Current Forecast Models Research Articles

Innovative machine learning for drilling fluid density prediction: a novel central force search-adaptive XGBoost in HPHT environments

Oil and gas industries are facing a special dilemma when it comes to high-pressure, high-temperature (HPHT) drilling as the accurate forecasting of the drilling fluid density (DFD) is a vital factor for safe and efficient operations. Complicated relationships and inconsistencies in HPHT situations are rarely mapped by current forecasting models, while their buggy performance and safety risks during drilling can be underestimated. In this research, we propose a novel machine learning (ML) approach to enhance the accuracy of DFD anticipation under HPHT conditions: central force search-adaptive extreme gradient boosting (CFS-XGB). This paper uses a dataset that has drilling variables together with the DFD for HPHT situations to examine the accuracy of the CFS-XGB model. Excluding the abnormalities of data or mistakes, the reliability of the original data is maintained by applying min–max normalization. After that, finding the important features with the help of the boosted principal component analysis (BPCA) approach to the normalized data will ensure a major improvement in the CFS-XGB methodology’s prediction efficacy. This research is experimented in the Python platform, and the performance of the proposed CFS-XGB method is analyzed in terms of MSE, R2, and AAPRE metrics. The suggested approach performs better than the current methods in forecasting the drilling fluid concentration in HPHT settings, according to the experimental data. This development in predictive modeling helps increase the productivity and safety of drilling operations, which will eventually help the oil and gas sector manage the challenges posed by HPHT drilling settings.

An adaptive network with consecutive and intertwined slices for real-world time-series forecasting

Real-world systems are chiefly comprised of multiple sensors and devices, whose instantaneous data and upcoming tendencies are demanded by the decision makers to formulate future schemes. Accuracy and timeliness are both of paramount significance. Thereby, although the deep forecasting models are promising, the space and resources are often limited in reality, rendering their adaptability requisite. Unfortunately, the majority of current deep forecasting models are far from adaptive and acquire heavy hyper-parameter tuning processes to obtain the satisfactory performances. Moreover, their strategies to reduce the model complexities sometimes bring extra hyper-parameters. To tackle these issues, we propose AdaNS: an Adaptive Network with consecutive and intertwined Slices. The data-driven features of time-series in frequency domain are used in AdaNS to adaptively determine the model structure, as well as hyper-parameters, and categorize variables. In accordance with these frequency-based features, input sequences are first sliced in a consecutive way to extract the universal features and then in an intertwined way to extract the local features, for hierarchical and comprehensive forecasting. Extensive experiments show that AdaNS achieves state-of-the-art performances on fourteen benchmarks, virtually without any hyper-parameter tuning. The source code is available at https://github.com/OrigamiSL/AdaNS.

Comparing statistical forecasting methods for modelling respiratory virus healthcare demand

Abstract Background Emergency departments in the United Kingdom are under sustained pressure with rising demand for healthcare, gradually decreasing the functionality of the NHS. Forecasts can aid management in the allocation of appropriate healthcare supplies and staffing needs in advance of an expected surge, as well as allow stakeholders to assess most likely outcomes and potential worst-case scenarios. This is especially valuable during the seasonal waves of respiratory infections. Respiratory viruses are usually concentrated in a 6-8 week seasonal surge during the winter period, creating large pressure on the health system. Current forecast models’ performance depreciates significantly after 1 week. This analysis will forecast 6 weeks of respiratory health admissions, comparing traditional and newly emerging forecasting methods. Methods Using 20 years of English hospital admissions data, we evaluated both within season training models (2-20 weeks) and longer term seasonal models (1-10 years), to forecast 6 weeks of hospital admissions. Respiratory admissions were defined according to ARI/ILI ICD10 codes assigned in hospital, stratified by age and region. Models were iteratively constructed, trained and probabilistic forecasts were evaluated across the respiratory season of September to April using Weighted Interval Score. Averages of each model across iterations were generated for comparison. Results For non-seasonal models, shorter model training lengths created better forecast models for 6 weeks. For seasonal models, optimal training length varied across model complexity. Simple models performed best at forecasting 1 week, however performance deteriorated the most as the forecast window increased. Overall, the Prophet model performed best on average at forecasting 6 weeks across all scenarios. Conclusions Applying our framework for optimal model selection in forecasting analysis will help to inform better practice for future health demand modelling. Key messages • This analysis will inform better practice for future health demand forecasting 6 weeks in advance, allowing for preparation of resources for seasonal surges in healthcare demand. • This analysis suggests using models with modest levels of increased complexity over simpler models could significantly improve forecast performance in the short-medium term.

