Velocity Log Research Articles

Virtual Metrology Filter-Based Algorithms for Estimating Constant Ocean Current Velocity

The strap-down inertial navigation system (SINS) and Doppler velocity log (DVL) integrated navigation system are widely used for autonomous underwater vehicles (AUVs). Whereas DVL works in the water tracking mode, the velocity provided by DVL is relative to the current layer and cannot be directly used to suppress the divergence of SINS errors. Therefore, the estimation and compensation of the ocean current velocity play an essential role in improving navigation positioning accuracy. In recent works, ocean currents are considered constant over a short term in small areas. In the common KF algorithm with the ocean current as a state vector, the current velocity cannot be estimated because the current velocity and the SINS velocity error are coupled. In this paper, two virtual metrology filter (VMF) methods are proposed for estimating the velocity of ocean currents based on the properties that the currents remain unchanged at the adjacent moments. New measurement equations are constructed to decouple the current velocity and the SINS velocity error, respectively. Simulations and lake tests show that both proposed methods are effective in estimating the current velocity, and each has its advantages in estimating the ocean current velocity or the misalignment angle.

A novel INS/USBL/DVL integrated navigation scheme against complex underwater environment

In view of challenges of complex underwater environments with a high occurrence of sensor outliers, traditional Kalman filter (KF)-based localization methods are difficult to achieve precise positioning. To address this issue, a factor graph optimization (FGO)-based tightly-coupled (TC) inertial navigation system (INS)/ultra-short baseline system (USBL)/Doppler velocity log (DVL) scheme and core fusion algorithm are proposed. The FGO method is used to construct a TC INS/USBL/DVL factor graph model, and a weight function is added to adjust the weights of each factor, thereby improving the utilization of underwater sensor information and enhancing the accuracy and reliability of underwater navigation. The feasibility of the proposed scheme is verified through simulations and field tests. The results show that the proposed method outperforms KF-loosely-coupled (KF-LC), KF-TC, and FGO-LC methods, with horizontal position accuracy improvements of 29.2%, 6.6%, and 13.2%, respectively. Moreover, the proposed method exhibits smooth navigation error performance in the presence of abnormal sensor information.

A committee machine-based estimation of shear velocity log by combining intelligent systems and rock-physics model using metaheuristic algorithms

Estimation of reservoir parameters such as porosity, lithology and determination of elastic moduli is based on well-logging data and seismic velocity information. However, the lack of shear velocity log in many wells, and the high costs of its acquisition have led to developing different approaches for shear velocity estimation. Currently, shear velocity estimation is accomplished by common industrial methods such as empirical equations, regression analysis, intelligent methods and rock-physics models (RPMs). The current study proposes that robust, accurate and cost-effective intelligent methods coupled with suitable RPM provide reasonable estimations of the shear velocity in an optimal processing time. Hybridizing intelligent models with RPMs in the framework of a committee machine is an optimal solution for shear velocity estimation of carbonate reservoirs. The intelligent methods used in this study include neural network (NN), fuzzy logic (FL) and an adaptive-neuro fuzzy inference system (ANFIS). In this research, for each individual intelligent model and a developed RPM, the optimal weights were allocated by Metaheuristic optimization algorithms including genetic algorithm (GA), ant colony optimization routing (ACOR) and simulated annealing (SA)). To obtain the best results with the lowest mean squared error (MSE), a total of 9408, 10801 and 12288 models were created and tested in MATLAB to optimally parametrize the GA, ACOR and SA, respectively. The results showed that the combination of the applied intelligent models with the developed RPMs leads to a higher correlation coefficient with reference to the measured Shear velocity in test dataset. The use of a combination of intelligent methods in the form of committee-machine instead of individual methods has led to a reduction in error and improved the results by up to 2% Considering the high sensitivity of shear wave velocity in geomechanical and reservoir characterization studies, even small improvements in its estimation can significantly reduce error in the characterization of hydrocarbon reservoirs.

