Measuring and Modeling Labor Productivity Using Historical Data

This paper shows that the stabilization of the unemployment rate between the pre-1930 and post-1948 eras is an artifact of improvements in data collection procedures. Prewar methods are used to construct postwar unemployment data that are consistent with the historical data. The constructed postwar series is nearly as volatile as the pre-1930 unemployment data. The constructed postwar data are systematically more volatile than the actual postwar data because the cyclical behavior of the labor force and productivity are misspecified in the construction procedures. The relationship between the actual and constructed postwar unemployment series is used to construct new historical data.

An artificial neural network (ANN) simulation was utilized to determine the lapping parameters such as rotation speed, lapping duration and lapping pressure under a constant slurry supply for n-type crystalline Silicon (c-Si) wafers. Experiments were done with a Logitech PM5 lapping and polishing machine to obtain input data and target data for training, testing and validation of ANN. Lapping operation had five main parameters affecting surface quality: rotation speed, lapping duration, lapping pressure, flowrate of abrasive slurry and particle size in abrasive slurry. However, in this study slurry flowrate was assumed constant due the researches performed before. 218 lapping operations were performed with different values of the selected parameters and new lapping parameters were derived for different lapping conditions to achieve the best surface quality by using an ANN. In this study, wafers in 400 µm thickness cut under identical conditions from n-type single c-Si ingot in a STX 1202 DWS cutting machine were employed. Surface roughness (R a ) values were measured three times from different points of the wafers after lapping with a contact type surface roughness measurement tool using a microscopic scale stylus profiler (SP). In ANN simulation 70% of R a values were utilized for training, 15% of R a values were utilized for validation and 15% of R a values were utilized for test data. Results obtained from ANN simulation validated with a success above 99%.

Reservoir model history matching is a complex, time-consuming, and resource intensive process that needs to be carried out carefully for building reliable predictive tools to manage Oil & Gas assets. Reservoir models encompass detailed geological description representing subsurface heterogeneities that influence its dynamics. To intelligently manage and preserve the complexity of the reservoir models, an artificial intelligence, Progressive-Recursive Self-Organizing Maps (PR-SOM), algorithm was developed. PR-SOM is an unsupervised artificial intelligence neural network algorithm that classifies the reservoir grid cells into progressive reservoir parameters to identify similarly adjoining regions. The algorithm explores and identifies model geo-bodies with similarities and dissimilarities in a progressive and recursive manner. This allows history matching to be conducted on much smaller subsets of the reservoir model of similar geological features. In this work, an artificial intelligence (AI) algorithm was applied, first, to guide the reservoir-wide history match processes. Next, the algorithm was applied to fine-tune well performance using information form well testing and historical data. The algorithm uses both static properties (permeability, rock quality indices, porosity, flow zonation … etc.) and dynamic properties (pressure or saturation) to construct similarities matrix. The results show that the clusters’s growth is progressive, controlled and quality assured by accounting for the controlling reservoir parameters. The number of mapped regions (clusters) is determined by optimizing the similarity matrix recursively. The quality of the global reservoir history match shows the effectiveness of the algorithm, better quality matching for historical production data, and fewer iterations (i.e. less simulation runs). The process is repeated to calibrate the reservoir model near wellbores by limiting the AI algorithm to only the drainage regions seen from well tests and historical data. The results show that employed AI-guided history matching revealed similarities and dissimilarities in the reservoir model. That not only enhance field and well match, but also allowed us to maintain the heterogeneity contrasts inherited from the Earth model. The advanced algorithm was successfully used to assess the extent of geological heterogeneity and its impact on reservoir dynamics, to enhance history match quality, minimize human interaction, and to reduce computational requirements.

