Predicting Microhabitat Suitability for an Endangered Small Mammal Using Sentinel-2 Data

Accurate mapping is a main challenge for endangered small-sized terrestrial species. Freely available spatio-temporal data at high resolution from multispectral satellite offer excellent opportunities for improving predictive distribution models of such species based on fine-scale habitat features, thus making it easier to achieve comprehensive biodiversity conservation goals. However, there are still few examples showing the utility of remote-sensing-based products in mapping microhabitat suitability for small species of conservation concern. Here, we address this issue using Sentinel-2 sensor-derived habitat variables, used in combination with more commonly used explanatory variables (e.g., topography), to predict the distribution of the endangered Cabrera vole (Microtus cabrerae) in agrosilvopastorial systems. Based on vole surveys conducted in two different seasons over a ~176,000 ha landscape in Southern Portugal, we assessed the significance of each predictor in explaining Cabrera vole occurrence using the Boruta algorithm, a novel Random forest variant for dealing with high dimensionality of explanatory variables. Overall, results showed a strong contribution of Sentinel-2-derived variables for predicting microhabitat suitability of Cabrera voles. In particular, we found that photosynthetic activity (NDI45), specific spectral signal (SWIR1), and landscape heterogeneity (Rao’s Q) were good proxies of Cabrera voles’ microhabitat, mostly during temporally greener and wetter conditions. In addition to remote-sensing-based variables, the presence of road verges was also an important driver of voles’ distribution, highlighting their potential role as refuges and/or corridors. Overall, our study supports the use of remote-sensing data to predict microhabitat suitability for endangered small-sized species in marginal areas that potentially hold most of the biodiversity found in human-dominated landscapes. We believe our approach can be widely applied to other species, for which detailed habitat mapping over large spatial extents is difficult to obtain using traditional descriptors. This would certainly contribute to improving conservation planning, thereby contributing to global conservation efforts in landscapes that are managed for multiple purposes.

[1]  A. Mira,et al.  Vegetation analysis in colonies of an endangered rodent, the Cabrera vole (Microtus cabrerae), in southern Portugal , 2006, Ecological Research.

[2]  Laurence Hubert-Moy,et al.  Evaluation of Sentinel-2 time-series for mapping floodplain grassland plant communities , 2019, Remote Sensing of Environment.

[3]  P. Levelt,et al.  ESA's sentinel missions in support of Earth system science , 2012 .

[4]  A. Coffin.  From roadkill to road ecology : a review of the ecological effects of roads , 2007 .

[5]  T. Pinto-Correia,et al.  Exploring the use of landscape as the basis for the identification of High Nature Value farmland: a case-study in the Portuguese montado. , 2012 .

[6]  S. Parsley.  Breaking the habit. , 1989, HealthTexas.

[7]  A. Mira,et al.  Environmental determinants of the distribution of the Cabrera vole (Microtus cabrerae) in Portugal: Implications for conservation , 2008 .

[8]  Mark Broich,et al.  Evaluating static and dynamic landscape connectivity modelling using a 25-year remote sensing time series , 2018, Landscape Ecology.

[9]  João F. Gonçalves,et al.  Assessing the multi-scale predictive ability of ecosystem functional attributes for species distribution modelling , 2018, PloS one.

[10]  Verónica Andreo,et al.  Rodents and satellites: Predicting mice abundance and distribution with Sentinel-2 data , 2019, Ecol. Informatics.

[11]  A. Mira,et al.  VEGETATION STRUCTURE AND COMPOSITION OF ROAD VERGE AND MEADOW SITES COLONIZED BY CABRERA VOLE (MICROTUS CABRERAE THOMAS) , 2007 .

[12]  Gabriel Navarro,et al.  Evaluation of forest fire on Madeira Island using Sentinel-2A MSI imagery , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[13]  P. Beja,et al.  Spatial population structure of the Cabrera vole in Mediterranean farmland: The relative role of patch and matrix effects , 2007 .

