Data-driven Workflows Research Articles

Pharmacological profiles of neglected tropical disease drugs

According to the World health Organization there are a group of 20 diverse infectious Neglected Tropical Disease (NTD) conditions that primarily affect populations in low-income and developing regions. Despite the limited attention and funding compared to other health concerns, significant efforts to develop drugs for treating and controlling NTDs have been made. However, there is room for developing NTD drugs with improved safety, efficacy and ecotoxicological profiles. In order to facilitate this, we have adapted our existing validated data-driven workflows for understanding disease comorbidity to systematically evaluate the approved drugs that target the major World Health Organization defined NTDs. The foundation for this work comprised assembling the physicochemical, biological and clinical properties of each NTD drug and identifying patterns that reveal the underlying cause of their efficacy and side-effect profiles. Subsequently, computational methods were employed to identify analogs with potentially improved profiles and validated in a case study focusing on the teratogenic antileishmanial drug miltefosine. The wider impact of NTD drugs with regards to a One Health cross-disciplinary perspective at the human-animal-environment interface are also discussed.

PrivData Network: A Privacy-Preserving On-Chain Data Factory and Trading Market

Privacy concerns often raise when sensitive data are collected, traded, and processed. The data owner typically loses her ultimate control of the data after data-outsourcing. In this work, we present the PrivData Network – a community-controlled privacy-preserving data factory and trading market. It can be viewed as a standalone data ecosystem that enables privacy-preserving data-driven workflows in a controlled environment for orchestrating and automating data movement and data transformation. In particular, we design a data encapsulation mechanism with privacy assurance, which can guarantee data privacy, usage policy compliance and metadata validity. We also design a privacy policy language and utilize a static analysis library that transfers the program to the defined policy language. To ensure the correctness of data processing, we propose a publicly verifiable secure multiparty computation protocol for mixed circuits, which guarantees the output correctness even if all parties are corrupted. Its online efficiency is comparable to conventional semi-honest secret-sharing-based MPC schemes. Finally, we implemented a prototype of our system in C++ and benchmark it on various tasks, such as biometric matching, logistic regression, and decision trees, etc.

Nonlinear dimensionality reduction then and now: AIMs for dissipative PDEs in the ML era

This study presents a collection of purely data-driven workflows for constructing reduced-order models (ROMs) for distributed dynamical systems. The ROMs we focus on, are data-assisted models inspired by, and templated upon, the theory of Approximate Inertial Manifolds (AIMs); the particular motivation is the so-called post-processing Galerkin method of Garcia-Archilla, Novo and Titi. Its applicability can be extended: the need for accurate truncated Galerkin projections and for deriving closed-formed corrections can be circumvented using machine learning tools. When the right latent variables are not a priori known, we illustrate how autoencoders as well as Diffusion Maps (a manifold learning scheme) can be used to discover good sets of latent variables and test their explainability. The proposed methodology can express the ROMs in terms of (a) theoretical (Fourier coefficients), (b) linear data-driven (POD modes) and/or (c) nonlinear data-driven (Diffusion Maps) coordinates. Both Black-Box and (theoretically-informed and data-corrected) Gray-Box models are described; the necessity for the latter arises when truncated Galerkin projections are so inaccurate as to not be amenable to post-processing. We use the Chafee-Infante reaction-diffusion and the Kuramoto-Sivashinsky dissipative partial differential equations to illustrate and successfully test the overall framework.

Process Mining Organization (PMO) Modeling and Healthcare Processes

Process mining organizatioQn (PMO) is an innovative approach based on artificial intelligence (AI) decision making suitable for designing healthcare processes for human resource (HR) organizations. The proposed work suggests some examples of PMO-based Business Process Modeling and Notation (BPMN) workflows by highlighting the advances in HR management and in risk decrease according to healthcare scenarios. Specifically proposed are different examples of “TO BE” process pipelines related to an upgrade of the organizational healthcare framework, including digital technologies and telemedicine. Important elements are provided to formulate HR management guidelines supporting PMO design. The proposed BPMN workflows are the result of different consulting actions in healthcare institutions based on the preliminary mapping of “AS IS” processes highlighting bottlenecks and needs in HR organization. A pilot experimental dataset is used to show how it is possible to apply AI algorithms providing organization corrective actions. The paper is mainly focused on discussing some validated BPMN models managing HR in the healthcare sector. The methodology is based on the application of the BPMN approach to deploy human resource organizational processes. The results show AI data-driven workflows adopted in healthcare and examples of AI fuzzy c-means outputs addressing organizational actions.

