Robust Data Model Research Articles

Digitalization and Dynamic Criticality Analysis for Railway Asset Management

The primary aim of this paper is to support the optimization of asset management in railway infrastructure through digitalization and criticality analysis. It addresses the current challenges in railway infrastructure management, where data-driven decision making and automation are key for effective resource allocation. The paper presents a methodology that emphasizes the development of a robust data model for criticality analysis, along with the advantages of integrating advanced digital tools. A master table is designed to rank assets and automatically calculate criticality through a novel asset attribute characterization (AAC) process. Digitalization facilitates dynamic, on-demand criticality assessments, which are essential in managing complex networks. The study also underscores the importance of combining digital technology adoption with organizational change management. The data process and structure proposed can be viewed as an ontological framework adaptable to various contexts, enabling more informed and efficient asset ranking decisions. This methodology is derived from its application to a metropolitan railway network, where thousands of assets were evaluated, providing a practical approach for conducting criticality assessments in a digitized environment.

Edge–cloud collaborative estimation lithium-ion battery SOH based on MEWOA-VMD and Transformer

The State of Health (SOH) of lithium-ion batteries significantly impacts the performance, safety, and reliability of the battery, making it a crucial component of the battery management system. Addressing the issues of inadequate accuracy and lack of robustness in current SOH estimation methods, this study introduces a novel methodology for estimating SOH in lithium-ion batteries. It leverages the multi-population evolution whale optimization algorithm optimized variational mode decomposition (MEWOA-VMD) in conjunction with Transformer architecture. This framework enhances the efficiency and accuracy of SOH estimation by leveraging the computational capabilities of edge devices for real-time data processing, as well as the robust data processing power and model training advantages offered by cloud computing. Specifically, MEWOA is utilized to optimize VMD parameters, enabling MEWOA-VMD to fully decompose the capacity signal of lithium-ion batteries. This results in a component showing a global attenuation trend and a set of fluctuating components that represent capacity regeneration, thereby minimizing the impact of capacity regeneration on SOH estimation. Subsequently, all components are collectively input into the Transformer, marking the first application of this method for input. To enhance convergence speed and training efficiency, the layer normalization (LN) layer within the neural network architecture is proactively advanced. Finally, various artificial neural networks are compared and validated on three publicly available datasets. Furthermore, Gaussian noise is introduced into the original data to validate robustness. To confirm the practical applicability of the proposed method, real-world vehicle data is used for SOH estimation. The results indicate that the proposed method achieves a maximum MSE of no more than 0.009% across three publicly available datasets, showcasing improved accuracy and stability in SOH estimation. The practical applicability is further validated using real-world vehicle data, proving the proposed method’s potential for application in edge cloud-based battery management systems.

The Digital Divide, Wealth, and Inequality: An Examination of Socio-Economic Determinants of Collaborative Environmental Governance in Thailand through Provincial-Level Panel Data Analysis

Collaborative environmental governance (CEG) is a tripartite process that engages the government, private sector, and general public in decision-making related to environmental challenges, focusing on fostering more sustainable and efficient solutions. Understanding the specific factors influencing the degree of CEG presents a significant challenge, particularly in developing countries. This study aims to identify and assess the socio-economic determinants affecting the degree of CEG in Thailand, a representative developing country. Utilizing robust panel data models, which are well-suited to handle the complex variability of socio-economic factors, we analyzed provincial-level data from 2017 and 2019. Our findings revealed the associations between the degree of CEG and variables such as the internet access divide, economic activities, income inequality, and budget allocations for environmental activities. This research fills critical gaps in our understanding of how these determinants shape collaborative governance efforts, offering novel insights that challenge existing paradigms and providing actionable recommendations for policymakers striving to enhance environmental governance in developing regions.

