‘The Best of Two Worlds’—Combining Classifier Fusion and Ecological Models to Map and Explain Landscape Invasion by an Alien Shrub

Abstract

The spread of invasive alien species promotes ecosystem structure and functioning changes, with detrimental effects on native biodiversity and ecosystem services, raising challenges for local management authorities. Predictions of invasion dynamics derived from modeling tools are often spatially coarse and therefore unsuitable for guiding local management. Accurate information on the occurrence of invasive plants and on the main factors that promote their spread is critical to define successful control strategies. For addressing this challenge, we developed a dual framework combining satellite image classification with predictive ecological modeling. By combining data from georeferenced invaded areas with multispectral imagery with 10-meter resolution from Sentinel-2 satellites, a map of areas invaded by the woody invasive Acacia longifolia in a municipality of northern Portugal was devised. Classifier fusion techniques were implemented through which eight statistical and machine-learning algorithms were ensembled to produce accurate maps of invaded areas. Through a Random Forest (RF) model, these maps were then used to explore the factors driving the landscape-level abundance of A. longifolia. RF models were based on explanatory variables describing hypothesized environmental drivers, including climate, topography/geomorphology, soil properties, fire disturbance, landscape composition, linear structures, and landscape spatial configuration. Satellite-based maps synoptically described the spatial patterns of invaded areas, with classifications attaining high accuracy values (True Skill Statistic, TSS: 0.895, Area Under the Receiver Operating Curve, ROC: 0.988, Kappa: 0.857). The predictive RF models highlighted the primary role of climate, followed by landscape composition and configuration, as the most important drivers explaining the species abundance at the landscape level. Our innovative dual framework—combining image classification and predictive ecological modeling—can guide decision-making processes regarding effective management of invasions by prioritizing the invaded areas and tackling the primary environmental and anthropogenic drivers of the species’ abundance and spread.

Sentinel-2 versus PlanetScope Images for Goldenrod Invasive Plant Species Mapping

“…Dao et al [40], analyzing invasive grassland species, confirmed that statistically important spectral ranges were especially the blue (below 500 nm), red-edge (680-730 nm), and near-infrared (NIR, beyond 730 nm). This was not confirmed by Mouta et al [41], who identified the invasive species Acacia longifolia using Sentinel-2 images, and ecological models demonstrated the usefulness of the blue (458-523 nm) and green (543-578 nm) channel, in which the yellow flowers of Acacia as well as other yellow plants can be better distinguished due to the high presence of carotenoids and other pigments. This observation was not confirmed in our research, because the yellow range of the PlanetScope (B5) obtained an MDA value of 11.39 during flowering, which was below the average (17.51; Table 5); in the remaining periods, the usefulness of the yellow band was even lower, taking the last, eighth place in the ranking of all spectral channels offered with the PlanetScope detector.…”

Remote Sensing and Invasive Plants in Coastal Ecosystems: What We Know So Far and Future Prospects

“…Yet, hyperspectral aircraft missions need accurate programming of non-recurrent, expensive and time-consuming data collection, which, combined with the high storage, management, and computation efforts, restrict their use to few study cases [44]. Similarly, other aircraft data (e.g., multispectral, panchromatic/RGB data and active LiDAR and SAR) registered on single missions, being unable to depict phenological vegetation features, are little used for IAP detection, mapping and modelling [55][56][57][58]. The use of free satellite data, despite the coarse spatial resolution (fine as Landsat, veryhigh as Sentinel-2), has gained in importance especially after 2014, also thanks to their high temporal resolution.…”

“…However, the use of Landsat images to detect and model IAP on coastal areas could decrease in the future and be replaced by the latest satellite images with finer spatial resolution and similar revisit period (e.g., Sentinel-2, PlanetScope, etc.) [58][59][60]72]. The most recent RS platforms as UAVs with ultra-high spatial resolution (below 1 m) certainly offer adequate images to detect and model IAP and to analyze the entire complexity of coastal environments [50].…”

Sentinel-2 Time Series and Classifier Fusion to Map an Aquatic Invasive Plant Species along a River—The Case of Water-Hyacinth

“…Finally, to convert the model result from probability/suitability to a binary outcome, we applied a numerical threshold that maximizes the TSS score [29]. Values close to the TSS cutoff were considered pixels with very low spectral similarity to E. crassipes, in opposition to values close to the maximum (1000), which were considered to have very-high spectral similarity to E. crassipes.…”

“…The package biomod2 [27] is a platform implemented in R well-known and frequently used by the scientific community that can combine different modelling/classification techniques in a final consensus model that discriminates the presence/absence of a species across space [28]. The biomod2 frame-work can be applied to perform pixel-based supervised classification through an ensemble approach, "classifier fusion" [29]. Therefore, it can be used as a suitable multi-classifier stacking ensemble that standardizes the uncertainty present in the individual models and determines a general prediction consistent with all classification methods [30,31].…”