FAFTransformer: Multivariate time series prediction method based on multi‐period feature recombination

AbstractMultivariate time series forecasting is widely used in various fields in real life. Many time series prediction models have been proposed. The current forecasting model lacks the mining of correlation between sequences based on different periods and correlation of periodical features between different periods when dealing with data. In this paper, we propose a multivariate data prediction model FAFTransformer based on the reorganization of multi‐periodic features, which first extracts the multi‐periodic information of the time series using the method of frequency domain analysis. The temporal dependencies within sequences are then captured using convolution based on different periods, and the correlations between sequences are learned by combining the multivariate attention mechanism to obtain the intra‐sequence and inter‐sequence correlations under the same period. Finally, period fusion is proposed to capture the correlation of period characteristics between different periods. The experimental results show that the model achieves the best results on multiple datasets compared to the latest seven predictive models for time‐series data.

Southern Hemisphere baroclinic activity in seasonal forecasts

Accurate prediction of mid-latitude baroclinic activity is extremely relevant for understanding global climate dynamics and improving long-term weather forecasts. However, current seasonal forecast models struggle to accurately represent the variability of baroclinic activity in the Southern Hemisphere, which may affect their reliability and usefulness. Baroclinic instability in the mid-latitudes is a significant component of the climate system, as it is associated with the meridional transport of a large amount of energy and momentum. Therefore, the ability of the models to correctly predict the properties of the atmospheric circulation in this latitudinal region is a very important requirement. The aim of this study is to estimate the energy of atmospheric phenomena typical of the mid-latitudes, such as baroclinic perturbations, and to understand how seasonal forecasts can be practically used to assess the energy transfer in the atmosphere. We compare the Southern Hemisphere mid-latitude winter variability of the seasonal forecasts of the ECMWF, DWD and Météo France forecasting systems with the ERA5 reanalysis. The analysis is performed by computing the Hayashi spectra of the 500-hPa geopotential height field. Both the reanalysis and the seasonal forecast show a series of peaks in the spectral region of eastward-travelling waves, which corresponds to the high frequency and high wavenumber domain. We quantify the amount of energy released from the atmosphere by calculating the Baroclinic Amplitude Index. The results suggest that seasonal forecasts may not accurately capture the variability of geopotential height power spectra in the Southern Hemisphere, which poses a challenge in correctly distributing the energy over spatial and temporal dimensions. This study will show that this problem is particularly pronounced for wavenumber 4 over a period of 8 days. This misrepresentation likely contributes to the uncertainties in precipitation forecasting, with discrepancies exacerbated by a suboptimal description of baroclinic instability and dynamical components in the models. Our findings highlight the need for an improved representation of baroclinic processes in seasonal forecast models, which could lead to substantial advancements in long-term weather prediction capabilities and in a more complete understanding of climate dynamics.

Current state and forecast model development of the agrarian structure of the Southern Federal District

Current state and forecast model development of the agrarian structure of the Southern Federal District

Solar energy prediction in IoT system based optimized complex-valued spatio-temporal graph convolutional neural network

The accurate prediction of solar energy generation is significant for efficient energy management in Internet of Things (IoT) devices. However, current forecasting models frequently fail to account for the dynamic nature of weather conditions. Also, traditional methods often have limited accuracy and scalability. This paper proposes Solar Energy Prediction in IoT system based optimized Complex-Valued Spatio-Temporal Graph Convolutional Neural Network (SEP-CVSGCNN-IoT) to overcome the limitations of existing models. Initially, the data are collected from solar panel and weather forecast. The collected data is given to the pre-processing using Data-Adaptive Gaussian Average Filtering (DAGAF) to remove the unwanted data and replace missing data. The pre-processed data is given into Nutcracker Optimization (NCO) algorithm for selecting optimal features. Then, the selected features are given to the Complex-Valued Spatio-Temporal Graph Convolutional Neural Network (CVSGCNN) for solar energy prediction. Finally, Dipper Throated Optimization Algorithm (DTOA) is proposed to enhance the weight parameter of CVSGCNN classifier, which precisely predicts solar energy in IoT. The proposed SEP-CVSGCNN-IoT method provides 18.46%, 26.34, 15.69 and 20.84% higher accuracy and 18.24%, 23.77, 24.34 and 16.29% lower mean absolute error when analyzed with existing techniques, such as deep learning enhanced solar energy prediction and AI-driven IoT (DL-ESEF-AI), towards efficient renewable energy prediction using deep learning (TEE-REP-DL), a new deep learning method for effectual forecasting of short-term PV energy production (DL-EF-SPEP) and metaheuristic-dependent hyper parameter tuning for recurrent deep learning: application to the solar energy generation prediction (HT-RDL-PSEG) respectively.