An information entropy-based fuzzy stochastic configuration network for robust data modeling

In data-driven modeling, the generalization performance of a neural network based on the minimum mean square error criterion may be affected when the samples contain noise. To handle uncertain data modeling problems, this study contributes a novel robust data modeling method called information entropy-based fuzzy stochastic configuration networks (IEFSCNs), which incorporates the maximum correntropy criterion (MCC) to reflect the squared error of the training sample set and uses the quantized minimum error entropy (QMEE) criterion to mine the distribution structure of the modeling data and suppress outlier data. Fuzzy systems are designed to generate nodes in the fuzzy transformation layer. A nonlinear enhancement layer is established as a hidden layer to enhance the representational capacity of the target system. The fuzzy transformation and nonlinear enhancement layers are fully connected to determine the outputs of the IEFSCNs. In addition, an incremental parameter learning algorithm is developed based on a supervision mechanism for optimizing the cost function, and its convergence property is demonstrated. Owing to the superiorities of the cost function by synthesizing MCC and QMEE, IEFSCNs can improve the modeling accuracy and reduce noise suppression. The performances are evaluated using various regression and classification tasks. Compared with existing methods, including SCNs, RVFL, F-SCNs, RSC-KDE, RSC-MCC, and SM-RSC, the proposed method demonstrates an effective robust modeling performance by reducing network structure redundancy while enhancing its ability to suppress noisy data.

Enhancing municipal solid waste leachate treatment efficiency: AI-based prediction of electrocoagulation/flocculation recovery using iron electrodes

ABSTRACT This study addresses a gap in municipal leachate (MUPL) treatment by introducing a pioneering application of artificial intelligence (AI) in the electrocoagulation/electroflocculation (EC/EF) process utilizing iron electrodes. The overarching aim is to demonstrate the efficacy of AI, particularly a multi-layer perceptron (MLP)-based feed-forward artificial neural network (ANN) incorporating the Levenberg-Marquardt (LMb) algorithm, in predicting and optimizing EC/EF outcomes for turbidity (TDY) removal. The research methodology involved experimentation and robust ANN data modeling. The significance of this work emerges from the successful integration of AI, showcasing its potential in advancing wastewater, demonstrated through a strong positive correlation (0.994) between the ANN model predictions and experimental outcomes. The study achieves a remarkable 99.4% TDY removal at an electrolysis time of 10 min and contributes valuable insights into the critical parameters influencing the EC/EF process. Results from the ANN modeling exhibit high predictive accuracy, supported by elevated R-squared values and minimal mean square error. Statistical analyses underscore the significance of key process parameters, highlighting the influential roles of current intensity and settling time. The study emphasized the favourable impact of maintaining an acidic pH range, as it reduced electrostatic repulsion between particles, facilitating pollutant agglomeration, and identified electrolysis time as a key factor in enhancing treatment efficiency, supported by a strong positive correlation between electrolysis time and TDY reduction. Energy cost savings were realized by not requiring temperature elevation. Achieving a 99.4% TDY removal translates to substantial reductions in other pollutants present in the MUPL, thereby elevating water quality and ensuring compliance.

Exploring the Influence of the Digital Economy on Energy, Economic, and Environmental Resilience: A Multinational Study across Varied Carbon Emission Groups

Rapid advancements in digital technologies have accelerated global change, underscoring the critical role of resilience in addressing the escalating energy, economic, and environmental challenges. This paper investigates the effects and mechanisms of the digital economy on energy, economic, and environmental resilience within the context of these challenges. By utilizing panel data from 66 countries spanning the period from 2000 to 2020, this analysis employs robust panel data models and incorporates tests such as the Hausman and Leamer tests, and exploratory factor analysis. The results reveal a notable positive impact of the digital economy on resilience across various countries and time periods. However, when it comes to carbon emissions, a more intricate pattern emerges, suggesting a negative influence on resilience in environmental, energy, and economic domains. Interestingly, countries with below-average carbon emissions show more positive effects on economic resilience due to the digital economy. On the other hand, the effect of the digital economy on energy resilience is less prominent in below-average carbon-emitting nations, while carbon emissions have a more significant impact within this subgroup. Above-average carbon-emitting countries experience limited effects of the digital economy on environmental resilience, while below-average carbon-emitting countries face challenges with significant carbon emissions impacting their environmental resilience.

Redefining governance: a critical analysis of sustainability transformation in e-governance.

