Forecasting Model Research Articles

How Effective Are Forecasting Models in Predicting Effects of Exoskeletons on Fatigue Progression?

Forecasting can be utilized to predict future trends in physiological demands, which can be beneficial for developing effective interventions. This study implemented forecasting models to predict fatigue level progression when performing exoskeleton (EXO)-assisted tasks. Specifically, perceived and muscle activity data were utilized from nine recruited participants who performed 45° trunk flexion tasks intermittently with and without assistance until they reached medium-high exertion in the low-back region. Two forecasting algorithms, Autoregressive Integrated Moving Average (ARIMA) and Facebook Prophet, were implemented using perceived fatigue levels alone, and with external features of low-back muscle activity. Findings showed that univariate models without external features performed better with the Prophet model having the lowest mean (SD) of root mean squared error (RMSE) across participants of 0.62 (0.24) and 0.67 (0.29) with and without EXO-assisted tasks, respectively. Temporal effects of BSIE on delaying fatigue progression were then evaluated by forecasting back fatigue up to 20 trials. The slope of fatigue progression for 20 trials without assistance was ~48-52% higher vs. with assistance. Median benefits of 54% and 43% were observed for ARIMA (with external features) and Prophet algorithms, respectively. This study demonstrates some potential applications for forecasting models for workforce health monitoring, intervention assessment, and injury prevention.

Optimized ensemble deep random vector functional link with nature inspired algorithm and boruta feature selection: Multi-site intelligent model for air quality index forecasting

Air quality index (AQI) forecasting is complex due to its variability, instability, and inconsistent trends resulting from dynamic atmospheric conditions, various contaminants, and interactions between environmental factors. Advanced modeling techniques are needed to accurately forecast AQI values to capture subtle patterns and variations in air quality data. Thus, a new forecasting model is suggested in this study to improve the accuracy of AQI forecasting. The model integrates three-phase decomposition technique, a feature selection approach, and ensemble Deep Random Vector Functional Link (EDRVFL), optimized using adaptive teaching-learning-based optimization and differential evolution (ATLDE). The AQI series was first broken down into a group of intrinsic mode functions (IMFs) with different frequencies using multivariate variational mode decomposition (MVMD). Subsequently, a feature selection method based on the Boruta technique was applied to identify the most significant input variables. Finally, for daily AQI levels forecasting, ATLDE optimized the EDRVFL model (EDRVFL-ATLDE). Three daily AQI series gathered from Chengdu, Wuhan, and Taiyuan in China from January 1, 2018, to December 30, 2022, were used to test and confirm the proposed model via empirical research. Based on the results, the proposed model can yield the superior results for three cities (Chengdu: correlation coefficient (R = 0.987), root mean square error (RMSE = 5.583), Wuhan: (R = 0.987), (RMSE = 3.299), and Taiyuan: (R = 0.996), (RMSE = 4.521)) in China. The experimental findings demonstrated the feasibility of the three-phase hybrid methodology, outperforming all other models regarding forecast accuracy.

Forecasting the CBOE VIX and SKEW Indices Using Heterogeneous Autoregressive Models

We analyze the predictability of daily data on the CBOE VIX and SKEW indices, used to capture the average level of risk-neutral risk and downside risk, respectively, as implied by S&P 500 index options. In particular, we use forecast models from the Heterogeneous Autoregressive (HAR) class to test whether and how lagged values of the VIX and of the SKEW may increase the forecasting power of HAR for the SKEW and the VIX. We find that a simple HAR is very hard to beat in out-of-sample experiments aimed at forecasting the VIX. In the case of the SKEW, the benchmarks (the random walk and an AR(1)) are clearly outperformed by HAR models at all the forecast horizons considered and there is evidence that special definitions of the SKEW index based on put options data only yield superior forecasts at all horizons.