A new hybrid deep neural network for multiple sites PM2.5 forecasting

Many studies have confirmed that fine particulate matter (PM2.5) poses significant hazards to both human health and the ecological environment. Predicting future trends in PM2.5 concentrations is crucial for preventing air pollution hazards to human health. However, current machine learning-based forecasting models often focus on specific regions or sites, resulting in poor spatial generalization performance. To address this issue, this study utilizes ERA5 meteorological reanalysis data, MERRA2 assimilated aerosol optical depth (AOD) data, and ground pollutant monitoring site data to construct a three-dimensional dataset. A novel hybrid deep neural network model (D_GAT) is proposed to simultaneously forecast the future 72h PM2.5 concentration trends for all sites in China. The D_GAT model combines the advantages of a graph attention network and a long short-term memory neural network, which can effectively aggregate spatial information between sites and simulate the spatial transport process and time series change characteristics of pollutant particles. Moreover, the proposed calculation method for attention scores quantified based on the actual pollutant propagation characteristics, combined with the upper atmosphere pollution transport process represented by AOD, can better express the pollution contributions of different neighboring sites to the predicted central site. Experimental results show that, compared to four other baseline models, the novel model achieves an average R2 of 0.732 for all sites in 72-h prediction, which is the highest among the five models, and the prediction accuracy of 72h is also in the forefront compared with the current similar research. The RMSE and MAE are 14.63 μg/m3 and 9.49 μg/m3, respectively, which are 2–4 μg/m3 lower than the other four baseline models, indicating that it has higher reliability and can achieve the goal of timely prediction and early warning. Overall, the new model is an effective tool for multiple sites generalization forecasting.

CLIMAEXTREMO: A New Risk Indicator for the Health Risk to Building Occupants during Extreme Weather Events in Portugal

Portugal is the country in Europe where the death rate in winter and summer has the highest correlation with outdoor temperatures. The Portuguese National Institute of Public Health Ricardo Jorge has developed a national warning system for heat waves called ICARO, which has been in place since 1999 (and is the oldest in Europe). However, it presents some limitations, namely, the low spatial resolution (five regions in Portugal’s mainland), the low temporal forecasting period (one day), and the fact that it was only accessible to health authorities until very recently. This work describes the development of a new public dashboard that uses a new early warning index for extreme weather events, the CLIMAEXTREMO index, which extends the current warning system by improving the current forecasting models for risk by integrating new sources of public data and increasing the spatial and time resolution of the warnings to the municipality or the parish level. The new index is a combination of a new model to estimate the relative mortality increase (updating the model used in ICARO) together with a model of the indoor temperature of building archetypes for all municipalities and a vulnerability index that considers socio-demographic economic indicators. This work discusses the results of the new risk indicator for the heat waves that occurred in Portugal at the end of June and mid-August 2023, and it shows that the index was able to indicate a high risk for the municipalities that had an increase in the number of deaths during that period.

Forecast combination using grey relational analysis and Choquet fuzzy integral for container throughput forecasting

Utilizing the accurate and reliable demand forecasting model for the port logistics industry decision makers, can prevent misguided decisions ensuing from inaccurate forecasting. Current forecasting models of container throughput forecasting focus on the development of single or related hybrid models. However, these studies focus on improving the forecast accuracy, while neglecting the risk of failure. Combination forecasting can improve the forecast accuracy and reduce the risks from model selection failure. The previous research on port container throughput (PCT) combination forecasting focused on using a small number of linear models to generate the combined values, and neglected the nonlinear combined models reflecting the interaction between variables. Given the significance of combination forecasting for the PCT prediction, this study establishes a nonlinear combined model using the grey relational analysis (GRA) and Choquet fuzzy integral. The empirical results indicate that the proposed combined model outperforms both the other considered linear and nonlinear models. The findings assist the port decision-makers in both the public and private sectors for understanding the future PCT, and devising timely response plans aligned with actual circumstances and trends, besides formulating the appropriate development plans and decisions to modify the current situation or sustain competitive advantages.