With the rapid growth of information and communication technologies, governments worldwide are embracing digital transformation to enhance service delivery and governance practices. In the rapidly evolving landscape of information technology (IT), secure data management stands as a cornerstone for organizations aiming to safeguard sensitive information. Robust data modeling techniques are pivotal in structuring and organizing data, ensuring its integrity, and facilitating efficient retrieval and analysis. As the world increasingly emphasizes sustainability, integrating eco-friendly practices into data management processes becomes imperative. This study focuses on the specific context of Pakistan and investigates the potential of cloud computing in advancing e-governance capabilities. Cloud computing offers scalability, cost efficiency, and enhanced data security, making it an ideal technology for digital transformation. Through an extensive literature review, analysis of case studies, and interviews with stakeholders, this research explores the current state of e-governance in Pakistan, identifies the challenges faced, and proposes a framework for leveraging cloud computing to overcome these challenges. The findings reveal that cloud computing can significantly enhance the accessibility, scalability, and cost-effectiveness of e-governance services, thereby improving citizen engagement and satisfaction. This study provides valuable insights for policymakers, government agencies, and researchers interested in the digital transformation of e-governance in Pakistan and offers a roadmap for leveraging cloud computing technologies in similar contexts. The findings contribute to the growing body of knowledge on e-governance and cloud computing, supporting the advancement of digital governance practices globally. This research identifies monitoring parameters necessary to establish a sustainable e-governance system incorporating big data and cloud computing. The proposed framework, Monitoring and Assessment System using Cloud (MASC), is validated through secondary data analysis and successfully fulfills the research objectives. By leveraging big data and cloud computing, governments can revolutionize their digital governance practices, driving transformative changes and enhancing efficiency and effectiveness in public administration.

Improvement of pasture biomass modelling using high-resolution satellite imagery and machine learning

Robust quantification of vegetative biomass using satellite imagery using one or more forms of machine learning (ML) has hitherto been hindered by the extent and quality of training data. Here, we showcase how ML predictive models demonstrably improve when additional training data is used. We collated field datasets of pasture biomass obtained via destructive sampling, ‘C-Dax’ reflective measurements and rising plate meters (RPM) from ten livestock farms across four States in Australia. Remotely sensed data from the Sentinel-2 constellation was used to retrieve aboveground biomass using a novel machine learning paradigm hereafter termed “SPECTRA-FOR” (Spectral Pasture Estimation using Combined Techniques of Random-forest Algorithm for Features Optimisation and Retrieval). Using this framework, we show that the low temporal resolution of Sentinel-2 in high latitude regions with persistent cloud cover leads to extensive gaps between cloud-free images, hindering model performance and, thus, contemporaneous ability to forecast real-time pasture biomass. By leveraging the spectral consistency between Sentinel-2 and Planet Lab SuperDove to overcome this limitation, we used ten spectral bands of Sentinel-2, four bands of Sentinel-2 as a proxy for pre-2022 SuperDove (referred to as synthetic SuperDove or SSD), and the actual SuperDove (ASD), given that SuperDove imagery has a higher resolution and more frequent passage compared with Sentinel-2. Using their respective bands as input features to SPECRA-FOR, model performance for the ten bands of Sentinel-2 were R2 = 0.87, root mean squared error (RMSE) of 439 kg DM/ha and mean absolute error (MAE) of 255 kg DM/ha, while that for SSD increased to an R2 of 0.92, RMSE of 346 kg DM/ha and MAE = 208 kg DM/ha. The study revealed the importance of robust data mining, imagery harmonisation and model validation for accurate real-time modelling of pasture biomass with ML.

The Morais Dictionary: Following Best Practices in a Retro-digitized Dictionary Project

This article outlines essential best practices for retro-digitized dictionary projects, using the ongoing MORDigital project (DOI 10.54499/PTDC/LLT-LIN/6841/2020) as a case study. The MORDigital project focuses on digitally transforming the historically significant Portuguese Morais dictionary’s first three editions (1789, 1813, 1823). While the primary objective is to create faithful digital versions of these renowned dictionaries, MORDigital stands out by going beyond the mere adoption of established best practices. Instead, it reflects on the choices made throughout the process, providing insights into the decision-making process. The key topics emphasized include (1) the establishment of a robust data model; (2) the refinement of metadata; (3) the implementation of consistent identifiers; and (4) the enhancement of encoding techniques; additionally exploring the issue of structuring domain labelling. The article aims to contribute to the ongoing discourse on best practices in retro-digitized dictionary projects and their implications for data preservation and knowledge organization.

Prediction of X-ray fluorescence copper grade using regularized stochastic configuration networks

In copper ore flotation processes, accurate measurement and estimation of the copper grade of the final products are crucial for field operations and control. Due to the presence of multicollinearity and outliers in the measured data, the existing on-stream X-ray fluorescence grade analyzer is inaccurate. To address these issues, this study proposes a robust data modeling algorithm to improve the performance of copper grade prediction. Specifically, a regularized stochastic configuration network and a generalized M−estimation method are used to overcome the uncertainties in the processing data. The experimental results clearly demonstrate that the proposed model outperforms other modeling algorithms in terms of prediction accuracy and robustness.

