Mapping subaerial sand-gravel-cobble fluvial sediment facies using airborne lidar and machine learning

Diaz-Gomez, Romina; Pasternack, G. B.; Guillon, Hervé; Byrne, C. F.; Schwindt, Sebastian; Larrieu, Kenneth G.; Solís, Samuel Sandoval

doi:10.1016/j.geomorph.2021.108106

Cited by 11 publications

(10 citation statements)

References 115 publications

(154 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For our K1 and S2 examples, the grain size patterns change significantly with respect to the sampling location within the same gravel bar (Figure 9). Similar trends of locally high variability in grain size distributions have also been observed in other field surveys (e.g., Chardon et al, 2020; Díaz Gómez et al, 2022; Rice & Church, 1998). In addition, spatial differences in sedimentary patterns, for example, vertical and lateral sorting and/or armouring (see also Bunte & Abt, 2001), can cause a change in the obtained results of grain size patterns.…”

Section: Discussionsupporting

confidence: 85%

Automated detecting, segmenting and measuring of grains in images of fluvial sediments: The potential for large and precise data from specialist deep learning models and transfer learning

Mair,

Witz,

Do Prado

et al. 2023

Earth Surf Processes Landf

View full text Add to dashboard Cite

The size of sedimentary particles in rivers bears information on the sediment entrainment or deposition mechanisms and the hydraulic conditions controlling them. However, collecting such data from coarse‐grained sediments is work intensive, both in the field and remotely. Therefore, attention has turned to machine learning models to improve the data acquisition. Despite their success, current methods need large quantities of data and yield results limited to a few percentile values of grain size datasets, often additionally affected by a systematic bias. In most cases, the root of these limitations is the challenge of accurately segmenting grains. Here, we present a new approach to improve the segmentation of individual grains based on the capacity of transfer learning in convolutional neural networks. Specifically, we re‐train a state‐of‐the‐art model for cell segmentation in biomedical images to find and segment coarse‐grained particles in images of fluvial sediments. Our results show that the performance in the segmentation tasks can be directly transferred to images of fluvial sediments and that our re‐trained models outperform existing methods. We document that our results are achievable with only 10%–20% of the data needed for training other deep learning models designed to measure the size of fluvial sediments. Moreover, we find that traits in our data control the segmentation performance. This enables data‐driven approaches to create specialist segmentation models. Additionally, comparing our automatically obtained datasets with the results retrieved from image and field‐based surveys confirms that improvements in segmentation are directly leading to more precise and more accurate grain size data even if data collection occurs in images taken at different conditions. Finally, we release a software package, the trained models and our data. The goal is to offer a tool to efficiently segment and measure grains in sediment images in an automated way, which can be adapted to different settings.

show abstract

Section: Discussionsupporting

confidence: 85%

Automated detecting, segmenting and measuring of grains in images of fluvial sediments: The potential for large and precise data from specialist deep learning models and transfer learning

Mair,

Witz,

Do Prado

et al. 2023

Earth Surf Processes Landf

View full text Add to dashboard Cite

show abstract

“…The MDGS has both advantages and limitations compared with existing mobile grain size estimation methods. For example, aerial‐based methods (e.g., airborne‐LiDAR and UAV‐photogrammetry) generally cover large areas with few spatial gaps, although these methods are often only capable of resolving coarse sediments (e.g., gravels) owing to relatively low‐resolution data (e.g., Carbonneau et al, 2004, 2018; Gómez et al, 2022; Woodget & Austrums, 2017). The MDGS can map both fine and coarse sediment surfaces but often contains spatial gaps (e.g., Figure 6).…”

Section: Discussionmentioning

confidence: 99%

“…Smoothing (with a 1-m cross-shore moving average window) was applied to slope and mean grain size plots in (e-g). [Color figure can be viewed at wileyonlinelibrary.com] are often only capable of resolving coarse sediments (e.g., gravels) owing to relatively low-resolution data (e.g., Carbonneau et al, 2004Carbonneau et al, , 2018G omez et al, 2022;Woodget & Austrums, 2017). The MDGS can map both fine and coarse sediment surfaces but often contains spatial gaps (e.g., Figure 6).…”

Section: Seasonal Grain Size Trends and Comparison With Waves And Bea...mentioning

confidence: 99%

“…Recent advances in automated grain size analysis techniques include remote sensing methods. Several studies used LiDAR and hyperspectral cameras attached to mobile survey platforms such as airplanes and ground‐based vehicles to automatically map and classify generalized regions of different (often coarse) grain sizes over spatially large areas (e.g., Deronde et al, 2008; Gómez et al, 2022; Matsumoto & Young, 2018). Other approaches used digital photographs to automatically identify and calculate individual grain sizes (i.e., object‐based image analysis, Adams, 1979; Graham et al, 2005; Carbonneau et al, 2018), or calculate average grain sizes for each photograph using statistical analysis (e.g., Barnard et al, 2007; Buscombe et al, 2010; Carbonneau et al, 2004; Rubin, 2004).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of an automated mobile grain size mapping of a mixed sediment beach