Estimation of constant ocean current velocity based on SINS/DVL integrated navigation with an augmented observable quantities filter

Ideally, navigation and positioning information for Autonomous Underwater Vehicles (AUVs) can be provided by a combined navigation system based on a velocity-matching Strap-down Inertial Navigation System (SINS) and Doppler velocity log (DVL). However, the velocity accuracy of DVL is affected by ocean currents when the DVL is operating in water track mode in deep ocean scenarios. The velocity of the currents remains stable over small areas of the ocean within a few hours and can be considered a constant value. Estimation and compensation of the ocean current velocity is a prerequisite for high-precision navigation performance and an important topic for oceanographic research. In this paper, we propose an Augmented Observable Quantities (AOQ)-based filter that constructs a new measurement equation from the difference between the velocities of the previous state and the current state to decouple the ocean current velocity from the velocity error of SINS, and without introducing other sources to provide any information on velocity or position. The simulation and lake test show that the AOQ filter can estimate the ocean current velocity and mitigate its effect on navigation accuracy.

Gas hydrate saturation from NGHP 02 LWD data in the Mahanadi Basin

During the Indian National Gas Hydrate Program (NGHP) Expedition 02, Logging-while-drilling (LWD) logs were acquired at three sites (NGHP-02-11, NGHP-02-12, and NGHP-02-13) across the Mahanadi Basin in area A. We applied rock physics theory to available sonic velocity logs to know the distribution of gas hydrate at site NGHP-02-11 and NGHP-02-13. Rock physics modeling using sonic velocity at well location shows that gas hydrate is distributed mainly within the depth intervals of 150–265 m and 100–215 mbsf at site NGHP-02-11 and NGHP-02-13, respectively, with an average saturation of about 4% of the pore space and the maximum concentration of about 40% of the pore space at 250 m depth at site NGHP-02-11, and at site NGHP-02-13 an average saturation of about 2% of the pore space and the maximum concentration of about 20% of the pore space at 246 m depth, as gas hydrate is distributed mainly within 100–246 mbsf at this site. Saturation of gas hydrate estimated from the electrical resistivity method using density derived porosity and electrical resistivity logs from Archie's empirical formula shows high saturation compared to that from the sonic log. However, estimates of hydrate saturation based on sonic P-wave velocity may differ significantly from that based on resistivity, because gas and hydrate have higher resistivity than conductive pore fluid and sonic P-wave velocity shows strong effect on gas hydrate as a small amount of gas reduces the velocity significantly while increasing velocity due to the presence of hydrate. At site NGHP-02-11, gas hydrate saturation is in the range of 15%–30%, in two zones between 150-180 and 245–265 mbsf. Site NGHP-02-012 shows a gas hydrate saturation of 20%–30% in the zone between 100 and 207 mbsf. Site NGHP-02-13 shows a gas hydrate saturation up to 30% in the zone between 215 and 246 mbsf. Combined observations from rock physics modeling and Archie’s approximation show the gas hydrate concentrations are relatively low (<4% of the pore space) at the sites of the Mahanadi Basin in the turbidite channel system.

Tightly Coupled, Graph-Based DVL/IMU Fusion and Decoupled Mapping for SLAM-Centric Maritime Infrastructure Inspection

In this article, we address the problem of simultaneous localization and mapping (SLAM)-centric maritime infrastructure inspection [using unmanned surface vehicles (USVs)] via novel approaches in tightly-coupled, graph-based DVL/IMU fusion and decoupled mapping. As our first contribution, we formalize the preintegration of linear velocity measurements, obtained by a Doppler velocity log (DVL), in combination with angular velocity measurements, obtained by an inertial measurement unit (IMU), as binary factors encoding relative position. To evaluate state estimation improvements imparted by DVL/IMU fusion, we implement our proposed factor within a state-of-the-art, graph-based lidar-visual-inertial (LVI) SLAM system as our second contribution. Accuracy and robustness improvements are demonstrated in simulation by comparing maximum <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a posteriori</i> pose estimates with and without DVL/IMU fusion against ground truth poses. As our third contribution, we propose a map generation framework for downstream inspection applications decoupled from SLAM. In our framework, volumetric data (captured by sonar, lidar, etc.) is transformed into a common world coordinate frame using extrinsic calibrations and SLAM pose estimates as input. Our framework operates over the complete set of raw volumetric data, whereas SLAM systems (both online and offline) typically operate over a subset of down-sampled volumetric data. To address the processing of additional volumetric data, we present innovations in refined pose correction and staged filtering for user-controlled denoising. We experimentally evaluate our map generation framework against the LVI SLAM system adopted for this study using real-world data and demonstrate improvements to map quality metrics important to inspection.

