Advanced Machine Learning Models Research Articles

Analyzing Cancer Prognosis with Advanced Machine Learning Models

This study investigates the use of Support Vector Machines (SVM) and other machine learning algorithms for predicting the prognosis of lung, breast, and cervical cancer patients. The research evaluates the predictive accuracy, influential features, algorithm performance, and model generalization across different cancer types. Using publicly available datasets, the study highlights SVM's exceptional accuracy in prognosis prediction, with findings indicating its superiority over alternative algorithms. Notably, it identifies the key clinical, molecular, and pathological features that significantly impact predictive accuracy. The study also discusses the clinical applicability of these models, emphasizing their potential to aid healthcare professionals in making more informed treatment decisions. Acknowledging limitations, including data availability and computational resources, the study suggests future directions, encouraging the exploration of additional techniques, diverse datasets, and real-world clinical trials to validate the model’s effectiveness. Keywords Cancer, Medical Diagnosis, Markers, Learning, Patients, Machine Learning, Support Vector Machine

Detection of Diseases in Blackgram (Vigna mungo L.) Using Machine Learning Models: A Case Study

Black gram (Vigna mungo L.) is widely used in Indian cuisine and one of the most significant pulses cultivated in India. Identification of plant diseases at their earlier stages is essential to take necessary plant protection measures to reduce yield loss to the farmers. Anthracnose and Powdery Mildew are the major diseases in black gram which causes significant yield losses to the farmers. In this research study, advanced disease detection machine learning models such as Multinomial Logistic Regression, Random Forest Classifier were employed to assist the farmers in detection of plant leaf diseases in blackgram at their early stages of growth. For this present study, Image data sets were collected from Thanjavur block, Thanjavur district, Tamil Nadu. Results of the study showed that accuracy of Random Forest Classifier was higher with train accuracy 99.17% and test accuracy 97.00% when compared to the other machine learning methods for detection of plant leaf diseases in black gram, which aids in promotion of smart agriculture.

IBVP Dataset: RGB-Thermal rPPG Dataset with High Resolution Signal Quality Labels

Remote photo-plethysmography (rPPG) has emerged as a non-intrusive and promising physiological sensing capability in human–computer interface (HCI) research, gradually extending its applications in health-monitoring and clinical care contexts. With advanced machine learning models, recent datasets collected in real-world conditions have gradually enhanced the performance of rPPG methods in recovering heart-rate and heart-rate-variability metrics. However, the signal quality of reference ground-truth PPG data in existing datasets is by and large neglected, while poor-quality references negatively influence models. Here, this work introduces a new imaging blood volume pulse (iBVP) dataset of synchronized RGB and thermal infrared videos with ground-truth PPG signals from ear with their high-resolution-signal-quality labels, for the first time. Participants perform rhythmic breathing, head-movement, and stress-inducing tasks, which help reflect real-world variations in psycho-physiological states. This work conducts dense (per sample) signal-quality assessment to discard noisy segments of ground-truth and corresponding video frames. We further present a novel end-to-end machine learning framework, iBVPNet, that features an efficient and effective spatio-temporal feature aggregation for the reliable estimation of BVP signals. Finally, this work examines the feasibility of extracting BVP signals from thermal video frames, which is under-explored. The iBVP dataset and source codes are publicly available for research use.

Evaluation of the Omni-Secure Firewall System in a Private Cloud Environment

This research explores the optimization of firewall systems within private cloud environments, specifically focusing on a 30-day evaluation of the Omni-Secure Firewall. Employing a multi-metric approach, the study introduces an innovative effectiveness metric (E) that amalgamates precision, recall, and redundancy considerations. The evaluation spans various machine learning models, including random forest, support vector machines, neural networks, k-nearest neighbors, decision tree, stochastic gradient descent, naive Bayes, logistic regression, gradient boosting, and AdaBoost. Benchmarking against service level agreement (SLA) metrics showcases the Omni-Secure Firewall’s commendable performance in meeting predefined targets. Noteworthy metrics include acceptable availability, target response time, efficient incident resolution, robust event detection, a low false-positive rate, and zero data-loss incidents, enhancing the system’s reliability and security, as well as user satisfaction. Performance metrics such as prediction latency, CPU usage, and memory consumption further highlight the system’s functionality, efficiency, and scalability within private cloud environments. The introduction of the effectiveness metric (E) provides a holistic assessment based on organizational priorities, considering precision, recall, F1 score, throughput, mitigation time, rule latency, and redundancy. Evaluation across machine learning models reveals variations, with random forest and support vector machines exhibiting notably high accuracy and balanced precision and recall. In conclusion, while the Omni-Secure Firewall System demonstrates potential, inconsistencies across machine learning models underscore the need for optimization. The dynamic nature of private cloud environments necessitates continuous monitoring and adjustment of security systems to fully realize benefits while safeguarding sensitive data and applications. The significance of this study lies in providing insights into optimizing firewall systems for private cloud environments, offering a framework for holistic security assessment and emphasizing the need for robust, reliable firewall systems in the dynamic landscape of private clouds. Study limitations, including the need for real-world validation and exploration of advanced machine learning models, set the stage for future research directions.

