Log Information Research Articles

Seismic facies characterization using Rock Physics Templates and brittleness indices: Stybarrow field

This paper proposes a method for identifying the lithological properties of the medium based on the joint analysis of the Lamé parameters, Young's Modulus, and Poisson's Ratio. Additionally, an analysis of brittleness was proposed to identify brittle/ductile intervals and areas of potential reservoirs. The petroelastic properties were analyzed at well and seismic scales using ternary rock physics templates. The ternary templates were built from a self-consistent micromechanical model. In addition, the analysis allows for preserving the conditions of the environment subsurface in the seismic and log information. A workflow for petroelastic lithology interpretation was coupled with a workflow of brittleness modeling. The results correlate well with conventional qualitative methodologies applied in previous studies. A brittleness analysis methodology was developed and tested to identify reservoirs associated with the Lower Cretaceous in the Stybarrow field in Australia; the results highlight the high brittleness zones attenuated by hydrocarbons ( ). The proposed seismic-based methodology is an improvement to conventional analysis trends for identifying lithologies and prospective hydrocarbon zones.

A new machine learning approach for estimating shear wave velocity profile using borelog data

The shear wave velocity is among the key parameters that are responsible for damage caused during an earthquake. Determining shear wave velocity is a costly and time-consuming direct geophysical method. In the present paper, a machine learning model has been developed to obtain the subsurface shear wave velocity profile without using direct methods. The bore log information and the subsurface shear wave velocity profile available at various stations of Japan’s Kyoshin network (K-NET) have been utilized for training this machine learning model. The parametric correlation study indicates that simple parameters like rock/soil type, the thickness of the layer in the model, and standard penetration test (SPT-N) value directly correlate with the medium’s shear wave velocity. A stacked ensemble machine learning model named VelProfES (an acronym for Velocity Profiler using Ensemble machine learning models) has been developed in this paper and has been utilized for effective prediction of the shear wave velocity profile using basic information from borelog data. The dataset used in the training and testing of the machine learning model consists of borelog and shear wave velocity information from 1101 stations. Of 1101 stations, 657, 283, and 71 stations have been utilized for training, testing, and validating the machine learning model. Training, testing, and validation of the developed machine learning model consist of parameters from 12351, 5279, and 1388 velocity layers. The problem of data imbalance based on soil type has been addressed using an additional 10510 layers of synthetic borelog data generated from conditional generative adversarial networks (CTGANs). A feature and model ablation study was conducted for the VelProfES model to provide substantiation for the model and feature selection choices. The predicted shear wave velocity profiles were compared at specific stations, focusing on average velocities at 5, 10, 15, and 20 depths. Further, the predicted values have been compared with the empirical relation of Sil and Haloi (2017) and a trained polynomial model. The machine learning model demonstrates close alignment between predicted and actual values across a broad spectrum of velocities, a contrast not observed in the empirical relation and polynomial model. The results show that the machine learning models and augmented data generated using CTGANs can efficiently minimize the error between actual and predicted subsurface shear wave velocity values.

The Influence of Reservoir Architecture on the Connectivity of the Shahejie Formation in the Liuzhong Oilfield

The lack of research on fine reservoir structure and sand body patterns in the Jidong Oilfield currently restricts the efficient development of the oilfield. Therefore, this article mainly focuses on the study of the main types of facies of the Shahejie Formation, sand body splicing patterns, and the degree of sand-body connectivity. The interpretation and analysis of well-logging, three-dimensional (3D) seismic, and production data were used to lay the foundation for the study and evaluate the remaining oil distribution. The results indicate that the reservoir sandstones in the study area were mainly deposited in a submerged distributary channel, mouth bar, and distributary channel flank. Using logging information to identify individual sands, a deltaic sand assemblage pattern is proposed by analyzing the sedimentary architecture. In the vertical direction, the deltaic sand body collocation style can be divided into cut-and-stack and separated types. In the lateral direction, the multi-stage sand bodies exhibit three collocation patterns: the side-cutting type, the mouth bar contact type, and the submerged distributary channel flank contact type. The degree of sand-body connectivity under different splicing patterns was analyzed and verified using production dynamic data. It was found that the sand body splicing pattern with a vertical up-cut stack and the sand body splicing pattern with a lateral up-cut had the best inter-sand-body connectivity.

