Limited Sample Data Research Articles

On the training sample size and classification performance: An experimental evaluation in seismic facies classification

Machine learning algorithms (MLAs) perform better when enough high-quality training data is provided. However, a lack of training data is frequent in seismic facies classification and many other supervised learning applications. Data labeling for seismic facies classification is time-consuming and requires considerable effort from the domain knowledge expert. This study investigates the effect of training data size on the performance of three popular supervised MLAs used for seismic facies classification. We labeled slices from two seismic datasets of diverse geologic environments and varying classification complexity. AN Field in Malay Basin represents a simple classification problem with three classes, whereas a more complex six classes classification is defined in the Dangerous Grounds (DG) dataset offshore Sabah. The labeled data were constantly reduced by half, resulting in eight training subsets of varying sizes. We trained and evaluated support vector machine (SVM), random forest (RF), and neural network (NN) models using a 10-fold cross-validation (CV) procedure. Performance metrics were computed to study the change in performance in response to the training data size. The experimental results show that, for the DG dataset, where the classification is complex due to the heterogeneous geology and a more number of classes, the larger the training subset, the better the classification performance. Nevertheless, for the simple classification scenario of the AN dataset, the classifiers reached a performance plateau when trained on limited samples. We found that the NN model is the best performer on large datasets. The RF classifier performed well in both datasets. It proved to be robust when trained on limited samples of the DG data. The SVM performed the best where there was a clear margin of separation between the defined classes (the AN data). In contrast, it performed poorly on the DG data and exhibited a performance decline on the AN large subsets.

A prediction model based on an adaptive genetic algorithm and optimized Elman neural network for PV power

Due to the high volatility and randomness of PV power generation, fast change frequency, limited data samples and poor data conditions, the reliability, stability and economy of grid operation are affected seriously. Therefore, the accurate prediction of PV power generation can mitigate the impact of its volatility on the stability of national grid power operations. And it improves PV consumption capacity and enhances the security of microgrid and distribution grid interconnection. This paper first proposed a PV power prediction method. Secondly, through the introduction and analysis of three types of prediction methods, the first type of prediction is selected using statistical analysis and modeling methods. Thirdly, an optimized Elman neural network-based PV power prediction model is proposed to allow accurate prediction of PV power prediction. Finally, an example is given to verify the advantages of the algorithm.

Multi-Scale Spectral-Spatial Attention Network for Hyperspectral Image Classification Combining 2D Octave and 3D Convolutional Neural Networks

Traditional convolutional neural networks (CNNs) can be applied to obtain the spectral-spatial feature information from hyperspectral images (HSIs). However, they often introduce significant redundant spatial feature information. The octave convolution network is frequently utilized instead of traditional CNN to decrease spatial redundant information of the network and extend its receptive field. However, the 3D octave convolution-based approaches may introduce extensive parameters and complicate the network. To solve these issues, we propose a new HSI classification approach with a multi-scale spectral-spatial network-based framework that combines 2D octave and 3D CNNs. Our method, called MOCNN, first utilizes 2D octave convolution and 3D DenseNet branch networks with various convolutional kernel sizes to obtain complex spatial contextual feature information and spectral characteristics, separately. Moreover, the channel and the spectral attention mechanisms are, respectively, applied to these two branch networks to emphasize significant feature regions and certain important spectral bands that comprise discriminative information for the categorization. Furthermore, a sample balancing strategy is applied to address the sample imbalance problem. Expansive experiments are undertaken on four HSI datasets, demonstrating that our MOCNN approach outperforms several other methods for HSI classification, especially in scenarios dominated by limited and imbalanced sample data.

Examining The Effect of Sustainability Report Disclosure to Firm Value: A Study Based on Listed Public Companies in Indonesia Stock Exchange

Companies that mitigate and improve the environment can take advantage of this as a marketing tool in general. Consumers will support companies that have a positive impact on their surroundings. One of the tools that can be used as a form of responsibility and marketing tool is a sustainability report. Sustainability report are reports published by organizations or companies that explain the economic, environmental, and social impacts as result of their operating activities. The report also explains about corporate culture and governance as well as its relationship with the company's strategy and commitment to maintain the sustainability of the triple bottom line (people, planet, profit). Sustainability reporting disclosure index (SRDI) are measured from 89 listed public companies in Indonesia. Regression analysis took place for examining the effect of SRDI to the corresponding firm value represented by Tobin’s Q. Only certain limited sample data showed that there’s a significance effect between sustainability report disclosure and firm value. Enterprises who haven’t disclose their sustainability report still worth high value in share trade. This condition occurs due to investors' decisions to invest are influenced by media coverage, economic conditions, and changes in stock prices.

