A wetland permanence classification tool to support prairie wetland conservation and policy implementation

Wetland permanence, the duration and frequency that surface water is present, affects biological communities and whether wetlands are protected under legislation in some jurisdictions. Wetland drainage in the Prairie Pothole Region (PPR) has changed the distribution of wetlands because smaller and more temporary wetlands are more likely to be drained. This change in distribution affects biodiversity and other wetland ecosystem services. In Manitoba, Canada, wetlands are treated differently under the Water Rights Act based on permanence classification and can either be drained with a simplified registration (temporary and ephemeral wetlands), drained with a permit requiring mitigation (seasonal wetlands), or are protected from drainage (semipermanent and permanent wetlands). To facilitate implementing a conservation program targeting the most vulnerable wetlands, we built a classification model using LiDAR and Sentinel‐2 data (1312 training observations). Our random forest model had 73% accuracy on 563 test observations and is applicable across the agricultural region of southwestern Manitoba. We predicted the wetland permanence class of 365,499 wetlands and built an online tool to help practitioners implement a conservation program that pays producers to conserve temporary and ephemeral wetlands. Our approach is applicable elsewhere in the PPR and other regions with variation in wetland permanence.

[1]  D. Robinson,et al.  Climate, land cover and topography: essential ingredients in predicting wetland permanence , 2022, Biogeosciences.

[2]  J. Evans,et al.  Testing the effect of wetland spatiotemporal variability on amphibian occurrence across scales , 2022 .

[3]  Tyler J. Lark,et al.  Natural climate solutions for Canada , 2021, Science Advances.

[4]  Lisa H. Elliott,et al.  The relative importance of wetland area versus habitat heterogeneity for promoting species richness and abundance of wetland birds in the Prairie Pothole Region, USA , 2019, The Condor.

[5]  Brian Brisco,et al.  Wetland hydroperiod classification in the western prairies using multitemporal synthetic aperture radar , 2018 .

[6]  Raymond Finocchiaro,et al.  Temperature and Hydrology Affect Methane Emissions from Prairie Pothole Wetlands , 2016, Wetlands.

[7]  P. G. Blendinger,et al.  Effect of habitat and landscape structure on waterbird abundance in wetlands of central Argentina , 2016, Wetlands Ecology and Management.

[8]  L. Alexander.  Science at the boundaries: scientific support for the Clean Water Rule , 2015, Freshwater Science.

[9]  Charles R. Lane,et al.  Geographically Isolated Wetlands are Important Biogeochemical Reactors on the Landscape , 2015 .

[10]  N. Basu,et al.  Signatures of human impact: size distributions and spatial organization of wetlands in the Prairie Pothole landscape. , 2014, Ecological applications : a publication of the Ecological Society of America.

[11]  Michael G. Anderson,et al.  Variation in mallard vital rates in Canadian Aspen Parklands: The Prairie Habitat Joint Venture assessment , 2014 .

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

[13]  D. Pennock,et al.  Greenhouse gas emissions and carbon sequestration potential in restored wetlands of the Canadian prairie pothole region , 2011, Wetlands Ecology and Management.

[14]  Palmer Hough,et al.  Mitigation under Section 404 of the Clean Water Act: where it comes from, what it means , 2009, Wetlands Ecology and Management.

[15]  Richard A. Fournier,et al.  Towards a strategy to implement the Canadian Wetland Inventory using satellite remote sensing , 2007 .

[16]  Carolin Strobl,et al.  Unbiased split selection for classification trees based on the Gini Index , 2007, Comput. Stat. Data Anal..

[17]  J. Zedler,et al.  Wetland resources : Status, trends, ecosystem services, and restorability , 2005 .

[18]  M. J. Adams,et al.  Amphibian occurrence and aquatic invaders in a changing landscape: Implications for wetland mitigation in the willamette valley, Oregon, USA , 2005, Wetlands.

[19]  L. Breiman.  Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[20]  W. Mitsch,et al.  The value of wetlands: importance of scale and landscape setting. , 2000 .

[21]  J. Burger,et al.  Relationships among Isolated Wetland Size, Hydroperiod, and Amphibian Species Richness: Implications for Wetland Regulations , 2000 .

[22]  J. P. Ball,et al.  AVIAN HABITAT SELECTION AND PRAIRIE WETLAND DYNAMICS: A 10‐YEAR EXPERIMENT , 1997 .

[23]  Anne D. Marble,et al.  A Guide to Wetland Functional Design , 1991 .

[24]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[25]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[26]  H. A. Kantrud,et al.  Population Estimates of Breeding Birds in North Dakota , 1972 .

[27]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

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

[29]  Vaishali Ganganwar,et al.  An overview of classification algorithms for imbalanced datasets , 2012 .

[30]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[31]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[32]  N. H. Euliss,et al.  Wetlands of the Prairie Pothole Region: Invertebrate species composition, ecology, and management , 1999 .

[33]  T. C. Winter,et al.  Hydrologic Functions of Prairie Wetlands , 1998 .

[34]  H. A. Kantrud,et al.  Classification of natural ponds and lakes in the glaciated prairie region , 1971 .