ESnet/JLab FPGA Accelerated Transport

To increase the science rate for high data rates/volumes, Thomas Jefferson National Accelerator Facility (JLab) has partnered with Energy Sciences Network (ESnet) to define an edge to compute cluster traffic shaping / steering transport capability featuring data event aware network shaping and forwarding. The keystone of this ESnet+JLab FPGA Accelerated Transport (EJFAT) is the joint development of a dynamic compute work Load Balancer (LB) of UDP streamed data. The LB is a suite consisting of a Field Programmable Gate Array (FPGA) executing the dynamically configurable, low fixed latency LB <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data plane</i> featuring real-time packet redirection and high throughput, and a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">control plane</i> running on the FPGA host computer that monitors network and compute farm telemetry in order to make dynamic load-balancing decisions for destination compute host redirection / load balancing. The LB provides for three-tier horizontal scaling across LB suites, cluster compute hosts, and CPUs within a host. The LB effectively provides seamless integration of edge / cluster computing to support direct experimental data processing for immediate use by JLab science programs and others such as the Electron-Ion Collider (EIC) as well as data centers of the future requiring high throughput and low latency for both time-critical (e.g., data acquisition systems) and data-driven (data center) workflows.

Versatile software-defined HPC and cloud clusters on Alps supercomputer for diverse workflows

Supercomputers have been driving innovations for performance and scaling benefiting several scientific applications for the past few decades. Yet their ecosystems remain virtually unchanged when it comes to integrating distributed data-driven workflows, primarily due to rather rigid access methods and restricted configuration management options. X-as-a-Service model of cloud has introduced, among other features, a developer-centric DevOps approach empowering developers of infrastructure, platform to software artefacts, which, unfortunately contemporary supercomputers still lack. We introduce vClusters (versatile software-defined clusters), which is based on Infrastructure-as-code (IaC) technology. vClusters approach is a unique fusion of HPC and cloud technologies resulting in a software-defined, multi-tenant cluster on a supercomputing ecosystem, that, together with software-defined storage, enable DevOps for complex, data-driven workflows like grid middleware, alongside a classic HPC platform. IaC has been a commonplace in cloud computing, however, it lacked adoption within multi-Petascale ecosystems due to concerns related to performance and interoperability with classic HPC data centres’ ecosystems. We present an overview of the Swiss National Supercomputing Centre’s flagship Alps ecosystem as an implementation target for vClusters for HPC and data-driven workflows. Alps is based on the Cray-HPE Shasta EX supercomputing platform that includes an IaC compliant, microservices architecture (MSA) management system, which we leverage for demonstrating vClusters usage for our diverse operational workflows. We provide implementation details of two operational vClusters platforms: a classic HPC platform that is used predominantly by hundreds of users running thousands of large-scale numerical simulations batch jobs; and a widely used, data-intensive, Grid computing middleware platform used for CERN Worldwide LHC Computing Grid (WLCG) operations. The resulting solution showcases reuse and reduction of common configuration recipes across vCluster implementations, minimising operational change management overheads while introducing flexibility for managing artefacts for DevOps required by diverse workflows.

Impact of Established and Emerging Software Tools on the Metabolite Identification Landscape.