A performance-enhanced DVL/SINS integrated navigation system based on data-driven approach

With the aid of Doppler velocity logger (DVL), strapdown inertial navigation systems (SINSs) can provide continuous and accurate navigation parameters for unmanned underwater vehicles (UUVs). However, owing to the complex underwater environment, partial DVL beams may fail to be reflected by the seafloor, resulting in DVL measurement outage. In this study, a novel data-driven approach enhancing DVL/SINS integrated navigation system is proposed to improve the robustness and accuracy of UUV navigation with limited DVL beams. First, to make full use of the available beam, the velocities of DVL beams are used to assist the SINS navigation instead of the 3D velocity of DVL. Subsequently, a virtual beam predictor based on multi-output least-squares support vector regression (MLS-SVR) is built to run in parallel with the DVL/SINS integrated system. Specifically, when the DVL operates normally, all four beams can be applied for integrated navigation and stored as the training dataset. Once partial beams are missing, the available beams and the outputs of SINS and pressure sensors can train the MLS-SVR model along with the corresponding missing beams in the training set. Subsequently, the missing beams can be predicted by the trained model for integrated navigation together with the available beams. UUV sea trials indicate that the proposed system can accurately predict unavailable beams and improve the positioning accuracy of the DVL/SINS integrated navigation system.

Development and testing of a navigation solution for Autonomous Underwater Vehicles based on stereo vision

Autonomous Underwater Vehicles (AUVs) employed for inspection and monitoring applications require a reliable estimate of their navigation status to successfully accomplish the scheduled mission. Considering that they are typically endowed with vision systems to collect images of the surveyed environment, approaches based on Visual Odometry (VO) allow to utilise the optical payload also to perform robot navigation. Despite a large body of prior research, the topic of navigation based on stereo vision is still an open problem in the marine domain. Within this context, this paper proposes an underwater navigation framework utilising a stereo camera as a linear velocity sensor. The purpose is to assess the potentiality of a stereo vision system to indirectly measure the linear velocity of an AUV, and provide this information to the navigation framework of the vehicle. The proposed strategy consists in a visual inertial odometry solution fusing linear velocity estimates, derived from optical information, with attitude and depth measurements to retrieve the robot navigation status. Such linear velocity estimates are computed exploiting a stereo VO algorithm, relying on a 3D-to-2D approach, whose source code is made available online. The developed strategy is evaluated on real underwater datasets acquired during monitoring surveys performed by an AUV equipped with Doppler Velocity Log (DVL), bottom-looking stereo camera, inertial unit, and depth sensor. The results, obtained through a comparison with the DVL taken as benchmark, confirm the approach as feasible and exploitable in underwater inspection and monitoring contexts.

DVL Model Prediction Based on Fuzzy Multi-Output Least Squares Support Vector Machine in SINS/DVL

For an underwater Strapdown Inertial Navigation System/Doppler velocity log (SINS/DVL) integrated navigation system, the short-term failure of DVL may lead to the loss of reliable external velocity information from DVL, which will cause the SINS errors to accumulate. To circumvent this problem, this paper proposes a velocity predictor based on fuzzy multi-output least squares support vector machine (FMLS-SVM) to predict DVL measurements when DVL malfunctions occur. Firstly, the single-output least squares support vector machine (LS-SVM) model is extended to the multi-output LS-SVM model (MLS-SVM), and the self-adaptive fuzzy membership is introduced to fuzzify the input samples to overcome the over-fitting problem caused by the excessive sensitivity to the outlier points. Secondly, the fuzzy membership function is designed from the idea of the K nearest neighbor (KNN) algorithm. Finally, considering the influence of vehicle maneuver on the prediction model of DVL, the dynamic attitude angles are extended to the input samples of the prediction model to improve the adaptability of the DVL prediction model under large maneuver conditions. The performance of the method is verified by lake experiments. The comparison results show that the velocity predictor based on FMLS-SVM can correctly provide the estimated DVL measurements, effectively prolong the fault tolerance time of DVL faults, and improve the accuracy and reliability of the SINS/DVL integrated navigation system.

