Analyses of inter-class spectral separability and classification accuracy of benthic habitat mapping using multispectral image

Wicaksono, Pramaditya; Aryaguna, Prama Ardha

doi:10.1016/j.rsase.2020.100335

Cited by 12 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Across spatial resolutions, the most confusion occurred between the Submergent and Floating classes. The spectral resolution of our sensor may have been inadequate (i.e., inappropriate bandwidths and/or number of bands) to distinguish both classes with such similar structural values, as observed in previous RS studies of riparian and marine systems [6,47]. Future research should assess the potential benefits of using higher spectral resolution sensors (e.g., hyperspectral) on UAS in attempts to distinguish interspersed floating and submergent vegetation in wetlands.…”

Section: Importance Of Uas Flight Parameterization and Spectral Resolution Of Uas Sensormentioning

confidence: 89%

“…Dominant EFB within and around Emergent stands may also have created objects with a mix of species and in slightly coarser 11 cm pixels, as observed with the confusion between classifying Floating and Emergent vegetation in our best performing model. The mixed spatial distribution of species across vegetation zones resulted in less distinct spectral and structural bands of the image objects for the classes, and likely led to lower classification accuracy [47]. In the 3 cm data, the finer spatial resolution better captured these species, producing more appropriately sized objects with distinct spectral and structural values compared to the segmentation outputs of the 11 cm data (Table S2, Figure S5).…”

Section: Pixel-vs Object-based Classification Approachmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2021

View full text Add to dashboard Cite

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.

show abstract

Section: Importance Of Uas Flight Parameterization and Spectral Resolution Of Uas Sensormentioning

confidence: 89%

Section: Pixel-vs Object-based Classification Approachmentioning

confidence: 99%

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

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Classes identified as largely spectrally inseparable here (e.g. low‐density seagrass classes versus surrounding bare sediment or bare sediment versus mosaics of different species) are common in other seagrass remote sensing projects and were likely more difficult to distinguish as numerical trends are less clear due to spectral similarity (Wicaksono & Aryaguna 2020). As such, although accuracies were acceptable, some mapped extents should be treated with caution.…”

Section: Discussionmentioning

confidence: 99%

Identifying spatio‐temporal trends in seagrass meadows to inform future restoration

Dalby

Pucino

Tan

et al. 2022

Restoration Ecology

View full text Add to dashboard Cite

Seagrass restoration requires information on a range of factors including site environmental conditions, appropriate planting techniques, and the identification of sites most likely to support seagrass. To address the question of where to focus restoration efforts, a key first step is to identify trends in the spatio‐temporal distribution of seagrasses to identify areas of persistence, loss, and recent gains. Areas of recent recovery (and adjacent areas), can then be targeted by practitioners for assisted recovery and restoration, whilst areas of persistent loss can be avoided. Here we identified the contemporary distribution, density, and species composition of seagrass ecosystems (using Sentinel 2 imagery and supervised object‐based imagery analysis) and integrated these data with historic extents to identify spatio‐temporal trends in seagrass distribution in Western Port, Victoria, Australia. Contemporary classifications demonstrated acceptable accuracies (Overall Accuracy 0.77–0.85, User Accuracy 0.76–0.97) and predicted a contemporary seagrass extent of 222 km2; with 48 km2 of low‐density recovery predicted to have occurred since 1999. Comparisons with historical seagrass extents indicated some seagrass recovery since large‐scale losses in 1983, although some areas of loss were also present. Recovery included a net gain of approximately 95 km2 in the past 20 years and an eastward range expansion; suggesting environmental conditions have improved and are now conducive for restoration efforts in some areas. Results demonstrate that accurate, low‐cost, remote sensing of seagrass ecosystems is possible and show how understanding spatio‐temporal trends can guide the spatial allocation of resources by prioritizing areas for restoration where recovery is beginning to occur.

show abstract

“…At different depths, the response of two different-color elements can be similar on a wide part of the light spectrum. Hence, with an unknown depth variation, the spectral responses of elements such as dead corals, seagrasses, bleached corals and live corals can be mixed up and their separability significantly affected, making it harder to map correctly [144]. Nevertheless, this depth heterogeneity problem can be overcome: when mixing satellite images with in situ measurements (such as single-beam echo sounder), it is possible to have an accurate benthic mapping of reefs with complex structures in shallow waters [108].…”

Section: Water Penetration and Benthic Heterogeneitymentioning

confidence: 99%

Mapping of Coral Reefs with Multispectral Satellites: A Review of Recent Papers

et al. 2021

View full text Add to dashboard Cite

Coral reefs are an essential source of marine biodiversity, but they are declining at an alarming rate under the combined effects of global change and human pressure. A precise mapping of coral reef habitat with high spatial and time resolutions has become a necessary step for monitoring their health and evolution. This mapping can be achieved remotely thanks to satellite imagery coupled with machine-learning algorithms. In this paper, we review the different satellites used in recent literature, as well as the most common and efficient machine-learning methods. To account for the recent explosion of published research on coral reel mapping, we especially focus on the papers published between 2018 and 2020. Our review study indicates that object-based methods provide more accurate results than pixel-based ones, and that the most accurate methods are Support Vector Machine and Random Forest. We emphasize that the satellites with the highest spatial resolution provide the best images for benthic habitat mapping. We also highlight that preprocessing steps (water column correction, sunglint removal, etc.) and additional inputs (bathymetry data, aerial photographs, etc.) can significantly improve the mapping accuracy.

show abstract

Analyses of inter-class spectral separability and classification accuracy of benthic habitat mapping using multispectral image

Cited by 12 publications

References 30 publications

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

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

Identifying spatio‐temporal trends in seagrass meadows to inform future restoration

Mapping of Coral Reefs with Multispectral Satellites: A Review of Recent Papers

Contact Info

Product

Resources

About