Improving Weather Forecasts for Sailing Events Using a Combination of a Numerical Forecast Model and Machine Learning Postprocessing

Accurate predictions of wind and other weather phenomena are essential for making informed strategic and tactical decisions in sailing. Sailors worldwide utilize current state-of-the-art forecasts, yet such forecasts are often insufficient because they do not offer the high temporal and geographic resolution required by sailors. This paper examines wind forecasting in competitive sailing and demonstrates that traditional wind forecasts can be improved for sailing events by using an integration of traditional numerical modeling and machine learning (ML) methods. Our primary objective is to provide practical and more precise wind forecasts that will give sailors a competitive edge. As a case study, we demonstrate the capabilities of our proposed methods to improve wind forecasting at Lake Kinneret, a popular sailing site. The lake wind pattern is highly influenced by the area’s topographic features and is characterized by unique local and mesoscale phenomena at different times of the day. In this research, we simulate the Kinneret wind during the summers of 2015–2021 in up to one-kilometer resolution using the Weather Research and Forecasting (WRF) atmospheric model. The results are used as input for convolutional neural network (CNN) and multilayer perceptron (MLP) ML models to postprocess and improve the WRF model accuracy. These advanced ML models are trained using training datasets based on the WRF data as well as real data measured by the meteorological service, and subsequently, a validation process of the trained ML model is performed on unseen datasets against site-specific meteorological service observations. Through our experimental analysis, we demonstrate the limitations of the WRF model. It uncovers notable biases in wind direction and velocity, particularly a persistent northern bias in direction and an overestimation of wind strength. Despite its inherent limitations, this study demonstrates that the integration of ML models can potentially improve wind forecasting due to the remarkable prediction accuracy rate achieved by the CNN model, surpassing 95%, while achieving partial success for the MLP model. Furthermore, a successful CNN-based preliminary forecast was effectively generated, suggesting its potential contribution to the future development of a user-friendly tool for sailors.

Monitoring the Industrial waste polluted stream - Integrated analytics and machine learning for water quality index assessment

The Water Quality Index (WQI) is a primary metric used to evaluate and categorize surface water quality which plays a crucial role in the management of fresh water resources. Machine Learning (ML) modeling offers potential insights into water quality index prediction. This study employed advanced ML models to get potential insights into the prediction of water quality index for the Aik-Stream, an industrially polluted natural water resource in Pakistan with 19 input water quality variables aligning them with surrounding land use and anthropogenic activities. Six machine learning algorithms, i.e. Adaptive Boosting (AdaBoost), K-Nearest Neighbors (K-NN), Gradient Boosting (GB), Random Forests (RF), Support Vector Regression (SVR), and Bayesian Regression (BR) were employed as benchmark models to predict the Water Quality Index (WQI) values of the polluted stream to achieve our objectives. For model calibration, 80% of the dataset was reserved for training, while 20% was set aside for testing. In our comparative analyses of predictive models for water quality index, the Gradient Boost (GB) model stood out the fittest for its precision, utilizing a combination of just seven parameters (chemical oxygen demand, total organic carbon, oil & grease, Ammonia- nitrogen, arsenic, nickel and zinc), surpassing other models by achieving better results in both training (R2 = 0.88, RMSE = 7.24) and testing (R2 = 0.85, RMSE = 8.67). Analyzing feature importance showed that all the selected variables, except for NO3 N, TDS and temperature had an impact on the accuracy of the models predictions. It is concluded that the application of machine learning to assess water quality in polluted environments enhances accuracy and facilitates real-time tracking, enabling proactive risk mitigations.

Progress and Opportunities for Machine Learning in Materials and Processes of Additive Manufacturing.