Scientists’ ability to detect drug-related metabolites at trace concentrations has improved over recent decades. High-resolution instruments enable collection of large amounts of raw experimental data. In fact, the quantity of data produced has become a challenge due to effort required to convert raw data into useful insights. Various cheminformatics tools have been developed to address these metabolite identification challenges. This article describes the current state of these tools. They can be split into two categories: Pre-experimental metabolite generation and post-experimental data analysis. The former can be subdivided into rule-based, machine learning-based, and docking-based approaches. Post-experimental tools help scientists automatically perform chromatographic deconvolution of LC/MS data and identify metabolites. They can use pre-experimental predictions to improve metabolite identification, but they are not limited to these predictions: unexpected metabolites can also be discovered through fractional mass filtering. In addition to a review of available software tools, we present a description of pre-experimental and post-experimental metabolite structure generation using MetaSense. These software tools improve upon manual techniques, increasing scientist productivity and enabling efficient handling of large datasets. However, the trend of increasingly large datasets and highly data-driven workflows requires a more sophisticated informatics transition in metabolite identification labs. Experimental work has traditionally been separated from the information technology tools that handle our data. We argue that these IT tools can help scientists draw connections via data visualizations and preserve and share results via searchable centralized databases. In addition, data marshalling and homogenization techniques enable future data mining and machine learning.

Abstract 2349: SAP30, a novel drug response specific transcription factor in high-risk neuroblastoma

Abstract Neuroblastoma is the most devastating extracranial solid malignancy in children. Despite an intense treatment regimen, the prognosis for high-risk neuroblastoma patients remains poor, with less than 40% survival. So far, MYCN status/amplification is considered the most prognostic factor but corresponds to only 25% of neuroblastoma patients. Therefore, it is essential to identify a better prognosis and prediction marker of therapy response in neuroblastoma patients. The identification of master regulators with good prognostic and drug response abilities are not successful due to the complexity and lack of data-driven bioinformatic workflows. We applied robust bioinformatic data mining tools such as Weighted Gene Co-expression Network Analysis, cisTarget, and Single-Cell rEgulatory Network Inference and Clustering on three neuroblastoma patient datasets (n=1252). We found Sin3A Associated Protein 30 (Sap30), a driver transcription factor positively associated with high-risk, progression, stage 4, and poor survival in high-risk neuroblastoma patient cohorts. Tumors of high-risk neuroblastoma patients and relapse-specific patient-derived xenografts showed higher Sap30 levels. The Genomics of Drug Sensitivity in Cancer, The Cancer Cell Line Encyclopedia, and CRISPR-Cas9 screens indicated that Sap30 essentiality is associated with Cisplatin resistance and further showed higher levels in Cisplatin resistant patient-derived xenograft tumor cell lines. The silencing of Sap30 in cells reduced cell growth, induced cell death, mitochondrial membrane potential loss in vitro, and reduced tumorigenicity in vivo. Altogether, these results indicate that Sap30 is a novel prognostic and Cisplatin resistant marker and thus a potential drug target in high-risk neuroblastoma patients. Citation Format: Philip Prathipati, Anup S. Pathania, Nagendra K. Chaturvedi, Subash C. Gupta, Siddappa N. Byrareddy, Don W. Coulter, Kishore B. Challagundla. SAP30, a novel drug response specific transcription factor in high-risk neuroblastoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 2349.

S-ProvFlow. Storing and Exploring Lineage Data as a Service

Abstract We present a set of configurable Web service and interactive tools, s-ProvFlow, for managing and exploiting records tracking data lineage during workflow runs. It facilitates detailed analysis of single executions. It helps users manage complex tasks by exposing the relationships between data, people, equipment and workflow runs intended to combine productively. Its logical model extends the PROV standard to precisely record parallel data-streaming applications. Its metadata handling encourages users to capture the application context by specifying how application attributes, often using standard vocabularies, should be added. These metadata records immediately help productivity as the interactive tools support their use in selection and bulk operations. Users rapidly appreciate the power of the encoded semantics as they reap the benefits. This improves the quality of provenance for users and management. Which in turn facilitates analysis of collections of runs, enabling users to manage results and validate procedures. It fosters reuse of data and methods and facilitates diagnostic investigations and optimisations. We present S-ProvFlow's use by scientists, research engineers and managers as part of the DARE hyper-platform as they create, validate and use their data-driven scientific workflows.