Multi-drug-resistant tuberculosis and its associated factors among pulmonary tuberculosis patients linked to first-line anti-tuberculosis drugs in north-west Ethiopia

Introduction. Multi-drug-resistant tuberculosis (MDR-TB) is an emerging global challenge. Ethiopia is one of the 20 top countries with the highest estimated numbers of incidents of MDR-TB. Recently, the World Health Organization warned that drug-resistant TB is escalating and called for concerted action to reduce the spread of drug resistance. Hypothesis. The current study investigated MDR-TB in patients receiving first-line anti-TB drug treatment and associated factors. Aim. The study aimed to determine the prevalence of MDR-TB and its associated factors among smear-positive pulmonary TB patients receiving first-line anti-TB drug treatment. Methodology. An institution-based cross-sectional study was employed. All data were collected from laboratory result log books and information via a questionnaire. Samples from 205 smear-positive pulmonary TB patients were selected among first-line drug treatment by a systematic sampling method. Specimens were transported to Felege Hiwot referral hospital laboratory for GeneXpert testing. Factors associated with an outcome variable in binary multi-variable logistic regression analysis at P<0.05 were considered statistically significant variables. An ethical approval letter was taken to the respective health facility and written consent was obtained from each participant. Results. The overall prevalence of MDR-TB was 9.3 % (95 % CI, 5.4 13.7 %). Sign and symptom experience of anti-TB drug side effects [adjusted odds ratio (AOR)=0.18, 95 % CI=0.03–0.99, P=0.049] and co-morbidity (AOR=0.03, 95 % CI=0.01–0.55, P=0.02) were statistically associated with the development of MDR-TB infection Conclusion. The prevalence of MDR-TB was high (9.3 %) and contributed highly to new cases (8.3 %). Factors associated with MDR-TB were previous treatment, co-morbidity and laboratory diagnosis method prior to TB treatment. Therefore, this finding aims to maximize early detection and treatment, strengthening TB infection control, and proper implementation of directly observed therapy short course recommendations to reduce the burden of MDR-TB.

DESIGNING INVENTORY INFORMATION SYSTEM AT PT HAADI WAHANA JAYA DESKTOP BASED

This research documents the implementation process of a desktop-based inventory information system at PT Haadi Wahana Jaya with the aim of increasing the efficiency and accuracy of inventory management. Through a research and development approach, this system is designed to meet the company's specific needs. With an intuitive user interface design, the system provides easy access and navigation for users. The login form allows users to access inventory information securely, with the implementation of additional security features such as CAPTCHA. In addition, integration with financial and production systems ensures interdepartmental connectivity and better coordination. Implementation results show increased operational efficiency, optimization of inventory levels, and accurate real-time reporting. Although some challenges in terms of culture change were encountered, user feedback indicated a higher level of satisfaction. The conclusion of this research underlines the positive contribution of desktop-based inventory information systems to PT Haadi Wahana Jaya's inventory management.

AS-Parser: Log Parsing Based on Adaptive Segmentation

System logs have long been recognized as valuable data for analyzing and diagnosing system failures. One fundamental task of log processing is to convert unstructured logs into structured logs through log parsing. All previous log parsing approaches follow a general framework that first segments each log into a token sequence and then computes similarity between two sequences. However, all existing approaches share the common drawback: the flat segmentation with fixed delimiters fails to understand the structural information of logs, which causes low parsing accuracy. To address this problem, we propose a novel log parsing approach, AS-Parser. Our approach introduces a hierarchical log segmentation mechanism that can adaptively segment logs into a tree structure. It can automatically recognize the appropriate delimiters and capture the common structural information. Moreover, we propose three improvements that enhance both the effectiveness and efficiency of our approach. On the public benchmark, AS-Parser performs best on 14 out of 16 datasets, with an average parsing accuracy of 0.943, far exceeding existing approaches.

