Acoustic Characterization of Seafloor Sediment Employing a Hybrid Method of Neural Network Architecture and Fuzzy Algorithm

De, Chanchal; Chakraborty, Bhaskar

doi:10.1109/lgrs.2009.2024438

Cited by 20 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of the two multifractal techniques could substantiate the hitherto applied numerical inversion based characterization [12], [13], and the soft computational technique based classification [14], [15], of the seafloor sediments employing the backscatter data. The section on 'material and methods' covers the study area, data set descriptions, and the implementation aspects of the multifractal techniques.…”

Section: Introductionmentioning

confidence: 89%

Multifractal Approach for Seafloor Characterization

Chakraborty

Haris

Latha

et al. 2014

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

This study involves multifractal characterization of pockmark seepage associated seafloor along the central part of the western continental margin of India (WCMI). Six representative blocks of backscatter and bathymetry co-registered image data were used to characterize the seafloor. Two distinct multifractal formalisms were applied to determine the characteristics. The first formalism employs data analyses using generalized dimension D(q) and multifractal singularity spectrum f(α) linked shape parameters, based on the 'strange' attractors that exhibit multifractal scaling. The second approach is designed as 'stochastic' multifractal fields that connect the image block quantification to the three fundamental parameters namely, degree of multifractality α, sparseness C 1 and degree of smootheness H. The present investigation using the two multifractal formalisms to characterize the seafloor backscatter and bathymetry data provides comparative results that can be expounded upon.

show abstract

Section: Introductionmentioning

confidence: 89%

Multifractal Approach for Seafloor Characterization

Chakraborty

Haris

Latha

et al. 2014

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

show abstract

“…As a result, an echo recorded at a greater depth is expanded in time and an echo recorded at a lesser depth is compressed along the time axis (when compared with a reference depth). Consequently, the acoustic returns from the same seafloor sediment type lying at different depths do not have the same shape (De and Chakraborty, 2009). Accordingly, a first-order correction was applied to remove the influence of the depth on the time spread.…”

Section: Depth-dependent Correctionmentioning

confidence: 99%

“…Several studies while comparing the fractal dimension of the echo envelopes with the ground truth sediment have concluded that the fractal dimension (as a measure of complexity and roughness) is a good descriptor of a bottom type in the investigated area (Tegowski and Lubniewski, 2000;Tegowski et al, 2003;Tegowski, 2005;van Walree et al, 2005;De and Chakraborty, 2009). The fractal dimension describes the statistical and geometrical properties of the data.…”

Section: Relationship With Fractal Dimensionsmentioning

confidence: 99%

“…The model-based techniques often utilize physics-based acoustic backscatter models to characterize the seafloor sediments by optimizing the match between the measured and the modeled signals (Sternlicht and de Moustier, 2003a, b;van Walree et al, 2006;De and Chakraborty, 2011;Snellen et al, 2011). The empirical methods however rely on the statistical and artificial neural network-based approaches to correlate the features of echo signals with the sediment type (van Walree et al, 2005;Chakraborty et al, 2004;De and Chakraborty, 2009;Amiri-Simkooei et al, 2011;Madricardo et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stochastic formalism-based seafloor feature discrimination using multifractality of time-dependent acoustic backscatter

Haris

Chakraborty

2014

Nonlin. Processes Geophys.

Self Cite

View full text Add to dashboard Cite

Abstract. Dual-frequency echo-envelope data acquired using the normal-incidence single-beam echosounder system (SBES) have been examined to study its scale invariant properties. The scaling and multifractality of the SBES echo envelopes (at 33 and 210 kHz) were validated by applying a stochastic-based multifractal analysis technique. The analyses carried out substantiate the hierarchy of multiplicative cascade dynamics in the echo envelopes, demonstrating a first-order multifractal phase transition. The resulting scale invariant parameters (α, C 1 , and H ) establish gainful information that can facilitate distinctive delineation of the sediment provinces in the central part of the western continental shelf of India. The universal multifractal parameters among the coarse and fine sediments exhibit subtle difference in α and H , whereas the codimension parameter C 1 representing the sparseness of the data varies. The C 1 values are well clustered at both the acoustic frequencies, demarcating the coarse and fine sediment provinces. Statistically significant correlations are noticeable between the computed C 1 values and the ground truth sediment information. The variations in the multifractal parameters and their behavior with respect to the ground truth sediment information are in good corroboration with the previously estimated sediment geoacoustic inversion results obtained at the same locations.

show abstract

“…In seabed as well as terrestrial land cover mapping unsupervised techniques have been previously used to create attribute classes and maps from geophysical and remote sensing data which could then be linked to geology by means of ground-truth samples (e.g. Paasche et al 2006;De & Chakraborty 2009;Eberle et al 2015). More recently supervised machine learning techniques became popular for predictive modelling of marine sediment (e.g.…”

mentioning

confidence: 99%

Predictive modelling of grain-size distributions from marine electromagnetic profiling data using end-member analysis and a radial basis function network

Baasch

Müller

Dobeneck

2018

Geophysical Journal International

View full text Add to dashboard Cite

In this work, we present a new methodology to predict grain-size distributions from geophysical data. Specifically, electric conductivity and magnetic susceptibility of seafloor sediments recovered from electromagnetic profiling data are used to predict grain-size distributions along shelf-wide survey lines. Field data from the NW Iberian shelf are investigated and reveal a strong relation between the electromagnetic properties and grain-size distribution. The here presented workflow combines unsupervised and supervised machine-learning techniques. Non-negative matrix factorization is used to determine grain-size end-members from sediment surface samples. Four end-members were found, which well represent the variety of sediments in the study area. A radial basis function network modified for prediction of compositional data is then used to estimate the abundances of these end-members from the electromagnetic properties. The end-members together with their predicted abundances are finally back transformed to grain-size distributions. A minimum spatial variation constraint is implemented in the training of the network to avoid overfitting and to respect the spatial distribution of sediment patterns. The predicted models are tested via leave-one-out crossvalidation revealing high prediction accuracy with coefficients of determination (R 2) between 0.76 and 0.89. The predicted grain-size distributions represent the well-known sediment facies and patterns on the NW Iberian shelf and provide new insights into their distribution, transition and dynamics. This study suggests that electromagnetic benthic profiling in combination with machine learning techniques is a powerful tool to estimate grain-size distribution of marine sediments.

show abstract

Acoustic Characterization of Seafloor Sediment Employing a Hybrid Method of Neural Network Architecture and Fuzzy Algorithm

Cited by 20 publications

References 25 publications

Multifractal Approach for Seafloor Characterization

Multifractal Approach for Seafloor Characterization

Stochastic formalism-based seafloor feature discrimination using multifractality of time-dependent acoustic backscatter

Predictive modelling of grain-size distributions from marine electromagnetic profiling data using end-member analysis and a radial basis function network

Contact Info

Product

Resources

About