Flexible, robust and minimal-overhead Event Data Model for track reconstruction in ACTS

ACTS (A Common Tracking Software) is an experiment independent toolkit for track reconstruction, which is designed from the ground up for thread-safety and high performance. It is built to accommodate different experiment deployment scenarios, and also serves as community platform for research and development of new approaches and algorithms. The Event Data Model (EDM) is a critical piece of the tracking library that is visible to clients. Until this point, ACTS was mostly focused on an internal EDM, targeting data interchange various components in the toolkit. This contribution reports on a new and improved client EDM for ACTS. For an experiment-agnostic toolkit like ACTS, this requires strong abstractions of potentially experiment-specific details, including event context data like sensor alignments, and tracking inputs like measurements. By applying similar abstraction strategies, the presented EDM can be an expressive, low-overhead abstraction over experiment-specific backends, and seamlessly integrates into an experiment framework and IO model. The presented EDM includes the ACTS track class, the main data type which tracking clients interact with. It is designed to be interfaced with different IO backends, and also flexible enough to support dynamic information required by various track fitters. At the same time, careful design ensures it can seamlessly serve as a key data object in experiment reconstruction data flows. In this contribution, the interaction of this centerpiece of the example workflows in ACTS with the standalone ROOT IO, as well as the integration with the EDM4hep package will be shown, and key performance characteristics discussed.

A robust transfer deep stochastic configuration network for industrial data modeling

A robust transfer deep stochastic configuration network for industrial data modeling is proposed to address challenging problems such as the presence of outliers (or noise) and conditional drift of the data model due to changes in working conditions. Assuming that outliers follow the t-distribution, the maximum a posteriori estimation is employed to evaluate the read-out weights, and the expectation maximization algorithm is used to iteratively optimize the hyperparameters of the distribution. Moreover, the knowledge contained in the data are expressed in the form of the model structure, connection weights and outlier distribution, and a knowledge-data-based robust transfer strategy is developed to offset the impact of insufficient training data on the learning performance of a deep stochastic configuration network with a new working condition. Comparative experiments are carried out using the historical furnace temperature data of a municipal solid waste incineration plant in China. The results show that the proposed method performs more favorably in robust data modeling and mitigates the impact of changes in working conditions on the applicability and accuracy.

Tropical cyclone frequency: turning paleoclimate into projections

Future changes to tropical cyclone (TC) climate have the potential to dramatically impact the social and economic landscape of coastal communities. Paleoclimate modeling and paleohurricane proxy development offer exciting opportunities to understand how TC properties (like frequency) change in response to climate variability on long time scales. However, sampling biases in proxies make it difficult to ascertain whether signals in paleohurricane records are related to climate variability or just stochasticity. Short observations and simulation biases prevent TC models from capturing the full range of climate variability and TC characteristics. Integration of these two data types can help address these uncertainties. Robust data model comparison in paleotempestology will require (a) simulating TCs using new paleoclimate data assimilation products and climate model ensembles, (b) building a central repository of open access paleohurricane proxies, (c) compiling paleohurricane records, and (d) filling key gaps in the existing paleohurricane networks. Incorporating the combined information from both paleohurricane proxies and paleo TC simulations into risk assessments for coastal communities could help improve adaptation strategies.

Robust Dynamic Space-Time Panel Data Models Using?-Contamination: an Application to Crop Yields and Climate Change

Robust Dynamic Space-Time Panel Data Models Using?-Contamination: an Application to Crop Yields and Climate Change

Effects of Urban Producer Service Industry Agglomeration on Export Technological Complexity of Manufacturing in China.

Based on the measurement of producer service industry agglomeration and export technological complexity of manufactured products in 288 Chinese cities from 2000 to 2015, this paper illustrates the evolvement and spatial characteristics of the two factors through visualization figures, and discusses the effects of producer services agglomeration on export technological complexity of manufacturing through robust panel data models. The findings are as follows: as with the influence of industrial connection, empirical outcomes indicate that urban producer service agglomeration can promote technological complexity of export manufacturing on the full-sample level. Visualization analysis shows that the scale of producer service industry agglomeration and the export technological complexity of manufactured products around Chinese cities kept rising constantly during the study period. However, although the export technological complexity displayed a trickle-down effect, the producer service industry agglomeration experienced continuous polarization both on the national and the regional levels. Accordingly, as is shown in the empirical analysis by areas, regions with strong support from producer service industry saw a remarkable promotion in the export manufacturing technology, while the northwest and the northeast gradually lagged behind. Such results sufficiently prove that heterogeneity does exist in the performances of industrial connection between producer service industry and export manufacturing in cities of different regions in China.

