Production Forecasts Research Articles

Time series forecasting of oil production in Enhanced Oil Recovery system based on a novel CNN-GRU neural network

An accurate prediction of oil production is critical for the oilfield development, and many deep learning models have been widely employed for this purpose. However, those methods show insufficiencies in extracting complex features from multivariable time series datasets, which leaves the prediction of oil production still challenging. In this study, a novel CNN-GRU model combining Convolutional Neural Networks (CNN) and Gate Recurrent Unit (GRU) neural network was proposed to accurately predict oil production for Enhanced Oil Recovery (EOR) performance. The CNN layer can extract the features from variables affecting oil production, and the GRU layer models temporal information using the transmitted features for prediction. The Bayesian Optimization algorithm (BO) was employed to design the optimal hyper-parameters of CNN-GRU. For evaluation purpose, two case studies were carried out with the production data from a CO2-EOR project and a waterflooding project. The prediction performance of the proposed approach was compared with typical deep learning methods and a hybrid (statistical and machine learning) method. The results of experiments and comparisons indicate that the proposed CNN-GRU model outperforms other prediction approaches. The CNN-GRU model provides future oil production of wells, enabling engineers to make informed decisions in development plan of reservoirs.

Forecasting of Maize Production in Bangladesh using ARIMA and Mixed Model Approaches

Maize (_Zea maysL._) is the most vital cereal crop in Bangladesh and, after rice and wheat, it is also the leading crop of the world. Maize is the highest-yielding grain crop, having multiple uses. It serves as a primary raw material for the production of feed, food, fodder, and fuel. Thus, maize can play an important role as an alternative and a multipurpose food crop in Bangladesh. This study considered the BBS-published secondary yearly maize data, including area and production in Bangladesh, over the period 1970-71 to 2019-20. The best-selected Box-Jenkins ARIMA model is ARIMA (0, 2, 1) for forecasting maize production all over Bangladesh. When the area of maize is considered in the mixed model, i.e., ARIMA (1, 0, 0) is the best model rather than the univariate ARIMA (0, 2, 1) model. The length of the 95% confidence interval of the forecast value for the mixed model is smaller than that for the ARIMA model. Therefore, the forecasting performance of the mixed model is better than that of the econometric model like ARIMA; the reason could be the consideration of an explanatory variable like area. Thus, the mixed model approach can be applied for policy decisions based on the forecasting of maize production in Bangladesh.

The history of UK weather forecasting: the changing role of the central guidance forecaster. Part 7: Operational forecasting in the twenty‐first century: graphical guidance products, risk assessment and impact‐based warnings

AbstractMet Office guidance forecasters continue to add value to NWP products, but in ways that could scarcely have been imagined half a century ago. We focus on how technological advances including ‘Field Modification’ have facilitated the creation of forecast products and new forms of graphical guidance to assist in the communication of the preferred weather story. We also describe a new impact‐based severe weather warnings service. This involves the interpretation of forecast outputs, including ensembles, and collaboration with other agencies to assess risks and impacts, thus enabling appropriate mitigating action to be taken in support of local and national resilience.

Enhancing Sustainable Dairy Industry Growth through Cold-Supply-Chain-Integrated Production Forecasting

Cold supply chains (CSCs) are critical for preserving the quality and safety of perishable products like milk, which plays a vital role in the daily lives of a vast population, especially in countries like India. This research centers on sustainable milk production in Northern India, with priorities of ensuring efficiency and waste reduction within the cold supply chain. Leveraging data from a prominent North India-based dairy company, Company ‘X’, an ARIMA model is applied for predicting monthly milk production trends. Utilizing the Statistical Package for the Social Sciences (IBM SPSS STATISTICS 20) software, the study forecasts Company ‘X’s monthly milk production and identifies four distinct ARIMA models based on the autocorrelation function (ACF) and the partial autocorrelation function (PACF). By comparing predicted and actual milk production values (April–October 2021), sustainability metrics are integrated into ARIMA forecasts. Implications for the dairy sector’s sustainability and alignment with the Sustainable Development Goals (SDGs) are assessed through error terms such as R squared (R2) and mean absolute percentage error (MAPE). The study promotes sustainable milk production practices in Northern India’s dairy sector, resonating with the SDGs to optimize demand–supply dynamics and foster a more environmentally conscious dairy industry.