Prior coarse grid simulation models in the Greater Burgan field were unable to capture the stratigraphically diverse nature of the Wara reservoir, and accurately match the existing historical data, resulting in unrealistic predictions of fluid flow from individual reservoir layers. Most simulation failures are blamed on the inability to correctly model reservoir heterogeneity, rather than problems associated with the data it is trying to match. In reality it is probably a function of both. This paper emphasizes the importance of a systematic review of historical production data to assure the accurate initialization of a simulation model and to assess if a full history match should or should not be undertaken. Not only does there need to be sufficient geologic and engineering detail to accurately characterize the fluid and flow properties of the Wara reservoir, but more importantly issues involving the validity, accuracy, and lack of historic data need to be addressed, before deciding whether a reasonable reservoir model for history match could be developed. The reservoir size, long history, and high production rates of the Greater Burgan field magnify the impact, and highlight the importance of correcting data errors, and recognizing data uncertainty and gaps. Introduction A reservoir simulation model is only as good as the data going into it. Data review and validation is necessary to understand the accuracy and limitations of the data and should always be the first step toward developing a successful reservoir simulation model. Results from a simulation based on inaccurate data may be more damaging to the planning and economics of developing a reservoir than not having a predictive simulation model at all. A systematic review of the Wara production data in the Greater Burgan field identified data problems that have changed prior simulation assumptions about the reservoir character, flow characteristics, and reservoir drive mechanisms. These results will help improve the history match and therefore the accuracy of future development prediction cases. Previous simulation studies in the Greater Burgan field identified the need for more pressure support in the Wara reservoir than what the modeled aquifer could provide. The source of this pressure support has been modeled as fluid influx from the underlying Burgan formation through faults or vertical migration where shale and carbonate barriers between the Burgan and Wara reservoirs may be locally missing. The key to determining the need for this additional pressure support is the assumption that the reported historical production is correct and properly represents the actual volume of fluid produced from the Wara reservoir. Because production data is the primary factor influencing the fluid flow and pressure characteristics in a simulation model it is imperative that this data be reviewed, validated, and updated to be as accurate as possible. The aim of this paper is to show the impact to the initialization of a reservoir simulation model by using reported data without investigating it's accuracy or relationship to historical field practices. Companion papers highlight other aspects of the ongoing effort to characterize the Wara reservoir. Background of the Wara Formation The Burgan field was discovered in 1936 with drilling of the Burgan #1 well into the Wara formation. Several delineation wells were drilled prior to World War II but full scale field development did not occur until 1946 when the first production from the field was exported. Production from the Greater Burgan Field has been primarily from the Wara and Burgan (third & fourth sand) reservoirs. P. 565

This paper describes the design, implementation and testing of the software tool designated as UV-SRNA-PDA (Universidad del Valle’s artificial neural network simulator for a personal digital assistant), which is oriented to artificial neural networks simulation and complex industrial processes identification. This application works on a PDA (personal digital assistant) Palm T5 using a customized data acquisition system. Two kinds of artificial neural networks were implemented: perceptron and multi-layer perceptron (MLP) using as learning algorithms the following: backpropagation, descendent gradient, variable learning rate and momentum. To test the proposed system, first and second order systems were selected (only the latter is reported here), finding their neural models and validating their results with MATLAB and UV-SRNA 2.0 (PC version of UV-SRNA-PDA). These tests achieved an average training error of 5.62 × 10-3 ± 3.55 × 10-4 and an average validating error of 4.56 × 10-3 ± 5.95 × 10-4. In both cases, the results were better or comparable with those from other software simulation tools. However, the typical training time on the UV-SRNA-PDA was 900 s compared to 3 s in MATLAB and 8 s in UV-SRNA 2.0.

Water is a big challenge not only in India but in many countries of the world. Machine learning and forecasting model has been employed towards water demand and ground water level prediction. But in terms of water scarcity, much less work has been carried out by employing machine learning algorithms like 'artificial neural network' (ANN) and 'grey forecasting' model for forecasting water scarcity and none has focused on historical data like water availability, water consumption for a particular area and stress value for predicting water scarcity. So accordingly, we here have developed a water scarcity prediction system based on historical data by employing 'deep neural networks' which is an advanced form of 'artificial neural networks'. We have also compared 'deep neural network' with existing machine learning algorithms such as support vector machine (SVM), logistic regression and Naive Bayes. From the analysis of algorithms based on dataset, deep neural networks have been found as the best prediction model for water scarcity.

Artificial neural network (ANN) is a modern computing paradigm. That can be used for the pattern recognition and other. Backpropagation is artificial neural network which using hidden layer addition. Computation of artificial neural network through some certain step like training phase and examination. After both the step reached, so a neural network capable to recognize pattern to be entered will be found. The purpose of this research is simulation of artificial neural network that capable to pattern recognition from output of electrocardiogram by helped of MATLAB program. Input of result electrocardiogram record, then input of data can be normalization after that data can be proccesed by backpropagation computing with two step (training phase and examination phase). Output of ANN is like explaning condition of patient is normal, rhinitis kronis or epistaksis. Keyword : rhinitis kronis, epistaksis, artificial neural network.