[14]  Witold R. Rudnicki,et al.  Feature Selection with the Boruta Package , 2010 .

[15]  S. Otto.  Adaptation, speciation and extinction in the Anthropocene , 2018, Proceedings of the Royal Society B.

[16]  Andrew K. Skidmore,et al.  Erratum to "Capturing the fugitive: Applying remote sensing to terrestrial animal distribution and diversity" [Int. J. Appl. Earth Observ. Geoinform. (2007) 1-20] , 2007, International Journal of Applied Earth Observation and Geoinformation.

[17]  J. Priotto,et al.  Effects of agroecosystem landscape complexity on small mammals: a multi-species approach at different spatial scales , 2019, Landscape Ecology.

[18]  Xuesong Han,et al.  Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence , 2017, PeerJ.

[19]  Pedro Beja,et al.  Conserving the Cabrera vole, Microtus cabrerae, in intensively used Mediterranean landscapes , 2006 .

[20]  Luis Alonso,et al.  Evaluation of Sentinel-2 Red-Edge Bands for Empirical Estimation of Green LAI and Chlorophyll Content , 2011, Sensors.

[21]  Paul F. Donald,et al.  Habitat connectivity and matrix restoration: the wider implications of agri‐environment schemes , 2006 .

[22]  R. Tingley,et al.  Conservation planners tend to ignore improved accuracy of modelled species distributions to focus on multiple threats and ecological processes , 2016 .

[23]  H. Jones,et al.  Remote Sensing of Vegetation: Principles, Techniques, and Applications , 2010 .

[24]  W. Thuiller,et al.  Predicting species distribution: offering more than simple habitat models. , 2005, Ecology letters.

[25]  Andrew K. Skidmore,et al.  Capturing the fugitive: Applying remote sensing to terrestrial animal distribution and diversity , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Ben Collen,et al.  Global effects of land use on local terrestrial biodiversity , 2015, Nature.

[27]  J. Evans,et al.  Modeling Species Distribution and Change Using Random Forest , 2011 .

[28]  Q. Wang,et al.  Modelling and spatial discrimination of small mammal assemblages: an example from western Sichuan (China). , 2009, Ecological modelling.

[29]  Duccio Rocchini,et al.  Will remote sensing shape the next generation of species distribution models? , 2015 .

[30]  N. Pettorelli,et al.  Using the satellite-derived NDVI to assess ecological responses to environmental change. , 2005, Trends in ecology & evolution.

[31]  Matthias Drusch,et al.  Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services , 2012 .

[32]  Peter M. Atkinson,et al.  A linearised pixel-swapping method for mapping rural linear land cover features from fine spatial resolution remotely sensed imagery , 2007, Comput. Geosci..

[33]  A. Melfi,et al.  Image fusion of Sentinel-2 and CBERS-4 satellites for mapping soil cover in the Wetlands of Pantanal , 2017 .

[34]  Gareth Jones,et al.  Ground validation of presence‐only modelling with rare species: a case study on barbastelles Barbastella barbastellus (Chiroptera: Vespertilionidae) , 2010 .

[35]  Onisimo Mutanga,et al.  Intra-and-Inter Species Biomass Prediction in a Plantation Forest: Testing the Utility of High Spatial Resolution Spaceborne Multispectral RapidEye Sensor and Advanced Machine Learning Algorithms , 2014, Sensors.

[36]  A. Bloom,et al.  Are Inventory Based and Remotely Sensed Above-Ground Biomass Estimates Consistent? , 2013, PloS one.

[37]  S. Godinho,et al.  Chapter 4 Changing Agriculture – Changing Landscapes: What is Going on in the High Valued Montado , 2013 .

[38]  F. Jiguet,et al.  Road network in an agrarian landscape: Potential habitat, corridor or barrier for small mammals? , 2015 .

[39]  Alex Zvoleff,et al.  Calculate Textures from Grey-Level Co-Occurrence Matrices(GLCMs) , 2015 .