A novel time-lagged logistic grey model and its application in forecasting energy production volume

Scientific and accurate prediction of energy production is important for exploring energy alternative paths, adjusting energy structure and industrial layout in a targeted manner, and promoting strategic energy transformation. In this paper, a time-lagged logistic grey forecasting model with harvesting term is established by combining the Logistic model, which has the ability of historical recurrence and short- and medium-term forecasting ability, and the grey forecasting model, which has the characteristics of strong adaptability and small computational effort. The least squares method is used to estimate the parameters of the new model, and the mathematical method is used to calculate the time response equation of the new model, and the modeling steps and flow chart of the new model are obtained. Finally, the oil production data of a province in China is used as the validity analysis of the model, and the new model is compared with two classical grey prediction models, three optimized grey prediction models, and one other prediction model. Through the comparison of seven indicators, the results show that the new model is significantly better than other models. Based on the validity analysis results, the new model is applied to the energy production forecast of three typical provinces in China. The horizontal and vertical comparison shows that the model can effectively predict the three kinds of energy production, and can provide technical support for the strategy and measures to adjust the energy security structure and promote the healthy and sustainable development of the energy industry.

The Destructive Sir Ivan Fire in New South Wales, Australia; Simulations Using a Coupled Fire—Atmosphere Model

The destructive Sir Ivan Dougherty fire burned 55,000 hectares around 250 km northwest of Sydney in New South Wales on 12 February 2017. Record hot temperatures were recorded in the area during the lead-in days and the fire conditions at the time were described as the ‘worst ever seen in NSW’. The observed weather conditions were hot, dry and very windy ahead of a synoptic frontal wind change during the afternoon. ‘Extreme’ to ‘catastrophic’ fire weather was predicted, and the potential for extreme fire behaviour was identified several days in advance. The Australian coupled fire–atmosphere model ACCESS-Fire has been run to explore the characteristics of the Sir Ivan fire. Several features resulting from fire–atmosphere interaction are produced in the simulations. Simulated heat flux along the fire perimeter shows increased intensity on the northern fire flank in response to gradual backing winds ahead of the main frontal wind change. Temporal and spatial variability in fire activity, seen as pulses in fire intensity and fireline wind speed, develop in response to boundary layer rolls in the wind fields. Deep moist convection consistent with the observed pyrocumulonimbus (pyroCb) cloud is simulated over the fire at around the time of the frontal wind change, and matches guidance from the ‘PyroCb Firepower Threshold’ tool, which showed transient favourable conditions. After the wind change, short-lived near-surface and elevated vortices suggest organised rotating features on the northern flank of the fire. The coupled model captures processes that cannot be produced in uncoupled fire predictions and that are not captured in current operational meteorological forecast products provided to Australian fire agencies. This paper links the features from coupled simulations to available observations and suggests pathways to embed the learnings in operational practice.

An innovative adaptive hybrid prediction model based on deep learning methods (CEEMDAN-GRU) for green hydrogen production, In case study: Turkey

Due to global warming, countries have turned to renewable and clean energy sources. Among these sources, they have started to prefer hydrogen energy and green hydrogen production as the cleanest type of energy in producing hydrogen energy. In this study, an innovative adaptive hybrid forecasting model based on deep learning was proposed to be used in green hydrogen production forecasting. The energy required for the electrolysis method used in hydrogen production was planned to be provided by wind energy. A new perspective was introduced in determining hydrogen production with the proposed model. In particular, the wind regime in 9 provinces selected for the case study was determined and the most suitable wind turbine power for the system was calculated according to this regime by applying the decomposition method to wind speeds, the most important input of wind energy. Depending on the determined turbine powers, the amount of hydrogen that can be produced was estimated. In the prediction process, 70 % of the data was used as training data (24528), 5 % as validation data (1752) and 25 % as test data (8760). The highest accuracy rate obtained in hydrogen energy forecasting among the selected provinces is 92.045 %. The lowest error and the highest regression rates (The root mean square error (RMSE): 0.600, Mean absolute percentage error (MAPE): 0.100 and the coefficient of determination (R2): 0.990) in wind speed prediction were realized in İzmir province. The highest wind turbine power was calculated as 225 kW.