A GNSS-aided DVL calibration method based on quaternion estimation for underwater vehicles

Doppler velocity logger (DVL) error parameters can significantly influence the navigation accuracy of DVL/strapdown inertial navigation system (SINS) integration for unmanned underwater vehicles (UUV). To improve the navigation accuracy of UUV, this study proposes a two-stage DVL calibration method aided by global navigation satellite system (GNSS) measurements. First, utilizing the velocity of GNSS/SINS integrated navigation, the scale factor error of DVL is calculated by the moduli of velocities in UUV body frame and DVL instrument frame. Then, using the measurements throughout the calibration process, the calibration problem of the installation angle is converted to a nonlinear constraint optimization problem by describing the angle as a unit quaternion. Moreover, an easy-to-implement quaternion estimation algorithm is chosen to solve the problem and obtain the optimal quaternion. Simulation and sea trial indicate that the proposed method can rapidly and accurately estimate the DVL error parameters in different scenarios, and the position accuracy of the DVL/SINS system is improved.

Research on Error Correction Technology in Underwater SINS/DVL Integrated Positioning and Navigation

Underwater vehicles are key carriers for underwater inspection and operation tasks, and the successful implementation of these tasks depends on the positioning and navigation equipment with corresponding accuracy. In practice, multiple positioning and navigation devices are often combined to integrate the advantages of each equipment. Currently, the most common method for integrated navigation is combination of the Strapdown Inertial Navigation System (SINS) and Doppler Velocity Log (DVL). Various errors will occur when SINS and DVL are combined together, such as installation declination. In addition, DVL itself also has errors in the measurement of speed. These errors will affect the final accuracy of the combined positioning and navigation system. Therefore, error correction technology has great significance for underwater inspection and operation tasks. This paper takes the SINS/DVL integrated positioning and navigation system as the research object and deeply studies the DVL error correction technology in the integrated system.

Upscaling method based on sedimentary cycle prior and its application to well‐to‐seismic tie

AbstractA well‐to‐seismic tie is a typical upscaling problem. The traditional well‐to‐seismic tie methods often use the velocity log directly to tie well logs to seismic data without considering the upscaling problem led by the velocity dispersion due to thin beds. We propose an upscaling method based on the Backus average method to upscale the well‐log velocity to seismic velocity and apply it to a well‐to‐seismic tie problem. For Backus average method, choosing an appropriate average window is a crucial issue. We introduce a synchrosqueezing optimal basic wavelet transform to calculate an average window. The synchrosqueezing optimal basic wavelet transform is a time–frequency representation method, which can extract the sedimentary cycle information from seismic data. Considering the relationship between the sedimentary cycle and the thin‐bed thickness, we propose a workflow to estimate the instantaneous thin‐bed thickness based on synchrosqueezing optimal basic wavelet transform and determine the window length of the Backus average at each depth point. Then, the Backus average is used to estimate the effective velocity, which is further used to calculate the initial time–depth function and transfer the reflection coefficients from the depth domain to the time domain. Choosing an appropriate seismic wavelet is another fundamental problem for the well‐to‐seismic tie process. This paper introduces an alternating iterative deep neural network‐based method to estimate the seismic wavelet. Thus realistic synthetic seismograms can be computed by convolving the estimated seismic wavelet and the reflection coefficient, which can be stretched or squeezed to match the near‐well seismic trace. We show that the proposed workflow effectively reduces the errors in a well‐to‐seismic tie procedure caused by velocity dispersion of thin beds.

Development and experimental evaluation of visual-acoustic navigation for safe maneuvering of unmanned surface vehicles in harbor and waterway areas

Ship maneuvering in narrow harbor environments requires accurate navigation data to operate safely. Since Global Navigation Satellite Systems (GNSS) can be unreliable and inaccurate in such environments, other aiding techniques should be used for increased redundancy and reliability. To this end, we present a GNSS-free sensor suite consisting of visual, acoustic, and inertial sensors that can be used to navigate small vehicles in a harbor environment. The proposed method is aided by two navigation systems: a doppler velocity log (DVL) for low-drift velocity aiding and a visual fiducial system to estimate the drift-free position and attitude of a camera onboard the vehicle with respect to easily identifiable tags at the dockside. The visual and acoustic measurements are fused with inertial data using an error-state Kalman filter for robust state estimation. To benchmark the performance, we employ an unmanned surface vehicle equipped with a dual-antenna real-time kinematic GNSS receiver for accurate positioning and heading. The benefits of supplementing landmark-based navigation with acoustic measurements are demonstrated by conducting adverse scenarios that include noisy measurements and sensor dropouts in the harbor environment. As a result, the proposed visual-acoustic system can supplement satellite-based navigation systems for safety-critical harbor maneuvering.

