A novel UAV-based approach for biomass prediction and grassland structure assessment in coastal meadows

Villoslada, Miguel; Bergamo, Thaisa; Ward, Raymond D.; Joyce, Christopher; Sepp, Kalev

doi:10.1016/j.ecolind.2020.107227

Cited by 45 publications

(39 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PBIA performed better than the OBIA classification in most of the study areas except for KUD and MA2 in the RF classifier and KUD in the KNN classifier (Figure 4). In these areas, there are greater cattle grazing pressures (though still at a low intensity) in than the other sites [37], which may create larger patches of homogeneous plant communities in terms of the reflectance response. In this instance, the segments would have grouped pixels that are more homogeneous, in part explaining the marginally better performance of the OBIA classification in this site.…”

Section: Discussionmentioning

confidence: 98%

“…Figure 1 shows the location of the six study sites on the west coast of Estonia within nature protection areas and under low-intensity land management regimes [33,37]. Kudani (KUD), Tahu North (TAN) and Tahu South (TAS) are within the Silma Nature Reserve; Ralby (RAL) and Rumpo East (RUE) are within the Vormsi Landscape Protection Area; and Matsalu02 (MA2) is within the Matsalu National Park.…”

Section: Study Areasmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Classification and Accuracy Assessment from High-Resolution Images of Coastal Wetlands

et al. 2021

View full text Add to dashboard Cite

High-resolution images obtained by multispectral cameras mounted on Unmanned Aerial Vehicles (UAVs) are helping to capture the heterogeneity of the environment in images that can be discretized in categories during a classification process. Currently, there is an increasing use of supervised machine learning (ML) classifiers to retrieve accurate results using scarce datasets with samples with non-linear relationships. We compared the accuracies of two ML classifiers using a pixel and object analysis approach in six coastal wetland sites. The results show that the Random Forest (RF) performs better than K-Nearest Neighbors (KNN) algorithm in the classification of pixels and objects and the classification based on pixel analysis is slightly better than the object-based analysis. The agreement between the classifications of objects and pixels is higher in Random Forest. This is likely due to the heterogeneity of the study areas, where pixel-based classifications are most appropriate. In addition, from an ecological perspective, as these wetlands are heterogeneous, the pixel-based classification reflects a more realistic interpretation of plant community distribution.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Study Areasmentioning

confidence: 99%

Machine Learning Classification and Accuracy Assessment from High-Resolution Images of Coastal Wetlands

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Majority of available research on the photogrammetric use of UAV for establishing DEMs and DSMs does not provide the precise input parameters of performed imaging (Martínez-Carricondo et al, 2018;Ajibola et al, 2019;Donager et al, 2021;Sankey et al, 2021;Villoslada Peciña et al, 2021). The information tends to be either incomplete (Uysal et al, 2015;La Salandra et al, 2021) or relate to UAV technology employed in fixed-wing units (Zmarz et al, 2018;Donager et al, 2021;Sankey et al, 2021;Vavulin et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

“…Traditional methods of generating DEMs are time consuming and cost-inefficient as they require on-site surveying and expensive measuring equipment (e.g., on-ground and aerial LiDAR scanners). Owing to the development of technology and its increasing availability, Unmanned Aerial Vehicles (UAV) have become a viable option for establishing precise DEMs in relation to relatively vast areas and at very low cost (Moore et al, 1991;Walker and Willgoose, 1999;Thar and Ahmad, 2013;Audronis, 2015;Uysal et al, 2015;Akbari et al, 2016;Martínez-Carricondo et al, 2018;Zmarz et al, 2018;Ajibola et al, 2019;Akturk and Altunel, 2019;Donager et al, 2021;La Salandra et al, 2021;Sankey et al, 2021;Vavulin et al, 2021;Villoslada Peciña et al, 2021). And thus, over the past several years low-altitude photogrammetry (Kędzierski et al, 2014) has become one of the main methods of generating DEMs.…”

Section: Introductionmentioning

confidence: 99%

Assessment of the Applicability of UAV for the Creation of Digital Surface Model of a Small Peatland

Czapiewski

2022

Front. Earth Sci.