The importance of oxygen for explaining rapid shifts in a marine fish.

Large-scale shifts in marine species biogeography have been a notable impact of climate change. An effective explanation of what drives these species shifts, as well as accurate predictions of where they might move, is crucial to effectively managing these natural resources and conserving biodiversity. While temperature has been implicated as a major driver of these shifts, physiological processes suggest that oxygen, prey, and other factors should also play important roles. We expanded upon previous temperature-based distribution models by testing whether oxygen, food web productivity, salinity, and scope for metabolic activity (the Metabolic Index) better explained the changing biogeography of Black Sea Bass (Centropristis striata) in the Northeast US. This species has been expanding further north over the past 15 years. We found that oxygen improved model performance beyond a simple consideration of temperature (ΔAIC = 799, ΔTSS = 0.015), with additional contributions from prey and salinity. However, the Metabolic Index did not substantially increase model performance relative to temperature and oxygen (ΔAIC = 0.63, ΔTSS = 0.0002). Marine species are sensitive to oxygen, and we encourage researchers to use ocean biogeochemical hindcast and forecast products to better understand marine biogeographic changes.

Towards the selection of a longer record of quantitative precipitation forecast dataset from TIGGE ensembles for India during the monsoon season

ABSTRACT A reliable forecast of summer monsoon precipitation is crucial in India. To select a longer record of forecast data from the THORPEX Interactive Grand Global Ensemble (TIGGE) archives, we applied two criteria: the length of the dataset should be at least 10 years of continuous record, and the forecast product should have at least 20 ensemble members for a lead time of minimum 5 days. We evaluate the ensemble quantitative precipitation forecasts (QPFs) obtained from the four agencies throughout the monsoon season (June to September) from 2011 to 2020 in 22 river basins of India in forecasting normal and extreme precipitation events. The Integrated Multi-satellite Retrievals for Global Precipitation Measurement (IMERG) is used as observation data. The proficiency of QPFs is evaluated using six criteria from deterministic, dichotomous, and probabilistic error statistics. The error values are classified into three categories – low, moderate, and high. A Forecast Reliability Index is formulated using the given four QPFs, and three categories for each of the six error statistics to answer (a) which QPF shows better performance in which river basin and (b) whether any conclusion can be made on the overall performance of a QPF for all the River Basins of India.

Very short-term scenario-based probabilistic forecasting of PV park power production

Very short-term scenario-based probabilistic forecasting of PV park power production

Bi-objective sales planning using machine learning for industrial valves

Accurate prediction and forecasting of industrial products’ consumption, enables up-to-date and efficient supply, replacement of worn-out items, and prevention of resource wastage. Planning and forecasting the usage of industrial products can help often based on historical years’ performance and environmental factors, using either traditional methods or smart systems. However, the instability of some sales behavior in certain products and the lack of previous data for new products or sales offices can create problems in intelligent systems. In this paper, we present a hybrid and bi-objective model in the form of a business intelligence system that first fits an appropriate function to the products, providing a new estimated combination for the type and sales amount of all products, while taking into account the profit margin. This new intelligent system allows for flexible planning for the company, generating a special scenario for each new input strategy. Furthermore, using machine learning and based on similarity measurements and the company’s previous data, we predict the sales behavior for new products and sales offices in their first year of operation. Finally, the model announces the sales trend of each product in different time periods, separately for each sales office, taking into account the previous two stages. The current investigation outlines the integration of the proposed model into the business intelligence system of Mirab Valves Company, a reputable manufacturer of industrial valves, and its subsequent effective application as an exemplar. The model’s efficacy in forecasting sales of new products and sales offices is established at 79% and 92%, respectively.