Load forecasting (LF) is an essential factor in power system management. LF helps the utility maximize the utilization of power-generating plants and schedule them both reliably and economically. In this paper, a novel and hybrid forecasting method is proposed, combining a long short-term memory network (LSTM) and neural prophet (NP) through an artificial neural network. The paper aims to predict electric load for different time horizons with improved accuracy as well as consistency. The proposed model uses historical load data, weather data, and statistical features obtained from the historical data. Multiple case studies have been conducted with two different real-time data sets on three different types of load forecasting. The hybrid model is later compared with a few established methods of load forecasting found in the literature with different performance metrics: mean average percentage error (MAPE), root mean square error (RMSE), sum of square error (SSE), and regression coefficient (R). Moreover, a guideline with various attributes is provided for different types of load forecasting considering the applications of the proposed model. The results and comparisons from our test cases showed that the proposed hybrid model improved the forecasting accuracy for three different types of load forecasting over other forecasting techniques.

SUMMARYResearch backgroundBiogas production from palm oil mill effluent (POME) is inherently unstable due to variations in feedstock composition and operating conditions. These fluctuations can lead to inconsistent biogas quality, variable methane content and fluctuating hydrogen sulphide (H2S) concentration. This poses significant challenges for bioscrubbers in removing H2S to meet quality standards for gas engines used for electricity generation. This research aims to address these challenges by integrating simulation models with a computer programme and artificial neural network (ANN) to predict the performance of a bioscrubber at a POME treatment plant in Johor, Malaysia.Experimental approachFirst, the process flowsheet model was simulated using a computer programme. The H2S removal was then predicted using a machine learning algorithm, specifically ANN, based on two years of historical data obtained from the biogas plant. A detailed techno-economic analysis was also carried out to determine the economic feasibility of the process.Results and conclusionsThe simulation results showed a biogas yield of 26.12 Nm3 per m3 POME, which is in line with industry data with less than 1 % deviation. The ANN model achieved a high coefficient of determination (R2) of 0.9 and a low mean squared error (MSE), with the bioscrubber reaching an H2S removal efficiency of approx. 96 %. The techno-economic analysis showed that the process is feasible with a net present value (NPV) of $131 000 and a payback period of 7 years.Novelty and scientific contributionThe integration of ANN and the computer programme provides a robust framework for predicting bioscrubber performance and ensuring stable bioscrubber operation due to their complementary strengths. ANN accurately predicts H2S removal based on daily recorded data, while the computer programme estimates parameters that are not monitored daily, such as chemical oxygen demand (COD), biological oxygen demand (BOD) and total suspended solids (TSS). This research provides valuable insights into sustainable biogas production practices and offers opportunities to improve energy efficiency and environmental sustainability in the palm oil industry.

Surface network production flow in the oil and gas industry is a complex process influenced by fluid properties, pipeline configurations, and operational conditions. Traditionally, this estimation is performed using nodal analysis or empirical correlations, both of which rely on physical assumptions and theoretical models. However, these conventional methods often introduce significant assumptions and simplifications that may not fully capture the complexities of real-world production behavior. In this work, a Data-Driven approach was used, where machine-learning models analyze historical production data to learn patterns without relying on physics-based assumptions. Trends and relationships are identified solely from historical data, eliminating the need for complex physical equations or empirical formulas. The objective is to use pure data analytics to build an accurate oil-production prediction model. This study explores the application of machine-learning techniques for oil and gas production forecasting, integrating exploratory data analysis (EDA) and predictive modeling using historical production data from different oil platforms. A Python-Dash dashboard was developed for historical monitoring of key production metrics, featuring dynamic visualization and seamless data integration. Prediction of oil, gas, and water rates was carried out using three regression models, Random Forest, XGBoost, and Support Vector Regression (SVR) with data preprocessing ensuring numerical consistency and null-free values for effective training. Model performance was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² score, with XGBoost identified as the best-performing model. Predictions on the validation dataset were visualized through line plots, highlighting production trends and fluctuations. The cleaned and forecasted data were exported for further analysis and decision-making. This approach demonstrates the potential of machine learning in optimizing oilfield operations and enhancing resource management through accurate production forecasting.

