Iterative Workflow Research Articles

Accelerating Agile Quality Assurance with AI-Powered Testing Strategies

The infusion of Artificial Intelligence (AI) into Agile software development is revolutionizing the domain of software testing, reshaping conventional methodologies to meet the demands of today’s complex and accelerated development cycles. Agile frameworks, renowned for their iterative workflows and adaptability, often encounter limitations in scaling to the velocity and intricacy of modern projects. AI emerges as a game-changer, introducing sophisticated capabilities such as hyper-automation, predictive defect analytics, and context-aware decision-making, thereby addressing these limitations with precision and scalability. This paper investigates the transformative influence of AI on Agile testing methodologies, with a focus on specific use cases, the operational efficiencies gained through AI-augmented workflows, and the seamless collaboration between human testers and intelligent systems. A comprehensive, architecture-driven framework for embedding AI into Agile testing cycles is presented, with empirical validation through case studies that demonstrate tangible improvements in accuracy, productivity, and sprint adaptability. Keywords: Agile Methodology, Artificial Intelligence, Quality Assurance, Predictive Analytics, Test-Driven Development (TDD), Behavior-Driven Development (BDD), Natural Language Processing

Whombat: An open‐source audio annotation tool for machine learning assisted bioacoustics

Abstract Automated analysis of bioacoustic recordings using machine learning (ML) methods has the potential to greatly scale biodiversity monitoring efforts. The use of ML for high‐stakes applications, such as conservation and scientific research, demands a data‐centric approach with a focus on selecting and utilizing carefully annotated and curated evaluation and training data that are relevant and representative. Creating annotated bioacoustic datasets presents a number of challenges, such as managing large collections of recordings with associated metadata, developing flexible annotation tools that can accommodate the diverse range of vocalization profiles of different organisms and addressing the scarcity of expert annotators. We present Whombat, a user‐friendly, browser‐based interface for managing audio recordings and annotation projects, with several visualization, exploration and annotation tools. It enables users to quickly annotate, review, and share annotations, as well as visualize and evaluate a set of machine learning predictions on a dataset. The tool facilitates an iterative workflow where user annotations and machine learning predictions feedback to enhance model performance and annotation quality. We demonstrate the flexibility of Whombat by showcasing two distinct use cases: (1) a project aimed at enhancing automated UK bat call identification at the Bat Conservation Trust (BCT), and (2) a collaborative effort among the USDA Forest Service and Oregon State University researchers exploring bioacoustic applications and extending automated avian classification models in the Pacific Northwest, USA. Whombat is a flexible tool that can effectively address the challenges of annotation for bioacoustic research. It can be used for individual and collaborative work, hosted on a shared server or accessed remotely, or run on a personal computer without the need for coding skills. The code is open‐source, and we provide a user guide.

Vesicle Picker: A tool for efficient identification of membrane protein complexes in vesicles

Electron cryomicroscopy (cryo-EM) has recently allowed determination of near-atomic resolution structures of membrane proteins and protein complexes embedded in lipid vesicles. However, particle selection from electron micrographs of these vesicles can be challenging due to the strong signal contributed from the lipid bilayer. This challenge often requires iterative and laborious particle selection workflows to generate a dataset of high-quality particle images for subsequent analysis. Here we present Vesicle Picker, an open-source program built on the Segment Anything model. Vesicle Picker enables automatic identification of vesicles in cryo-EM micrographs with high recall and precision. It then exhaustively selects all potential particle locations, either at the perimeter or uniformly over the surface of the projection of the vesicle. The program is designed to interface with cryoSPARC, which performs both upstream micrograph processing and downstream single particle image analysis. We demonstrate Vesicle Picker’s utility by determining a high-resolution map of the vacuolar-type ATPase from micrographs of native synaptic vesicles (SVs) and identifying an additional protein or protein complex in the SV membrane.

Utility of learning health systems in radiation oncology.

