Incorporation of neighborhood information improves performance of SDB models

Knudby, Anders; Richardson, Galen

doi:10.1016/j.rsase.2023.101033

Cited by 7 publications

(8 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training tiles were passed through a data augmentation step, which randomly flipped and rotated tiles to expose the model to different orientations. To reduce the number of features, the CNNs in this study use valid padding strategies to discard the data at the edges of the tile [19,45]. Valid padding ensures that convolutional filters are only applied to values in the tile and that the height and width of the output tile is eroded [19,45,46].…”

Section: Convolutional Neural Network Trainingmentioning

confidence: 99%

“…The user can define the number of trees included in the model, however each decision tree within the random forest operates independently [17]. The advantages of random forest models are their ease of optimization and high predictive performance [11,16,18,19]. Random forest models have been successfully implemented in multi-scale lichen mapping applications [4,15].…”

Section: Introductionmentioning

confidence: 99%

“…Recent approaches to lichen mapping involve using neural networks, to create lichen maps. Neural networks can be designed to have high predictive performance at regression and classification tasks, but are substantially less interpretable, slower to train, and harder to optimize than random forest models [11,19,21]. For example, He et al used binary lichen maps from WorldView (WV) imagery (50 cm) to train a regression dense neural network to predict lichen coverage (%) in Landsat 8 OLI imagery (30 m) [20].…”

Section: Introductionmentioning

confidence: 99%

“…A small body of published work has focused on implementing CNNs for regression applications. Regression CNN models have been implemented to map freshwater shortages, bathymetry, chlorophyll-a (Chl-a) in lakes, and lichen [19,[29][30][31][32]. Aptoula et al developed a six-layer CNN which used 3x3 tiles with 12 Sentinel-2 bands to estimate Chl-a in Lake Balik [32].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dense neural network outperforms other machine learning models for scaling-up lichen cover maps in Eastern Canada

Richardson,

Knudby,

Chen

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Lichen mapping is vital for caribou management plans and sustainable land conservation. Previous studies have used random forest, dense neural network, and convolutional neural network models for mapping lichen coverage. However, to date, it is not clear how these models rank in this task. In this study, these machine learning models were evaluated on their ability to predict lichen percent coverage in Sentinel-2 imagery in Québec and Labrador, Canada. The models were trained on 10-m resolution lichen coverage (%) maps created from 20 drone surveys collected in July 2019 and 2022. The dense neural network achieved a higher accuracy than the other two, with a reported mean absolute error of 5.2% and an R2 of 0.76. By comparison, the random forest model returned a mean absolute error of 5.5% (R2: 0.74) and the convolutional neural network had a mean absolute error of 5.3% (R2: 0.74). A regional lichen map was created using the trained dense neural network and a Sentinel-2 imagery mosaic. There was greater uncertainty on land covers that the model was not exposed to in training, such as mines and deep lakes. While the dense neural network requires more computational effort to train than a random forest model, the 5.9% performance gain in the test pixel comparison renders it the most suitable for lichen mapping. This study represents progress toward determining the appropriate methodology for generating accurate lichen maps from satellite imagery for caribou conservation and sustainable land management.

show abstract

Section: Convolutional Neural Network Trainingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dense neural network outperforms other machine learning models for scaling-up lichen cover maps in Eastern Canada

Richardson,

Knudby,

Chen

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…17 Indeed, RF models exhibit lower errors than other SDB machine learning techniques, making it advantageous for the generation of accurate models. 15,[18][19][20][21][22][23][24][25][26] Most SDB research has been conducted in marine waters, where the concentration of suspended solids is low, and the concentration of phytoplankton is less than an annual average of 1.0 mg/m 3 , the underwater transparency is extremely high, or in atolls and coastal waters with low turbidity. 2,3,5,[9][10][11][27][28][29] The coastal waters of the Korean Peninsula's West, South, and East Seas differ considerably in marine environmental characteristics, including depth distribution, water turbidity, and sediment composition.…”

mentioning

confidence: 99%

Estimation of shallow bathymetry using Sentinel-2 satellite data and random forest machine learning: a case study for Cheonsuman, Hallim, and Samcheok Coastal Seas

Kwon,

Shin,

Kim

et al. 2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Bathymetry, the measurement of sea depth, has conventionally been conducted using echo-sounders on vessels. However, various factors limit conventional shipborne surveys in coastal regions, including data continuity, geographic obstacles, diplomatic concerns, and marine infrastructures. Remote sensing technology can address these limitations, particularly with the advancement of satellite imaging technology. Indeed, many studies are underway to develop machine learning-based water depth estimation technologies. However, previous studies have focused on clear waters with low turbidity or uniform seabed sediment. Therefore, in this study, we developed a satellite-derived bathymetry (SDB) model using the random forest machine learning algorithm, which was applied to three coastal areas around the Korean Peninsula with distinct characteristics: clear waters (Samcheok), high turbidity (Cheonsuman), and varied seabed sediments (Hallim). We then compared the accuracy of the bathymetric mapping data derived in these three areas. The estimated depth values exhibited the highest accuracy in Samcheok, followed by Hallim and Cheonsuman. Based on Worldview-3 images and on-site surveys, we confirmed the presence of basalt on the seabed. However, the remote reflectance was attenuated due to the effect of the black rock, leading to an overestimation of the depth. In the future, additional satellite images will be applied as training data for the machine learning model to advance the SDB technology using turbidity and seabed sediment distribution data for each area. Ultimately, the SDB results will be applied as depth monitoring data to facilitate safe ship passage in coastal areas, including ports that require periodic and consistent coastal bathymetry. In addition, they can be applied as input data for numerical ocean models, contributing to various fields.

show abstract

Automated classification of valid and invalid satellite derived bathymetry with random forest

Sharr,

Parrish,

Jung

2024

International Journal of Applied Earth Observation and Geoinfor

View full text Add to dashboard Cite

Incorporation of neighborhood information improves performance of SDB models

Cited by 7 publications

References 60 publications

Dense neural network outperforms other machine learning models for scaling-up lichen cover maps in Eastern Canada

Dense neural network outperforms other machine learning models for scaling-up lichen cover maps in Eastern Canada

Estimation of shallow bathymetry using Sentinel-2 satellite data and random forest machine learning: a case study for Cheonsuman, Hallim, and Samcheok Coastal Seas

Automated classification of valid and invalid satellite derived bathymetry with random forest

Contact Info

Product

Resources

About