Comparison of Different Analytical Strategies for Classifying Invasive Wetland Vegetation in Imagery from Unpiloted Aerial Systems (UAS)

Detecting newly established invasive plants is key to prevent further spread. Traditional field surveys are challenging and often insufficient to identify the presence and extent of invasions. This is particularly true for wetland ecosystems because of difficult access, and because floating and submergent plants may go undetected in the understory of emergent plants. Unpiloted aerial systems (UAS) have the potential to revolutionize how we monitor invasive vegetation in wetlands, but key components of the data collection and analysis workflow have not been defined. In this study, we conducted a rigorous comparison of different methodologies for mapping invasive Emergent (Typha × glauca (cattail)), Floating (Hydrocharis morsus-ranae (European frogbit)), and Submergent species (Chara spp. and Elodea canadensis) using the machine learning classifier, random forest, in a Great Lakes wetland. We compared accuracies using (a) different spatial resolutions (11 cm pixels vs. 3 cm pixels), (b) two classification approaches (pixel- vs. object-based), and (c) including structural measurements (e.g., surface/canopy height models and rugosity as textural metrics). Surprisingly, the coarser resolution (11 cm) data yielded the highest overall accuracy (OA) of 81.4%, 2.5% higher than the best performing model of the finer (3 cm) resolution data. Similarly, the Mean Area Under the Receiving Operations Characteristics Curve (AUROC) and F1 Score from the 11 cm data yielded 15.2%, and 6.5% higher scores, respectively, than those in the 3 cm data. At each spatial resolution, the top performing models were from pixel-based approaches and included surface model data over those with canopy height or multispectral data alone. Overall, high-resolution maps generated from UAS classifications will enable early detection and control of invasive plants. Our workflow is likely applicable to other wetland ecosystems threatened by invasive plants throughout the globe.

[1]  Kyle D. Woodward,et al.  A multi-plot assessment of vegetation structure using a micro-unmanned aerial system (UAS) in a semi-arid savanna environment , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[2]  P. Wicaksono,et al.  Analyses of inter-class spectral separability and classification accuracy of benthic habitat mapping using multispectral image , 2020 .

[3]  F. Flores-Verdugo,et al.  Assessing the effect of flight altitude and overlap on orthoimage generation for UAV estimates of coastal wetlands , 2020, Journal of Coastal Conservation.

[4]  Z. Al-Ali,et al.  A comparative study of remote sensing classification methods for monitoring and assessing desert vegetation using a UAV-based multispectral sensor , 2020, Environmental Monitoring and Assessment.

[5]  E. Storey.  Mapping plant growth forms using structure-from-motion data combined with spectral image derivatives , 2020, Remote sensing letters.

[6]  Hui Li,et al.  Class-imbalanced dynamic financial distress prediction based on Adaboost-SVM ensemble combined with SMOTE and time weighting , 2020, Inf. Fusion.

[7]  Shane C. Lishawa,et al.  European frogbit (Hydrocharis morsus-ranae) invasion facilitated by non-native cattails (Typha) in the Laurentian Great Lakes , 2019, Journal of Great Lakes Research.

[8]  Yu Dong,et al.  Automatic Identification of Shrub-Encroached Grassland in the Mongolian Plateau Based on UAS Remote Sensing , 2019, Remote. Sens..

[9]  Erik A. Bolch,et al.  Using Hyperspectral UAS Imagery to Monitor Invasive Plant Phenology , 2019, Optical Sensors and Sensing Congress (ES, FTS, HISE, Sensors).

[10]  Michael J. Anteau,et al.  Typha (Cattail) Invasion in North American Wetlands: Biology, Regional Problems, Impacts, Ecosystem Services, and Management , 2019, Wetlands.

[11]  Anita Simic Milas,et al.  Mapping Invasive Phragmites australis in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers , 2019, Remote. Sens..

[12]  Jan van Aardt,et al.  Influence of Drone Altitude, Image Overlap, and Optical Sensor Resolution on Multi-View Reconstruction of Forest Images , 2019, Remote. Sens..

[13]  Caspar A. Mücher,et al.  SegOptim - A new R package for optimizing object-based image analyses of high-spatial resolution remotely-sensed data , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[14]  Petra Símová,et al.  UAV for mapping shrubland vegetation: Does fusion of spectral and vertical information derived from a single sensor increase the classification accuracy? , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[15]  Brady S. Hardiman,et al.  Linking Landsat to terrestrial LiDAR: Vegetation metrics of forest greenness are correlated with canopy structural complexity , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[16]  Jana Müllerová,et al.  Using Single- and Multi-Date UAV and Satellite Imagery to Accurately Monitor Invasive Knotweed Species , 2018, Remote. Sens..