[40]  J. Koprowski,et al.  Circuit theory to estimate natal dispersal routes and functional landscape connectivity for an endangered small mammal , 2017, Landscape Ecology.

[41]  Michael I. Miller,et al.  A comparison of random forest variable selection methods for classification prediction modeling , 2019, Expert Syst. Appl..

[42]  A. Mira,et al.  Factors influencing predator roadkills: The availability of prey in road verges. , 2019, Journal of environmental management.

[43]  K. Ekschmitt,et al.  Influence of grain size on species–habitat models , 2011 .

[44]  P. Ehrlich,et al.  Accelerated modern human–induced species losses: Entering the sixth mass extinction , 2015, Science Advances.

[45]  P. Sá-Sousa,et al.  Introducing the montado, the cork and holm oak agroforestry system of Southern Portugal , 2011, Agroforestry Systems.

[46]  Maïlys Lopes,et al.  Bee diversity in crop fields is influenced by remotely-sensed nesting resources in surrounding permanent grasslands , 2018, Ecological Indicators.

[47]  Cornelius Senf,et al.  Habitat metrics based on multi‐temporal Landsat imagery for mapping large mammal habitat , 2019, Remote Sensing in Ecology and Conservation.

[48]  Giovanni Rapacciuolo,et al.  Strengthening the contribution of macroecological models to conservation practice , 2018, Global Ecology and Biogeography.

[49]  D. Barrett,et al.  Estimating fractional cover of photosynthetic vegetation, non-photosynthetic vegetation and bare soil in the Australian tropical savanna region upscaling the EO-1 Hyperion and MODIS sensors. , 2009 .

[50]  P. Beja,et al.  Combining distribution modelling and non-invasive genetics to improve range shift forecasting , 2015 .

[51]  Daniel Fink,et al.  Correcting for bias in distribution modelling for rare species using citizen science data , 2018 .

[52]  M. L. Mathias,et al.  Is habitat selection by the Cabrera vole (Microtus cabrerae) related to food preferences , 2008 .

[53]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[54]  R. Escadafal,et al.  Remote sensing of arid soil surface color with Landsat thematic mapper , 1989 .

[55]  G. Matteucci,et al.  The reliability of a composite biodiversity indicator in predicting bird species richness at different spatial scales , 2016 .

[56]  M. Hardisky.  The Influence of Soil Salinity, Growth Form, and Leaf Moisture on-the Spectral Radiance of Spartina alterniflora Canopies , 2008 .

[57]  H. Rebelo,et al.  Painting maps with bats: species distribution modelling in bat research and conservation , 2016 .

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

[59]  M. Price.  High Nature Value Farming in Europe: 35 European Countries—Experiences and Perspectives , 2013 .

[60]  Matthew A. Williamson,et al.  Decision Support Frameworks and Tools for Conservation , 2018 .

[61]  António Mira,et al.  Microtus cabrerae (Rodentia: Cricetidae) , 2014 .

[62]  Domingo Alcaraz-Segura,et al.  Remotely Sensed Variables of Ecosystem Functioning Support Robust Predictions of Abundance Patterns for Rare Species , 2019, Remote. Sens..

[63]  J. Arroyo,et al.  Soil seed bank and floristic diversity in a forest-grassland mosaic in southern Spain , 2003 .

[64]  Nicolas Brodu,et al.  Super-Resolving Multiresolution Images With Band-Independent Geometry of Multispectral Pixels , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[65]  B. Gao.  NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space , 1996 .

[66]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[67]  Pedro J. Leitão,et al.  Improving Models of Species Ecological Niches: A Remote Sensing Overview , 2019, Front. Ecol. Evol..

[68]  Nathalie Pettorelli,et al.  Better together: Integrating and fusing multispectral and radar satellite imagery to inform biodiversity monitoring, ecological research and conservation science , 2017 .