Abstract LB-242: Proteomic Data Commons: A resource for proteogenomic analysis

Abstract The objective of the National Cancer Institutes' Proteomic Data Commons (PDC) is to make cancer-related proteomic datasets accessible to the public. The PDC provides the cancer research community with a unified data repository that enables data sharing across cancer proteomic studies and also enables multi-omic integration in support of precision medicine. As a domain-specific repository within the Cancer Research Data Commons (CRDC), the vision for the PDC is to provide researchers the ability to find and analyze proteomic data across a wide variety of tumor types. Currently, the PDC houses data, supported by a large collection of metadata attributes, for nearly 40 datasets from over 12 cancer types produced by several large-scale cancer research programs, each with cohort sizes greater than 100 patients. The PDC facilitates the analysis of proteomic, genomic, and imaging data derived from the same tumor. Most of the datasets in the PDC also have corresponding genomic and imaging data available in the Genomic Data Commons and The Cancer Imaging Archive respectively. Researchers can discover which genomic variants are detectable at the protein-level or better understand associations between gene expression, copy number variation, and protein abundance. The resource is currently available to the public in beta phase (https://pdc.esacinc.com) and will be officially launched on the cancer.gov domain in March 2020. The PDC data portal is supported by a robust and extensible data model and provides user-friendly exploration, visualization and data analysis. This allows researchers to search for and visualize expression of proteins (through their mapped genes) across all studies, analyze protein abundance for all cases in a study through heatmaps, build and explore pan-cancer cohorts using highly curated, clinical metadata, and comprehensively view a study without needing to download the data. The PDC provides quick access to mapping of peptide identities and quantities on the human genome as well as protein databases containing patient/tumor-specific variants and novel splicing events. It also enables fast, accurate, and convenient proteomic validation of novel genomic alterations through the PepQuery algorithm. Through a highly versatile application programming interface (API), PDC allows users to interact with data programmatically and facilitates integration with data from other resources in their scripts for multi-omic analysis. Big data interoperability is critical for progress in precision medicine. PDC is designed to interoperate with other resources including the CRDC nodes, allowing users to analyze PDC data with the tools and pipelines available on the NCI cloud resources. It further allows users to use their own tools to co-analyze genomic and proteomic data available from a common sample on Amazon Web Services (AWS) platform or on a local system. The presentation will provide an overview of the PDC and it's available datasets, as well as a discussion of how it facilitates multi-omic data analyses. Citation Format: Ratna Rajesh Thangudu, Paul A. Rudnick, Michael Holck, Deepak Singhal, Michael J. MacCoss, Nathan J. Edwards, Karen A. Ketchum, Christopher R. Kinsinger, Erika Kim, Anand Basu. Proteomic Data Commons: A resource for proteogenomic analysis [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr LB-242.

Respiratory illness, hospital visits, and health costs: Is it air pollution or pollen?