413 Background: Current health information systems lack a robust framework for longitudinal integration of internal experiences and external evidence into existing workflows. The result is labor intensive, error-prone and fragmented systems plagued with process gaps. Learning health systems (LHS) can be a potential solution to address these gaps. We created and implemented a novel LHS framework in radiation oncology (RO). We hypothesize that this framework can be leveraged to identify and implement opportunities for improvement using a patient-oriented endpoint of time from radiation simulation to treatment start (RSTS). Methods: An RO-LHS was developed through a collaboration between an academic, multi-facility radiation oncology department and an industry partner (Medlever). The end-to-end clinical workflow was embedded into the Medlever platform following an interdisciplinary, iterative analysis with representatives from key teams (clerical, finance and clinical). A novel nomenclature was created to label standardized, customizable templates, which choreograph logic-driven tasks that cover all sub-steps of RSTS. The primary endpoint of RSTS was compared pre- and post-implementation, stratified by key variables, such as facility, staff member, and radiation treatment modality. Results: The iterative workflow analysis identified >700 variables and decision points necessary for >200 cancer and benign conditions routinely managed in RO. >450 treatment protocols were templated.180 logic-driven tasks were created and linked to key parameters, resulting in a choregraphed precision workflow for each patient. Using the first iteration of the build, a total of 512 patients were managed during a 50-day period (03/01/2024-04/20/2024) and were compared to 2875 patients treated prior to implementation. Post-implementation, RSTS was shortened by 36.4% (p<0.001). We identified significant differences in RSTS by radiation modalities (protons vs all others), across facilities, and by providers (p<0.01 for all). Analysis of fractional domain of RSTS, 56% of the time was driven by physician-directed tasks, while 44% was comprised of physics and dosimetry-driven work. Physician-directed tasks had the greatest heterogeneity in time to completion. The biggest variation was noted for the contouring completion task. Significant differences were identified by provider (p<0.001) in nearly each step of the process, including steps not directly tied to physician’s work. Conclusions: Through an inter-disciplinary implementation of the first iteration of a LHS in our RO department, we have significantly shortened RSTS. The implementation and analysis has also enabled us to better understand underlying heterogeneities and identify further opportunities for optimization of RSTS. An LHS framework provides a generalizable solution that could be adapted in other RO clinics.

Exploring Synergies, Differences, and Impacts of Agile and DevOps on Software Development Efficiency

Agile and DevOps are now the preferred methods for satisfying the ever-changing demands for better software. Improvements in efficiency, adaptability, and collaboration are the aims of newly proposed solutions. It examines the impact of these factors on software development efficiency, focussing special attention to the ways in which they differ and complement one another. The focus of DevOps is continuous integration and delivery with operational automation, whereas Agile is on iterative improvement, consumer cooperation, and adaptation. Acquire an understanding of how these methods can be combined or utilised independently with the goal to achieve maximum performance in software tasks. One method that ranks the importance of factors including improvement velocity, quality, cooperation, and automation in relation to their impact on efficiency is the Multivocal Software Factor Prioritisation Development Approach (MSFPDA). By giving these considerations priority, this method integrates the most beneficial features of both methodologies. With the goal to maximise the stability, adaptability, automation, and scalability of both Agile and DevOps, MSFPDA employs comment looping structures, iterative workflows, and continuous monitoring. The simulation analysis is used by the granting studies to evaluate MSFPDA's performance in exceptional improvement circumstances. By identifying and prioritising critical components, MSFPDA can improve software program efficiency, according to this assessment. Blending Agile and DevOps presents a variety of issues, such as managing automation complexity, assuring non-stop delivering without sacrificing agility, and harmonising the team's tradition. This methodology for software enhancement has enormous ability, and the results of the simulations demonstrate how MSFPDA can be utilised in real-world scenarios, improving multiple processes.

Subcutaneous edema segmentation on abdominal CT using multi-class labels and iterative annotation.

Anasarca is a condition that results from organ dysfunctions, such as heart, kidney, or liver failure, characterized by the presence of edema throughout the body. The quantification of accumulated edema may have potential clinical benefits. This work focuses on accurately estimating the amount of edema non-invasively using abdominal CT scans, with minimal false positives. However, edema segmentation is challenging due to the complex appearance of edema and the lack of manually annotated volumes. We propose a weakly supervised approach for edema segmentation using initial edema labels from the current state-of-the-art method for edema segmentation (Intensity Prior), along with labels of surrounding tissues as anatomical priors. A multi-class 3D nnU-Net was employed as the segmentation network, and training was performed using an iterative annotation workflow. We evaluated segmentation accuracy on a test set of 25 patients with edema. The average Dice Similarity Coefficient of the proposed method was similar to Intensity Prior (61.5% vs. 61.7%; ). However, the proposed method reduced the average False Positive Rate significantly, from 1.8% to 1.1% ( ). Edema volumes computed using automated segmentation had a strong correlation with manual annotation ( ). Weakly supervised learning using 3D multi-class labels and iterative annotation is an efficient way to perform high-quality edema segmentation with minimal false positives. Automated edema segmentation can produce edema volume estimates that are highly correlated with manual annotation. The proposed approach is promising for clinical applications to monitor anasarca using estimated edema volumes.