Stochastic kinematic analysis of rock slope failure angle based on multi algorithm optimization, a case study of the proposed bridge project

ABSTRACT Due to the randomness and complexity of the discontinuity distribution, it is always complicated to analyse the three-dimensional stability problem of discontinuity-controlled rock slope in the field of engineering geology. Specifically, when restricted by poor sampling conditions, the discontinuity data obtained are very limited. To solve this problem, we propose a stochastic kinematic method to estimate the slope failure angle based on limited data. Taking the high-steep rock slope on the right bank of a proposed bridge as an example, the stochastic kinematic method based on multiple algorithms (Monte Carlo simulation, Latin hypercube, and Bayesian estimation) is used to analyse the failure angles of potentially unstable blocks in two modes of plane and wedge failure. After statistical optimisation, the slope failure angles are determined to be 65.69° (plane failure) and 58.65° (wedge failure); this approach is more objective than the empirical formula method and can be used as the basis for judging the slope stability. The method proposed in this study fully considers the randomness of discontinuity distribution and combination, and can use limited sample data to realise failure angle analysis and stability judgement. The result is important as a reference of significance for engineering construction and disaster prevention.

Regeneration of pavement surface textures using M‐sigmoid‐normalized generative adversarial networks

AbstractThe high cost of collecting surficial textures has been the bottleneck problem for many decades. To bridge this gap, this study aims to propose a complete framework based on the generative adversarial networks (GANs) architecture for texture regeneration using limited texture data samples. Four variants of the GAN were compared to achieve the best regeneration performance. Prior to running GAN, specifically improved data augmentation and modified sigmoid normalization operations were dedicated to avoiding the loss of texture information and the non‐convergence problem. After running GAN, the estimation metrics were introduced and discussed separately to quantitatively evaluate the rationality and diversity of the regenerated textures. The results demonstrated that the use of improved data augmentation and normalization methods significantly enhanced the regeneration capability of GAN, and more importantly the skewed distribution of surficial heights which is not achievable by present texture regeneration methods was most effectively regenerated by deep regret analytic GAN with well generalization ability. Our study provides a promising choice to generate virtually realistic pavement surface textures.

Progressive Geological Modeling and Uncertainty Analysis Using Machine Learning

Three-dimensional geological modeling is a process of interpreting geological features from limited sample data and making predictions, which can be converted into a classification task for grid units in the geological space. In sedimentary settings, it is difficult for a single geological classification process to comprehensively express the complex geological spatio-temporal relationships of underground space. In response to this problem, we proposed a progressive geological modeling strategy to reconstruct the subsurface based on a machine learning approach. The modeling work consisted of two-stage classifications. In the first stage, a stratigraphic classifier was built by mapping spatial coordinates into stratigraphic classes, which reflected the geological time information of the geological unit. Then, the obtained stratigraphic class was used as a new feature for the training of the lithologic classifier in the second stage, which allowed the stratigraphic information to be implicitly converted into a new rule condition and enabled us to output the lithologic class with stratigraphic implications. Finally, the joint Shannon entropy of two classifications was calculated to evaluate the uncertainty of the total steps. The experiment built a fine-grained 3D geological model with integrated expression of stratigraphic and lithologic information and validated the effectiveness of the strategy. Moreover, compared with the conventionally trained classifier, the misclassification of the lithologic class between different strata in the progressive classification results has been reduced, with the improvement of the F1-score from 0.75 to 0.78.