Forecasting electricity production from various energy sources in Türkiye: A predictive analysis of time series, deep learning, and hybrid models

When it comes to energy sources used in electricity production, the future forecasting of electricity production from renewable energy sources is highly important for both the success of technological advancements in the renewable energy field and energy security. To forecast electricity production from renewable energy sources reliably, it is necessary to accurately model the components of the relevant series. The central argument of this paper is that the various components derived from electricity production data, particularly the residual component, retain valuable predictive information despite their intricate and nonlinear nature. While linear modelling may be highly accurate initially, repeating residuals within linear structures is a discrepancy in terms of data type and methodology. In this paper, different types of hybrid models that combine a decomposition method and both machine learning and statistical approaches are suggested for forecasting electricity production from different energy sources.

Assessing the ability of a new seamless short-range ensemble rainfall product to anticipate flash floods in the French Mediterranean area

Abstract. Flash floods have dramatic economic and social consequences, and efficient adaptation policies are required to reduce their impacts, especially in the context of global change. Developing more efficient flash flood forecasting systems can largely contribute to these adaptation requirements. The aim of this study was to assess the ability of a new seamless short-range ensemble quantitative precipitation forecast (QPF) product, called PIAF-EPS (Prévision Immédiate Agrégée Fusionnée ensemble prediction system) and recently developed by Météo-France, to predict flash floods when used as input to an operational hydrological forecasting chain. For this purpose, eight flash flood events that occurred in the French Mediterranean region between 2019 and 2021 were reanalysed, using a hydrological-modelling chain similar to the one implemented in the French Vigicrues Flash operational flash flood monitoring system. The hydrological forecasts obtained from PIAF-EPS were compared to the forecasts obtained with different deterministic QPFs from which PIAF-EPS is directly derived. The verification method applied in this work uses scores calculated on contingency tables and combines the forecasts issued on each 1 km2 pixel of the territory. This offers a detailed view of the forecast performances, covering the whole river network and including the small ungauged rivers. The results confirm the added value of the ensemble PIAF-EPS approach for flash flood forecasting, in comparison to the different deterministic scenarios considered.

Maize Production Forecasting in Iraq: A Box-Jenkins Approach for the Period of 2022-2026

This study aims to forecast the production of Iraq’s maize crop using Auto Regressive Integrated Moving Average (ARIMA) models. Using the semi-annual data for the period 1980-2021, the production of the maize crop was forecasted for 5 years, starting from 2022 to 2026. The data were obtained from the Ministry of Planning and International Cooperation, Planning and Monitoring Department, Agricultural Statistics Department, Iraq. The forecasted production of maize in Iraq during the period 2021-2026 is characterized by fluctuations between highs and lows, similar to the production of maize during the study period. The highest expected production value of maize in Iraq was in the second half of 2023, reaching 585 thousand tons, while the lowest expected production was 500 thousand tons in the first half of 2022. This study is significant in providing valuable insights that can guide the formulation of effective policies regarding maize production, pricing, and consumption in the country.

Implementation of Asynchronous Distributed Gauss-Newton Optimization Algorithms for Uncertainty Quantification by Conditioning to Production Data

