remap-app.org) that enables volunteers, managers, and scientists with little or no experience in remote sensing to develop high-resolution classified maps of land cover and land use change over time. REMAP utilizes the geospatial data storage and analysis capacity of the Google Earth Engine, and requires only spatially resolved training data that define map classes of interest (e.g., ecosystem types). The training data, which can be uploaded or annotated interactively within REMAP, are used in a random forest classification of up to 13 publicly available predictor datasets to assign all pixels in a focal region to map classes. Predictor datasets available in REMAP represent topographic (e.g. slope, elevation), spectral (Landsat Archive image composites) and climatic variables (precipitation, temperature) that can inform on the distribution of ecosystems and land cover classes. The ability of REMAP to develop and export high-quality classified maps in a very short (<10 minute) time frame represents a considerable advance towards globally accessible and free application of remote sensing technology. By enabling access to data and simplifying remote sensing classifications, REMAP can catalyse the monitoring of land use and change to support environmental conservation, including developing inventories of biodiversity, identifying hotspots of ecosystem diversity, ecosystem-based spatial conservation planning, mapping ecosystem loss at local scales, and supporting environmental education initiatives.

[1]  Adam Lewis,et al.  Rapid, high-resolution detection of environmental change over continental scales from satellite data – the Earth Observation Data Cube , 2016, Int. J. Digit. Earth.

[2]  Belinda A. Margono,et al.  Humid tropical forest disturbance alerts using Landsat data , 2016 .

[3]  Curtis E. Woodcock,et al.  Time series analysis of satellite data reveals continuous deforestation of New England since the 1980s , 2016 .

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

[5]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[6]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[7]  Anthea L. Mitchell,et al.  Integrated Land Cover and Change Classifications , 2017 .

[8]  J. Kovacs,et al.  Large-scale dieback of mangroves in Australia’s Gulf of Carpentaria: a severe ecosystem response, coincidental with an unusually extreme weather event , 2017 .

[9]  T. Regan,et al.  The use of range size to assess risks to biodiversity from stochastic threats , 2017 .

[10]  D. Keith,et al.  Guidelines for the application of IUCN Red List of Ecosystems Categories and Criteria. Version 1.1 , 2017 .

[11]  Jan G. P. W. Clevers,et al.  Assessing the Accuracy of Remotely Sensed Data—Principles and Practices, Second edition, Russell G. Congalton, Kass Green. CRC Press, Taylor & Francis Group, Boca Raton, FL (2009), 183 pp., Price: $99.95, ISBN: 978-1-4200-5512-2 , 2009 .

[12]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[13]  Mark A. Burgman,et al.  Scientific Foundations for an IUCN Red List of Ecosystems , 2013, PloS one.

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

[15]  Ben Scott,et al.  Supporting Red List threat assessments with GeoCAT: geospatial conservation assessment tool , 2011, ZooKeys.

[16]  Ned Horning,et al.  Losing a jewel—Rapid declines in Myanmar’s intact forests from 2002-2014 , 2017, PloS one.

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

[18]  Haihua Shen,et al.  Rapid loss of lakes on the Mongolian Plateau , 2015, Proceedings of the National Academy of Sciences.

[19]  Damien Arvor,et al.  Earth Observation Data for Habitat Monitoring ( EODHaM ) system , 2014 .

[20]  Michael W. Beck,et al.  The role of ecosystems in coastal protection: Adapting to climate change and coastal hazards , 2014 .

[21]  Fabio Attorre,et al.  Vegetation mapping from high-resolution satellite images in the heterogeneous arid environments of Socotra Island (Yemen) , 2013 .

[22]  D. Gruner,et al.  Poleward expansion of mangroves is a threshold response to decreased frequency of extreme cold events , 2013, Proceedings of the National Academy of Sciences.

[23]  Hugh P. Possingham,et al.  Tracking the rapid loss of tidal wetlands in the Yellow Sea , 2014 .

[24]  R. Fuller,et al.  Protecting stopover habitat for migratory shorebirds in East Asia , 2015, Journal of Ornithology.

[25]  Calvin K. F. Lee,et al.  Redlistr: tools for the IUCN Red Lists of ecosystems and threatened species in R , 2019, Ecography.

[26]  S. Sarkar,et al.  Systematic conservation planning , 2000, Nature.

[27]  Paulo Pereira,et al.  Mapping the environment. , 2018, The Science of the total environment.

[28]  Ashbindu Singh,et al.  Status and distribution of mangrove forests of the world using earth observation satellite data , 2011 .

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

[30]  M. Hansen,et al.  The last frontiers of wilderness: Tracking loss of intact forest landscapes from 2000 to 2013 , 2017, Science Advances.

[31]  P. Mumby,et al.  Mangroves enhance the biomass of coral reef fish communities in the Caribbean , 2004, Nature.

[32]  Neil D. Burgess,et al.  Deforestation in an African biodiversity hotspot: extent, variation and the effectiveness of protected areas , 2013 .

[33]  Ellen I. Damschen,et al.  Habitat fragmentation and its lasting impact on Earth’s ecosystems , 2015, Science Advances.

[34]  Conghe Song,et al.  Long-term land cover dynamics by multi-temporal classification across the Landsat-5 record , 2013 .

[35]  Thomas R. Loveland,et al.  A review of large area monitoring of land cover change using Landsat data , 2012 .

[36]  R. Lucas,et al.  The Roles of Remote Sensing in Nature Conservation , 2017, Springer International Publishing.

[37]  R. Lucas,et al.  Aberystwyth University Distribution and Drivers of Global Mangrove Forest Change, 1996-2010 , 2017 .

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

[39]  T. John.  Geoscience information online; Queensland Department of Natural Resources and Mines , 2001 .

[40]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[41]  Mark A. Burgman,et al.  The IUCN Red List of Ecosystems: Motivations, Challenges, and Applications , 2015 .

[42]  Stuart R. Phinn,et al.  Continental Scale Mapping of Tidal Flats across East Asia Using the Landsat Archive , 2012, Remote. Sens..

[43]  David E. Knapp,et al.  Automated mapping of tropical deforestation and forest degradation: CLASlite , 2009 .

[44]  C. Ticehurst,et al.  Mangrove response to environmental change in Australia's Gulf of Carpentaria , 2016, Ecology and evolution.

[45]  Peter Leimgruber,et al.  Mapping Distinct Forest Types Improves Overall Forest Identification Based on Multi-Spectral Landsat Imagery for Myanmar's Tanintharyi Region , 2016, Remote. Sens..

[46]  Emily Nicholson,et al.  The role of satellite remote sensing in structured ecosystem risk assessments. , 2018, The Science of the total environment.

[47]  J. L. Parra,et al.  Very high resolution interpolated climate surfaces for global land areas , 2005 .

[48]  Nathalie Pettorelli,et al.  The Normalized Difference Vegetation Index , 2014 .

[49]  R. Lucas,et al.  Mapping changes in the largest continuous Amazonian mangrove belt using object-based classification of multisensor satellite imagery , 2013 .

[50]  D. Harvey.  The Last Frontiers , 2012 .

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

[52]  M. Spalding,et al.  A practical guide to the application of the IUCN Red List of Ecosystems criteria , 2015, Philosophical Transactions of the Royal Society B: Biological Sciences.

[53]  W. Bailey.  A practical guide to the application of AJNR guidelines for nomenclature and classification of lumbar disc pathology in Magnetic Resonance Imaging (MRI) , 2006 .