[69]  A. Mira,et al.  Accounting for Connectivity Uncertainties in Predicting Roadkills: a Comparative Approach between Path Selection Functions and Habitat Suitability Models , 2019, Environmental Management.

[70]  N. Guiomar,et al.  Estimating tree canopy cover percentage in a mediterranean silvopastoral systems using Sentinel-2A imagery and the stochastic gradient boosting algorithm , 2018 .

[71]  A. Clevenger,et al.  Highway verges as habitat providers for small mammals in agrosilvopastoral environments , 2012, Biodiversity and Conservation.

[72]  W. Ripple,et al.  Extinction risk is most acute for the world’s largest and smallest vertebrates , 2017, Proceedings of the National Academy of Sciences.

[73]  Sunil Kumar,et al.  Effects of spatial heterogeneity on butterfly species richness in Rocky Mountain National Park, CO, USA , 2008, Biodiversity and Conservation.

[74]  Y. Wiersma,et al.  Predictive species and habitat modeling in landscape ecology : concepts and applications , 2011 .

[75]  S. Godinho,et al.  An analysis of the drivers that affect greening and browning trends in the context of pursuing land degradation-neutrality , 2019, Remote Sensing Applications: Society and Environment.

[76]  Corey J A Bradshaw,et al.  Synergies among extinction drivers under global change. , 2008, Trends in ecology & evolution.

[77]  Erle C. Ellis,et al.  Monitoring biodiversity in the Anthropocene using remote sensing in species distribution models , 2020 .

[78]  S. Martínez.  Les étages bioclimatiques de la végétation de la Péninsule Ibérique , 1980 .

[79]  J. Engler,et al.  Avian SDMs : current state, challenges, and opportunities , 2017 .

[80]  Jennifer A. Miller,et al.  Mapping Species Distributions: Spatial Inference and Prediction , 2010 .

[81]  S. Rambal,et al.  The dehesa system of southern Spain and Portugal as a natural ecosystem mimic , 1999, Agroforestry Systems.

[82]  Y. Handrich,et al.  Road-related landscape elements as a habitat: A main asset for small mammals in an intensive farming landscape , 2017 .

[83]  J. Ragle,et al.  IUCN Red List of Threatened Species , 2010 .

[84]  N. Guiomar,et al.  The effects of grazing management in montado fragmentation and heterogeneity , 2016, Agroforestry Systems.

[85]  N. Guiomar,et al.  Assessment of environment, land management, and spatial variables on recent changes in montado land cover in southern Portugal , 2016, Agroforestry Systems.

[86]  N. Pettorelli,et al.  The Normalized Difference Vegetation Index (NDVI): unforeseen successes in animal ecology , 2011 .

[87]  John Bell,et al.  A review of methods for the assessment of prediction errors in conservation presence/absence models , 1997, Environmental Conservation.

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

[89]  Duccio Rocchini,et al.  Measuring Rao's Q diversity index from remote sensing: An open source solution , 2017 .

[90]  R. Robinson,et al.  Integrating dynamic environmental predictors and species occurrences: Toward true dynamic species distribution models , 2019, Ecology and evolution.

[91]  Elia Quirós,et al.  Overstory-understory land cover mapping at the watershed scale: accuracy enhancement by multitemporal remote sensing analysis and LiDAR , 2019, Environmental Science and Pollution Research.

[92]  F. Moreira,et al.  Drivers of survival in a small mammal of conservation concern: An assessment using extensive genetic non-invasive sampling in fragmented farmland , 2019, Biological Conservation.

[93]  A. Lehmann,et al.  Using Niche‐Based Models to Improve the Sampling of Rare Species , 2006, Conservation biology : the journal of the Society for Conservation Biology.

[94]  J. Qi,et al.  Remote Sensing for Grassland Management in the Arid Southwest , 2006 .

[95]  Witold R. Rudnicki,et al.  The All Relevant Feature Selection using Random Forest , 2011, ArXiv.