Summary Previous implementation of the distributed Gauss-Newton (DGN) optimization algorithm ran multiple optimization threads in parallel, employing a synchronous running mode (S-DGN). As a result, it waits for all simulations submitted in each iteration to complete, which may significantly degrade performance because a few simulations may run much longer than others, especially for time-consuming real-field cases. To overcome this limitation and thus improve the DGN optimizer’s execution, we propose two asynchronous DGN (A-DGN) optimization algorithms in this paper. The two A-DGN optimization algorithms are (1) the local-search algorithm (A-DGN-LS) to locate multiple maximum a-posteriori (MAP) estimates and (2) the integrated global-search algorithm with the randomized maximum likelihood (RML) method (A-DGN + RML) to generate hundreds of RML samples in parallel for uncertainty quantification. We propose using batch together with a checking time interval to control the optimization process. The A-DGN optimizers check the status of all running simulations after every checking time frame. The iteration index of each optimization thread is updated dynamically according to its simulation status. Thus, different optimization threads may have different iteration indices in the same batch. A new simulation case is proposed immediately once the simulation of an optimization thread is completed, without waiting for the completion of other simulations. We modified the training data set updating algorithm using each thread’s dynamically updated iteration index to implement the asynchronous running mode. We apply the modified QR decomposition method to estimate the sensitivity matrix at the best solution of each optimization thread by linear interpolation of all or a subset of the training data to avoid the issue of solving a linear system with a singular matrix because of insufficient training data points in early batches. A new simulation case (or search point) is generated by solving the Gauss-Newton (GN) trust-region subproblem (GNTRS) using the estimated sensitivity matrix. We developed a more efficient and robust GNTRS solver using eigenvalue decomposition (EVD). The proposed A-DGN optimization methods are tested and validated on a 2D analytical toy problem and a synthetic history-matching problem and then applied to a real-field deepwater reservoir model. Numerical tests confirm that the proposed A-DGN optimization methods can converge to solutions with matching quality comparable to those obtained by the S-DGN optimizers, saving on the time required for the optimizer to converge by a factor ranging from 1.3 to 2 when compared to the S-DGN optimizer depending on the problem. The new A-DGN optimization algorithms improve efficiency and robustness in solving history-matching or inversion problems, especially for uncertainty quantification of subsurface model parameters and production forecasts of real-field reservoirs by conditioning production data.

An Integrated Approach for Wildfire Photography Telemetry using WRF Numerical Forecast Products

Forest fire detection using machine vision has recently emerged as a hot research topic. However, the complexity of background information in smoke images often results in deep learning models losing crucial details while capturing smoke image features. To address this, we present a detection algorithm called Multichannel Smoke YOLOv5s (MCSYOLOv5s). This algorithm comprises a smoke flame detection module, multichannel YOLOv5s (MC‐YOLOv5s), and a smoke cloud classification module, Smoke Classification Network (SCN). MC‐YOLOv5s uses a generative confrontation structure to design a dual‐channel feature extraction network and adopts a new feature cross-fusion mechanism to enhance the smoke feature extraction ability of classic YOLOv5s. The SCN module combines Weather Research and Forecasting numerical forecast results to classify smoke and clouds to reduce false positives caused by clouds. Experimental results demonstrate that our proposed forest fire monitoring method, MCS‐YOLOv5s, achieves higher detection accuracy of 95.17%, surpassing all comparative algorithms. Moreover, it effectively reduces false alarms caused by clouds.

Short-Term Forecasting of Daily Pan Evaporation Using Corrected Numerical Weather Forecasts Products

Short-Term Forecasting of Daily Pan Evaporation Using Corrected Numerical Weather Forecasts Products

Downscaled seasonal forecasts for the California Current System: Skill assessment and prospects for living marine resource applications

Ocean forecasting is now widely recognized as an important approach to improve the resilience of marine ecosystems, coastal communities, and economies to climate variability and change. In particular, regionally tailored forecasts may serve as the foundation for a wide range of applications to facilitate proactive decision making. Here, we describe and assess ~30 years of retrospective seasonal (1–12 month) forecasts for the California Current System, produced by forcing a regional ocean model with output from a global forecast system. Considerable forecast skill is evident for surface and bottom temperatures, sea surface height, and upper ocean stratification. In contrast, mixed layer depth, surface wind stress, and surface currents exhibit little predictability. Ocean conditions tend to be more predictable in the first half of the year, owing to greater persistence for forecasts initialized in winter and dynamical forecast skill consistent with winter/spring influence of the El Niño–Southern Oscillation (ENSO) for forecasts initialized in summer. Forecast skill above persistence appears to come through the ocean more than through the atmosphere. We also test the sensitivity of forecast performance to downscaling method; bias correcting global model output before running the regional model greatly reduces bias in the downscaled forecasts, but only marginally improves prediction of interannual variability. We then tailor the physical forecast evaluation to a suite of potential ecological applications, including species distribution and recruitment, bycatch and ship-strike risk, and indicators of ecosystem change. This evaluation serves as a template for identifying promising ecological forecasts based on the physical parameters that underlie them. Finally, we discuss suggestions for developing operational forecast products, including methodological considerations for downscaling as well as the respective roles of regional and global forecasts.

