Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559198
Jin-yan Du, Yi Zheng, Zongwei Liu, Zhen Wang, Hao Cui, Ye Li
The ocean ambient noise contains abundant information of the ocean environment, so it is necessary to study its characteristics. As a function of frequency, geographical location and time, the directivity of ambient noise is an important characteristic of ocean ambient noise and an important factor affecting the gain of hydrophone array. A single vector hydrophone can simultaneously measure the acoustic pressure and particle velocity at the same point, and can be considered as a scalar array. In this paper, a method using minimum variance distortionless response (MVDR) beamforming for ocean ambient noise directivity analysis is studied, and the measured data of a shallow ocean low frequency ambient noise received by a single vector hydrophone is processed and analyzed. The results can be used to understand the ocean ambient noise characteristics of the area.
{"title":"Investigation of the Directivity of Shallow Ocean Low Frequency Ambient Noise with Single Vector Hydrophone","authors":"Jin-yan Du, Yi Zheng, Zongwei Liu, Zhen Wang, Hao Cui, Ye Li","doi":"10.1109/OCEANSKOBE.2018.8559198","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559198","url":null,"abstract":"The ocean ambient noise contains abundant information of the ocean environment, so it is necessary to study its characteristics. As a function of frequency, geographical location and time, the directivity of ambient noise is an important characteristic of ocean ambient noise and an important factor affecting the gain of hydrophone array. A single vector hydrophone can simultaneously measure the acoustic pressure and particle velocity at the same point, and can be considered as a scalar array. In this paper, a method using minimum variance distortionless response (MVDR) beamforming for ocean ambient noise directivity analysis is studied, and the measured data of a shallow ocean low frequency ambient noise received by a single vector hydrophone is processed and analyzed. The results can be used to understand the ocean ambient noise characteristics of the area.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126617234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559193
David P. Williams
A new image complexity metric has been developed that fuses the concept of lacunarity, a measure of pixel intensity variation, with the notion of spatial information, a quantity that captures edge energy. This new metric, which we call the “muesli” complexity, successfully quantifies the relative difficulty of performing target detection in synthetic aperture sonar (SAS) images. This has been experimentally validated via the results of a human operator study, as well as the results of an object detection algorithm, using a set of over 3000 SAS images collected in diverse environments. In the former assessment method, it has been observed that the subjective human rankings of image difficulty correlate well with the complexity value. In the latter examination approach, it has been observed that the degrees to which false alarms are generated and true targets are missed by the detection algorithm are each proportional to the complexity value of the image.
{"title":"The New Muesli Complexity Metric for Mine-Hunting Difficulty in Sonar Images","authors":"David P. Williams","doi":"10.1109/OCEANSKOBE.2018.8559193","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559193","url":null,"abstract":"A new image complexity metric has been developed that fuses the concept of lacunarity, a measure of pixel intensity variation, with the notion of spatial information, a quantity that captures edge energy. This new metric, which we call the “muesli” complexity, successfully quantifies the relative difficulty of performing target detection in synthetic aperture sonar (SAS) images. This has been experimentally validated via the results of a human operator study, as well as the results of an object detection algorithm, using a set of over 3000 SAS images collected in diverse environments. In the former assessment method, it has been observed that the subjective human rankings of image difficulty correlate well with the complexity value. In the latter examination approach, it has been observed that the degrees to which false alarms are generated and true targets are missed by the detection algorithm are each proportional to the complexity value of the image.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124195689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559128
J. Koch, T. Pailevanian, M. Garrett, C. Yahnker, Renuad Detry, D. Levine, M. Gildner
This paper presents the hardware design and development of the AquaSimian limb, a 7 degree of freedom robotic limb for performing manipulation tasks typical to the subsea servicing industry. Tasks are performed through a supervised autonomy framework that makes efficient use of operator input, 3D scene reconstructions, automated motion planning, and parameterized behaviors. The limb must robustly interact with its environment to perform tasks such as turning a subsea valve or inserting a hot stab. The limb features high power density actuators and a 6 degree of freedom force torque sensor. A custom 3-function robotic gripper mounted to the force torque sensor allows dexterous yet robust interaction with underwater task panels. The system includes capabilities to detect and autonomously respond to any leaks or motor faults by disconnecting motor power when the system is in an off-nominal state and notifying the operator through LED lighting on the Light Lids that seal the actuator assembly housings. This highly capable robotic limb serves as a testbed for JPL development of technologies for autonomous operation of mobile manipulation systems.
