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

Abstract

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 the 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 develop ecosystem maps from remote sensing data. We have developed a free and open‐access online remote sensing and environmental modelling application, the Remote Ecosystem Monitoring and Assessment Pipeline (Remap; https://remap-app.org), that enables volunteers, managers and scientists with little or no experience in remote sensing to generate classifications (maps) of land cover and land use change over time. Remap utilizes the geospatial data storage and analysis capacity of 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 (archival Landsat image composites) and climatic variables (precipitation, temperature) that are relevant to 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 min) 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.

Redlistr: tools for the IUCN Red Lists of ecosystems and threatened species in R

“…We mapped the distribution of the Aral Sea in 2001 and 2016 using REMAP (Supplementary material Appendix 1 Fig. S1; Murray et al 2018), imported the mapped distribution as a raster file into R, reprojected it to a suitable projected coordinate system (UTM40), and used the getArea function to determine its area in 2001 and 2016.…”

“…Such tools can also support iterative analysis of large datasets, streamline the reapplication of the criteria in subsequent assessments, and promote reproducible workflows in the red listing process. Currently, a range of tools for supporting red listing exist, each developed to meet different needs, including the geospatial conservation assessment tool (GeoCAT, Bachman et al 2011), RAMAS Red List (Akçakaya and Root 2007), and the remote ecosystem monitoring and assessment pipeline (REMAP, Murray et al 2018). However, as interactive software, these tools are limited in their ability to be applied iteratively, making repeat assessments difficult, and typically requiring specific input data formats.…”

A continental measure of urbanness predicts avian response to local urbanization

“…Fortunately, we now have access to broad-scale empirical datasets numbering millions of observations -generally collected through citizen science programs (Sullivan et al 2009, Prudic et al 2017, Van Horn et al 2018) -revolutionizing ecological and conservation research (Cooper et al 2007, Silvertown 2009, Pocock et al 2018. Simultaneously, the field of remote sensing is rapidly advancing (Kwok 2018), with increasing numbers of sensors, targeted missions for ecology (Wikelski et al 2007, Bioucas-Dias et al 2013, Jetz et al 2016, freely available data, and improved access to data analysis pipelines (Gorelick et al 2017, Murray et al 2018). These biodiversity data, combined with remotely sensed data, are increasing our understanding of biodiversity responses to environmental change (Pettorelli et al 2014a(Pettorelli et al , b, 2016, especially at macro-ecological scales (Hochachka and Fink 2012, La Sorte et al 2014, Jokimäki et al 2017, Horton et al 2018, including bird responses to urbanization (Bino et al 2008).…”

Changes in Vegetation on Mount Agung Volcano Bali Indonesia

“…Change in land use and land cover has been a significant aspect of environmental management and conservation planning for many decades (Murray et al 2017a). The role of remote sensing (RS) and geographical information systems (GIS) in ecology, especially in fire and vegetation management, has been recognized (Arno et al 1977;Chuvieco and Congalton 1989;Keane et al 2001;van Wilgen et al 2000;Verlinden and Laamanen 2006).…”

“…Land cover maps permit the portrayal of the distribution of ecosystems and land cover types, assessments of biodiversity and identification of areas undergoing loss, fragmentation, and degradation (Haddad et al 2015;Murray et al 2017a). Studies on vegetation and landscape of Mt.…”