Ability of the GRAPES Ensemble Forecast Product to Forecast Extreme Temperatures over the Tibetan Plateau

Due to climate change, extreme temperature events are receiving increased attention. Based on the climate state deviation and threat score (TS), the ability of the Global/Regional Assimilation and Prediction System (GRAPES) ensemble model to forecast extreme temperature events was examined. The “optimal” Extreme Forecast Index (EFI) was derived for plateau forecasting, and its predictability was examined based on the receiver operating characteristic (ROC) curve method. Meanwhile, the applicability of the Shift of Tails (SOT) index to extreme temperature forecasting was analyzed using extreme temperature cases. Results showed that the GRAPES model has a warm bias for both summer extreme high temperature and winter extreme low temperature, and the warm bias decreases slightly with an increase in the forecasting lead time. The ensemble mean and median forecasts are less effective, and the maximum value is more predictable. However, for the ensemble forecast model, the extreme information in its forecast is more unstable, and the limitation of the extreme temperature forecast in the plateau region is higher. With different forecast lead times, the TS tends to increase and then decrease with an increase in the EFI threshold, which means that there is an optimal EFI. The optimal EFI thresholds for summer extreme high-temperature forecasts are all less than −0.5, while for winter extreme low-temperature forecasts, they are almost all less than 0. From the ROC curves, the EFI has a certain level of predictability for summer extreme high temperatures but poorer forecasting effects. Furthermore, the EFI has some predictability for extreme summer high temperatures, but the prediction effect is poor. For the extremely low temperatures in winter, which are poorly predicted by the model itself, post-processing of the extreme information predicted by the model with the EFI can improve the forecasting effect of the model. Through analysis of individual cases, it was found that the extreme intensity reflected by the SOT_+ (0.9) index of the model was closer to reality for the prediction of extremely high temperatures, whereas for the prediction of extremely low temperatures, the extreme intensity indicated by the SOT_− (0.1) index of the model was weaker. Therefore, the SOT index can play an important auxiliary role in the prediction of the intensity of extreme events based on the EFI.

Solar parking lot management: An IoT platform for smart charging EV fleets, using real-time data and production forecasts

The fast transition to the electrification of the energy system, combined with an exponential growth of the market share of electric vehicles, is leading to a tight interrelation between electric energy production and transportation, two prominent sectors in fossil fuels consumption and greenhouse gas emissions. Accelerating this process, the management of electric fluxes, aiming at optimizing production and demand coupling, plays a crucial role in reaching the net-zero emission target. The proposed software platform is designed to optimally manage the energy fluxes for a solar powered parking lot, serving a fleet of electric vehicles; the real-time knowledge of energy production and demand, in conjunction with forecasted power generation, allows the maximization of renewable energy self-consumption, thus reducing the exchange with the external grid. The software platform can work either in design mode, allowing the dimensioning of the various parking lot components, or in real-time mode managing instantaneously the energy balance. As a case study, it is tested on the 2019 parking lot mobility data of a research center, assuming a complete transformation of the then existing fleet of employees' cars to electric vehicles. A comparison of the resulting energy flows with those projected by an established commercial tool is performed, as well as a preliminary economic evaluation. Both consistency of the simulation results and favorable economics validate the presented smart charging algorithm and Internet of Things platform for the real-time energy management of a solar parking lot.