Penerapan Algoritma Genetika Untuk Penjadwalan Mata Pelajaran Di SMK Negeri 1 Kota Tambolaka

consider other things such as avoiding the same or repeated schedules in one day, the number of teaching staff involved, and practicum subjects which in their implementation require a laboratory. The subject scheduling process at SMK Negeri 1 Tambolaka City is still carried out manually by Deputy Head 1 for the curriculum field, who currently uses Microsoft Excel software, which has the potential for errors and often requires correction before the schedule is implemented. Because the subject scheduling process is very important, a solution is needed in making subject schedules. Therefore, this research aims to optimize course schedules by applying a genetic algorithm to the course scheduling application. In this research, the process of preparing rosters for applied subjects was carried out at school using a web-based genetic algorithm method so that schedule collisions did not occur and the process was more optimal. In the experiment, the results of this subject scheduling application system consisted of several forms and menus, including a login form, department data menu, subject data, class data, teachers, hour ranges, special schedules, and the scheduling menu. Creating a teacher's teaching schedule using a genetic algorithm can produce a schedule automatically and systematically, thereby displaying the schedule for the day and time of each teacher's teaching schedule. The application of genetic algorithms in scheduling teacher teaching at SMK Negeri 1 Tambolaka City is a very optimal solution for scheduling, so that the possibility of similarities in the same teacher's teaching time and hours is very small.

Integrated Study for Seservoir Characterization of Kadanwari Area of Lower Indus Basin, Pakistan Using Seismic Data and Well Data

As a developing nation, Pakistan is confronted with serious energy challenges as a result of a scarcity of hydrocarbons. And the major objective of this paper is to assess the hydrocarbon potential of a study zone in Pakistan’s central Sindh Basin, which is known as the Kadanwari Gas area. The characterization of the reservoir has been accomplished by the use of conventional geophysical techniques, including 2D seismic data and well log information. By converting the time structure map of seismic, it is possible to produce the depth contour map. And a method for converting seismic data to Acoustic Impedance is described. Based on well logs collected after drilling, Petro-physical characteristics such as shale volume, porosity, water saturation, and hydrocarbon saturation were calculated. It was established that the review area is part of the extensional structural system by normal faulting that was seen on seismic sections. The seismic interpretation of these lines that emerged proved the existence of the Horst and Grabben structures as a consequence of normal faulting. The region around these buildings has a significant amount of potential for hydrocarbon accumulation.

Pore Pressure Uncertainty Characterization Coupling Machine Learning and Geostatistical Modelling

Pore pressure prediction is fundamental when drilling deep and geologically complex reservoirs. Even in relatively well-characterized hydrocarbon reservoir fields, with a considerable number of drilled wells, when located in challenging geological environments, poor prediction of abnormal pore pressure might result in catastrophic events that can cause harm to human lives and infrastructures. To better quantify drilling risks, the uncertainty associated with the pore pressure prediction should be integrated within the geo-modelling workflow. Leveraging a challenging real case from the Brazilian pre-salt, the work presented herein proposes a seismic-driven gradient pore pressure modelling workflow, which combines machine learning and geostatistical co-simulation to predict high-resolution gradient pore pressure volumes. First, existing angle-dependent seismic reflection data are inverted for P- and S-wave velocity and density. Then, K-nearest neighbor is used to create a regression model between pore pressure gradient and P- and S-wave velocity, density and depth based on the well log information. The trained model is applied to predict a three-dimensional gradient pore pressure model from the models obtained from geostatistical seismic inversion. This gradient pore pressure model is a smooth representation of the highly variable subsurface and is used as secondary variable in stochastic sequential co-simulation with joint probability distributions to generate multiple high-resolution realizations of gradient pore pressure. The ensemble of co-simulated models can be used to assess the spatial uncertainty about the gradient pore pressure predictions. The results of the application example show the ability of the method to reproduce the spatial patterns observed in the seismic data and to reproduce existing gradient pore pressure well logs at two blind well locations, which were not used to condition the gradient pore pressure predictions.

Public cloud network intrusion and internet legal supervision based on abnormal feature detection

The increasing number of public cloud network intrusion incidents poses a serious threat to internet security. This article provides an effective public cloud network intrusion detection and internet security legal countermeasure based on the method of anomaly feature detection. The research adopts the method of anomaly feature detection to identify abnormal behavior and intrusion behavior by collecting and analyzing data traffic and log information of public cloud networks. Develop corresponding protective measures and disposal plans based on legal measures for internet security. Through experiments and case analysis, the method based on anomaly feature detection proposed in this article has achieved good results in public cloud network intrusion detection and legal countermeasures for internet security. By utilizing abnormal features and relevant laws and regulations in a reasonable manner, the security of cloud networks can be effectively improved and intrusion risks can be reduced.