Evaluating the thermal stability of an interior permanent magnet synchronous machine through iterative multi‐physics simulation

AbstractThis paper investigates the thermal operating capability of an interior permanent magnet synchronous machine. An iterative workflow is presented, combining electromagnetic modeling, control, power‐loss modeling, and thermal modeling to identify maximum thermal stable operating points. Special attention is given to the critical temperatures of winding and permanent magnets. A nonlinear reduced order model based on finite element method model was used to simulate the system, including an inverter model with space vector pulse width modulation in combination with field‐oriented control. Furthermore, an advanced iron core loss model and thermal lumped parameter model were employed. The presented approach allows for evaluating losses and their impact on steady‐state temperatures. The obtained results highlight the significant influence of space vector pulse width modulation on iron core losses and the importance of considering both advanced power‐loss models and adequate thermal models when analyzing the machine's thermal state. This research emphasizes the concept of a thermally stable envelope, providing a comprehensive understanding of the thermal boundaries under various operating conditions.

Developing new electrocatalysts for oxygen evolution reaction via high throughput experiments and artificial intelligence

The development of non-noble metal electrocatalysts for the Oxygen Evolution Reaction (OER) is advancing towards the use of multi-element materials. To reveal the complex correlations of multi-element OER electrocatalysts, we developed an iterative workflow combining high-throughput experiments and AI-generated content (AIGC) processes. An increased number of 909 (compared to 145 in previous literature) universal descriptors for inorganic materials science were constructed and used as Artificial Neural Network (ANN) input. A large number of statistical ensembles with each ANN individual ensemble having a reduced number of descriptors were integrated with a new Hierarchical Neural Network (HNN) algorithm. This algorithm addresses the longstanding challenge of balancing overwhelming descriptor numbers with insufficient datasets in traditional ANN approaches to materials science problems. As a result, the combination of AIGC and experimental validation significantly enhanced prediction accuracy, increase the R2 values from 0.7 to 0.98 for Tafel slopes.

An iterative workflow introduced to model complex heterogeneous reservoirs: an example from NEAG-2 Field, north Western Desert, Egypt

An iterative workflow introduced to model complex heterogeneous reservoirs: an example from NEAG-2 Field, north Western Desert, Egypt

Next generation risk assessment for occupational chemical safety – A real world example with sodium-2-hydroxyethane sulfonate

Next Generation Risk Assessment (NGRA) is an exposure-led approach to safety assessment that uses New Approach Methodologies (NAMs). Application of NGRA has been largely restricted to assessments of consumer use of cosmetics and is not currently implemented in occupational safety assessments, e.g. under EU REACH. By contrast, a large proportion of regulatory worker safety assessments are underpinned by toxicological studies using experimental animals. Consequently, occupational safety assessment represents an area that would benefit from increasing application of NGRA to safety decision making. Here, a workflow for conducting NGRA under an occupational safety context was developed, which is illustrated with a case study chemical; sodium 2-hydroxyethane sulphonate (sodium isethionate or SI). Exposures were estimated using a standard occupational exposure model following a comprehensive life cycle assessment of SI and considering factory-specific data. Outputs of this model were then used to estimate internal exposures using a Physiologically Based Kinetic (PBK) model, which was constructed with SI specific Absorption, Distribution, Metabolism and Excretion (ADME) data. PBK modelling indicated a worst-case plasma maximum concentration (Cmax) of 0.8 μM across the SI life cycle. SI bioactivity was assessed in a battery of NAMs relevant to systemic, reproductive, and developmental toxicity; a cell stress panel, high throughput transcriptomics in three cell lines (HepG2, HepaRG and MCF-7 cells), pharmacological profiling and specific assays relating to developmental toxicity (Reprotracker and devTOX quickPredict). Points of Departure (PoDs) for SI ranged from 104 to 5044 µM. Cmax values obtained from PBK modelling of occupational exposures to SI were compared with PoDs from the bioactivity assays to derive Bioactivity Exposure Ratios (BERs) which demonstrated the safety for workers exposed to SI under current levels of factory specific risk management. In summary, the tiered and iterative workflow developed here represents an opportunity for integrating non animal approaches for a large subset of substances for which systemic worker safety assessment is required. Such an approach could be followed to ensure that animal testing is only conducted as a “last resort” e.g. under EU REACH.