Robust Interactive Multimodel INS/DVL Intergrated Navigation System With Adaptive Model Set

A Robust Interactive Multiple Model (RIMM) algorithm with the adaptive model set is proposed to improve the performance of Inertial Navigation System (INS) and Doppler Velocity Logs (DVL) integrated navigation system under complex measurement environment with undesirable heavy-tailed non-Gaussian noise. Specifically, an improved Huber kernel function is applied to the robust error state Kalman filter (ESKF) for its benefit of better resisting larger measurement outliers. In addition, a flexible adaptive model set update strategy is proposed where the model set is determined by the current and historical measurement information stored in the sliding window. And for model set update, the main model is no longer fixed, it will be determined based on the probability weights corresponding to each model. This innovative RIMM algorithm is compared with error state Kalman filter, Interactive Multiple Model (IMM) and Hybrid Interactive Multiple Model (HIMM) through simulations, AUV lake trial and semi-physical simulations. Experimental results show that our proposed algorithm has outstanding accuracy and robustness under heavy-tailed non-Gaussian noise environment.

An INS/DVL integrated navigation filtering method against complex underwater environment

In this paper, a filtering method against complex underwater environment is proposed for the inertial navigation system/doppler velocity log (INS/DVL) of the unmanned underwater vehicle (UUV). The method has two stages. The first stage is the pre-cruise. In this stage, the martingale distance is constructed. And according to chi-square test, the two thresholds can be obtained, which are used to determine the complexity of the environment. Then, these thresholds are used in cruise of UUV. During cruise, the martingale distance is similarly constructed. The environment is judged in real time according to chi-square test. When the martingale distance exceeds the first threshold, the environment is considered to be of high complexity. The robust method based on covariance matching is used. When the martingale distance lies between the first and second thresholds, the UUV is considered to be in a low complex environment, and the adaptive method is used. Otherwise, the conventional nonlinear filter is performed. Finally, the results of field experiment show that the method can avoid the over compensation of parameters in stable case from conventional methods, and comprehensively solve the problem of degradation of accuracy due to different environment.

A novel adaptive nonlinear Kalman filter scheme for DVL-aided SINS alignment in underwater vehicles

The rapid and accurate initial alignment of a strapdown inertial navigation system (SINS) aided by a Doppler velocity logger (DVL) still poses a significant challenge in unmanned underwater vehicle navigation. In this study, a novel adaptive nonlinear filtering alignment scheme is developed for a SINS with a large misalignment angle. In previous studies, the frame-inconsistency problem of the nonlinear SINS error model was neglected. Thus, a modified nonlinear error model of a SINS is derived here rigorously as the process model of the nonlinear Kalman filter. In addition, the noise amplification of applying Sage-Husa adaptive Kalman filter (SHAKF) in alignment is analyzed, and a novel arctangent fading memorial factor is introduced to dynamically adjust the weight of current measurements. Simulations and field experiments indicate that the proposed algorithm is efficient in underwater DVL/SINS in-motion alignment. The alignment accuracy and convergence rate of the modified model are significantly improved compared to those of the traditional model. The arctangent fading memorial SHAKF can reliably estimate the measurement noise and improve the performance of alignment.

Introducing realistic distributions of gas bubble size and inclusion aspect ratio to model the coexistence of gas hydrate and free gas

The coexisting free gas within the hydrate stability zone is recognized by laboratory and field studies. The conventional resistivity method fails to obtain hydrate saturation in the sediment with gas hydrate and free gas because both of them are electrical insulators. Hydrate saturation can be obtained from a velocity log based on a certain rock physics model. However, few studies of rock physics have been conducted on gas and hydrate coexistence. In this study, a more realistic distribution of gas bubble size and inclusion aspect ratio was introduced into an effective medium model to elucidate how such coexistence affects velocity and attenuation at a broad-band frequency. The modeling results obtained indicate that such coexistence decreases P-wave velocity at low frequencies, while increases P- and S-wave velocities at high frequencies. The velocity decrease of P-wave at low frequencies is attributed to the overwhelming effect of gas bubble vibration, while it seems not to affect P-wave velocity at high frequencies significantly. Moreover, coexisting gas hydrate and free gas may strengthen P-wave attenuation at the broad-band frequency range. It is found that the damping of oscillating gas bubbles dominates P-wave attenuation at low frequencies, while squirt flow in the porous hydrate is more likely to contribute to P-wave attenuation at high frequencies. Hydrate morphology is also a significant factor affecting P-wave velocity and attenuation at high frequencies. This research reveals that rock physics modeling can provide insight into how to characterize the coexisting gas hydrate and free gas as referring to the acoustic velocity and attenuation at seismic, sonic, and ultrasonic frequencies.