In recent years, there has been widespread adoption of machine learning (ML) technologies to unravel intricate relationships among diverse parameters in various additive manufacturing (AM) techniques. These ML models excel at recognizing complex patterns from extensive, well-curated datasets, thereby unveiling latent knowledge crucial for informed decision-making during the AM process. The collaborative synergy between ML and AM holds the potential to revolutionize the design and production of AM-printed parts. This review delves into the challenges and opportunities emerging at the intersection of these two dynamic fields. It provides a comprehensive analysis of the publication landscape for ML-related research in the field of AM, explores common ML applications in AM research (such as quality control, process optimization, design optimization, microstructure analysis, and material formulation), and concludes by presenting an outlook that underscores the utilization of advanced ML models, the development of emerging sensors, and ML applications in emerging AM-related fields. Notably, ML has garnered increased attention in AM due to its superior performance across various AM-related applications. It is envisioned that the integration of ML into AM processes will significantly enhance 3D printing capabilities across diverse AM-related research areas.

From NMR to AI: Designing a Novel Chemical Representation to Enhance Machine Learning Predictions of Physicochemical Properties.

A novel approach to the utilization of nuclear magnetic resonance (NMR) spectroscopy data in the prediction of logD through machine learning algorithms is shown. In the analysis, a data set of 754 chemical compounds, organized into 30 clusters, was evaluated using advanced machine learning models, such as Support Vector Regression (SVR), Gradient Boosting, and AdaBoost, and comprehensive validation and testing methods were employed, including 10-fold cross-validation, bootstrapping, and leave-one-out. The study revealed the superior performance of the Bucket Integration method for dimensionality reduction, consistently yielding the lowest root mean square error (RMSE) across all data sets and normalization schemes. The SVR prediction models demonstrated remarkable computational efficiency and low cost, with the best RMSE value reaching 0.66. Our best model outperformed existing tools like JChem Suite's logD Predictor (0.91) and CplogD (1.27), and a comparison with traditional molecular representations yielded a comparable RMSE (0.50), emphasizing the robustness of our NMR data integration. The widespread availability of NMR data in pharmaceutical and industrial research presents an untapped resource for predictive modeling, highlighting the need for accessible methodologies like ours that complement the analytical toolbox beyond conventional 2D approaches. Our approach, designed to leverage the rich spatial data from NMR spectroscopy, provides additional insights and enriches drug discovery and computational chemistry with a freely accessible tool.

Assessment of the uniaxial compressive strength of intact rocks: an extended comparison between machine and advanced machine learning models

Assessment of the uniaxial compressive strength of intact rocks: an extended comparison between machine and advanced machine learning models

A novel deep Siamese framework for burned area mapping Leveraging mixture of experts

Due to the complexity of the areas and the diversity of the objects, traditional Burned Area Mapping (BAM) methods cannot provide promising results. Moreover, these methods focus on additional processing to improve their results, which is time-consuming and complex. Therefore, an advanced framework is needed to achieve accurate results in burned area mapping. In this context, this study proposes a novel Siamese-based mixture of expert networks for burned area mapping, which takes advantage of a mixture of experts (MoE) and position and channel attention mechanisms for deep feature generation. The proposed framework has two deep feature extractor channels to account for the bi-temporal multispectral pre- and post-fire input datasets. To evaluate the performance of the SMoE model, three multispectral Sentinel-2 were used in different countries. The results were compared with other advanced machine and deep learning models, including Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), 2D-Siamse Convolutional Neural Network (2D-SCNN), and 3D-Siamse Convolutional Neural Network (3D-SCNN). The result of the burned mapping shows that the proposed model has a high effectiveness compared to other models, as it provides an average accuracy of more than 98% and 0.91 b y overall accuracy (OA) and kappa coefficient (KC) indices, respectively.

A machine learning stacking model accurately estimating gastric fluid volume in patients undergoing elective sedated gastrointestinal endoscopy

ABSTRACT Background The current point-of-care ultrasound (POCUS) assessment of gastric fluid volume primarily relies on the traditional linear approach, which often suffers from moderate accuracy. This study aimed to develop an advanced machine learning (ML) model to estimate gastric fluid volume more accurately. Methods We retrospectively analyzed the clinical data and POCUS data (D1: craniocaudal diameter, D2: anteroposterior diameter) of 1386 patients undergoing elective sedated gastrointestinal endoscopy (GIE) at Nanjing First Hospital to predict gastric fluid volume using ML techniques, including six different ML models and a stacking model. We evaluated the models using the adjusted Coefficient of Determination (R2), mean absolute error (MAE) and root mean square error (RMSE). The SHapley Additive exPlanations (SHAP) method was used to interpret the importance of the variables. Finally, a web calculator was constructed to facilitate its clinical application. Results The stacking model (Linear regression + Multilayer perceptron) performed best, with the highest adjusted R2 of 0.718 (0.632 to 0.804). The mean prediction bias was 4 ml (MAE: 4.008 (3.68 to 4.336)), which is better than that of the linear model. D1 and D2 ranked high in the SHAP plot and performed better in the right lateral decubitus (RLD) than in the supine position. The web calculator can be accessed at https://cheason.shinyapps.io/Stacking_regressor/. Conclusion The stacking model and its web calculator can serve as practical tools for accurately estimating gastric fluid volume in patients undergoing elective sedated GIE. It is recommended that anesthesiologists measure D1 and D2 in the patient’s RLD position.