An Integrated CEEMDAN to Optimize Deep Long Short-Term Memory Model for Wind Speed Forecasting

Accurate wind speed forecasting is crucial for the efficient operation of renewable energy platforms, such as wind turbines, as it facilitates more effective management of power output and maintains grid reliability and stability. However, the inherent variability and intermittency of wind speed present significant challenges for achieving precise forecasts. To address these challenges, this study proposes a novel method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and a deep learning-based Long Short-Term Memory (LSTM) network for wind speed forecasting. In the proposed method, CEEMDAN is utilized to decompose the original wind speed signal into different modes to capture the multiscale temporal properties and patterns of wind speeds. Subsequently, LSTM is employed to predict each subseries derived from the CEEMDAN process. These individual subseries predictions are then combined to generate the overall final forecast. The proposed method is validated using real-world wind speed data from Austria and Almeria. Experimental results indicate that the proposed method achieves minimal mean absolute percentage errors of 0.3285 and 0.1455, outperforming other popular models across multiple performance criteria.

Application of deep learning in summer climate prediction over northwestern China based on CWRF model

This study analyzes the performance of the Climate–Weather Research and Forecasting (CWRF) model in predicting the summer temperature and precipitation in northwestern China (NWC) for the 1991–2021 period. It also examines the improvements in prediction resulting from the implementation of convolutional neural network (CNN) and long short-term memory (LSTM) downscaling methods. The results indicate that the CWRF model demonstrates reasonable ability in capturing the characteristics of climatological temperature and precipitation in NWC. Both the climatological temperature and precipitation predictions consistently demonstrate a systematic underestimation, revealing evident biases in regions characterized by complex terrain. In terms of interannual variation, the temperature prediction outperforms the precipitation prediction, whereas there is no significant difference in the temperature predictions for lead Months 1–3. However, uncertainties increase as the lead time is extended in precipitation prediction. Therefore, the combination of dynamical and statistical downscaling is employed to the summer temperature and precipitation prediction over NWC. It is shown both the CNN and LSTM downscaling methods can improve the prediction ability of the CWRF model for summer climatological temperature and precipitation. The LSTM method significantly reduces the root mean square error (RMSE) of precipitation and temperature predictions, indicating an improvement in predicting the spatial structure. At the interannual scale, the CNN method is less dependent on the lead time of prediction than the LSTM method is, and the interannual correlation coefficient of precipitation and temperature is greater than 0.1 compared with that of the raw CWRF model. These results provide valuable insights into understanding the prediction capabilities of the CWRF model in NWC and highlight the necessity of applying downscaling methods to the CWRF model to increase its prediction ability.

Future projection of extreme precipitation using a pseudo-global warming method: A case study of the 2013 Alberta flooding event

The June 2013 extreme precipitation event in Alberta resulted in devastating flash floods that caused significant economic losses and societal disruption. In this study, two high-resolution experiments were conducted using the Weather Research and Forecasting (WRF) model to study the change of the 2013 Alberta extreme precipitation event in a warmer climate. The control experiment was forced with 6-hourly ERA-Interim reanalysis data, while the sensitivity experiment was forced with perturbed ERA-Interim reanalysis data with climate change signals derived from ten global climate models under the Representative Concentration Pathway 8.5 emission scenario. The results indicate that the 2013 Alberta extreme precipitation event is projected to exhibit two significant characteristics in a warming climate. First, precipitation is expected to increase over the Canadian Rocky Mountain region and eastern British Columbia. Second, the precipitation is expected to decrease over the Alberta and Saskatchewan Prairies. Future changes in the extreme precipitation event are associated with changes in the cyclone evolution, moisture transport, and atmospheric stability change caused by climate change. We also found that the increase in atmospheric stability due to the decrease of relative humidity in the lower atmosphere cause less precipitation to form over the plains and later enhance the orographic precipitation in the Canadian Rockies. In addition to the general increase of precipitable water under global warming, this mechanism causes the storm's precipitation to be more concentrated near the Canadian Rockies. The findings from this study could be beneficial for understanding future changes in extreme precipitation events that share similar characteristics.