MiR-15a and miR-15b modulate natural killer and CD8+T-cell activation and anti-tumor immune response by targeting PD-L1 in neuroblastoma

Neuroblastoma (NB) is an enigmatic and deadliest pediatric cancer to treat. The major obstacles to the effective immunotherapy treatments in NB are defective immune cells and the immune evasion tactics deployed by the tumor cells and the stromal microenvironment. Nervous system development during embryonic and pediatric stages is critically mediated by non-coding RNAs such as micro RNAs (miR). Hence, we explored the role of miRs in anti-tumor immune response via a range of data-driven workflows and in vitro & in vivo experiments. Using the TARGET, NB patient dataset (n=249), we applied the robust bioinformatic workflows incorporating differential expression, co-expression, survival, heatmaps, and box plots. We initially demonstrated the role of miR-15a-5p (miR-15a) and miR-15b-5p (miR-15b) as tumor suppressors, followed by their negative association with stromal cell percentages and a statistically significant negative regulation of T and natural killer (NK) cell signature genes, especially CD274 (PD-L1) in stromal-low patient subsets. The NB phase-specific expression of the miR-15a/miR-15b-PD-L1 axis was further corroborated using the PDX (n=24) dataset. We demonstrated miR-15a/miR-15b mediated degradation of PD-L1 mRNA through its interaction with the 3'-untranslated region and the RNA-induced silencing complex using sequence-specific luciferase activity and Ago2 RNA immunoprecipitation assays. In addition, we established miR-15a/miR-15b induced CD8+T and NK cell activation and cytotoxicity against NB in vitro. Moreover, injection of murine cells expressing miR-15a reduced tumor size, tumor vasculature and enhanced the activation and infiltration of CD8+T and NK cells into the tumors in vivo. We further established that blocking the surface PD-L1 using an anti-PD-L1 antibody rescued miR-15a/miR-15b induced CD8+T and NK cell-mediated anti-tumor responses. These findings demonstrate that miR-15a and miR-15b induce an anti-tumor immune response by targeting PD-L1 in NB.

BIM and Automation in Complex Building Assessment

When using Building Information Modeling (BIM) for complex building design, optimizing the building quality in a design phase becomes an important part of integrated and advanced building design. The use of data from an information model in the design phase allows efficient assessment of different design strategies and structural variants and a higher quality of the final design. This paper aims to analyze and verify possible BIM data-driven workflows for Complex Building Quality Assessment (CBQA) and a suitable BIM data structure set up for automatic assessment and evaluation. For an efficient automation process in complex quality building assessment in the design phase, it is necessary first to understand the data structure of the Industry Foundation Classes (IFC), which is widely accepted and used for buildings, and second to understand the data structure of the assessment methodology used for the assessment. This article describes possible data workflows for an automatic assessment based on the experience gained on a case study of the real pilot project of a residential building, where the complex building quality was tested using SBToolCZ, the Czech national assessment method. This article presents the experience and recommendations for setting up the data model of a building for automatic assessment.

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis.

The design of molecular catalysts typically involves reconciling multiple conflicting property requirements, largely relying on human intuition and local structural searches. However, the vast number of potential catalysts requires pruning of the candidate space by efficient property prediction with quantitative structure-property relationships. Data-driven workflows embedded in a library of potential catalysts can be used to build predictive models for catalyst performance and serve as a blueprint for novel catalyst designs. Herein we introduce kraken, a discovery platform covering monodentate organophosphorus(III) ligands providing comprehensive physicochemical descriptors based on representative conformer ensembles. Using quantum-mechanical methods, we calculated descriptors for 1558 ligands, including commercially available examples, and trained machine learning models to predict properties of over 300000 new ligands. We demonstrate the application of kraken to systematically explore the property space of organophosphorus ligands and how existing data sets in catalysis can be used to accelerate ligand selection during reaction optimization.