View full text Add to dashboard Cite

Rapid development and growing availability of Unmanned Aerial Vehicles (UAV) translates into their more wide-spread application in monitoring of the natural environment. Moreover, advances in computer analysis techniques allow the imaging performed with UAVs to be used in creating Digital Elevation Models (DEM) and Digital Surface Models (DSM). DEMs are often employed in studies on geology, environment, engineering, and architecture. The presented paper discusses the procedures enabling the making of a precise DEM, discusses the aerial imaging data processing technique as well as determines the accuracy of obtained products in comparison with an existing Digital Elevation Model. Based on available literature the author indicates four sets of input parameters applicable in UAV imaging. Data collection missions were performed on two separate days in the area of a small peatland located in the Tuchola Pinewood, Poland. The study aims to address two research issues. Firstly, the author investigates the possibility of creating a DSM based on UAV imaging performed under unfavorable conditions and indicates whether results obtained via this method display sufficient quality to be seen as an alternative to the traditional surveying techniques (LiDAR). Secondly, the article determines the input parameters for a photogrammetric flight that ensure the highest accuracy of a resulting DSM. The analyses show a strong positive correlation between the DSMs prepared based on UAV imaging with data obtained by means of traditional methods (LiDAR). Mean correlation coefficient ranged from 0.45 to 0.75 depending on the type of land use and input parameters selected for a given flight. Furthermore, the analysis revealed that DSMs prepared based on UAV imaging—provided the most suitable input parameters are selected—can be a viable alternative to standard measurements, with the added benefit of low cost and the capacity for repeatable data collection in time. Admittedly, the method in question cannot be utilized in relation to peatlands overgrown with high vegetation (trees, shrubs) as it effectively diminishes the accuracy of obtained DSMs.

show abstract

“…As such, UAS platforms cannot only characterize the spatial distribution of vegetation but also detect various patterns of change across natural and human-modified environments. Because UASs can match the spatial and temporal resolutions of local-scale investigations, they may provide new insights into patterns of plant community change in response to herbivore activity in tundra [1], habitat destruction in coastal meadows [2], and grazing management in grasslands [3]. In human-modified environments, UASs can detect plant physiological characteristics to monitor disease severity [4][5][6][7] and crop productivity [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Multisensor UAS mapping of Plant Species and Plant Functional Types in Midwestern Grasslands

Hall

Lara

2022

Remote Sensing

View full text Add to dashboard Cite

Uncrewed aerial systems (UASs) have emerged as powerful ecological observation platforms capable of filling critical spatial and spectral observation gaps in plant physiological and phenological traits that have been difficult to measure from space-borne sensors. Despite recent technological advances, the high cost of drone-borne sensors limits the widespread application of UAS technology across scientific disciplines. Here, we evaluate the tradeoffs between off-the-shelf and sophisticated drone-borne sensors for mapping plant species and plant functional types (PFTs) within a diverse grassland. Specifically, we compared species and PFT mapping accuracies derived from hyperspectral, multispectral, and RGB imagery fused with light detection and ranging (LiDAR) or structure-for-motion (SfM)-derived canopy height models (CHM). Sensor–data fusion were used to consider either a single observation period or near-monthly observation frequencies for integration of phenological information (i.e., phenometrics). Results indicate that overall classification accuracies for plant species and PFTs were highest in hyperspectral and LiDAR-CHM fusions (78 and 89%, respectively), followed by multispectral and phenometric–SfM–CHM fusions (52 and 60%, respectively) and RGB and SfM–CHM fusions (45 and 47%, respectively). Our findings demonstrate clear tradeoffs in mapping accuracies from economical versus exorbitant sensor networks but highlight that off-the-shelf multispectral sensors may achieve accuracies comparable to those of sophisticated UAS sensors by integrating phenometrics into machine learning image classifiers.

show abstract

A novel UAV-based approach for biomass prediction and grassland structure assessment in coastal meadows

Cited by 45 publications

References 104 publications

Machine Learning Classification and Accuracy Assessment from High-Resolution Images of Coastal Wetlands

Machine Learning Classification and Accuracy Assessment from High-Resolution Images of Coastal Wetlands

Assessment of the Applicability of UAV for the Creation of Digital Surface Model of a Small Peatland

Multisensor UAS mapping of Plant Species and Plant Functional Types in Midwestern Grasslands

Contact Info

Product

Resources

About