Evaluation of the Urban Canopy Scheme TERRA-URB in the ICON Model at Hectometric Scale over the Naples Metropolitan Area

The present work is focused on the validation of the urban canopy scheme TERRA-URB, implemented in ICON weather forecast model. TERRA-URB is used to capture the behavior of urbanized areas as sources of heat fluxes, mainly due to anthropogenic activities that can influence temperature, humidity, and other atmospheric variables of the surrounding areas. Heat fluxes occur especially during the nighttime in large urbanized areas, characterized by poor vegetation, and are responsible for the formation of Urban Heat and Dry Island, i.e., higher temperatures and lower humidity compared to rural areas. They can be exacerbated under severe conditions, with dangerous consequences for people living in these urban areas. For these reasons, the need of accurately forecasting these phenomena is particularly felt. The present work represents one of the first attempts of using a very high resolution (about 600 m) in a Numerical Weather Prediction model. Performances of this advanced version of ICON have been investigated over a domain located in southern Italy, including the urban metropolitan area of Naples, considering a week characterized by extremely high temperatures. Results highlight that the activation of TERRA-URB scheme entails a better representation of temperature, relative humidity, and wind speed in urban areas, especially during nighttime, also allowing a proper reproduction of Urban Heat and Dry Island effects. Over rural areas, instead, no significant differences are found in model results when the urban canopy scheme is used.

Data-driven forecasting of embankment settlements on soft soils using constant rate of strain test data

Geotechnical engineers continually seek accurate methodologies for predicting the time-dependent settlement of embankments on soft soils. This paper introduces a novel data-driven approach that utilises constant rate of strain (CRS) test data to forecast embankment settlements. The proposed framework circumvents the requirement to subjectively assign soil parameters used in traditional forecasting models by directly integrating CRS test data into an automated analytical process, thereby significantly reducing manual effort and user-dependent variation in forecast results. The accuracy of the method is demonstrated through applications to real-world trial embankments in Australia and the Netherlands. All data used in this study are freely available in digital format from Datamap.

Tropical Aviation Turbulence Induced by the Interaction Between a Jet Stream and Deep Convection

AbstractOn 18 December 2022, Hawaiian Airlines flight HA35 encountered severe turbulence without warning in a cloud‐free height. We reproduced this incident using the Weather Research and Forecasting Model (WRF) at a convection‐permitting resolution. We found that this case of tropical upper‐level turbulence occurred primarily due to the fast‐growing convective tower in the unstable layer created by gravity wave breaking. At lower altitudes, a mesoscale convective system (MCS) caused a decrease in wind speed in both upstream and downstream regions. At upper levels, a large‐scale jet descended and accelerated after flowing over the top of the MCS, which acted like a barrier and produced a situation similar to a downslope windstorm due to mountain terrain. Upper‐level turbulence is 2–3 km higher than the top of the MCS. The critical level above the jet and the locally self‐induced critical level created the locally enhanced descending jet stream, which destabilized the flow through Kelvin–Helmholtz instabilities. The convective tower existed near the flight route and played an important role in triggering turbulence in the unstable environment through its convective gravity waves.

High-resolution projections of future FWI conditions for Portugal according to CMIP6 future climate scenarios

Wildfires are catastrophes of natural origin or initiated by human activities with high disruptive potential. "Portugal, located in western Iberia, has recently experienced several large fire events, including megafires, due to a combination of factors such as orography, vegetation, climate, and socio-demographic conditions that contribute to fuel accumulation.". One approach to studying fire danger is to use fire weather indices that are commonly used to quantify meteorological conditions that can lead to fire ignition and spread. This study aims to provide high-resolution (~ 6 km) future projections of the Fire Weather Index (FWI) for Portugal using the Weather Research and Forecasting (WRF) model, forced by the Max Planck Institute (MPI) model from the CMIP6 suite, under three emission scenarios (SSP2-4.5, SSP3-7.0, and SSP58.5) for the present period (1995–2014) and two future periods (2046–2065 and 2081–2100). The results show good agreement between FWI and its subcomponents from the WRF and reanalysis. The modelled FWI reproduced the climatological distribution of fire danger Projections indicate an increase in days with very high to extreme fire danger (FWI > 38) across all scenarios and time frames, with the southern and northeastern regions experiencing the most significant changes. The southern and northeastern parts of the territory experienced the largest changes, indicating significant changes between the scenarios and regions. This study suggests that FWI and its subcomponents should be investigated further. Our results highlight the importance of creating new adaptation measures, especially in the areas most at risk, prepared in advance by different players and authorities, so that the increasing risk of wildfires can be mitigated in the future.