An Adaptation of the Spiral Model for the Integration of Hypothesis- and Data-Driven Workflows

An Adaptation of the Spiral Model for the Integration of Hypothesis- and Data-Driven Workflows

A Data-Driven Approach to the Development and Understanding of Chiroptical Sensors for Alcohols with Remote γ-Stereocenters.

Dynamic covalent chemistry-based sensors have recently emerged as powerful tools to rapidly determine the enantiomeric excess of organic small molecules. While a bevy of sensors have been developed, those for flexible molecules with stereocenters remote to the functional group that binds the chiroptical sensor remain scarce. In this study, we develop an iterative, data-driven workflow to design and analyze a chiroptical sensor capable of assessing challenging acyclic γ-stereogenic alcohols. Following sensor optimization, the mechanism of sensing was probed with a combination of computational parametrization of the sensor molecules, statistical modeling, and high-level density functional theory (DFT) calculations. These were used to elucidate the mechanism of stereochemical recognition and revealed that competing attractive noncovalent interactions (NCIs) determine the overall performance of the sensor. It is anticipated that the data-driven workflows developed herein will be generally applicable to the development and understanding of dynamic covalent and supramolecular sensors.

Technology Focus: Reservoir Simulation (July 2021)

In reviewing the long list of papers this year, it has become apparent to me that the hot topic in reservoir simulation these days is the application of data analytics or machine learning to numerical simulation and with it quite often the promise of data-driven work flows—code for needing to think about the physics less. Data-driven work flows have their place, especially when we have a lot of data and the system is very complex. I’m thinking shales especially, but seeing it being applied to more conventional reservoirs gave me a moment of pause. I can’t help but think that, in terms of the hype cycle as related to the application of machine learning to numerical simulation, we may be approaching the peak of inflated expectations. I say “approaching,” because many companies appear to be dipping their toes in the water, perhaps because they think they should, but few are truly committing to it. Many vocal champions of the approach exist, but most decision-makers just don’t understand it yet. If we cannot explain how something works simply, then thoughtful leaders will tend not to trust it. Whether it be numerical-simulation findings or self-organizing neural networks, the need will always exist for a deep understanding and clarity of explanation of both the discipline and method used. To decision-makers, it will be an attractive concept, but they will generally ask to validate against more traditional methods. I look forward to a future when we are through the trough of disillusionment and start climbing the slope of enlightenment to a new level of productivity. I suspect, though, that it will take at least another 5 years, as our current crop of knowledgeable evangelists become decision-makers themselves and can put in place work flows and teams to leverage the approach appropriately for their problems, intelligently leveraging their years of hard-won experience. I will lay a wager with you, though, that when that time comes, those new ways of working more efficiently will rely just as much if not more upon a deep understanding of reservoir engineering as our current methods. I hope you enjoy these papers, which include examples of both the new approach as well as tried-and-true approaches. Recommended additional reading at OnePetro: www.onepetro.org. SPE 202436 - Fast Modeling of Gas Reservoirs Using Proper Orthogonal Decomposition/Radial Basis Function (POD/RBF) Nonintrusive Reduced-Order Modeling by Jemimah-Sandra Samuel, Imperial College London, et al. IPTC 21417 - A New Methodology for Calculating Wellbore Shut-In Pressure in Numerical Reservoir Simulations by Babatope Kayode, Saudi Aramco, et al. SPE 201658 - Mechanistic Model Validation of Decline Curve Analysis for Unconventional Reservoirs by Mikhail Gorditsa, Texas A&amp;M University, et al.