Full waveform inversion with combined misfit functions and application in land seismic data

Full waveform inversion reconstructs subsurface structures by matching the synthetic waveform to the observed waveform. Inaccuracy of the source wavelets can, thus, easily lead to an inaccurate model. Simultaneously updating source wavelets and model parameters is a conventionally used strategy. However, when the initial model is very far from the true model, cycle skipping exists, and estimating a reliable source wavelet is very difficult. We propose a combinatory inversion workflow based on seismic events. We apply a Gaussian time window around the first break and gradually increase its width to include more seismic events. The influence of inaccurate source wavelets is alleviated by applying a Gaussian time window around the first break to evaluate the normalized cross-correlation-based objective function. There are inevitable small model artifacts caused by inter-event interactions when calculating cross-correlations. As a result, we switch to the optimal transport function to clean the model and update the source wavelets simultaneously. The combinatory strategy has been applied to models with different types of geological structures. Starting from a crude initial model, we recovered a high-resolution and high-fidelity model and the source wavelets in two synthetic experiments. Finally, we apply our inversion strategy to a real-land seismic dataset in Southeast China and obtain a higher-resolution velocity model. By comparing an inversion velocity profile with well log information and the recorded data with the simulated data, we conclude that our inversion results for the field data are accurate and this new strategy is effective.

Research on Fault Detection for Microservices Based on Log Information and Social Network Mechanism Using BiLSTM-DCNN Model

The microservice architecture breaks through the traditional cluster architecture mode based on virtual machines and uses containers as carriers to interact through lightweight communication mechanisms to reduce system coupling and provide more flexible system service support. With the expansion of the system scale, a large number of system logs with complex structures and chaotic relationships are generated. How to accurately analyze the system logs and make efficient fault prediction is particularly important for building a safe and reliable system. By studying neural network technology, this paper proposes an Attention-Based Bidirectional Long Short-Term Memory Network (Bi-LSTM). Combined with the dual channel convolutional neural network model (DCNN), it uses the attention mechanism to explore the differences between dimensional features, realizes multi-dimensional feature fusion, and establishes a BiLSTM-DCNN deep learning model that integrates the attention mechanism. From the perspective of social network analysis, a data preprocessing method is proposed to process fault redundant data and improve the accuracy of fault prediction under Microservices. Compare BiLSTM-DCNN with the mainstream system log analysis machine learning models SVM, CNN and Bi-LSTM, and explore the advantages of BiLSTM-DCNN in processing microservice system log text. The model is applied to simulation data and HDFS data set for experimental comparison, which proves the good generalization ability and universality of BiLSTM-DCNN.

PERANCANGAN DAN PEMBUATAN SISTEM KEARSIPAN ELEKTRONIK DOKUMEN PROSES BISNIS BERBASIS MICROSOFT ACCESS

Document archiving is something that is often done by every company, one of which is PT Nusantara Turbine and Propulsion. Document archiving at PT Nusantara Turbine and Propulsion, especially in the Aero Engines Sales and Trading Division, still uses conventional systems. Therefore, the process of searching for documents can take quite a long time. In addition, there is a case experienced by secretaries, namely the loss of archives. This loss of archives is caused by borrowing archives. To overcome this problem, an electronic archive system was created that can store and display information about archives. The system can also record the data of the person who borrowed the archive. In this case, the application that supports the process of designing and creating the system is Microsoft Access. System design and creation can be started from DFD Level 0 and Level 1 and ERD design. As for the creation is done in Microsoft Access which starts from creating tables, forms, reports to queries. The results of the project are the front page, login form, main menu, data input menu, report menu and document search. All features that have been made are tested to the secretary as a user of SAEDPB. The results of the trial were declared acceptable because there were no obstacles when operating. With the search feature and storage of documents in the form of soft files, it is expected to help secretaries in rediscovering archives easily and quickly. This is supported by several studies that say that electronic records management can make it easier for someone when archiving and rediscovering archives. Therefore, the use of SAEDPB is expected to make work more effective and efficient, especially in archiving.
 