BackgroundBoth air pollution and airborne pollen can cause respiratory health problems. Since both are often jointly present in ambient air, it is important to control for one while estimating the effect of the other when considering pollution-abating policies. To date only a limited number of studies have considered the health effects of both irritants jointly for a general population, and for a sufficiently long time period to allow for variation in seasonal concentrations of both components. The primary goal of this study is to determine the causal impact of fine particulate matter (PM2.5) on hospital visits and related treatment costs, while controlling for potentially confounding pollen effects. Our study area is the metropolitan hub of Reno/Sparks in Northern Nevada. MethodsTaking advantage of a rare sample of daily pollen counts over a prolonged period of time (2009–2015), we model the effects of PM2.5 and pollen on respiratory-related hospital admissions for the population at large, plus specific age groups. Pollen data are provided by a local allergy clinic. Data on PM2.5 and other air pollutants are obtained from the U.S. Environmental Protection Agency's air quality data web site. We collect daily meteorological data from the National Centers for Environmental Information's data repository. Data on hospital admissions are given by the Nevada Center for Surveys, Evaluations, and Statistics. Our econometric approach centers on a fully robust count data (Poisson) model, estimated via Quasi-Maximum Likelihood. ResultsWe find that for our sample PM2.5 effects are largely robust to the inclusion of both pollen counts and temporal indicators. In contrast, pollen effects vanish when time fixed effects are added, pointing at their correlation with unobserved temporal confounders. At the same time, model fit improves with the inclusion of temporal indicators. Based on our preferred specification, we find a significant PM2.5 effect of approximately 0.5% additional hospital visits per day due to a one μg/m3 increase in PM2.5. This translates into expected augmented treatment costs of $2700 per day for the same unit-change in PM2.5. These figures can mount quickly when more pronounced and/or longer episodes of particulate matter pollution are considered, perhaps due to wildfire smoke. For instance, the expected increase in patients and costs due to a month-long 10-unit-jump of PM2.5 over the long-run annual average would amount to an extra 70 patients and approximately $680,000 in additional treatment costs.

Spectral and spatial kernel water quality mapping.

An empirical approach through remote sensing generally produces a robust data model of water quality for inland and coastal water. Traditional regressions in water quality mapping fail because the bio-optical relationship of turbid water exhibits nonlinear and heterogeneous patterns. In addition, in situ data are generally insufficient in the water quality mapping. Mapping based on a relatively small amount of water quality samples is considered a practical issue in environmental monitoring. Learning-based algorithms that require a large amount of data are inapplicable in this case. According to the concept of Nadaraya-Watson estimator, the kernel model can estimate nonlinear and spatially varying water quality maps effectively in turbid water.Experiments indicate that the kernel estimator provides better goodness-of-fit between the observed and derived concentrations of water quality parameter, e.g., chlorophyll-a in turbid water. The kernel estimator is feasible for a relatively small size of ground observations. Approximately 30% improvement of cross-validation error was identified in this approach when compared with traditional regressions. The model offers a robust approach without further calibrations for estimating the spatial patterns of water quality by using remote sensing reflectance and a small set of observations, considering spatial and spectral information, e.g., multiple bands and band ratios.

A Novel Hybrid Machine Learning Algorithm for Limited and Big Data Modeling With Application in Industry 4.0

To meet the challenges of manufacturing smart products, the manufacturing plants have been radically changed to become smart factories underpinned by industry 4.0 technologies. The transformation is assisted by employment of machine learning techniques that can deal with modeling both big or limited data. This manuscript reviews these concepts and present a case study that demonstrates the use of a novel intelligent hybrid algorithms for Industry 4.0 applications with limited data. In particular, an intelligent algorithm is proposed for robust data modeling of nonlinear systems based on input-output data. In our approach, a novel hybrid data-driven combining the Group-Method of Data-Handling and Singular-Value Decomposition is adapted to find an offline deterministic model combined with Pareto multi-objective optimization to overcome the overfitting issue. An Unscented-Kalman-Filter is also incorporated to update the coefficient of the deterministic model and increase its robustness against data uncertainties. The effectiveness of the proposed method is examined on a set of real industrial measurements.

The Political Economy of Capital Flight: Governance Quality and Capital Flight in the East Africa Community

This paper examines the impacts of political economy factors on an illicit capital outflow in the East African Community using robust panel data models. The main findings of the study are as follows: An increase in Gross Domestic Product is a statistically significant variable and reduces an illicit flow of illegal capital outflow from the Community. However, foreign direct investment, total grant and exchange rate statistically significant and aggravate the outflow of capital. This is due to poor governance and economic policies that governments favor foreign investors over local investors. An aggregate index of poor regulatory quality and government ineffectiveness, state fragile index, and the political instability index are statistically significant and positively influence an illicit capital flight from the Community. However, the existed perceived corruption level does not positively contribute to capital flight, but an intensive corruption level positively influences capital flight overtime, bringing a mixed sign of negative and positive depending on the level of corruption that affects capital flight overtime in the Community. The study, therefore, recommends that member countries in the Community need to undertake an effective governance and regulatory qualities, political stability and controlling power of corruption in order to control capital flight. Keywords : Capital flight, governance quality, political stability index, regulatory quality index, Government Effectiveness, Control of Corruption, World Bank Residual Methods DOI : 10.7176/JESD/10-11-02 Publication date :June 30 th 2019