Uncertainty analysis using experimental design and response surface techniques has been extensively used in the field of reservoir simulation. This study outlines an innovative workflow to generate multiple realizations of forward stratigraphic modelling of three Lower Cretaceous reservoirs from onshore Abu Dhabi. Forward stratigraphic modelling is a deterministic technique that simulates basin infill providing a better understanding of vertical and lateral facies distribution and connectivity in sedimentary basins. During the course of forward modelling a variety of environmental and stratigraphic parameters are used. Due to the uncertainties of these parameters it is critical to assess their impact on the development of the basin fill. The experimental design and response surface techniques have been innovatively applied at reservoir scale to enhance the understanding of major controlling parameters on carbonate production and to produce alternative facies distribution scenarios in the study reservoirs. The methodology used in this study was based on running multiple simulations, through varying key input parameters. The best stratigraphic models were then selected based on calibration quality and geological consistency. Calibration quality was assessed by two user defined quantitative functions called Thickness Calibration Indicator and Rock Texture Calibration Indicator. The initial step in the workflow identified uncertain environmental parameters (e.g. eustasy, carbonate production versus depth, carbonate production versus time, wave parameters, gravity and wave transport and erosion rates) from a manually calibrated reference case and ranges of values for each parameter defined based on the knowledge of geology over the area. Latin Hypercube experimental design was then used to define a set of simulations to allow an efficient and uniform sampling of the entire uncertain domain. Sensitivity analysis was then performed on simulation responses (texture and thickness calibration indicators) using the technique of nonparametric Response Surface Modelling (RSM). The influence (quantitative and qualitative) of the impacting parameters on responses was studied to identify the most influential parameters as well as the ranges yielding good calibration indicator values. A further set of simulations was then launched that considered the most influential parameters and their precise ranges. Non critical parameters were assigned with the constant values from the reference case model. These simulations generated a series of well calibrated models. A filtering of simulations with high calibration indicator values and good geological consistency was then performed to choose acceptable multi-realizations. Finally, thickness and texture confidence properties were mapped based on the selected multi-realizations and the reference case. Sensitivity study on three Lower Cretaceous reservoirs from onshore Abu Dhabi successfully addressed the uncertainty associated with forward stratigraphic model input parameters. Sensitivity analysis was performed using Experimental Design and RSM. This was applied to enhance the understanding of the major controlling environmental parameters on carbonate production for individual sequence with each of the study reservoirs.

Smart and sustainable solid waste management systems (SWMS) are of major interest in the development of smart sustainable cities (SSC). Selective waste collection and transportation are known to be major expenditures of city waste management systems. In this paper, we investigate a waste management system for domestic waste in a Norwegian municipality as a case study. Different scenarios for route planning are considered to improve cost and time usage. The study provides an auxiliary management system for multi-objective TSP using Google Maps and operation research (OR) tools for optimal domestic waste collection. Additionally, a prediction model for scheduling future waste collection trips is provided, whereby challenges such as road conditions, road traffic, CO2 and other gases emissions, and fuel consumption are considered. The proposed prediction model considers the hazards associated with food waste bins that need to be emptied more frequently than bins containing other waste types such as plastic and paper. Both proposed models signify consistency and correctness.

Understanding complex systems by the help of modeling, simulation, and control is a well-known challenge across several application domains. As such, these type of systems are not amenable to empirical models, typically due to their dynamic and non-linear nature. Data-driven methods, have in recent years gained traction regarding their application to such complex systems. This paper presents findings from a systematic literature review of data-driven methods applied to complex systems in recent years. The review is a result of a search strategy resulting in 1106 scientific publications, out of which forty one were identified as primary studies. It is our goal that the review findings will guide researchers with an evidence-base regarding data-driven methods, thereby equipping them with an arsenal of applied methods across various application domains. Also, the objective is to construct a knowledge-base based on these methods' contributions while applied to different types of problems. Additionally, the review findings may also guide researchers to realize potential gaps for future research.

This paper aims to explore modern techniques based on artificial intelligence (AI) and data science, in order to produce data-driven workflows to analyze, model, and simulate reservoir pressure dynamics. In this paper, it was investigated a data-driven workflow to model reservoir pressure at any point in space and time from sparse pressure data observed at wells, without building a physics-based numerical model. This workflow was termed as spatiotemporal modelling of reservoir pressure. Spatiotemporal modelling of reservoir pressure was based on a three-step workflow including multivariate analysis of pressure data and relevant explanatory variables (features), pressure modelling and spatiotemporal interpolation. The overall workflow provided a comprehensive method to understand and map the reservoir pressure dynamics using data science tools. Several modelling techniques such as generalized additive models, artificial neural networks and spatiotemporal kriging were investigated for their applicability and accuracy. The workflow was applied to a real oil and gas reservoir case, for which the reservoir pressure prediction accuracy was optimized through a few experiments. The optimum experiment produced highly accurate prediction with a mean absolute error of 26.85 psi measured on the training dataset. Moreover, a portion of data used was kept to evaluate blind test accuracy, which amounted to a mean absolute error of 55 psi, for the optimum case. The proposed data-driven workflow was aimed to improve current methods of reservoir engineering and simulation. The suggested workflow showed high accuracy in reservoir pressure predictions with high efficiency in terms of computational resources and time. Additionally, the proposed workflow was developed using open-source libraries which pose no additional cost to computation, in contrast to extremely expensive industry standard physics-based reservoir simulation software. Finally, this workflow could also be used to model other reservoir variables such as production ratios (Water cut, and Gas-Oil Ratio), contacts (Water-Oil contact and Gas-Oil contact), among others.