{"title":"Development of a Robotic Limb for Underwater Mobile Manipulation","authors":"J. Koch, T. Pailevanian, M. Garrett, C. Yahnker, Renuad Detry, D. Levine, M. Gildner","doi":"10.1109/OCEANSKOBE.2018.8559128","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559128","url":null,"abstract":"This paper presents the hardware design and development of the AquaSimian limb, a 7 degree of freedom robotic limb for performing manipulation tasks typical to the subsea servicing industry. Tasks are performed through a supervised autonomy framework that makes efficient use of operator input, 3D scene reconstructions, automated motion planning, and parameterized behaviors. The limb must robustly interact with its environment to perform tasks such as turning a subsea valve or inserting a hot stab. The limb features high power density actuators and a 6 degree of freedom force torque sensor. A custom 3-function robotic gripper mounted to the force torque sensor allows dexterous yet robust interaction with underwater task panels. The system includes capabilities to detect and autonomously respond to any leaks or motor faults by disconnecting motor power when the system is in an off-nominal state and notifying the operator through LED lighting on the Light Lids that seal the actuator assembly housings. This highly capable robotic limb serves as a testbed for JPL development of technologies for autonomous operation of mobile manipulation systems.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123656980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559159
B. Binnerts, I. Mulders, Koen C. H. Blom, M. Colin, H. Dol
Autonomous Underwater Vehicles (AUVs) offer an automated solution for the collection of environmental data underwater. While they provide an effective solution in scenarios where their task is limited to basic sensor data collection, supervisory control by an operator is still needed to make more complicated decisions. Because raw data of camera and sonar data is too large in size to be communicated acoustically underwater, the assessment of data is performed post mission. This delayed access can however lead to ineffective data collection (if the data quality is found to be insufficient post mission) and longer operations that depend on the data can only be done after the data has been collected. In order to enhance the situational awareness and decision-making capabilities of AUV operators, we investigate and demonstrate in this paper the feasibility of underwater acoustic streaming of camera and sonar data. First, the performance of the underwater acoustic MSFRSS modulation is investigated by means of channel replay simulations. Next, the efficiency of the JPEG 2000 image compression and HEVC video compression protocols is analysed. Finally, the combined performance of these two technologies is tested in the TNO anechoic basin (water tank) using a demonstration setup. Although further tests of the system under more realistic operational conditions are needed to quantify its performance, the first results are promising and indicate that live underwater acoustic streaming is a realistic future capability of AUVs.
{"title":"Development and Demonstration of a Live Data Streaming Capability Using an Underwater Acoustic Communication Link","authors":"B. Binnerts, I. Mulders, Koen C. H. Blom, M. Colin, H. Dol","doi":"10.1109/OCEANSKOBE.2018.8559159","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559159","url":null,"abstract":"Autonomous Underwater Vehicles (AUVs) offer an automated solution for the collection of environmental data underwater. While they provide an effective solution in scenarios where their task is limited to basic sensor data collection, supervisory control by an operator is still needed to make more complicated decisions. Because raw data of camera and sonar data is too large in size to be communicated acoustically underwater, the assessment of data is performed post mission. This delayed access can however lead to ineffective data collection (if the data quality is found to be insufficient post mission) and longer operations that depend on the data can only be done after the data has been collected. In order to enhance the situational awareness and decision-making capabilities of AUV operators, we investigate and demonstrate in this paper the feasibility of underwater acoustic streaming of camera and sonar data. First, the performance of the underwater acoustic MSFRSS modulation is investigated by means of channel replay simulations. Next, the efficiency of the JPEG 2000 image compression and HEVC video compression protocols is analysed. Finally, the combined performance of these two technologies is tested in the TNO anechoic basin (water tank) using a demonstration setup. Although further tests of the system under more realistic operational conditions are needed to quantify its performance, the first results are promising and indicate that live underwater acoustic streaming is a realistic future capability of AUVs.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122393413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559225
Razieh Nejati Fard, O. Eidsvik, E. Tedeschi, Ingrid Schølberg
The aim of this paper is to present a methodology for selecting proper voltage level and power cables as a part of the AC distribution system design for subsea vehicles, such as Remotely Operated Vehicles, seafloor trenchers and subsea mining machines. The design methodology encompasses a wide range of cable lengths and load power demands (up to 7 MW). Furthermore, both electrical and mechanical considerations have been taken into account in order to provide an optimum design for the power cable. The final decision is made considering the main parameters including voltage drop, power loss, reactive power exchanged in the cable, conductor cost, and top and bottom tension forces acting on the cable.