 Keywords: Archive, Electronic Archive, Microsoft Access

Impact of Changing ACGME Case Requirements on Radiation Oncology Resident Rotation Structure

The ACGME has updated case requirements for radiation oncology residents beginning with the graduating class of 2026, specifically introducing minimum cases across a wider range of disease sites. We aimed to assess the impact the ACGME update will have on residency rotation scheduling in our training program by retrospectively applying the case minimums to recent graduating classes and determining how rotations should be modified to meet the new standards. Our program utilizes the apprentice model where residents are assigned 1:1 or 1:2 to faculty supervisors. We abstracted case log information from residents graduating between 2020 and 2022, and cases were categorized based on the new ACGME requirements. We also abstracted total department treatment courses from our treatment tracking software which records disease site and resident participation. Hypothetical schedules were created to determine how resident rotations can be structured to ensure adequate exposure to meet all case minimums. The mean number of cases for graduating residents was 666 (range: 563-755). Six (67%) graduating residents would have not met at least one new ACGME site-specific requirement. The most common delinquencies were esophagus, anorectal, non-prostate genitourinary (GU), and lymphoma for which at least 3 residents each did not meet. Review of the treatment tracking software confirmed adequate case volume for these disease sites but that they were often not performed by a resident. We observed that these disease sites were less likely to be performed by a resident than other disease sites at our institution. Specifically, in 2022, 25% of all simulations went uncovered by residents but at-risk disease sites such as GI and GU each averaged 35% of simulations uncovered. We observed that when we retrospectively applied new ACGME minimums to recent graduating classes most residents would have been considered non-compliant despite adequate case volume at our institution. Case exposure, particularly for less common disease presentations, was highly dependent on rotation assignment. In the setting of increasing faculty-to-resident ratio requirements, conventional 1:1 assignments may not be adequate to meet new ACGME site minimums. We are currently comparing different resident coverage models that can be coupled with our traditional apprentice model to increase breadth of case exposure without compromising educational yield. Two models have arisen: a hybrid model where residents traditionally cover one attending and then cover the consults/simulations only of a second attending and a consult service model where residents are paired with 2 or more attendings but only see consults/simulations with these attendings. Coupling these models alongside the traditional apprentice model projects not only increased coverage of all simulations but improves coverage of traditionally "missed" simulations to at least 83% and upwards of 90% on most simulated schedules.

Feature selection algorithm for substation main equipment defect text mining based on natural language processing

AbstractThe dimension of relevant text feature space and feature weight of substation main equipment defect information is high, so it is difficult to accurately select mining features. The Natural Language Processing (NLP) medium and short‐term neural network model is used to realise the defect information text feature word segmentation in the log. After extracting the text features of defect information of main substation equipment with high categories to form the feature space; the TF‐IDF algorithm is designed to calculate the importance weight of text keywords, judge the criticality of defect information text feature vocabulary, accurately locate defect information text features, and realise defect information text feature mining. Experiments show that the algorithm has high precision for specific word segmentation of massive substation main equipment log information.

Site response analysis beneath the Kashmir basin (NW Himalaya) using ambient noise

Deep sedimentary valleys entrap and amplify seismic waves, which is further responsible for site-specific amplification over the allied region. Kashmir valley is a deep and active sedimentary basin in the northwest portion of the Himalayan lap. To characterize the site response for the intermountain Kashmir valley for the first time, we acquire single station microtremor measurements using Lennartz (three components/5s seismometer) at 141 sites with a grid of (5 km × 5 km) and two-dimensional (2D) array measurements using seven units of recording station of different geometry pattern at 38 sites across different lithological setup within the basin. We present here (1) a first-order predominant fundamental frequency (0.21–10.19 Hz) and subsequent sedimentary thickness maps for the entire valley, reflecting deep deposition with spatial heterogeneity in the area using the horizontal-to-vertical spectral ratio (HVSR) technique; (2) spatial classification of generated HVSR curves linking subsurface geomorphology and post strong ground-motion scenario in the valley; (3) extraction of the best dispersion characteristics of Rayleigh waves (fundamental mode) from all recorded vertical signals at each array site using frequency–wavenumber (F-K) method with an emphasis on signal synchronicity; and (4) retrieval of one-dimensional (1D) shear wave velocity ( VS) profiles across the valley from the inversion of dispersion curves using the neighborhood algorithm. Distinct model parameterizations were tested for the inversion to achieve the optimal inversion misfit. The collocated 1D VS profiles are consistent with newly drilled borehole logs information. Besides, the presented first-ever ambient noise survey–based site response study meets the objectives of site-specific seismic hazard and risk analysis of the Kashmir valley at the regional scale.