Observation of e+e−→ π0π0ψ2(3823)

Using a data sample corresponding to an integrated luminosity of 11.3 fb−1 collected at center-of-mass energies from 4.23 to 4.70 GeV with the BESIII detector, we observe the process e+e−→ π0π0ψ2(3823) for the first time with a statistical significance of 6.0 standard deviations. The ratio of average cross sections for e+e−→ π0π0ψ2(3823) and π+π−ψ2(3823) is determined to be mathcal{R}=frac{sigma left[{e}^{+}{e}^{-}to {pi}^0{pi}^0{psi}_2(3823)right]}{sigma left[{e}^{+}{e}^{-}to {pi}^{+}{pi}^{-}{psi}_2(3823)right]}=0.57pm 0.14pm 0.05 , which is consistent with expectations from isospin symmetry. Here and below, the first uncertainties are statistical and the second are systematic. The mass of the ψ2(3823) is measured to be M[ψ2(3823)] = 3824.5 ± 2.4 ± 1.0 MeV/c2. Due to the limited data sample, an upper limit of 18.8 MeV at 90% confidence level is set on the intrinsic width of ψ2(3823).

Adversarial Remote Sensing Scene Classification Based on Lie Group Feature Learning

Convolutional Neural Networks have been widely used in remote sensing scene classification. Since this kind of model needs a large number of training samples containing data category information, a Generative Adversarial Network (GAN) is usually used to address the problem of lack of samples. However, GAN mainly generates scene data samples that do not contain category information. To address this problem, a novel supervised adversarial Lie Group feature learning network is proposed. In the case of limited data samples, the model can effectively generate data samples with category information. There are two main differences between our method and the traditional GAN. First, our model takes category information and data samples as the input of the model and optimizes the constraint of category information in the loss function, so that data samples containing category information can be generated. Secondly, the object scale sample generation strategy is introduced, which can generate data samples of different scales and ensure that the generated data samples contain richer feature information. After large-scale experiments on two publicly available and challenging datasets, it is found that our method can achieve better scene classification accuracy even with limited data samples.

Nearest Neighbor-Based Strategy to Optimize Multi-View Triplet Network for Classification of Small-Sample Medical Imaging Data.

Multi-view classification with limited sample size and data augmentation is a very common machine learning (ML) problem in medicine. With limited data, a triplet network approach for two-stage representation learning has been proposed. However, effective training and verifying the features from the representation network for their suitability in subsequent classifiers are still unsolved problems. Although typical distance-based metrics for the training capture the overall class separability of the features, the performance according to these metrics does not always lead to an optimal classification. Consequently, an exhaustive tuning with all feature-classifier combinations is required to search for the best end result. To overcome this challenge, we developed a novel nearest-neighbor (NN) validation strategy based on the triplet metric. This strategy is supported by a theoretical foundation to provide the best selection of the features with a lower bound of the highest end performance. The proposed strategy is a transparent approach to identify whether to improve the features or the classifier. This avoids the need for repeated tuning. Our evaluations on real-world medical imaging tasks (i.e., radiation therapy delivery error prediction and sarcoma survival prediction) show that our strategy is superior to other common deep representation learning baselines [i.e., autoencoder (AE) and softmax]. The strategy addresses the issue of feature's interpretability which enables more holistic feature creation such that the medical experts can focus on specifying relevant data as opposed to tedious feature engineering.

Optimizing Marketing Management Strategies Through IT Innovation: Big Data Integration for Better Consumer Understanding

The dynamic business environment, the fusion of Information Technology (IT) innovation with marketing management strategies has emerged as a crucial element for success amidst heightened competition. As markets evolve and consumer behaviors shift, enterprises are compelled to adapt swiftly, employing innovative tools and methodologies to gain insights and maintain relevance. Within this context, the integration of Big Data analytics emerges as a transformative catalyst, offering unprecedented opportunities to comprehend consumer preferences and optimize marketing endeavors. The convergence of IT and marketing management signifies a paradigm shift in how businesses conceive and execute their strategies. Historically, marketing decisions relied heavily on intuition, market research, and limited data samples. However, the digital revolution has ushered in an era characterized by the generation and collection of vast amounts of data at an unprecedented pace. This proliferation of data presents both challenges and opportunities for marketers. While the sheer volume and complexity of data can be overwhelming, harnessing this reservoir of data can unlock invaluable insights into consumer behavior, preferences, and trends. The integration of Big Data into marketing management strategies has revolutionized consumer understanding and value creation. By leveraging vast amounts of consumer data, businesses can extract valuable insights to gain a competitive advantage and enhance consumer engagement. However, this integration also presents challenges, including concerns regarding data privacy and security. At the forefront of this data-driven revolution lies Big Data analytics—a multidisciplinary field utilizing advanced computational techniques to analyze large and diverse datasets. Unlike traditional analytics approaches, Big Data analytics excels in processing massive volumes of structured and unstructured data with agility and efficiency. By harnessing distributed computing, machine learning algorithms, and cloud infrastructure, organizations can extract actionable intelligence from previously unwieldy datasets. The integration of Big Data analytics into marketing management holds immense promise for unlocking new avenues of consumer understanding. By aggregating and analyzing disparate data sources, marketers can gain comprehensive insights into consumer preferences, behaviors, and sentiments, enabling more targeted and effective marketing strategies. Moreover, Big Data analytics empowers marketers to anticipate and respond to emerging trends and market shifts with unprecedented agility, ensuring a competitive edge in fast-paced industries. However, realizing the full potential of Big Data integration in marketing management requires more than technological prowess—it demands a strategic shift in organizational mindset and culture. Embracing a data-driven approach necessitates breaking down silos between departments, fostering cross-functional collaboration, and promoting a culture of experimentation and innovation. Additionally, it requires a commitment to ethical data practices to safeguard consumer privacy and data security throughout the data lifecycle.