Matsumoto

Young

2023

Earth Surf Processes Landf

View full text Add to dashboard Cite

Grain sizes influence beach morphologies, processes, and states (e.g., dissipative, reflective and intermediate), however previous studies analysing beach grain size are often spatially and temporarily sparse. In this study, an automated mobile grain size estimation method using digital photographs (mobile digital grain size, MDGS) was developed and tested at a mixed sediment beach consisting of sand and gravels. The data collection system consisted of a downward‐looking camera, Real Time Kinematic Global Navigation Satellite System, and a camera‐triggering single‐board computer, attached to an all‐terrain vehicle. Digital photographs were collected monthly from January 2021 to March 2022 over a section spanning ~700 m alongshore and processed automatically using an existing (non‐mobile) DGS estimation method. The MDGS results were generally consistent with manually estimated grain sizes (n = 962, r2 = 0.74, RMSE = 5.9 mm) and UAV orthomosaic imagery, although the MDGS sometimes overestimated manually estimated grain sizes particularly for photographs with relatively small sediments. Modelled nearshore waves and subaerial beach survey data from mobile terrestrial LiDAR were used to explore using MDGS in morphological studies. Seasonal grain size trends, observed relationships between nearshore wave height and spatially averaged beach grain size, and the general increasing trends of grain sizes with both beach elevation and local roughness/slope were consistent with previous studies, highlighting the use of MDGS for morpho‐sedimentary mixed sediment beach research. The MDGS provides a unique method to conduct spatially and temporarily high‐resolution mapping of gravel size sediments over large areas (>102 m alongshore). Potential improvements of the MDGS include additional low elevation cameras for improved fine (e.g., sand) grain size estimates, decreased time between photo triggering, and automated removal of erroneous photographs containing surface irregularities (e.g., tire tracks) and non‐sediment features (e.g., seaweed). Overall, the MDGS provides improved surface grain size mapping and investigations of complex grain size–morphology relationships of mixed sediment beaches.

show abstract

“…Overall, GeoAI outperforms conventional methods of fluvial landform classification, reaching a classification accuracy of over 80%. Most common applications are found in river channels and water body mapping [208,216], the classification of riverine landforms and vegetation successions [213,214,219,220], the estimation of catchment hydrogeomorphic characteristics (e.g., valley bottom, floodplain, and terrace) [212,221], and benthic and fish habitat mapping [207,211,222,223].…”

Section: Software: R Programmentioning

confidence: 99%

Geospatial Artificial Intelligence (GeoAI) in the Integrated Hydrological and Fluvial Systems Modeling: Review of Current Applications and Trends

Gonzales‐Inca

Calle

Croghan

et al. 2022

Water

View full text Add to dashboard Cite

This paper reviews the current GeoAI and machine learning applications in hydrological and hydraulic modeling, hydrological optimization problems, water quality modeling, and fluvial geomorphic and morphodynamic mapping. GeoAI effectively harnesses the vast amount of spatial and non-spatial data collected with the new automatic technologies. The fast development of GeoAI provides multiple methods and techniques, although it also makes comparisons between different methods challenging. Overall, selecting a particular GeoAI method depends on the application’s objective, data availability, and user expertise. GeoAI has shown advantages in non-linear modeling, computational efficiency, integration of multiple data sources, high accurate prediction capability, and the unraveling of new hydrological patterns and processes. A major drawback in most GeoAI models is the adequate model setting and low physical interpretability, explainability, and model generalization. The most recent research on hydrological GeoAI has focused on integrating the physical-based models’ principles with the GeoAI methods and on the progress towards autonomous prediction and forecasting systems.

show abstract

Mapping subaerial sand-gravel-cobble fluvial sediment facies using airborne lidar and machine learning

Cited by 11 publications

References 115 publications

Automated detecting, segmenting and measuring of grains in images of fluvial sediments: The potential for large and precise data from specialist deep learning models and transfer learning

Automated detecting, segmenting and measuring of grains in images of fluvial sediments: The potential for large and precise data from specialist deep learning models and transfer learning

Development of an automated mobile grain size mapping of a mixed sediment beach

Geospatial Artificial Intelligence (GeoAI) in the Integrated Hydrological and Fluvial Systems Modeling: Review of Current Applications and Trends

Contact Info

Product

Resources

About