Basement Mapping Using Nonlinear Gravity Inversion with Borehole and Seismic Constraints

We present an integrated method for mapping the basement structures of sedimentary basins by combining surface gravity data, seismic imaging, and borehole logging information. The core of the method is a nonlinear inversion algorithm for constructing the shape and depth of the basement from surface gravity data. By using the primal-logarithmic barrier method, we impose depth constraints from the borehole information. The basement depth was imaged by seismic interpretation and incorporated into the inversion as a reference model. As a result, the gravity inversion constructs basement structures that are closest to the seismic input while simultaneously satisfying the surface gravity data and borehole information. We used this new methodology to unveil the basement morphology of the Recôncavo Basin, Brazil. Recôncavo is a syn-rift onshore mature basin that exhibits a strong correlation between oil field distribution and tectonic framework. The seismic imaging in the area is ambiguous, and our approach improved the basement definition and highlighted exploration targets in the studied area.

IoT based Car Parking System using LoRaWAN Technology for CIT Campus

The usage of four-wheeler vehicles has increased over time, and finding a parking spot to park the cars in is getting much more challenging. This issue also exists on the CIT CAMPUS, which led to developing a parking system using IoT technology to make it simpler to find parking places. An IoT-based car parking system based on LoRaWAN technology is suggested as a solution to this issue. The purpose of this research is to design and implement a well-organised parking system with a user-friendly application which can avoid cramming in the car parking area. In the proposed system, Arduino-LoRa transmitter boards, Ultrasonic sensor and LG01-LoRa gateway are used for the implementation. Ultrasonic sensor-equipped Arduino-LoRa transmitter boards are positioned in various parking lots. It is used as a processing element which detects the availability of parking space in the parking area and transmits the data to the gateway that is situated close to the parking lots. The data is received by the gateway and forwards the slot information to the Things Network. The vacant spaces in the parking area could be viewed using a mobile application. The proposed system includes a gate entry management system that reads the number plate of a vehicle using YOLO- V3 algorithm and stores the real-time vehicle log information in the database. This method makes it easier for drivers to identify the available parking spaces offering a streamlined parking experience, which helps users spend less time in parking their cars.

AllInfoLog: Robust Diverse Anomalies Detection Based on All Log Features

Large-scale services are generating massive logs, which trace the runtime states and critical events. Anomaly detection via logs is critical for service maintenance and reliability assurance. Existing log-based anomaly detection methods make use of the limited information in log data, resulting in their incapability of detecting diverse anomalies related to unused log features. In this paper, we propose AllInfoLog, a robust log-based anomaly detection method taking advantage of all log information, to detect diverse types of anomalies. To capture all log features, AllInfoLog utilizes four encoders to extract semantic, parameter, time, and other feature embeddings, respectively. The embeddings of all log features are then combined to train an attention-based Bi-LSTM model to detect diverse anomalies. The experimental evaluations on real-world log datasets, synthetic datasets, and unstable log datasets demonstrate AllInfoLog outperforms the state-of-the-art log-based anomaly detection methods from aspects of performance and robustness, and has effectiveness to detect diverse types of anomalies.

Bioconcentration Assessment in Fish Based on In Vitro Intrinsic Clearance: Predictivity of an Empirical Model Compared to In Vitro-In Vivo Extrapolation Models.

To estimate the bioconcentration factor (BCF), the in vitro intrinsic clearance (CLINVITRO,INT) from rainbow trout liver S9 fractions (RT-S9) can be applied to in vitro-in vivo extrapolation (IVIVE) models, yet uncertainties remain in model parameterization. An alternative model approach is evaluated: a regression model was built in the form log BCF = a × log Kow + b × log CLINVITRO,INT. The coefficients a and b were fitted based on a training set of 40 chemicals. A high robustness of the coefficients and good accuracy of BCF prediction were found on independent datasets of neutral organic chemicals (measured log Kow 3.3-6.2). BCF predictions were similar to or in better agreement with in vivo BCFs compared to IVIVE models (2.4- to 2.9- vs 2.8- to 3.6-fold misprediction) for training and test sets. Species-matched models (trout, carp) did not result in improvements. This study presents the largest dataset on CLINVITRO,INT and BCFs to assess predictivity of the RT-S9 assay. The robustness of the regression statistics on different datasets and the high statistical weight of the CLINVITRO,INT term illustrate the predictive power of the RT-S9 assay as an important step toward regulatory acceptance to replace animal experiments.