Polynomial fuzzy information granule based [formula omitted]-triple I fuzzy reasoning algorithm and its short-term forecasting of time series

Short-term forecasting of time series is an important research topic, which involves data characteristic capture and intelligent reasoning. For this topic, the Gaussian polynomial fuzzy information granule with interpretability is granulated on data, enabling the extraction of data trend characteristic, besides, the associate characteristic within the data is captured through building fuzzy association rule. Building upon the data characteristics captured in fuzzy information granule and fuzzy association rule, an intelligent reasoning algorithm called the fuzzy information granule based α-Triple I algorithm is proposed, where the membership degree of data to granule is considered in reasoning, and next the accurate level of deviation from data to granule can be inferenced. Based on the excavated data characteristics and a rational inference, a short-term forecasting model is established. Its superiority in terms of accuracy and reliability when compared to 7 other models in real time series has been tested. Notably, the prediction of the novel model is accurate because the function of FAR is identified from FAR’s truth degree, which means the validity degree of prediction. The application of the proposed model for short-term forecasting holds a potential impact across various fields.

Real-time solar PV generation in a building using LSTM-based time series forecasting

The increasing demand for renewable energy has forced the researchers to lay importance on studying the behavior of these sources by monitoring the operational data and performing data analysis. The application of data analytics to renewable energy is one of the most powerful methods to maintain the system's reliability and stability. As the power system becomes more complex the necessity to perform data analytics also increases. When data analytic techniques are applied to solar energy generations through Photovoltaic (PV) dataset, the possible behavior of PV generation performance which is affected by changes in environmental conditions can be predicted and further analytical approaches allow us to detect possible PV panel and inverter failures. This paper is an attempt towards applying the intelligent data analytics approaches to solar PV generation of a real-time photovoltaic plant. The main purpose of the data analytics platform is to analyze the energy yield, assess the PV system performance, and forecast solar PV generation. In this article, Long Short-Term Memory (LSTM) machine learning model is developed to assess and interpret the available information from the gathered data of the PV plant. The proposed model is a sequence-to-sequence regression-based forecasting model which performs time series forecasting in a real-time 100 kW PV plant in the University building of SRM Institute of Science and Technology, Kattankulathur, Tamilnadu.

Assessments of multiple metocean forecasts in the North Atlantic Ocean

Accurate wind and wave forecasts are crucial for a variety of marine operations, including ship design, navigation safety, and engineering. This study evaluates the predictability of wind and wave conditions in the North Atlantic Ocean using both deterministic and ensemble forecast models. A dataset of 29 deep water buoys was used to validate deterministic and ensemble forecasts from the National Centres for Environmental Prediction (NCEP), the Canadian Meteorological Centre (CMC), the European Centre for Medium-Range Weather Forecasts (ECMWF), and the German Weather Service (DWD). A comparison of deterministic and ensemble forecast performance was conducted using eight statistical metrics focusing on the significant wave heights associated with 10-m wind speed. The results indicate that ensemble models exhibit higher correlation coefficients and lower scatter root mean square error especially beyond the 7th forecast day, outperforming deterministic models. The findings suggest that ensemble forecasts offer a more reliable estimation of forecast, enhancing predictability for marine operations.

Short-term PV energy yield predictions within city neighborhoods for optimum grid management