GPU-Enabled Serverless Workflows for Efficient Multimedia Processing

Serverless computing has introduced scalable event-driven processing in Cloud infrastructures. However, it is not trivial for multimedia processing to benefit from the elastic capabilities featured by serverless applications. To this aim, this paper introduces the evolution of a framework to support the execution of customized runtime environments in AWS Lambda in order to accommodate workloads that do not satisfy its strict computational requirements: increased execution times and the ability to use GPU-based resources. This has been achieved through the integration of AWS Batch, a managed service to deploy virtual elastic clusters for the execution of containerized jobs. In addition, a Functions Definition Language (FDL) is introduced for the description of data-driven workflows of functions. These workflows can simultaneously leverage both AWS Lambda for the highly-scalable execution of short jobs and AWS Batch, for the execution of compute-intensive jobs that can profit from GPU-based computing. To assess the developed open-source framework, we executed a case study for efficient serverless video processing. The workflow automatically generates subtitles based on the audio and applies GPU-based object recognition to the video frames, thus simultaneously harnessing different computing services. This allows for the creation of cost-effective highly-parallel scale-to-zero serverless workflows in AWS.

Potential of I/O Aware Workflows in Climate and Weather

The efficient, convenient, and robust execution of data-driven workflows and enhanced data management are essential for productivity in scientific computing. In HPC, the concerns of storage and computing are traditionally separated and optimised independently from each other and the needs of the end-to-end user. However, in complex workflows, this is becoming problematic. These problems are particularly acute in climate and weather workflows, which as well as becoming increasingly complex and exploiting deep storage hierarchies, can involve multiple data centres. The key contributions of this paper are: 1) A sketch of a vision for an integrated data-driven approach, with a discussion of the associated challenges and implications, and 2) An architecture and roadmap consistent with this vision that would allow a seamless integration into current climate and weather workflows as it utilises versions of existing tools (ESDM, Cylc, XIOS, and DDN’s IME). The vision proposed here is built on the belief that workflows composed of data, computing, and communication-intensive tasks should drive interfaces and hardware configurations to better support the programming models. When delivered, this work will increase the opportunity for smarter scheduling of computing by considering storage in heterogeneous storage systems. We illustrate the performance-impact on an example workload using a model built on measured performance data using ESDM at DKRZ.

Constrained clustering approaches to identify hydraulic flow units in petroleum reservoirs

Hydraulic flow units (HFUs) are recognized as volumetric regions that favor the flow of reservoir fluids. Their determination is made possible through correlations between data that are transferred from miscroscale to reservoir scale by upscaling. However, the strong dependence on microscale parameters inherited by commonplace analytical methods based on flow indicators is still less tractable to achieve models having uniform continuity of HFUs at reservoir scale. This paper is intended to propose a class of partitioning algorithms to deal with the problem of identifying hydraulic flow units in petroleum reservoirs. As a result, a novel viewpoint inspired on constrained clusterwise linear regression is presented to describe the identification problem. We have studied the micro-to-macroscale correspondence through a mathematical isomorphism that maps the sample domain onto the reservoir domain by using the so called flow zone indicator (FZI) as underlying parameter. Each HFU is theoretically identified by a partition of FZI points that must lie on a straight line of unitary slope in a log–log plot of two quantities: porosity and reservoir quality index (RQI). By setting up constrained clustering approaches with different must-link hard constraints, we have found multiple HFUs directly from the dataset without resorting to usual conversion formulae. Pros and cons of each approach are discussed from analyses performed over the UNISIM-I-D dataset (a reservoir model for the Namorado oilfield, Campos Basin, Brazil), as with their feasibility to devise new data-driven workflows turned to reservoir modeling and characterization, especially at the interest of exploration and production oil industry upstream. Besides, a short overall comparison by taking a correlative flow zone indicator (namely, FZI*) as underlying parameter is appended to the text. We point out that an existent tradeoff between analytical and physical requirements is a limiting factor to properly identify hydraulic flow units at reservoir scale regardless the flow indicator. In particular, it turns out that algorithms that find highly correlated partitions indicate HFUs that lack of uniform continuity and are less physically meaningful. Oppositely, algorithms that produce less correlated partitions determine HFUs with satisfactory local continuity and compactness, being more physically acceptable. Additionally, we show that a inter-clustering process is recommended when selecting data points associated to representative volumes and local spots characterizing HFUs.