Implementation of ABC - XYZ Analysis on Business Inventory Management using Machine Learning Model Technology By IJISRT

This paper presents a novel approach to optimize business inventory management through the integration of ABC-XYZ analysis with advanced machine learning models. Inventory management plays a critical role in the operational efficiency and profitability of businesses across various industries. Traditional methods such as ABC analysis and XYZ analysis have been widely used to classify inventory items based on their importance and demand variability. However, the effectiveness of these methods can be further enhanced by leveraging machine learning techniques to analyze historical data and make accurate predictions. In this study, we propose a framework that combines ABC-XYZ analysis with machine learning algorithms to classify inventory items and optimize inventory control policies. We demonstrate the effectiveness of our approach through a case study conducted on a real-world business dataset, highlighting significant improvements in inventory turnover, cost reduction, and customer satisfaction.

Cryptocurrency price prediction based on Xgboost, LightGBM and BNN

The valuation and prediction of cryptocurrency prices have become increasingly important in the financial market. Therefore, this study aims to focus on the selection and evaluation of machine learning models for cryptocurrency valuation. Thus, two types of machine learning models, gradient boosting trees (Xgboost and LightGBM) and neural networks, are compared to determine their effectiveness in generating features for cryptocurrency valuation. Additionally, correlation tests are conducted to identify the most suitable input variables for the models. The results demonstrate that the generated features have a significant impact on the accuracy of machine learning predictions for cryptocurrency prices. It highlights the potential of machine learning models in accurately predicting and evaluating the value of cryptocurrencies. Overall, the findings of this study contribute to the understanding of the role of machine learning in cryptocurrency valuation and provide valuable insights for investors and researchers. By leveraging machine learning techniques, investors can make informed decisions and develop effective investment strategies in the cryptocurrency market. This study contributes to cryptocurrency valuation research. Leveraging machine learning enables informed decisions and effective investment strategies. Furthermore, the findings inform the development of advanced machine learning models and algorithms for cryptocurrency valuation.

Machine learning analysis of patients’ perceptions towards generic medication in Greece: a survey-based study

Introduction:This survey-based study investigates Greek patients’ perceptions and attitudes towards generic drugs, aiming to identify factors influencing the acceptance and market penetration of generics in Greece. Despite the acknowledged cost-saving potential of generic medication, skepticism among patients remains a barrier to their widespread adoption.Methods:Between February 2017 and June 2021, a mixed-methods approach was employed, combining descriptive statistics with advanced machine learning models (Logistic Regression, Support Vector Machine, Random Forest, Gradient Boosting, and XGBoost) to analyze responses from 2,617 adult participants. The study focused on optimizing these models through extensive hyperparameter tuning to predict patient willingness to switch to a generic medication.Results:The analysis revealed healthcare providers as the primary information source about generics for patients. Significant differences in perceptions were observed across demographic groups, with machine learning models successfully identifying key predictors for the acceptance of generic drugs, including patient knowledge and healthcare professional influence. The Random Forest model demonstrated the highest accuracy and was selected as the most suitable for this dataset.Discussion:The findings underscore the critical role of informed healthcare providers in influencing patient attitudes towards generics. Despite the study’s focus on Greece, the insights have broader implications for enhancing generic drug acceptance globally. Limitations include reliance on convenience sampling and self-reported data, suggesting caution in generalizing results.