The global shift towards the exploitation of renewable energy sources is a key aspect in the transition to carbon-free societies. Although harnessing of PV energy disclosed the numerous environmental and economic benefits of PV systems, the ever-increasing share of PV systems in power generation has revealed their adverse effect on the electricity grid due to their dependence on weather conditions. Uncertain environmental parameters, especially cloud cover, can adversely affect the stability of the energy generated by a PV system, causing dynamic changes in PV power generation in a given future time period. Therefore, accurate predictions of PV power output are a major challenge, as they can contribute to the optimal management and flexibility of the power grid, and to the improvement of the operating efficiency of PV power stations, thus enabling the development of flexible green power electricity grids across cities. In addition, precise forecasting can provide system/grid operators with information needed for efficient capacity management and scheduling and ensure grid stability.Most forecasting models provide promising results in terms of error performance; however, they need weather variables or satellite information as inputs that make prognosis significantly challenging. Hence, the current work utilizes a data-driven method for predicting PV power generation from distributed PV systems. The spatio-temporal model Sparse Gaussian Conditional Random Fields was considered. Although this model was used extensively for wind forecasting, in this work, it was used for solar PV power output predictions. Moreover, the effect of varying spatial distribution for aggregated multiple PV systems was investigated on the forecast model performance. The main objective was to provide the solar PV energy sector with important information for building a smart grid for cities or regions.Continuous data from a grid-connected dense network of 21 PV systems was used within a region of 38.485 km2 in Nicosia, Cyprus. It should be noted that the test set includes data only from winter months. The results showed that the predicted power output signal responds to the fluctuation and follows the trend of the actual power signal, even on days with large variations in actual PV power. The average nRMSE of all PV systems in each dataset studied ranges from 0.119 to 0.146, proving that the proposed method delivered significant results that can be compared with existing results from similar studies. Overall, the proposed method can provide important information that can assist in decision-making for the management, optimization, and visualization of grids across cities.

OceanNet: a principled neural operator-based digital twin for regional oceans

While data-driven approaches demonstrate great potential in atmospheric modeling and weather forecasting, ocean modeling poses distinct challenges due to complex bathymetry, land, vertical structure, and flow non-linearity. This study introduces OceanNet, a principled neural operator-based digital twin for regional sea-suface height emulation. OceanNet uses a Fourier neural operator and predictor-evaluate-corrector integration scheme to mitigate autoregressive error growth and enhance stability over extended time scales. A spectral regularizer counteracts spectral bias at smaller scales. OceanNet is applied to the northwest Atlantic Ocean western boundary current (the Gulf Stream), focusing on the task of seasonal prediction for Loop Current eddies and the Gulf Stream meander. Trained using historical sea surface height (SSH) data, OceanNet demonstrates competitive forecast skill compared to a state-of-the-art dynamical ocean model forecast, reducing computation by 500,000 times. These accomplishments demonstrate initial steps for physics-inspired deep neural operators as cost-effective alternatives to high-resolution numerical ocean models.

Forecasting of changes in electricity consumption due to EV diffusion in South Korea: Development of integrated model considering diffusion and macro-econometric model

Electrification is on the increase globally. The transportation sector is being electrified to reduce greenhouse gas emissions. South Korea aims to diffuse 8.3 million battery electric vehicles (BEVs) by 2040 to reduce emissions in the transportation sector. However, BEV diffusion policies have not been considered for BEVs' electricity consumption. Given that the rapid diffusion of BEVs significantly increases the electricity demand, forecasting BEVs' electricity consumption is necessary to inform electricity production plans. Furthermore, electricity is produced through various energy sources, and electricity prices and consumption are affected; therefore, forecasts that reflect the overall energy market are needed. This study presents a forecasting model for BEV demand and energy consumption by combining it with a macroeconometric model that reflects the overall energy market and socioeconomic impact using an innovation diffusion model. Incorporating electricity prices and renewable energy consumption derived from the macroeconometric model, annual BEV demand and electricity consumption are predicted. Moreover, BEV demand is more diffused and slower when forecasted using the Generalized Bass model with electricity prices and renewable energy consumption, compared to forecast without these factors, and the predictive power of BEVs is superior to that forecasted using the Bass Model alone.