Bathymetric Reconstruction From Sidescan Sonar With Deep Neural Networks

In this article, we propose a novel data-driven approach for high-resolution bathymetric reconstruction from sidescan. Sidescan sonar intensities as a function of range do contain some information about the slope of the seabed. However, that information must be inferred. In addition, the navigation system provides the estimated trajectory, and normally, the altitude along this trajectory is also available. From these, we obtain a very coarse seabed bathymetry as an input. This is then combined with the indirect but high-resolution seabed slope information from the sidescan to estimate the full bathymetry. This sparse depth could be acquired by single-beam echo sounder, Doppler velocity log, and other bottom tracking sensors or bottom tracking algorithm from sidescan itself. In our work, a fully convolutional network is used to estimate the depth contour and its aleatoric uncertainty from the sidescan images and sparse depth in an end-to-end fashion. The estimated depth is then used together with the range to calculate the point's three-dimensional location on the seafloor. A high-quality bathymetric map can be reconstructed after fusing the depth predictions and the corresponding confidence measures from the neural networks. We show the improvement of the bathymetric map gained by using sparse depths with sidescan over estimates with sidescan alone. We also show the benefit of confidence weighting when fusing multiple bathymetric estimates into a single map.

Tightly Coupled INS/APS Passive Single Beacon Navigation

Unlike aerial or terrestrial navigation, the global navigation satellite system (GNSS) is not available underwater. This is a big challenge for underwater navigation. The inertial navigation system (INS) aided by the single-beacon acoustic positioning system (APS) provides one solution, but the long-range case is limited by low-SNR conditions. Inspired by passive synthetic aperture detection, we proposed a new tightly coupled navigation algorithm based on spatial synthesis and one-way-travel-time (OWTT) range measurement. We design two estimators: the DOA/range estimator using the model-based method and the tightly coupled INS/APS navigation estimator. Based on the improved UKF, all information is combined. Simulation is carried out in MATLAB. Compared with range-only tightly coupled INS/APS navigation, synthetic long baseline (SLBL) algorithm and Doppler velocity logger (DVL) aided centralized extended Kalman filter (CEKF) based single beacon INS/OWTT navigation, the proposed method’s performance is proven. The main contributions of this work are: (1). Propose a new architecture of underwater integrated navigation; (2). Apply the passive acoustic detecting method in the navigation to improve accuracy. (3). Apply the tightly coupled method to improve availability.

Morphology identification of gas hydrate based on a machine learning method and its applications on saturation estimation

SUMMARY Proper identification of hydrate morphology is an essential pre-condition for the quantification and exploitation of gas hydrate resources. However, the morphology results from core-based analysis and resistivity-based imaging could be discontinuous in hydrate-bearing intervals. Rock physical model-based methods could predict morphology within complete hydrate-bearing intervals, but the accuracy is not much satisfactory in some cases. In this study, we propose a machine learning (ML) method using the wavelet twin support vector machine (WTWSVM) to accurately differentiate the pore-filling and grain-displacing hydrate. By employing different combinations of well logs as the inputs of the WTWSVM, we find the optimal one for the data set in Hydrate Ridge, offshore Oregon is the combination of gamma-ray, resistivity, compressional and shear wave velocity logs, with an accuracy of 88.6 per cent and F1-score of 82.89 per cent. Compared with the two traditional rock-physics-based methods and three typical ML algorithms, the WTWSVM with those optimal inputs performs better in terms of accuracy and F1-score. We then use the WTWSVM to predict the hydrate morphology in the hydrate-bearing intervals at an unlabelled (i.e. unidentified hydrate morphology) site 1250F and a partially labelled (i.e. only a portion of the hydrate and its morphology is identified by IR images) site 1247B at Hydrate Ridge. Finally, the hydrate-morphology-related rock physics models are employed to construct 3-D crossplots of density, compressional and shear wave velocity, on which hydrate concentration, as well as other reservoir parameters, are estimated through projecting. The proposed WTWSVM method and workflow are proved to be valid based on the good agreement between the reservoir parameters from core measurement and elastic properties.