A Novel Sub-Bottom Profiler Seabed Sediment Classification Method Based on BPNN With Biot-Stoll Model and Attenuation-Based Model

Abstract

The exploitation and utilization of seabed sediments provide vital significance in many field. Recently, the classification of seabed sediments using Sub-Bottom Profiler (SBP) data has become a research focus. Concretely speaking, SBP data can be applied not only for recognizing the individual stratigraphic layers but also for classifying the seabed sediments by inversion models. To improve the sorting effect of gravel and mud simultaneously, we propose a sediment classification method based on the back propagation neural network (BPNN) with the Biot-Stoll model and the Attenuation-Based model. In this method, two datasets of the mean grain size derived from these two models respectively are trained through the BPNN classifier to classify seabed sediments. The proposed method is verified through the SBP data and in-situ sampling data collected from the sea north of Shandong Peninsula, China. The experimental results show that the overall accuracy of sediment classification is 89.4%, and the classification accuracy of gravel and mud reach 91.4% and 93.3%, respectively, confirming that gravel and mud can be more accurately distinguished based on the proposed method than the single Biot-Stoll model and the single Attenuation-Based model.

A review on the methane emission detection during offshore natural gas hydrate production

“…The instrument has high performance in formation resolution and formation penetration depth, and can choose any combination of sweep signals to design and adjust working parameters in real time, as well as to measure bedrock depth and thickness in offshore oilfield drilling (Yang et al, 2021). Therefore, it is a widely used instrument in Marine geological survey, geophysical exploration and ocean engineering, ocean observation, seabed resources exploration and development, waterway harbor engineering, seabed pipeline laying (Li et al, 2021).…”

Reflection signal classification of deep-sea surface sediment based on 1DCNN-DLSTM networks

“…Back-propagation neural network [11][12] is mostly used in the current research on SBP image classification. The basic principle and training algorithm of BP neural network are relatively simple and easy to understand and implement.…”