Remote sensing of water depths in shallow waters via artificial neural networks

Özçelik, Ceyhun; Yalçın, Arısoy

doi:10.1016/j.ecss.2010.05.015

Cited by 104 publications

(53 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although it could be argued that non-linear analysis techniques such as successive approximation models, look-up tables or neural networks [17,18,46,47] may perform better under certain circumstances than the linear separability measure used here, the significant spectral space class overlap that must be present for some factor combinations will confound any analytical method. Similarly, any pre-processing steps that only manipulate individual pixel spectra, such as removing water column effects by depth invariant indices [22,44] will have little impact on separability as identical spectra remain identical after transformation.…”

Section: Discussionmentioning

confidence: 99%

Environmental and Sensor Limitations in Optical Remote Sensing of Coral Reefs: Implications for Monitoring and Sensor Design

et al. 2012

View full text Add to dashboard Cite

A generic method was developed for analysing the capabilities of optical remote sensing of aquatic systems in terms of environmental components and imaging sensor configurations. The method was based on a component based model of the entire system in which not only benthic composition but other environmental components such as water inherent optical properties (IOPs), bathymetry, sun elevation, wind speed and sensor noise characteristics were defined by datasets with the potential to include across-image variation. The model was applied to data from Pacific Ocean reefs in an airborne sensor context to estimate the primary environmental or sensor factors confounding discrimination of benthic mixtures of key reef types: live coral, bleached coral, dead coral and macroalgae. Results indicate that spectral variation of benthic types and sub-pixel mixing is the primary limiting factor for benthic mapping objectives, whereas instrument noise levels are a minor factor.

show abstract

Section: Discussionmentioning

confidence: 99%

Environmental and Sensor Limitations in Optical Remote Sensing of Coral Reefs: Implications for Monitoring and Sensor Design

et al. 2012

View full text Add to dashboard Cite

show abstract

“…Therefore, it can use multi-band images for getting more accurate water depths [1]. Image bands are transformed through this approach to new uncorrelated bands known as components ordered by the amount of image variation they can elucidate [34].…”

Section: ) Imagery Data Pre-processingmentioning

confidence: 99%

“…Accurate bathymetric information is so important for costal science applications, shipping navigations and environmental studies of marine areas [1]. Mapping underwater features as rocks, sandy areas, sediments accumulation and coral reefs needs up to date water depths information [2], [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bathymetry Determination from High Resolution Satellite Imagery Using Ensemble Learning Algorithms in Shallow Lakes: Case Study El-Burullus Lake

Mohamed¹,

Negm²,

Zahran³

et al. 2016

IJESD

View full text Add to dashboard Cite

Abstract-Determination of bathymetric information is key element for near off shore activities and hydrological studies such as coastal engineering applications, sedimentary processes and hydrographic surveying. Remotely sensed imagery has provided a wide coverage, low cost and time-effective solution for bathymetric measurements. In this paper a methodology is introduced using Ensemble Learning (EL) fitting algorithm of Least Squares Boosting (LSB) for bathymetric maps calculation in shallow lakes from high resolution satellite images and water depth measurement samples using Eco-sounder. This methodology considered the cleverest sequential ensemble that assigns higher weights as Boosting for those training sets that are difficult to fit. The LSB ensemble using reflectance of Green and Red bands and their logarithms from Spot-4 satellite image was compared with two conventional methods; the Principal Component Analysis (PCA) and Generalized Linear Model (GLM). The retrieved bathymetric information from the three methods was evaluated using Echo Sounder data. The LSB fitting ensemble resulted in RMSE of 0.15m where the PCA and GLM yielded RMSE of 0.19m and 0.18m respectively over shallow water depths less than 2m. The application of the proposed approach demonstrated better performance and accuracy compared with the conventional methods.Index Terms-Bathymetry, PCA, GLM, least square boosting. I. INTRODUCTIONAccurate bathymetric information is so important for costal science applications, shipping navigations and environmental studies of marine areas [1]. Mapping underwater features as rocks, sandy areas, sediments accumulation and coral reefs needs up to date water depths information [2], [3]. Water depths data are essential also for accomplishing sustainable management [4], bathymetric information constitutes a key element hydrological modeling, flooding estimation and degrading or sediments removing [5], [6]. Manuscript received November 25, 2014; revised April 27, 2015. The work was supported by Mission Department, Egyptian Ministry of Higher Education (MoHE), Egypt-Japan University of Science and Technology (E-JUST) and partially supported by JSPS "Core-to-Core Program, B. Asia-Africa Science Platforms".H. Mohamed and Abdelazim Negm are with the Environmental Engineering Department, School of Energy and Environmental Engineering, Egypt-Japan University of Science and Technology, Alexandria, Egypt (e-mail: hassan.mohamed@ejust.edu.eg, negm@ejust.edu.eg).M. Zahran is with the Department of Geomatics Engineering, Faculty of Engineering at Shoubra, Benha University, Egypt (e-mail: mohamed.zahran01@feng.bu.edu.eg).O. Saavedra is with the Department of Civil Engineering, Tokyo Institute of Technology, Oookayama, Meguro, Tokyo, Japan. He is also with E-JUST, Egypt (e-mail: saavedra.o.aa@m.titech.ac.jp).Sonar remains the primary method for obtaining discreet water depth measurements with high accuracy [7]. Single beam sonar on survey vessel can acquire single point depths along sparsely surveying scan lines up to 50...

show abstract

“…The amount of detail in a bathymetry dataset depends on the resolution of the mapping system, its spatial accuracy, the amount of time and effort expended in making it, as well as consideration of its intended use (Ceyhun & Yalçın, 2010).…”

Section: Introductionmentioning

confidence: 99%

The Use of Digital Elevation Models (DEMs) for Bathymetry Development in Large Tropical Reservoirs

Anda¹,

Rangel‐Peraza²,

Obregon³

et al. 2012

Bathymetry and Its Applications

View full text Add to dashboard Cite

Remote sensing of water depths in shallow waters via artificial neural networks

Cited by 104 publications

References 15 publications

Environmental and Sensor Limitations in Optical Remote Sensing of Coral Reefs: Implications for Monitoring and Sensor Design

Environmental and Sensor Limitations in Optical Remote Sensing of Coral Reefs: Implications for Monitoring and Sensor Design

Bathymetry Determination from High Resolution Satellite Imagery Using Ensemble Learning Algorithms in Shallow Lakes: Case Study El-Burullus Lake

The Use of Digital Elevation Models (DEMs) for Bathymetry Development in Large Tropical Reservoirs

Contact Info

Product

Resources

About