Unlocking Inventory Efficiency: Harnessing Machine Learning for Sales Surge Prediction

Purpose: Sales forecasting plays a crucial role in inventory optimization for retail stores, especially during special events such as promotions, advertisements, holiday season, weather, social and economic situations etc. These events drive significant changes in customer buying patterns. Some of these events are captured in the current forecasting models as part of trend, seasonality, and cyclicality. But many times, unexpected local events such as extreme weather conditions, riots, and regional events such as marathons, concerts have a significant impact on sales surges which are usually not captured in the sales forecast. This leads to inventory being out of stock and store managers placing last-minute manual orders. By accurately predicting these sales pattern changes, retailers can make informed decisions, ensuring optimal inventory levels and maximizing profits. Methodology: In this paper, a data-driven solution was discussed that leverages machine learning models to predict sales pattern changes and surges during local events in a specific geographical location. Web scraping can be used to gather data on local events from a range of online sources, including Google News, local news channels, and social media platforms. By extracting pertinent details about upcoming events, it is possible to compile a thorough database of local happenings. Findings: Data Analysis of historical sales data mapped to its local events can provide insights on key department-categories where there is a surge in sales. Machine learning models can be used to analyze, experiment and train historical sales data in conjunction with the events data. Unique contribution to theory, practice and policy: Machine learning models would be trained to capture the complex relationships between different local events and their impact on sales. Therefore the study recommends using the machine learning approaches specified to consider various factors, such as event type, location, duration, and historical sales patterns, our models can effectively predict sales fluctuations during specific events.

Deep Learning in Carbon Neutrality Forecasting

With the growing urgency of global climate change, carbon neutrality, as a strategy to reduce greenhouse gas emissions into the atmosphere, is increasingly seen as a critical solution. However, current forecasting models still face significant challenges and limitations in accurately and effectively predicting carbon emissions and their associated effects. These challenges largely stem from the complexity of carbon emission data and the interplay of anthropogenic and natural factors. To overcome these obstacles, the authors introduce an advanced forecasting model, the SSA-Attention-BIGRU network. This model ingeniously integrates an external attention mechanism, bidirectional GRU, and SSA components, allowing it to synthesize various key factors and enhance prediction accuracy when forecasting carbon neutrality trends. Through experiments on multiple datasets, the results demonstrate that, compared to other popular methods, the SSA-Attention-BIGRU network significantly excels in prediction accuracy, robustness, and reliability.

A deep learning LSTM-based approach for forecasting annual pollen curves: Olea and Urticaceae pollen types as a case study

Airborne pollen can trigger allergic rhinitis and other respiratory diseases in the synthesised population, which makes it one of the most relevant biological contaminants. Therefore, implementing accurate forecast systems is a priority for public health. The current forecast models are generally useful, but they falter when long time series of data are managed. The emergence of new computational techniques such as the LSTM algorithms could constitute a significant improvement for the pollen risk assessment. In this study, several LSTM variants were applied to forecast monthly pollen integrals in Málaga (southern Spain) using meteorological variables as predictors. Olea and Urticaceae pollen types were modelled as proxies of different annual pollen curves, using data from the period 1992–2022. The aims of this study were to determine the LSTM variants with the highest accuracy when forecasting monthly pollen integrals as well as to compare their performance with the traditional pollen forecast methods. The results showed that the CNN-LSTM were the most accurate when forecasting the monthly pollen integrals for both pollen types. Moreover, the traditional forecast methods were outperformed by all the LSTM variants. These findings highlight the importance of implementing LSTM models in pollen forecasting for public health and research applications.