Feature Optimization-Based Machine Learning Approach for Czech Land Cover Classification Using Sentinel-2 Images

The Czech Republic is one of the countries along the Belt and Road Initiative, and classifying land cover in the Czech Republic helps to understand the distribution of its forest resources, laying the foundation for forestry cooperation between China and the Czech Republic. This study aims to develop a practical approach for land cover classification in the Czech Republic, with the goal of efficiently acquiring spatial distribution information regarding its forest resources. This approach is based on multi-level feature extraction and selection, integrated with advanced machine learning or deep learning models. To accomplish this goal, the study concentrated on two typical experimental regions in the Czech Republic and conducted a series of classification experiments, using Sentinel-2 and DEM data in 2018 as the main data sources. Initially, this study extracted various features, including spectral, vegetation, and terrain features, from the study area, then assessed and selected key features based on their importance. Additionally, this study also explored multi-level spatial contextual features to improve classification performance. The extracted features include texture and morphological features, as well as deep semantic information learned by utilizing a deep learning model, 3D CNN. Finally, an AdaBoost ensemble learning model with the random forest as the base classifier is designed to produce land cover classification maps, thus obtaining the spatial distribution of forest resources. The experimental results demonstrate that feature optimization significantly enhances the extraction of high-quality features of surface objects, thereby improving classification performance. Specifically, morphological and texture features can effectively enhance the discriminability between different features of surface objects, thereby improving classification accuracy. Utilizing deep learning networks enables more efficient extraction of deep feature information, further enhancing classification accuracy. Moreover, employing an ensemble learning model effectively boosts the accuracy of the original classification results from different individual classifiers. Ultimately, the classification accuracy of the two experimental areas reaches 92.84% and 93.83%, respectively. The user accuracies for forests are 92.24% and 93.14%, while the producer accuracies are 97.71% and 97.02%. This study applies the proposed approach for nationwide classification in the Czech Republic, resulting in an overall classification accuracy of 90.98%, with forest user accuracy at 91.97% and producer accuracy at 96.2%. The results in this study demonstrate the feasibility of combining feature optimization with the 3D Convolutional Neural Network (3DCNN) model for land cover classification. This study can serve as a reference for research methods in deep learning for land cover classification, utilizing optimized features.

Rent Price Prediction with Advanced Machine Learning Methods: A Comparison of California and Texas

The forecast of rent prices in dynamic housing markets is of fundamental importance to renters, landlords, investors, and politicians alike. Machine learning models offer flexibility, excel at modeling complex relationships, and provide outstanding forecast precision. This study compares advanced machine learning models, extreme gradient boosting regressor (XGBoost), light gradient boosting machine (LightGBM), random forest, ridge regression, and two ensemble approaches, to predict California and Texas rent prices. The two ensemble approaches include a hybrid regression of averaging base models and a 2-level stacked generalization model. The results revealed that a stacked generalization ensemble with base models random forest, XGBoost, LightGBM, and meta-model ridge regression achieved the best performance for the California dataset by generating the lowest MSE and highest R2 of 46116.3 and 0.8858, respectively. In contrast, random forest outperformed both ensemble models with the lowest MSE and MAPE of 18401.93 and 9.7003%, respectively, and the highest R2 of 0.7992. These methodologies can assess future rental property worth, serve as indicators for market dynamics, and aid in establishing real estate policies, thereby providing practical guidance to individuals, businesses, and policymakers.

Enhancing accessibility for improved diagnosis with modified EfficientNetV2-S and cyclic learning rate strategy in women with disabilities and breast cancer.

Breast cancer, a prevalent cancer among women worldwide, necessitates precise and prompt detection for successful treatment. While conventional histopathological examination is the benchmark, it is a lengthy process and prone to variations among different observers. Employing machine learning to automate the diagnosis of breast cancer presents a viable option, striving to improve both precision and speed. Previous studies have primarily focused on applying various machine learning and deep learning models for the classification of breast cancer images. These methodologies leverage convolutional neural networks (CNNs) and other advanced algorithms to differentiate between benign and malignant tumors from histopathological images. Current models, despite their potential, encounter obstacles related to generalizability, computational performance, and managing datasets with imbalances. Additionally, a significant number of these models do not possess the requisite transparency and interpretability, which are vital for medical diagnostic purposes. To address these limitations, our study introduces an advanced machine learning model based on EfficientNetV2. This model incorporates state-of-the-art techniques in image processing and neural network architecture, aiming to improve accuracy, efficiency, and robustness in classification. We employed the EfficientNetV2 model, fine-tuned for the specific task of breast cancer image classification. Our model underwent rigorous training and validation using the BreakHis dataset, which includes diverse histopathological images. Advanced data preprocessing, augmentation techniques, and a cyclical learning rate strategy were implemented to enhance model performance. The introduced model exhibited remarkable efficacy, attaining an accuracy rate of 99.68%, balanced precision and recall as indicated by a significant F1 score, and a considerable Cohen's Kappa value. These indicators highlight the model's proficiency in correctly categorizing histopathological images, surpassing current techniques in reliability and effectiveness. The research emphasizes improved accessibility, catering to individuals with disabilities and the elderly. By enhancing visual representation and interpretability, the proposed approach aims to make strides in inclusive medical image interpretation, ensuring equitable access to diagnostic information.