Machine-Learning-Assisted Discovery of Mechanosynthesized Lead-Free Metal Halide Perovskites for the Oxidative Photocatalytic Cleavage of Alkenes.

Lead-free metal halide perovskites can potentially be air- and water-stable photocatalysts for organic synthesis, but there are limited studies on them for this application. Separately, machine learning (ML), a critical subfield of artificial intelligence, has played a pivotal role in identifying correlations and formulating predictions based on extensive datasets. Herein, an iterative workflow by incorporating high-throughput experimental data with ML to discover new lead-free metal halide perovskite photocatalysts for the aerobic oxidation of styrene is described. Through six rounds of ML optimization guided by SHapley Additive exPlanations (SHAP) analysis, BA2CsAg0.95Na0.05BiBr7 as a photocatalyst that afforded an 80% yield of benzoic acid under the standard conditions is identified, which is a 13-fold improvement compared to the 6% with when using Cs2AgBiBr6 as the initial photocatalyst benchmark that is started. BA2CsAg0.95Na0.05BiBr7 can tolerate various functional groups with 22 styrene derivatives, highlighting the generality of the photocatalytic properties demonstrated. Radical scavenging studies and density functional theory calculations revealed that the formation of the reactive oxygen species superoxide and singlet oxygen in the presence of BA2CsAg0.95Na0.05BiBr7 are critical for photocatalysis.

Searching new cocrystal structures of CL-20 and HMX via evolutionary algorithm and machine learning potential

In this work, we report the discovery of energy cocrystals using an efficient iterative workflow combining an evolutionary algorithm and a machine learning potential (MLP). The compound 2,4,6,8,10,12-Hexanitro-2,4,6,8,10,12-hexaazaisowurtzitane (CL-20) has attracted significant attention owing to its higher energy density than traditional energetic materials. However, the higher sensitivity has limited its applications. An important way to reduce its sensitivity involves cocrystal engineering with traditional explosives. Many cocrystal structures are expected to be composed of these two components. We developed an efficient iterative workflow to explore the phase space of CL-20 and 1,3,5,7-tetranitro-1,3,5,7-tetraazacyclooctane (HMX) cocrystals using an evolutionary algorithm and an MLP. The algorithm was based on the Universal Structure Predictor: Evolutionary Xtallography (USPEX) software, and the MLP was the reactive force field with neural networks (ReaxFF-nn ) model. A set of high-density cocrystal structures was produced through this workflow; these structures were further checked via first-principles geometry optimizations. After careful screening, we identified several high-density cocrystal structures with densities of up to 1.937 g/cm3 and HMX: CL-20 ratios of 1:1 and 1:2. The influence of hydrogen bonds on the formation of high-density cocrystals was also discussed, and a roughly linear relationship was found between energy and density.

Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach

PurposeRadiological reporting is transitioning to quantitative analysis, requiring large-scale multi-center validation of biomarkers. A major prerequisite and bottleneck for this task is the voxelwise annotation of image data, which is time-consuming for large cohorts. In this study, we propose an iterative training workflow to support and facilitate such segmentation tasks, specifically for high-resolution thoracic CT data. MethodsOur study included 132 thoracic CT scans from clinical practice, annotated by 13 radiologists. In three iterative training experiments, we aimed to improve and accelerate segmentation of the heart and mediastinum. Each experiment started with manual segmentation of 5–25 CT scans, which served as training data for a nnU-Net. Further iterations incorporated AI pre-segmentation and human correction to improve accuracy, accelerate the annotation process, and reduce human involvement over time. ResultsResults showed consistent improvement in AI model quality with each iteration. Resampled datasets improved the Dice similarity coefficients for both the heart (DCS 0.91 [0.88; 0.92]) and the mediastinum (DCS 0.95 [0.94; 0.95]). Our AI models reduced human interaction time by 50 % for heart and 70 % for mediastinum segmentation in the most potent iteration. A model trained on only five datasets achieved satisfactory results (DCS > 0.90). ConclusionsThe iterative training workflow provides an efficient method for training AI-based segmentation models in multi-center studies, improving accuracy over time and simultaneously reducing human intervention. Future work will explore the use of fewer initial datasets and additional pre-processing methods to enhance model quality.

Integrated Design and Fabrication of Pneumatic Soft Robot Actuators in a Single Casting Step.