Deliberate Self-Poisoning: Real-Time Characterization of Suicidal Habits and Toxidromes in the Food and Drug Administration Adverse Event Reporting System.

Deliberate self-poisoning (DSP) using drugs is the preferred method of suicide at a global level. Its investigation is hampered by limited sample sizes and data reliability. We investigate the role of the US FDA Adverse Event Reporting System (FAERS), a consolidated pharmacovigilance database, in outlining DSP habits and toxidromes. We retrieved cases of 'intentional overdose' and 'poisoning deliberate' from the FAERS (January 2004-December 2021). Using descriptive and disproportionality analyses, we estimated temporal trends, potential risk factors, toxidromes, case-fatality rates and lethal doses (LDs) for the most frequently reported drugs. We retrieved 42,103 DSP cases (17% fatal). Most cases were submitted in winter. Reports of DSP involved younger people, psychiatric conditions, and alcohol use, compared with non-DSP, and fatality was higher in men and older patients. Suspected drugs were mainly antidepressants, analgesics, and antipsychotics. Multiple drug intake was recorded in more than 50% of the reports, especially analgesics, psychotropics, and cardiovascular agents. The most frequently reported drugs were paracetamol, promethazine, amlodipine, quetiapine, and metformin. We estimated LD25 for paracetamol (150g). Worldwide coverage of the FAERS complements existing knowledge about DSP and may drive tailored prevention measures to timely address the DSP phenomenon and prevent intentional suicides.

Self-Supervised RF Signal Representation Learning for NextG Signal Classification With Deep Learning

Deep learning (DL) finds rich applications in the wireless domain to improve spectrum awareness. Typically, DL models are either randomly initialized following a statistical distribution or pretrained on tasks from other domains in the form of transfer learning without accounting for the unique characteristics of wireless signals. Self-supervised learning (SSL) enables the learning of useful representations from Radio Frequency (RF) signals themselves even when only limited training data samples with labels are available. We present a self-supervised RF signal representation learning method and apply it to the automatic modulation recognition (AMR) task by specifically formulating a set of transformations to capture the wireless signal characteristics. We show that the sample efficiency (the number of labeled samples needed to achieve a certain performance) of AMR can be significantly increased (almost an order of magnitude) by learning signal representations with SSL. This translates to substantial time and cost savings. Furthermore, SSL increases the model accuracy compared to the state-of-the-art DL methods and maintains high accuracy when limited training data is available.

Bayesian updating of seismic fragility curves through experimental tests

Fragility curves, commonly derived using analytical methods, are important ingredients of seismic risk analysis of structures in the framework of performance-based earthquake engineering. Hence, the accurate estimation of realistic fragility functions is a decisive *: Bayesian updating considering a diffuse prior step in a reliable risk assessment. This paper proposes a Bayesian updating procedure applied to analytical fragility curves of reinforced concrete (RC) structures based on data from experimental tests, namely shaking table tests. The latter are commonly performed by progressively increasing the intensity of the input motion applied to the same test specimen. In this regard, the maximal benefit from the output of a shaking table test is sought here, aiming to convert n sequential stages of a shaking table test of a single virgin specimen into n equivalent shaking table tests that are performed on n virgin specimens. This is performed by modifying the intensity of the input motion applied during the stage-wise testing based on a damage index coefficient. The parametric studies performed to validate this objective reveal that the approach is more suitable for simple structures compared to large or complex structures. The ATC-58 and Markov Chain Monte Carlo (MCMC) approaches for Bayesian updating of fragility curves are also closely examined and compared. The proposed Bayesian updating is applied to a RC structure, where fragility curves that are derived from incremental dynamic analysis are updated using shaking table results. The updating is examined considering three damage state models, namely HAZUS, homogenized RC and strain-based damages states. This work also highlights the pitfalls of using a limited sample of experimental test data for updating less reliable priors. Besides, the MCMC-based approach is shown to be more robust in the presence of complex analytical fragilities than the ATC-58 approach.