Potential Predictability of the Madden‐Julian Oscillation in a Superparameterized Model

AbstractThe Madden‐Julian Oscillation (MJO) is a promising target for improving sub‐seasonal weather forecasts. Current forecast models struggle to simulate the MJO due to imperfect convective parameterizations and mean state biases, degrading their forecast skill. Previous studies have estimated a potential MJO predictability 5–15 days higher than current forecast skill, but these estimates also use models with parameterized convection. We perform a perfect‐model predictability experiment using a superparameterized global model in which the convective parameterization is replaced by a cloud resolving model. We add a second “silent” cloud resolving component to the control simulation that independently calculates convective‐scale processes using the same large‐scale forcings. The second set of convective states are used to initialize forecasts, representing uncertainty on the convective scale. We find a potential predictability of the MJO of 35–40 days in boreal winter using a single‐member ensemble forecast.

Predictable decadal forcing of the North Atlantic jet speed by sub-polar North Atlantic sea surface temperatures

Abstract. It has been demonstrated that decadal variations in the North Atlantic Oscillation (NAO) can be predicted by current forecast models. While Atlantic Multidecadal Variability (AMV) in sea surface temperatures (SSTs) has been hypothesised as the source of this skill, the validity of this hypothesis and the pathways involved remain unclear. We show, using reanalysis and data from two forecast models, that the decadal predictability of the NAO can be entirely accounted for by the predictability of decadal variations in the speed of the North Atlantic eddy-driven jet, with no predictability of decadal variations in the jet latitude. The sub-polar North Atlantic (SPNA) is identified as the only obvious common source of an SST-based signal across the models and reanalysis, and the predictability of the jet speed is shown to be consistent with a forcing from the SPNA visible already within a single season. The pathway is argued to be tropospheric in nature, with the SPNA-associated heating extending up to the mid-troposphere, which alters the meridional temperature gradient around the climatological jet core. The relative roles of anthropogenic aerosol emissions and the Atlantic Meridional Overturning Circulation (AMOC) at generating predictable SPNA variability are also discussed. The analysis is extensively supported by the novel use of a set of seasonal hindcasts spanning the 20th century and forced with prescribed SSTs.

Nonparametric Multivariate Probability Density Forecast in Smart Grids With Deep Learning

This paper proposes a nonparametric multivariate density forecast model based on deep learning. It not only offers the whole marginal distribution of each random variable in forecasting targets, but also reveals the future correlation between them. Differing from existing multivariate density forecast models, the proposed method requires no a priori hypotheses on the forecasted joint probability distribution of forecasting targets. In addition, based on the universal approximation capability of neural networks, the real joint cumulative distribution functions of forecasting targets are well-approximated by a special positive-weighted deep neural network in the proposed method. Numerical tests from different scenarios were implemented under a comprehensive verification framework for evaluation, including the very short-term forecast of the wind speed, wind power, and the day-ahead forecast of the aggregated electricity load. Testing results corroborate the superiority of the proposed method over current multivariate density forecast models considering the accordance with reality, prediction interval width, and correlations between different random variables.

Development of hybrid neural network and current forecasting model based dead reckoning method for accurate prediction of underwater glider position

Buoyancy-driven underwater gliders are considered to be advanced platforms for large-scale ocean exploration. However, it is greatly affected by ocean currents, and traditional dead reckoning navigation methods are inadequate in accurately predicting its own position, causing great difficulties in underwater target detection. To solve this problem, a navigation estimation method based on the current prediction model and a convolutional neural network-long short-term memory hybrid neural network is proposed in this paper to predict the position of underwater gliders. Analysis of the experimental results shows that the hybrid neural network model trained with underwater glider sea trial data and simulated motion data can predict the glider speed more accurately than the current-assisted dead reckoning navigation, and can predict the relative position of the glider more accurately with the updated feedback from the current prediction model. The test results show that the data-driven prediction method can greatly help to predict the position of underwater gliders in the absence of other underwater positioning and navigation equipment.