{"title":"Cable Selection Considerations for Subsea Vehicles","authors":"Razieh Nejati Fard, O. Eidsvik, E. Tedeschi, Ingrid Schølberg","doi":"10.1109/OCEANSKOBE.2018.8559225","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559225","url":null,"abstract":"The aim of this paper is to present a methodology for selecting proper voltage level and power cables as a part of the AC distribution system design for subsea vehicles, such as Remotely Operated Vehicles, seafloor trenchers and subsea mining machines. The design methodology encompasses a wide range of cable lengths and load power demands (up to 7 MW). Furthermore, both electrical and mechanical considerations have been taken into account in order to provide an optimum design for the power cable. The final decision is made considering the main parameters including voltage drop, power loss, reactive power exchanged in the cable, conductor cost, and top and bottom tension forces acting on the cable.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124853583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559178
W. Wilcock, D. Manalang, M. Harrington, E. Fredrickson, G. Cram, J. Tilley, J. Burnett, Derek Martin, Taro Kobayashi, J. Paros
Seafloor geodesy is challenging but important for understanding the hazards from earthquakes and tsunamis along subduction zones. Two methods of seafloor geodesy are presented based on obtaining self-calibrated measurements with resonant quartz crystal technology sensors. The A-0-A method for calibrating pressure observations utilizes the internal pressure of the instrument housing as a reference pressure to calibrate sensor drift. An 8-month seafloor test at a depth of 900 m, shows the method has reduced the relative drift between two pressure sensors to <1 mm. The rotating (or flipping) tiltmeter calibrates the accelerations of the horizontal channels of a triaxial accelerometer by rotating them into the vertical where the acceleration of gravity is used as a reference acceleration. Laboratory tests are very promising and deployments are planned on the seafloor and at a geodetic observatory.
{"title":"New Approaches to In Situ Calibration for Seafloor Geodetic Measurements","authors":"W. Wilcock, D. Manalang, M. Harrington, E. Fredrickson, G. Cram, J. Tilley, J. Burnett, Derek Martin, Taro Kobayashi, J. Paros","doi":"10.1109/OCEANSKOBE.2018.8559178","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559178","url":null,"abstract":"Seafloor geodesy is challenging but important for understanding the hazards from earthquakes and tsunamis along subduction zones. Two methods of seafloor geodesy are presented based on obtaining self-calibrated measurements with resonant quartz crystal technology sensors. The A-0-A method for calibrating pressure observations utilizes the internal pressure of the instrument housing as a reference pressure to calibrate sensor drift. An 8-month seafloor test at a depth of 900 m, shows the method has reduced the relative drift between two pressure sensors to <1 mm. The rotating (or flipping) tiltmeter calibrates the accelerations of the horizontal channels of a triaxial accelerometer by rotating them into the vertical where the acceleration of gravity is used as a reference acceleration. Laboratory tests are very promising and deployments are planned on the seafloor and at a geodetic observatory.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128968832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559248
Hyeonwoo Cho, Son-cheol Yu
Red snow crabs are an important resource for the fishing industry. They live at the bottom of the sea, and fish traps are used by fishermen to catch the snow crabs. The fishing period is typically one week, and ideally, the traps should have bait available for the entire duration in order to catch the maximum number of snow crabs. Fishermen in the East Sea of South Korea have utilized two types of fishing bait. The first is bait wrapped in a plastic bag to prevent the snow crabs from eating the bait, and the second is unwrapped bait. This study investigates the trade-off relationship between the duration longevity of the wrapped bait with the luring capability of the unwrapped bait. To measure each parameter, an underwater camera system was developed to record events inside the trap during the fishing expedition for each instance. The study determined the unwrapped bait to be two times more effective than the wrapped bait, in terms of the number of red snow crabs captured.