Bio-inspired soft robots have already shown the ability to handle uncertainty and adapt to unstructured environments. However, their availability is partially restricted by time-consuming, costly, and highly supervised design-fabrication processes, often based on resource-intensive iterative workflows. Here, we propose an integrated approach targeting the design and fabrication of pneumatic soft actuators in a single casting step. Molds and sacrificial water-soluble hollow cores are printed using fused filament fabrication. A heated water circuit accelerates the dissolution of the core's material and guarantees its complete removal from the actuator walls, while the actuator's mechanical operability is defined through finite element analysis. This enables the fabrication of actuators with non-uniform cross-sections under minimal supervision, thereby reducing the number of iterations necessary during the design and fabrication processes. Three actuators capable of bending and linear motion were designed, fabricated, integrated, and demonstrated as 3 different bio-inspired soft robots, an earthworm-inspired robot, a 4-legged robot, and a robotic gripper. We demonstrate the availability, versatility, and effectiveness of the proposed methods, contributing to accelerating the design and fabrication of soft robots. This study represents a step toward increasing the accessibility of soft robots to people at a lower cost.

Development of multiple heartcutting two-dimensional liquid chromatography with ion-pairing reversed-phase separations in both dimensions for analysis of impurities in therapeutic oligonucleotides

Oligonucleotides constitute an emerging and highly complex bioanalytical challenge and it is becoming increasingly clear that 1D methodologies are unable to fully resolve all possible impurities present in these samples. 2D-LC therefore constitutes a perfect solution wherein critical pairs can be sampled from a steep gradient 1D and separated in a shallower 2D gradient. Herein, we provide a facile 2D-LC method development approach to quickly generate high selectivity gradients utilizing ion pairing reverse phase (IPRP-IPRP). In particular we demonstrate how to iteratively generate a 12 % gradient from two training runs and then to utilize that data to predict retentions of analytes with a 2 % gradient with retention prediction errors as low as 3 and 11 %, respectively. This iterative method development workflow was applied to impurity profiling down to 1:1000 for the full-length product and phosphorothioate modified impurities. Additionally, we demonstrated the elucidation of critical pairs in complex crude pharmaceutical oligonucleotide samples by applying tailored high selectivity gradients in the second dimension. It was found that the iterative retention modeling approach allows fast and facile 2D-LC method development for complex oligonucleotide separations.

Deep learning workflow for the inverse design of molecules with specific optoelectronic properties

The inverse design of novel molecules with a desirable optoelectronic property requires consideration of the vast chemical spaces associated with varying chemical composition and molecular size. First principles-based property predictions have become increasingly helpful for assisting the selection of promising candidate chemical species for subsequent experimental validation. However, a brute-force computational screening of the entire chemical space is decidedly impossible. To alleviate the computational burden and accelerate rational molecular design, we here present an iterative deep learning workflow that combines (i) the density-functional tight-binding method for dynamic generation of property training data, (ii) a graph convolutional neural network surrogate model for rapid and reliable predictions of chemical and physical properties, and (iii) a masked language model. As proof of principle, we employ our workflow in the iterative generation of novel molecules with a target energy gap between the highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO).

Reshaping concrete

Less Economically Developed Countries (LEDCs) struggle to meet the demand for affordable housing in their growing cities. There are several reasons for this, but a major constraint is the high cost of construction materials. In LEDCs, material costs can constitute 60 to 80 percent of the total cost of residential construction. Nonetheless, their construction mimics the materially inefficient practices of the More Economically Developed Countries (MEDCs), which were developed to reduce labor over material costs. As a result, prismatic beams and flat slabs are often used despite their structural inefficiency. The mounting use of steel-reinforced concrete structures in LEDC cities also raises concern for the environmental costs of construction; construction accounts for 20-30 percent of LEDC carbon emissions. This research addresses these challenges with a flexible and accessible methodology for the design and analysis of materially efficient concrete elements that may reduce the economic and environmental costs of urban construction. Designed for the constraints of LEDCs, structural elements are optimized to reduce the embodied carbon associated with the concrete and reinforcing steel while resisting the required loads of a standard building structure. The optimization method includes a novel approach to 3D-shape parameterization, as well as a decoupled analytical engineering analysis method that accounts for the key failure modes and constraints of reinforced concrete design. This method is then built into an open-source toolkit, combined with machine learning for real-time analysis and visualization, and tested using lab- and full-scale prototypes. The goal of this research is to present several generalizable methods that are applicable and accessible to LEDC building designers. These methods can enable the design of concrete elements for multiple performance criteria such as structural behavior, acoustic transmission, and thermal mass. They can also enable an accessible design practice through machine learning, real-time iterative workflows, and visualization tools that include the end-user in the architectural design process. This paper provides a high-level overview of ongoing research that explores how materially efficient design methods might enable sustainable development through low-cost, low-carbon concrete structural systems for affordable housing in LEDCs.