TC-SRNet: Reconstruction and prediction of typhoon high-resolution turbulent fields based on meteorological numerical forecast scale wind fields and deep learning method

Meteorological numerical forecast models can provide a more accurate typhoon wind fields compared to engineering typhoon models due to their incorporate atmospheric multiphysical processes. However, the latest advancements in supercomputing power indicate that the current finest level of real-time weather forecasting typically operates on grid scales ranging from 1 to 4 km, while the convergence of typhoon intensity and turbulent field characteristics occurs at scales as fine as 62–185 m. Therefore, the primary scientific inquiry lies in determining how to achieve high-precision turbulent wind fields while considering the realistic atmospheric multiphysical processes, that means establish a “bridge” of typhoon wind field between kilometer-level and hundred-meter scales. This study investigates the super-resolution reconstruction of wind fields across different horizontal grid scales, utilizing a benchmark wind field at a 62 m horizontal grid scale (ground truth), which is based on a hybrid down-sampling skip connection (DSC)/multi-scale (MS) model. The research findings demonstrate that compared to traditional interpolation methods, the DSC/MS method significantly improves reconstruction accuracy, albeit with some residual high-frequency energy dissipation issues. Additionally, the DSC/MS method currently exhibits better reconstruction performance for 62 m scale wind fields based on kilometer-scale and smaller horizontal grid scales (1 km, 555 m, 185 m), with improved reconstruction as grid scale decreases. However, significant errors are observed in reconstructing fine turbulent fields at 62 m scale based on wind fields at 1.67 km horizontal grid scale. The findings presented in the present study can provide real and high-precision turbulent wind fields for structural wind engineering and wind energy assessment studies, thereby holding significant scientific and engineering application value.

An alternative fuzzy time series forecast model combined generalized fuzzy logical relationship, natural partitioning, and adaptive defuzzification

This paper, we propose generalized fuzzy logical relationships based on natural partitioning and adaptive defuzzification. The proposed method provides a better approach to improve performance by producing a good evaluation of the forecasted value. This study aims to minimize forecasting errors for each data series. The general suitability of the proposed model was tested by implementing it in the fore- casting of student enrollments at the University of Alabama. In order to show the superiority of the proposed model over existing methods, the results obtained have been compared with evaluations such as MSE, RMSE, MAE, MAPE, and forecasting error errors for each time series data. Comparative studies show that the proposed method is superior to existing methods for all evaluations provided.

Research on gold price prediction based on ARIMA model

Gold is one of the most prevalent currencies in the world and its price has a very strong influence in the global financial markets. Gold has safe-haven properties, which can have a significant impact on its demand and price, especially in times of social unrest or financial crisis. Now, the demand for gold by investors has increased dramatically. Therefore, being able to accurately predict the direction of the gold price can help investors to effectively develop investment strategies and risk management measures. The overall objective of this study is to forecast the price of gold futures for the next six months. In this study, the Kaggle website was searched to find the price of gold from 2020 to 2024 and finally the CLOSE price was chosen as the final predicted price. This paper uses the ARIMA model for gold price forecasting. By comparing the RSME size of each model, ARIMA (1, 1, 2) is finally chosen. From the prediction results the price of gold remains stable in the first half of the year and then increases significantly. From the results of the residual test, there is no autocorrelation, and then it is white noise.

RIME-CNN-BiLSTM: A novel optimized hybrid enhanced model for significant wave height prediction in the Gulf of Mexico

Accurate prediction of SWH in the ocean is critical to the development of ocean energy technologies. However, existing forecasting models have limitations in accuracy and reliability, which directly affect the efficiency of ocean energy utilization. To address this problem, this paper proposes a new ocean SWH prediction model, RIME-CNN-BiLSTM, for predicting 1, 6, 12, and 24 h SWH at three buoy observing stations in the Gulf of Mexico. The model combines the RIME algorithm, CNN, and BiLSTM to comprehensively capture multiple parameters that affect wave heights, such as sea breeze, waves, barometric pressure, and temperature. The parameters of the CNN-BiLSTM model are optimized by the RIME algorithm, which significantly improves the prediction accuracy and generalization ability. Compared with the traditional model, RIME-CNN-BiLSTM captures the nonlinear features more accurately, has better prediction ability for outliers, and shows stronger generalization performance in different sea areas of the Gulf of Mexico. In terms of predicting the wave height in the next 24 h, the improvements are 7.065%, 3.646% and 5.186%, respectively. The results show that the RIME-CNN-BiLSTM model performs well in all prediction time periods, significantly outperforms other benchmark models, and is able to accurately capture nonlinear features and effectively predict outliers.