{"title":"Underwater Camera System to Observe Effect of Fishing Bait on Number of Caught Snow Crabs","authors":"Hyeonwoo Cho, Son-cheol Yu","doi":"10.1109/OCEANSKOBE.2018.8559248","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559248","url":null,"abstract":"Red snow crabs are an important resource for the fishing industry. They live at the bottom of the sea, and fish traps are used by fishermen to catch the snow crabs. The fishing period is typically one week, and ideally, the traps should have bait available for the entire duration in order to catch the maximum number of snow crabs. Fishermen in the East Sea of South Korea have utilized two types of fishing bait. The first is bait wrapped in a plastic bag to prevent the snow crabs from eating the bait, and the second is unwrapped bait. This study investigates the trade-off relationship between the duration longevity of the wrapped bait with the luring capability of the unwrapped bait. To measure each parameter, an underwater camera system was developed to record events inside the trap during the fishing expedition for each instance. The study determined the unwrapped bait to be two times more effective than the wrapped bait, in terms of the number of red snow crabs captured.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127867412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559064
K. Shen, G. Pan, Jun Jiang, Zhun Li, R. Wei
The paper presented an optimization design of filament-wound composites pressure hull subjected to hydrostatic pressure for underwater vehicle application. An Optimization Platform was set up by interworking a genetic algorithm and numerical simulation. A sensitivity analysis was performed to study the effects of design variables on the buckling pressure, material failure pressure and design pressure. Results revealed that the buckling pressure or the material failure pressure would restrict the design pressure of different thickness of pressure shell. Application of composite materials for deep-water pressure shell had more reserve buoyancy, which would result in miniaturizing the size of underwater vehicles. Effects of different type of ring-stiffened configuration were analyzed. Mid-stiffened configuration can enhance stability significantly. End-stiffened configuration can minimize the effect of stiffness mismatch. Results of this study provided a valuable reference for designers of underwater vehicles. The paper suggest that new way of enhancement, such as variable thickness, composites ribs would be used to solve the conflict of buckling pressure and material failure pressure.
{"title":"Design Optimization of Composite Cylindrical Shell Under Hydrostatic Pressure","authors":"K. Shen, G. Pan, Jun Jiang, Zhun Li, R. Wei","doi":"10.1109/OCEANSKOBE.2018.8559064","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559064","url":null,"abstract":"The paper presented an optimization design of filament-wound composites pressure hull subjected to hydrostatic pressure for underwater vehicle application. An Optimization Platform was set up by interworking a genetic algorithm and numerical simulation. A sensitivity analysis was performed to study the effects of design variables on the buckling pressure, material failure pressure and design pressure. Results revealed that the buckling pressure or the material failure pressure would restrict the design pressure of different thickness of pressure shell. Application of composite materials for deep-water pressure shell had more reserve buoyancy, which would result in miniaturizing the size of underwater vehicles. Effects of different type of ring-stiffened configuration were analyzed. Mid-stiffened configuration can enhance stability significantly. End-stiffened configuration can minimize the effect of stiffness mismatch. Results of this study provided a valuable reference for designers of underwater vehicles. The paper suggest that new way of enhancement, such as variable thickness, composites ribs would be used to solve the conflict of buckling pressure and material failure pressure.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131765411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1109/OCEANSKOBE.2018.8559113
Elizaveta Dubrovinskaya, F. Dalgleish, B. Ouyang, P. Casari
The in situ detection, recognition and tracking of marine animal species is a very important step of field research in the domains of, among others, biology and ecology. Still, the direct observation of marine wildlife through equipment operating in the visible light spectrum is often impaired by the challenging conditions offered by ocean waters, where light can be subject to scattering and attenuation phenomena due to the water turbidity. As the use of powerful lighting may prove ineffective and even induce behavioral changes in marine animals, the design of minimally or non-invasive observation instruments becomes particularly important. In this paper, we consider the serial Light Detection And Ranging (LiDAR) system under development at the Florida Atlantic University (FAU). This LiDAR design is based on inexpensive components and on low average power red lasers which are subject to significant attenuation in water, but are both eye-safe and invisible to marine life. Considering the challenge of detecting and evaluating the presence of marine wildlife, we present a full processing pipeline for LiDAR data, that includes water turbidity detection, non-gated backscattering compensation, contrast enhancement, and the construction of a three-dimensional model of the detected target. The pipeline is applied to a number of tank test data, under different turbidity conditions.