[17]  Fernando Carvajal-Ramírez,et al.  Assessment of UAV-photogrammetric mapping accuracy based on variation of ground control points , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[18]  Su Zhang,et al.  The impact of small unmanned airborne platforms on passive optical remote sensing: a conceptual perspective , 2018, International Journal of Remote Sensing.

[19]  Elisabeth A. Addink,et al.  Multitemporal Classification of River Floodplain Vegetation Using Time Series of UAV Images , 2018, Remote. Sens..

[20]  C. Gough,et al.  Spatial Variation in Canopy Structure across Forest Landscapes , 2018, Forests.

[21]  Ben Somers,et al.  Can wetland plant functional groups be spectrally discriminated? , 2018, Remote Sensing of Environment.

[22]  Eija Honkavaara,et al.  A Novel Machine Learning Method for Estimating Biomass of Grass Swards Using a Photogrammetric Canopy Height Model, Images and Vegetation Indices Captured by a Drone , 2018 .

[23]  Kerrie L. Mengersen,et al.  UAVs and Machine Learning Revolutionising Invasive Grass and Vegetation Surveys in Remote Arid Lands , 2018, Sensors.

[24]  D. Du,et al.  Invasive European frogbit (Hydrocharis morsus-ranae L.) in North America: an updated review 2003–16 , 2018 .

[25]  Kunwar K. Singh,et al.  A meta-analysis and review of unmanned aircraft system (UAS) imagery for terrestrial applications , 2018 .

[26]  María Flor Álvarez-Taboada,et al.  Mapping of the Invasive Species Hakea sericea Using Unmanned Aerial Vehicle (UAV) and WorldView-2 Imagery and an Object-Oriented Approach , 2017, Remote. Sens..

[27]  P. Pyšek,et al.  Timing Is Important: Unmanned Aircraft vs. Satellite Imagery in Plant Invasion Monitoring , 2017, Front. Plant Sci..

[28]  Shengjie Hu,et al.  Global wetlands: Potential distribution, wetland loss, and status. , 2017, The Science of the total environment.

[29]  Andrea Berton,et al.  Assessment of a canopy height model (CHM) in a vineyard using UAV-based multispectral imaging , 2017 .

[30]  Nicholas J. Reo,et al.  Mechanical Harvesting Effectively Controls Young Typha spp. Invasion and Unmanned Aerial Vehicle Data Enhances Post-treatment Monitoring , 2017, Front. Plant Sci..

[31]  J. Greenberg,et al.  Measuring landscape-scale spread and persistence of an invaded submerged plant community from airborne remote sensing. , 2016, Ecological applications : a publication of the Ecological Society of America.

[32]  S. Tesfamichael,et al.  WETLAND ASSESSMENT USING UNMANNED AERIAL VEHICLE (UAV) PHOTOGRAMMETRY , 2016 .

[33]  Dewey Dunnington,et al.  EXIF Image Data in R , 2016 .

[34]  Adrien Michez,et al.  Mapping of riparian invasive species with supervised classification of Unmanned Aerial System (UAS) imagery , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[35]  Iryna Dronova,et al.  Object-Based Image Analysis in Wetland Research: A Review , 2015, Remote. Sens..

[36]  Aniruddha Ghosh,et al.  A comparison of selected classification algorithms for mapping bamboo patches in lower Gangetic plains using very high resolution WorldView 2 imagery , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[37]  Matthew O. Anderson,et al.  Radiometric and Geometric Analysis of Hyperspectral Imagery Acquired from an Unmanned Aerial Vehicle , 2012, Remote. Sens..

[38]  Timothy A. Warner,et al.  Kernel-Based Texture in Remote Sensing Image Classification , 2011 .

[39]  Shane C. Lishawa,et al.  Water Level Decline Promotes Typha X glauca Establishment and Vegetation Change in Great Lakes Coastal Wetlands , 2010, Wetlands.

[40]  Erle C. Ellis,et al.  Remote Sensing of Vegetation Structure Using Computer Vision , 2010, Remote. Sens..

[41]  Fan Xia,et al.  Assessing object-based classification: advantages and limitations , 2009 .

[42]  Gregory Asner,et al.  Applications of Remote Sensing to Alien Invasive Plant Studies , 2009, Sensors.

[43]  Susan L. Ustin,et al.  Identification of invasive vegetation using hyperspectral remote sensing in the California Delta ecosystem , 2008 .

[44]  C. Scott Findlay,et al.  Effect of Invasive Plant Species on Temperate Wetland Plant Diversity , 2004 .

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

[46]  Mathias Kneubühler,et al.  Individual tree crown delineation from high-resolution UAV images in broadleaf forest , 2021, Ecol. Informatics.

[47]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .