Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

An introduction to heat transfer

Solar Engineering Of Thermal Processes

This study was done using three nitrogenous compound s to evaluate their effects on postharvest characte ristics of chrysanthemum ( Chrysanthemum indicum) cut flowers. The study consisted of three separate and parallel experiments, in which ammonium sulfate, cal cium nitrate and potassium nitrate were used in different concentrations of zero, 50, 100, 200 and 500 mg dm N for pretreatment of stems for 6 hour before transferring to holding d-water solution. The result showed that petal ion leakage and leaf SPAD values were increased by increasing ammonium sulfate, but n ot calcium or potassium nitrate. Petal carotenoids were increased by pretreatment of ammonium sulfate a nd potassium nitrate. There was constant increase in water uptake by increasing the levels of calcium nit rate and potassium nitrate, while ammonium sulfate a t high concentrations (200 and 500 mg dm ‒3 N) resulted in significant less water uptake compared to control. Ammonium sulfate in 50 and 100 mg dm ‒3 increased shelf life of pretreated stems, but highe r concentrations significantly reduced cut flowers shelf life. Increasing concentrations of calcium nitrate and pa rticularly potassium nitrate have led to prolongation of fl wer shelf life to 12 days compared to 6 days of c ntrol. The results indicate that pretreatment of chr ysanthemum cut flowers with ammonium sulfate in rathe r low concentrations or with moderate to high concentra tions of calcium nitrate or potassium nitrate can s ignificantly improve shelf life and postharvest flower qualities.

Characteristics of postharvest quality of chrysanthemum cut flowers under pretreatment with nitrogenous compounds

/pdf/machine-learning-prediction-models-of-electrical-efficiency-2hct00cgss.pdf

Machine Learning Prediction Models of Electrical Efficiency of Photovoltaic-Thermal Collectors

Efficient and profitable oil production is subject to make reliable predictions about reservoir performance. However, restricted knowledge about reservoir distributed properties and reservoir structure calls for History Matching in which the reservoir model is calibrated to emulate the field observed history. Such an inverse problem yields multiple history-matched models which might result in different predictions of reservoir performance. Uncertainty Quantification restricts the raised model uncertainties and boosts the model reliability for the forecasts of future reservoir behaviour. Conventional approaches of Uncertainty Quantification ignore large scale uncertainties related to reservoir structure, while structural uncertainties can influence the reservoir forecasts more intensely compared with petrophysical uncertainty. What makes the quantification of structural uncertainty impracticable is the need for global regridding at each step of History Matching process. To resolve this obstacle, we develop an efficient methodology based on Cartesian Cut Cell Method which decouples the model from its representation onto the grid and allows uncertain structures to be varied as a part of History Matching process. Reduced numerical accuracy due to cell degeneracies in the vicinity of geological structures is adequately compensated with an enhanced scheme of class Locally Conservative Flux Continuous Methods (Extended Enriched Multipoint Flux Approximation Method abbreviated to extended EMPFA). The robustness and consistency of proposed Hybrid Cartesian Cut Cell/extended EMPFA approach are demonstrated in terms of true representation of geological structures influence on flow behaviour. In this research, the general framework of Uncertainty Quantification is extended and well-equipped by proposed approach to tackle uncertainties of different structures such as reservoir horizons, bedding layers, faults and pinchouts. Significant improvements in the quality of reservoir recovery forecasts and reservoir volume estimation are presented for synthetic models of uncertain structures. Also this thesis provides a comparative study of structural uncertainty influence on reservoir forecasts among various geological structures. Dedicated to my everything....Maryam Acknowledgements I am really grateful to my supervisor Professor Mike Christie. He provided me freedom to explore different ideas and meanwhile gave me insightful suggestions and guidance. I benefited a lot from all of the discussions and interactions with him. I am also indebted to my second supervisor Professor Margot Gerritsen for her invaluable hints on my PhD direction. The uncertainty project sponsors BP, BG, ConocoPhillips and JOGMEC are especially appreciated for their financial support during my PhD studies. Special thanks go to all my dear friends in Heriot-Watt University particularly the old and new members of Uncertainty Quantification Group (Monica, Vasya, Dan, Allanah, Linah, Yasin, Lorna, Simon, Asaad, Hamid). They made the life easier in Edinburgh for me away from my lovely wife. Many appreciations go to the PhD external examiner Professor Michael Edwards and PhD internal examiner Professor Sebastian Geiger for reviewing thoroughly my thesis and providing me many helpful corrections for improving my thesis. I take this opportunity to thank my family especially my parents, who always stand by me and share my joy and sorrow. Finally I express my sincere gratitude to my pure love, Maryam who gave me the motivation and confidence to do what I need to do. I love you Maryam!

Modelling and quantification of structural uncertainties in petroleum reservoirs assisted by a hybrid cartesian cut cell/enriched multipoint flux approximation approach

Model-based production optimization relies on a dynamic model that simulates the fluid flow in the oil reservoirs, and an economic objective function that assigns an economic measure to the recoverable oil reserves. An optimization algorithm utilizes the dynamic model to find the production scenario which maximizes the economic measure of profit. However, due to incompleteness and doubtfulness of available data, the reservoir model describing the complex subsurface geology is quite uncertain. Moreover, the definition of the economic objective functions such as net present value (NPV) requires economic variables such as oil price, interest rate, and production costs which unpredictably vary with time. In recent years, robust optimization (RO) has been widely used as an appropriate tool for handling the uncertainties in production optimization problems. However, previous works on robust optimization paid less attention to economic uncertainties arising from market volatility. Instead, they are mostly focused on geological uncertainties. This paper is devoted to production optimization under oil market uncertainty. To narrow down the range of economic uncertainties, a Bayesian framework for oil price history matching and forecasting has been developed which allows generating more reliable realizations of oil price future trend. It is common to include a measure of risk-averse in the objective function of RO problems. However, the quality of the solutions depends directly on the used risk measure. In the oil industry, risk measures such as worst-case scenario and CVaR (Conditional Value at Risk) have been used to mitigate the risk of low-profit realizations. These risk measures are appropriate in many cases for measuring the robustness. Though, they are inadequate in evaluating robustness in a relative sense in cases where the worst-case realizations have an undue effect on the final decisions. The risk measure defined based on the minimax regret approach takes into account all realizations instead of just considering the worst-case realizations. In this research, RO has been performed to maximize NPV using the minimax regret approach. In addition, the results are compared with the common risk measures used in the oil industry including expected profit, CVaR, and worst-case. Results show that while worst-case scenario and CVaR perform better than other risk measures in lower-profit realizations, they give inappropriate results for other scenarios. In contrast, regret-based approach and expected profit give nearly optimum solutions for all realizations. In this paper, the minimax regret approach was compared with other risk measures in the presence of oil price uncertainty. However, the results might be extended to optimization under geological uncertainty.

Comparative study of different risk measures for robust optimization of oil production under the market uncertainty: a regret-based insight

\n Production from previously uneconomic tight/shale formations has become feasible by constructing multifractured horizontal wells. Rate-transient analysis of these wells is commonly performed with the assumption of homogeneous-reservoir models, which might not be valid in reality. During hydraulic fracturing, secondary fractures might be formed in the reservoir. Because of the limited energy of hydraulic fracturing, the quality of secondary fractures decreases with the distance from the main fracture. This would negate the assumption of a homogeneous reservoir.\n In this paper, we present practical solutions that include reservoir heterogeneity in rate-transient analysis of multifractured wells. The solutions are developed for transient linear flow, which is a dominant-flow regime in many tight/shale reservoirs. In addition to forward solutions, inverse solutions are also developed that would ease the analysis procedure and reduce the uncertainty of estimation. The solutions are presented in simple formats and can be easily applied. We first developed the solutions such that they can be applied for any arbitrary permeability profile. We further considered special formats for the permeability/distance relationship and developed the relevant models. For a homogeneous system, the well-known square-root-of-time (time to the power of 0.5) plot is used. For the case of heterogeneity, however, the power of time should be greater than 0.5 and less than unity to produce a straight-line plot. We mathematically demonstrate this for a recognized format of the permeability/distance relationship.\n The presented solutions are verified with the numerical simulation of synthetic examples. Comparison of the results reveals the accuracy of the analytical solutions. Two field examples are also analyzed to indicate the practical applicability of the analytical solutions. The permeability/distance profiles for these field examples are derived using the inverse solutions.

Mohammad Hossein Ahmadi

Papers

Characteristics of postharvest quality of chrysanthemum cut flowers under pretreatment with nitrogenous compounds

Machine Learning Prediction Models of Electrical Efficiency of Photovoltaic-Thermal Collectors

Modelling and quantification of structural uncertainties in petroleum reservoirs assisted by a hybrid cartesian cut cell/enriched multipoint flux approximation approach

Comparative study of different risk measures for robust optimization of oil production under the market uncertainty: a regret-based insight

Practical Solutions for Rate-Transient Analysis of Tight/Shale Reservoirs with Interfracture Induced Heterogeneity