{"title":"Underwater LiDAR Signal Processing for Enhanced Detection and Localization of Marine Life","authors":"Elizaveta Dubrovinskaya, F. Dalgleish, B. Ouyang, P. Casari","doi":"10.1109/OCEANSKOBE.2018.8559113","DOIUrl":"https://doi.org/10.1109/OCEANSKOBE.2018.8559113","url":null,"abstract":"The in situ detection, recognition and tracking of marine animal species is a very important step of field research in the domains of, among others, biology and ecology. Still, the direct observation of marine wildlife through equipment operating in the visible light spectrum is often impaired by the challenging conditions offered by ocean waters, where light can be subject to scattering and attenuation phenomena due to the water turbidity. As the use of powerful lighting may prove ineffective and even induce behavioral changes in marine animals, the design of minimally or non-invasive observation instruments becomes particularly important. In this paper, we consider the serial Light Detection And Ranging (LiDAR) system under development at the Florida Atlantic University (FAU). This LiDAR design is based on inexpensive components and on low average power red lasers which are subject to significant attenuation in water, but are both eye-safe and invisible to marine life. Considering the challenge of detecting and evaluating the presence of marine wildlife, we present a full processing pipeline for LiDAR data, that includes water turbidity detection, non-gated backscattering compensation, contrast enhancement, and the construction of a three-dimensional model of the detected target. The pipeline is applied to a number of tank test data, under different turbidity conditions.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134050262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-28DOI: 10.1175/JTECH-D-17-0217.1
K. Patil, M. Deo
Prediction of sea surface temperature (SST) is desired for several applications ranging from climate studies to maintenance of coastal eco-system. Such prediction with the help of artificial, or simply, neural network has by now fairly stabilized. However corresponding studies are mostly applicable only to a specified single location. In this study we have expanded them to cover an entire sea basin. The basin under consideration is Bay of Bengal (BoB) located on the east side of the Indian peninsula. We have predicted SST at the daily time scale using time series approach in which we feed a selected length of past daily SST observations to the neural network and derive the predicted value of SST at multiple lead times (days) as output. The gridded NOAA v2 high resolution dataset derived from satellites was used for this purpose. At every grid in the BoB feed forward back propagation type of neural network was developed. The networks were trained using 70% of data and tested with the help of remaining 30%. The performance in testing of such large spatial-scale networks was judged on the basis of the error statistics of correlation coefficient, ‘r’, and root mean square error, RMSE. The prediction skill of ANN models were found to be very good at shorter lead times (1-3 days) and reasonably good at higher lead times (4-7 days). Apart from that, these ANN models were also evaluated for their performance during extreme weather events which are peculiar to BoB region and found to be capturing such events in advance with sufficient time. Overall therefore it is claimed that the basin-scale neural networks developed in this study can not only carry out multiple time step predictions of daily SST at individual grid points simultaneously but can also predict basin scale weather phenomena in advance.
{"title":"Basin-Scale Prediction of Sea Surface Temperature with Artificial Neural Networks","authors":"K. Patil, M. Deo","doi":"10.1175/JTECH-D-17-0217.1","DOIUrl":"https://doi.org/10.1175/JTECH-D-17-0217.1","url":null,"abstract":"Prediction of sea surface temperature (SST) is desired for several applications ranging from climate studies to maintenance of coastal eco-system. Such prediction with the help of artificial, or simply, neural network has by now fairly stabilized. However corresponding studies are mostly applicable only to a specified single location. In this study we have expanded them to cover an entire sea basin. The basin under consideration is Bay of Bengal (BoB) located on the east side of the Indian peninsula. We have predicted SST at the daily time scale using time series approach in which we feed a selected length of past daily SST observations to the neural network and derive the predicted value of SST at multiple lead times (days) as output. The gridded NOAA v2 high resolution dataset derived from satellites was used for this purpose. At every grid in the BoB feed forward back propagation type of neural network was developed. The networks were trained using 70% of data and tested with the help of remaining 30%. The performance in testing of such large spatial-scale networks was judged on the basis of the error statistics of correlation coefficient, ‘r’, and root mean square error, RMSE. The prediction skill of ANN models were found to be very good at shorter lead times (1-3 days) and reasonably good at higher lead times (4-7 days). Apart from that, these ANN models were also evaluated for their performance during extreme weather events which are peculiar to BoB region and found to be capturing such events in advance with sufficient time. Overall therefore it is claimed that the basin-scale neural networks developed in this study can not only carry out multiple time step predictions of daily SST at individual grid points simultaneously but can also predict basin scale weather phenomena in advance.","PeriodicalId":441405,"journal":{"name":"2018 OCEANS - MTS/IEEE Kobe Techno-Oceans (OTO)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132604463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：