Estimating Free Energy Barriers for Heterogeneous Catalytic Reactions with Machine Learning Potentials and Umbrella Integration.

Predicting the rate constants of elementary reaction steps is key for the computational modeling of catalytic processes. Within transition state theory (TST), this requires an accurate estimation of the corresponding free energy barriers. While sophisticated methods for estimating free energy differences exist, these typically require extensive (biased) molecular dynamics simulations that are computationally prohibitive with the first-principles electronic structure methods that are typically used in catalysis research. In this contribution, we show that machine-learning (ML) interatomic potentials can be trained in an automated iterative workflow to perform such free energy calculations at a much reduced computational cost as compared to a direct density functional theory (DFT) based evaluation. For the decomposition of CHO on Rh(111), we find that thermal effects are substantial and lead to a decrease in the free energy barrier, which can be vanishingly small, depending on the DFT functional used. This is in stark contrast to previously reported estimates based on a harmonic TST approximation, which predicted an increase in the barrier at elevated temperatures. Since CHO is the reactant of the putative rate limiting reaction step in syngas conversion on Rh(111) and essential for the selectivity toward oxygenates containing multiple carbon atoms (C2+ oxygenates), our results call into question the reported mechanism established by microkinetic models.

Virtual Gas Turbines: A novel flow network solver formulation for the automated design-analysis of secondary air system

AbstractThe complex and iterative workflow for designing the secondary air system (SAS) of a gas turbine engine still largely depends on human expertise and hence requires long lead times and incurs high design time-cost. This paper proposes an automated methodology to generate the whole-engine SAS flow network model from the engine geometry model and presents a convenient and inter-operable framework of the secondary air system modeller. The SAS modeller transforms the SAS cavities and flow paths into a 1D flow network model composed of nodes and links. The novel, object-oriented pre-processor embedded in the SAS modeller automatically assembles the conservation equations for all flow nodes and the loss correlations for all links. The twin-level, hierarchical SAS solver then solves the conservation equations of mass, momentum and energy supplemented with the correlations in the loss model library. The modelling swiftness, mathematical robustness and numerical stability of the present methodology are demonstrated through the results obtained from IP compressor rotor drum flow network model.

New Iterative Resistivity Modeling Workflow Reduces Uncertainty in the Assessment of Water Saturation in Deeply Invaded Reservoirs

A new iterative modeling workflow has been designed to reduce the uncertainty of water saturation (Sw) calculations in the tight Barik sandstone in the Sultanate of Oman. Results from this case study indicate that Sw can be overestimated by up to 20 s.u. if the as-acquired deep resistivity is used in volumetric calculations. Overbalanced drilling causes deep invasion of water-based mud (WBM) filtrate into porous and permeable rocks, leading to the radial displacement of in-situ saturating fluids away from the wellbore. In low-porosity reservoirs drilled with WBM, the inability of the filtration process to quickly build impermeable mudcake translates into long radial transition zones. Under certain reservoir and drilling conditions, deep resistivity logs cannot reliably measure true formation resistivity and are, therefore, unable to provide an accurate assessment of hydrocarbon saturation. The effect of mud-filtrate invasion on resistivity logs has been extensively documented. Processing techniques use resistivity inversion and tool-specific forward modeling to provide uninvaded formation resistivity logs, which are much better suited for in-place resource volume assessment. However, sensitivity analysis shows that the accuracy of invasion-corrected logs dramatically decreases as the depth of invasion increases, whereby the inversion process needs to be further constrained. The new workflow is designed to reduce the non-uniqueness of true formation resistivity models so that they honor multiple and independent petrophysical data. The inversion routine utilizes a Bayesian algorithm coupled with Markov-Chain Monte Carlo (MCMC) sampling. Inversion results are iteratively modified based on two rock property models : one derived from rock-core data (helium expansion porosity and Dean-Stark saturations) and the other using an equivalent log interpretation of thick reservoir intervals from oil-based mud (OBM) wells. Simulated borehole resistivity is compared to field logs after each validation loop against rock property models. The new inversion-based workflow is extensively tested in the unconventional tight Barik Formation across water-free hydrocarbon and perched water intervals, and inversion-derived Sw models are independently validated by capillary-pressure-derived saturation-height models and fluid inflow rate from production logs.