Integration of expert and data-driven workflows to manage reservoir and well life cycle in Arctic conditions using innovative SICLO methodology

SICLO (Source of data and information; Input data; Calculation/Analytic; Logic Analysis; Output/Value Delivery) methodology is an innovative concept for smart diagnostic, reservoir/well performance optimization and estimation of remaining reserves based on the integration of Petroleum Data Management System (PDMS) and expert rules. Implementation of SICLO methodology provides the best strategy on how to produce remaining reserves most profitably. PDMS is the foundation of SICLO methodology and provides structured and verified information that follows the Well Life Cycle. Within PDMS, data are organized and structured according to clearly defined principles and rules and filtered by different levels of quality control. Structured data allows integration of production and reservoir information with real-time data to achieve the maximum level of diagnosis of system operation performance according to reservoir and well potentials and system constraints. The built-in workflows and architecture of the whole process are automated and make the task accomplishment faster. SICLO methodology integrates expert-driven knowledge and pattern recognition tools improved by data-driven, artificial intelligence, neural network, and fuzzy logic technologies to deliver adaptive solutions for identifying locations of remaining reserves, optimizing oil and gas production, and minimizing associated operational costs.

Data-Driven Analytics Provide Novel Approach to Performance Diagnosis

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 192759, “Data-Driven Analytics: A Novel Approach to Performance Diagnosis Using Spatiotemporal Analysis in a Giant Field Offshore Abu Dhabi,” by Mohamed Mehdi El Faidouzi, SPE, and Djamel Eddine Ouzzane, ADNOC, prepared for the 2018 Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, 12–15 November. The paper has not been peer reviewed. This work describes a heuristic approach combining mathematical modeling and associated data-driven work flows for estimating reservoir-pressure surfaces through space and time using measured data. This procedure has been implemented successfully in a giant offshore field with a complex history of active pressure management with water and gas. This practical work flow generates present-day pressure maps that can be used directly in reservoir management by locating poorly supported areas and planning for mitigation activities. Field Overview The giant oil field offshore Abu Dhabi covers an area of approximately 40×25•km. The structure is a low-relief anticline. The fault pattern is dominated by steep northwest/southeast strikes, with less-abundant northeast/southwest strikes. The fault throws are generally small, and most faults are unlikely to be sealing laterally. The oil accumulation is separated by dense argillaceous limestones into three distinct, stacked reservoirs (A, B, and C), each approximately 20 to 35 ft thick. Formation-pressure tests showed good intrareservoir vertical pressure communication. Occasionally, especially toward the north and east, a generally tight clay-prone lithology forms a localized barrier between the upper and basal layers of Reservoirs A and B. The complete paper examines the case of the upper layers of Reservoir A in particular, a laterally extensive porous carbonate deposited in a shallow-water environment, although the work flows developed are equally applicable to other reservoir zones. Commercial production of Reservoir A began in the late 1960s. After an initial period of natural depletion, various pressure-maintenance strategies were deployed, namely dump-flood (1972–1984), peripheral water injection (from 1979), and crestal gas injection (from 2005). Spatiotemporal Analysis of Pressure Data Prediction of spatial random fields is a common task in geostatistics and arises in geology, mining, hydrology, and atmospheric sciences. Kriging procedures are used routinely to make optimal predictions at unsampled locations. For quantities that vary in space and time, such as reservoir pressure, spatiotemporal interpolation can provide more-accurate predictions than purely spatial interpolation because observations at other times are considered. In producing oil and gas assets, reservoir-pressure measurements are made at a much higher frequency in the time domain compared with the spatial domain, which requires additional wells to be drilled. The conventional approach of using a spatial interpolation on the basis of a certain time period misses valuable information and could result in inconsistencies between maps from one time period to the next. In this case study, the authors present a heuristic approach to estimating reservoir pressure maps in Reservoir A on the basis of spatiotemporal interpolation. Reservoir pressure is modeled using smooth functions that capture global trends while preserving the spatial and temporal continuity of pressure and pressure gradient. The residuals can be described by a stationary and spatially isotropic process. Residuals then can be predicted at unsampled space and time locations by kriging.