Revisiting the hybrid approach of anomaly detection and extreme value theory for estimating pedestrian crashes using traffic conflicts obtained from artificial intelligence-based video analytics

Pedestrians represent a group of vulnerable road users who are at a higher risk of sustaining severe injuries than other road users. As such, proactively assessing pedestrian crash risks is of paramount importance. Recently, extreme value theory models have been employed for proactively assessing crash risks from traffic conflicts, whereby the underpinning of these models are two sampling approaches, namely block maxima and peak over threshold. Earlier studies reported poor accuracy and large uncertainty of these models, which has been largely attributed to limited sample size. Another fundamental reason for such poor performance could be the improper selection of traffic conflict extremes due to the lack of an efficient sampling mechanism. To test this hypothesis and demonstrate the effect of sampling technique on extreme value theory models, this study aims to develop hybrid models whereby unconventional sampling techniques were used to select the extreme vehicle–pedestrian conflicts that were then modelled using extreme value distributions to estimate the crash risk. Unconventional sampling techniques refer to unsupervised machine learning-based anomaly detection techniques. In particular, Isolation forest and minimum covariance determinant techniques were used to identify extreme vehicle–pedestrian conflicts characterised by post encroachment time as the traffic conflict measure. Video data was collected for four weekdays (6 am–6 pm) from three four-legged intersections in Brisbane, Australia and processed using artificial intelligence-based video analytics. Results indicate that mean crash estimates of hybrid models were much closer to observed crashes with narrower confidence intervals as compared with traditional extreme value models. The findings of this study demonstrate the suitability of machine learning-based anomaly detection techniques to augment the performance of existing extreme value models for estimating pedestrian crashes from traffic conflicts. These findings are envisaged to further explore the possibility of utilising more advanced machine learning models for traffic conflict techniques.

Advanced Techniques for Geospatial Referencing in Online Media Repositories

In the digital transformation era, video media libraries’ untapped potential is immense, restricted primarily by their non-machine-readable nature and basic search functionalities limited to standard metadata. This study presents a novel multimodal methodology that utilizes advances in artificial intelligence, including neural networks, computer vision, and natural language processing, to extract and geocode geospatial references from videos. Leveraging the geospatial information from videos enables semantic searches, enhances search relevance, and allows for targeted advertising, particularly on mobile platforms. The methodology involves a comprehensive process, including data acquisition from ARD Mediathek, image and text analysis using advanced machine learning models, and audio and subtitle processing with state-of-the-art linguistic models. Despite challenges like model interpretability and the complexity of geospatial data extraction, this study’s findings indicate significant potential for advancing the precision of spatial data analysis within video content, promising to enrich media libraries with more navigable, contextually rich content. This advancement has implications for user engagement, targeted services, and broader urban planning and cultural heritage applications.

Data-augmented landslide displacement prediction using generative adversarial network

Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide. Accurately predicting landslide displacement enables effective early warning and risk management. However, the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models, such as state-of-the-art machine learning (ML) models. To address these challenges, this study proposes a data augmentation framework that uses generative adversarial networks (GANs), a recent advance in generative artificial intelligence (AI), to improve the accuracy of landslide displacement prediction. The framework provides effective data augmentation to enhance limited datasets. A recurrent GAN model, RGAN-LS, is proposed, specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data. A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data. Then, the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory (LSTM) networks and particle swarm optimization-support vector machine (PSO-SVM) models for landslide displacement prediction tasks. Results on two landslides in the Three Gorges Reservoir (TGR) region show a significant improvement in LSTM model prediction performance when trained on augmented data. For instance, in the case of the Baishuihe landslide, the average root mean square error (RMSE) increases by 16.11%, and the mean absolute error (MAE) by 17.59%. More importantly, the model's responsiveness during mutational stages is enhanced for early warning purposes. However, the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM. Further analysis indicates that an optimal synthetic-to-real data ratio (50% on the illustration cases) maximizes the improvements. This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results. By using the powerful generative AI approach, RGAN-LS can generate high-fidelity synthetic landslide data. This is critical for improving the performance of advanced ML models in predicting landslide displacement, particularly when there are limited training data. Additionally, this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.