Distributionally Robust Unit Commitment with N-k Security Criterion and Operational Flexibility of CSP

In order to reduce the conservatism of the robust optimization method and the complexity of the stochastic optimization method and to enhance the ability of power systems to deal with occasional line fault disturbance, this paper proposes a distributionally robust unit commitment (DRUC) model with concentrating solar power (CSP) operational flexibility and N-k safety criterion under distributed uncertainty. According to the limited historical sample data, under the condition of satisfying a certain confidence level, based on the imprecise Dirichlet model (IDM), an ambiguity set is constructed to describe the uncertainty of transmission line fault probability. Through the identification of the worst probability distribution in the ambiguity set, the adaptive robust optimal scheduling problem is transformed into a two-stage robust optimization decision model under the condition of deterministic probability distribution. The CSP flexibility column and constraint generation (C&CG) algorithm is used to process the model and the main problem and subproblem are solved by using the Big-M method, linearization technique, and duality principle. Then, a mixed integer linear programming problem (MILP) model is obtained, which effectively reduces the difficulty of solving the model. Finally, case studies on the IEEE 14 bus system and the IEEE 118 bus system demonstrate the efficiency of the proposed method, such as enhancing the ability of power systems to cope with occasional line fault disturbances and reducing the conservatism of the robust optimization method.

Positioning Accuracy Reliability Analysis of Industrial Robots Considering Epistemic Uncertainty and Correlation

Abstract Uncertainties widely existing in modeling parameters, such as link length, joint clearance, and rotation angle, have the serious impact on the motion performance of industrial robots. In this study, a reliability analysis method based on evidence theory is proposed to uniformly analyze the influence of epistemic uncertainty and their correlation in modeling parameters on the positioning accuracy of robotic end effector. For the epistemic uncertainty derived from the limited sample data of modeling parameters, a generalized evidence theory model based on parallelotope frame is developed, which can uniformly quantify epistemic uncertainty and correlation of modeling parameters using the evidence framework of discernment and joint focal elements with same parallelotope features. To overcome the contradiction between analysis efficiency and accuracy for industrial robot positioning with nonlinearity, an efficient space affine collocation method is further proposed based on dimension reduction decomposition. Under the parallelotope evidence theory model, this method can provide an accurate reliability analysis result at a lower computational cost. A six degrees-of-freedom industrial robot is showcased to demonstrate the effectiveness and advantages of the proposed method in positioning accuracy reliability analysis.

LAC-GAN: Lesion attention conditional GAN for Ultra-widefield image synthesis

Automatic detection of retinal diseases based on deep learning technology and Ultra-widefield (UWF) images plays an important role in clinical practices in recent years. However, due to small lesions and limited data samples, it is not easy to train a detection-accurate model with strong generalization ability. In this paper, we propose a lesion attention conditional generative adversarial network (LAC-GAN) to synthesize retinal images with realistic lesion details to improve the training of the disease detection model. Specifically, the generator takes the vessel mask and class label as the conditional inputs, and processes the random Gaussian noise by a series of residual block to generate the synthetic images. To focus on pathological information, we propose a lesion feature attention mechanism based on random forest (RF) method, which constructs its reverse activation network to activate the lesion features. For discriminator, a weight-sharing multi-discriminator is designed to improve the performance of model by affine transformations. Experimental results on multi-center UWF image datasets demonstrate that the proposed method can generate retinal images with reasonable details, which helps to enhance the performance of the disease detection model.

Bearing Fault Diagnosis of Hot-Rolling Mill Utilizing Intelligent Optimized Self-Adaptive Deep Belief Network with Limited Samples.