Smart transformation of the energy industry: basic principles and components

Introduction. With the development of modern technologies, the world is changing. Every branch of the economy needs transformation for adequate growth. Energy is no exception. Ukraine and the world are trying to transition to a digital economy and form a digital ecosystem of states. Given the high impact of energy on the economy and the implementation of the state’s digital ecosystem, it is crucial to choose the right long-term strategy for developing this industry while simultaneously reducing the impact on the environment. One of these ways is smart energy transformation, a gradual transition from using fossil fuels to environmentally friendly energy sources.The article aims to research the development of the smart energy sector’s technologies and their perspectives.Methods. Investigating the smart transformation trends and processes was provided using Google Trends Tools on the frame of systematic approach and analysing the development dynamic of innovative strategies implementation.Results. The main problems of traditional energy, caused by rising energy prices, which in turn are related to the exhaustion of readily available fields of organic and nuclear fuels, as well as frequent accidents at nuclear power plants, which in turn caused the need to analyse the state of energy consumption at the current stage of development. Against the background of problems with fossil energy sources, one of the key global trends in the development of the energy industry is the development of alternative energy sources and digital energy. These processes have already significantly influenced the economy of the fuel and energy complex in some countries and continue to develop. The proliferation of renewable energy is already beginning to have a global impact on electricity generation, consumption, and operation, especially in countries where the share of renewable energy in traditional energy exceeds 10 % in such countries, and Ukraine is projected too soon. The transition from current forecast generation models with essentially constant power to networks with which variable renewable energy sources are connected will likely require significant changes. Implementing renewable and distributed renewable energy will require more effort to manage, redistribute and accumulate energy flows in the grid. Digitisation can solve challenges that will only intensify in the future in three stages: «smart» energy generation, innovative management and settlement with customers, and wise consumption. The main problem here is the need for a considerable amount of data that will need to be processed to understand how the network works at any given time so that, with constant changes to its parameters, variables can be managed, forecasted, customers’ current needs and capabilities assessed energy services.Prospects. Digital technologies such as the Internet of Things, artificial intelligence, automation, complex cloud computing and blockchain are gaining popularity in the energy sector. Investments in these technologies are growing yearly and will become decisive by 2030. Digitisation of electrical systems was also investigated. The interconnectedness and evolving roles of generators, consumers and power grids will continue to be a central feature of the future of electricity supply.

Short-term load forecasting system based on sliding fuzzy granulation and equilibrium optimizer.

Short-term electricity load forecasting is critical and challenging for scheduling operations and production planning in modern power management systems due to stochastic characteristics of electricity load data. Current forecasting models mainly focus on adapting to various load data to improve the accuracy of the forecasting. However, these models ignore the noise and nonstationarity of the load data, resulting in forecasting uncertainty. To address this issue, a short-term load forecasting system is proposed by combining a modified information processing technique, an advanced meta-heuristics algorithm and deep neural networks. The information processing technique utilizes a sliding fuzzy granulation method to remove noise and obtain uncertainty information from load data. Deep neural networks can capture the nonlinear characteristics of load data to obtain forecasting performance gains due to the powerful mapping capability. A novel meta-heuristics algorithm is used to optimize the weighting coefficients to reduce the contingency and improve the stability of the forecasting. Both point forecasting and interval forecasting are utilized for comprehensive forecasting evaluation of future electricity load. Several experiments demonstrate the superiority, effectiveness and stability of the proposed system by comprehensively considering multiple evaluation metrics.

A novel wind speed forecasting combined model using variational mode decomposition, sparse auto-encoder and optimized fuzzy cognitive mapping network

The nonlinear, random and fluctuating characteristics of wind speed bring great challenges to its accurate forecast, so no model that can adapt to all situations. In order to solve the problem of unbalanced forecast accuracy and stability in the current wind speed forecast model, a novel and advanced wind speed combined forecast model (CFM) is proposed in this study. The CFM adopts a two-phase data processing strategy composed of variable mode decomposition-sparse autoencoder (VMD-SAE) to extract the original wind speed features, high-order fuzzy cognitive mapping (HFCM) neural network modeling and batch gradient descent optimization algorithm to make up for its shortcomings. The two-phase data processing strategy performs smoothing and feature information extraction processing on the original data. The forecast module adopts the SAE-HFCM combination strategy, and utilizes their respective advantages to achieve accurate and stable result output. The results show that this CFM has the best forecast accuracy and generalization performance compared with 7 benchmark models in datasets from three different sites. Compared with the benchmark models, the performance of CFM in point forecasting and interval forecasting, the average improvement percentage of IP_RMSE, IP_MAE and IP_MAPE minimum values are 40.9%, 40.1% and 40.6%, respectively. The performance of interval indicators is also the best, and its application prospects are broad.