Present trends towards using high frequency and big data such as SCADA allow the acquisition of large set of well data ranging over much longer periods of time than previously imaginable such as total production history. Such production and pressure data can contain information about the reservoir at a substantially larger radius of investigation than that accessible to unconventional derivative analysis, which is limited to the interpretation of single flow periods at constant rate. By contrast, deconvolution methods, do not suffer from this constraint as they are designed to perform well production and pressure data analysis at variable flow rate. In this work, we present a deconvolution method applied to multi-fractured horizontal shale gas wells. This work offers a new solution method to the long-standing deconvolution problem and makes deconvolution a viable tool for well-test and production and pressure data analysis. The following objective is proposed for this work: To apply this method to traditional variable-rate/pressure problems, such as long-term production data, high SCADA frequency pressure gauge data and well tests having multiple wells producing. This paper will show the deconvolution method based on the work of Von Schroeter et al and Michael Levitan et al. Deconvolution is a mathematical tool that extracts the drawdown type curve from the rate and pressure history. Essentially, the deconvolution process consists of the following steps: Generate a typecurve as an initial guess Superimpose this typecurve with historical rate data to calculate synthetic pressures Calculate the error between the calculated pressures and the measured pressures Generate a new typecurve and repeat the process until the error between calculated and measured pressures is minimized Deconvolution techniques provide an alternative to unconventional diagnostic analysis, and can show additional flow regime information that would not normally be seen within the specified time-frame of the buildup test. The deconvolved typecurve can then be analyzed for each multi-fractured shale gas horizontal well using unconventional diagnostic analysis techniques to determine various reservoir characteristics such as Stimulated Reservoir Volume (SRV) fracture half length, permeability, skin, reservoir size, effective wellbore length, effective stimulated stages, and more. We validate our work with examples using daily and minute data. Upon validation, we then demonstrate the deconvolution method using a variety of field cases, including traditional well tests, turnaround wellhead gauge data as well as production data of multi-fractured horizontal wells. Our work suggests that the deconvolution method has broad applicability in variable rate/pressure problems and can be implemented in typical well test and production data analysis applications. This study highlights not only the need of combining different frequency and quality controlled data but also pressure and rate type of data as well to get a full understanding of various reservoir characteristics within the SRV.

Traditional agricultural production requires numerous human and material resources; however, agricultural production efficiency is low. The successful development of plant protection unmanned aerial vehicles (UAVs) has changed the operation mode of traditional agricultural production, saving human, material, and financial resources and significantly improving production efficiency. To summarize the process of improving the productivity of plant protection UAVs, this study established a productivity calculation model of UAVs based on the time composition of the UAV agricultural plant protection process, including spraying, turning, replenishment, and transfer times. The time required for the unmanned aircraft application process was counted through years of tracking the application process of eight different plant protection unmanned aircraft. Plot lengths of 100, 300, 500, 700, 1,000, 1,500, 2,000, 2,500, 3,000, and 3,500 m were established to calculate the theoretical productivity. The results showed that the productivity of different types of plant protection UAVs increased with an increase in plot length in the range of 100 to 1,500 m; however, when the plot length reached a certain value, the productivity growth rate slowed down or even decreased slightly. Simultaneously, based on the working area per 10,000 mu, the recommended plot length and the number of configured models for different models were recommended. If the plant protection UAV was distinguished by electric and oil power, the time utilization rate of electric plant protection UAVs was 72.7%, and the labor productivity was 56.4 mu/person·h. In contrast, the time utilization rate of the heavy load oil-powered plant protection unmanned aircraft was 86%, and the labor productivity was 63.5 mu/person ·h. This study can support plant protection UAV enterprises to optimize equipment efficiency, provide evaluation methods for the operation efficiency assessment of plant protection UAVs, provide a reference for the selection of plant protection UAVs, and provide a basis for field planning.

Labor productivity: Benchmarking and variability in Egyptian projects

Artificial intelligence based modeling and optimization of poly(3-hydroxybutyrate-co-3-hydroxyvalerate) production process by using Azohydromonas lata MTCC 2311 from cane molasses supplemented with volatile fatty acids: A genetic algorithm paradigm

A survey of approaches for implementing optical neural networks