Given the complexity of the operating conditions of rolling bearings in the actual rolling process of a hot mill and the difficulty in collecting data pertinent to fault bearings comprehensively, this paper proposes an approach that diagnoses the faults of a rolling mill bearing by employing the improved sparrow search algorithm deep belief network (ISAA-DBN) with limited data samples. First, the fast spectral kurtosis approach is adopted to convert the non-stationary original vibration signals collected by the acceleration sensors installed at the axial and radial ends of the rolling mill bearings into two-dimensional (2D) spectral kurtosis time–frequency images with higher feature recognition, and the principal component analysis (PCA) technique is used to decrease the dimension of the data in order to achieve a high diagnosis rate with a limited number of samples. Subsequently, the sparrow search algorithm (SSA) is used to realize the intelligent optimized self-adaptive function of a deep belief network (DBN). Furthermore, the firefly disturbance algorithm is employed to improve the spatial search capability and robustness of SSA-DBN in order to achieve better performance of the ISSA-DBN method. Finally, the proposed approach is experimentally compared to other approaches used for diagnosis. The results show that the proposed approach not only retains the useful features of the data through dimension reduction but also improves the efficiency of the diagnosis and achieves the highest diagnosis accuracy with limited data samples. In addition, the optimal position of the sensor for diagnosing rolling mill roll faults is identified.

Digital Economy Meets Artificial Intelligence: Forecasting Economic Conditions Based on Big Data Analytics

Big data economy meets artificial intelligence, making the traditional statistical economy gradually evolve into an intelligent economy. Limited by human consciousness, traditional economic models have low prediction accuracy. In traditional statistical methods, the limited sample data also makes it impossible to effectively control and comprehensively forecast macroeconomic and development trends. Data economy has fundamentally transformed the traditional means of economic analysis. This is because the digital economy enables economic connectivity and precise data sharing, which can be used for precise economic statistics and mathematical analysis. Meanwhile, in terms of statistical methods, artificial intelligence methods no longer rely on human consciousness, but more objectively pay attention to economic cause and effect and are more accurate and comprehensive. This paper proposes an economic forecasting method based on artificial intelligence methods combined with big data analytics. In our model, we consider the economic statistics, equilibrium, and future prediction with the big data. Through the artificial intelligence method based on deep learning, the possible political factors, human activity factors, and social environmental factors in actual economic activities are effectively combined to form the main analysis subject affecting the economy. The results show that our model can be used as a basic model for economic statistics, economic analysis, economic decision-making, economic self-regulation, and other functions under the current development trend of the data economy.

Indication of Formation Water Geochemistry for Hydrocarbon Preservation: New Applications of Machine Learning in Tight Sandstone Gas Reservoirs.

The migration of formation water plays a crucial role in hydrocarbon accumulation and preservation. The hydrodynamic field controls the content of various ions in formation water and is an important participant in hydrocarbon evolution. One potential high-yield gas field is the tight sandstone gas reservoirs in the northern Tianhuan Depression of the Ordos Basin, China. However, due to the complex gas–water relationship and limited water sample data, the development of gas reservoirs has encountered great difficulties; we thus analyzed the geochemical characteristics of a large scale of formation water acquired from the Permian in the Ordos Basin (60 water samples collected from 45 wells in the He8 Member). The results showed that formation water is the original sedimentary water in tight sandstone reservoirs, which represent a closed hydrological environment, which is conducive to gas accumulation. This is also related to the demonstrated strong water–rock reaction and diagenetic. We also developed a statistical model between these geochemical parameters and gas preservation based on machine learning algorithms (decision trees). Note that machine learning, as a data-driven artificial intelligence algorithm, generates massive correlation models that can learn from the structured training data sets to carry out predictions or evaluations in newly presented data. This algorithm can process large amounts of information data more quickly and can build more perfect correlation models through deep learning mechanisms than traditional statistical methods. The results suggest that the metamorphism coefficient has the best indication effect on the preservation of gas reservoirs. The hydrological environment with (Cl–-Na+)/Mg2+ > 50.066, Na+/Cl– ≤ 0.476, and Ma2+/Ca2+ ≤ 0.102 is a good hydrocarbon accumulation area. This study can be applied, by analogy, to more comprehensively interpret the correlation between the geochemical characteristics of formation water and hydrocarbon storage and to improve the accuracy of predicting favorable hydrocarbon accumulation areas in tight sandstone gas reservoirs.