Reliable Forecasts Research Articles

Unveiling influential factors in the capital asset pricing model: A novel approach utilizing Taguchi method

This study uses a Design of Experiment (DOE) approach and the Taguchi method to examine how different factors affect the expected return within the framework of the CAPM. The Capital Asset Pricing Model (CAPM) is a financial framework that forecasts an investment’s expected return by taking into account its systematic risk. This model factors elements like the risk-free rate, market risk premium, and beta to ascertain the expected return for a given asset. Typically, historical market data and financial analysis provide the inputs for CAPM. This method, frequently used in manufacturing and engineering, is modified for use in the financial domain to evaluate the importance of variables like beta, market risk premium, and the risk-free rate. The research identifies the factors that influence investment performance and shows how much each factor contributes to the expected returns. It is possible to ascertain each factor's percentage contribution to the expected return through statistical analysis. This work improves knowledge of CAPM and creates opportunities for improving investment decision-making processes by bridging the gap between financial theory and experimental design. Financial practitioners can achieve more reliable and accurate investment return forecasts by incorporating DOE techniques into their existing analytical toolkit.

Building heating load forecasting based on the theory of transient heat transfer and deep learning

Reliable and accurate heating load forecasting can provide comprehensive information for the monitoring and control of Heating, Ventilation, and Air Conditioning (HVAC) in buildings, which reduce uncertainty on the load demand of energy effectively. Data-driven method has demonstrated a potential to forecast heating load, but current methods generally lack the consideration of features on model forecasting performance and applicability. Based on the theory of transient heat transfer and conduction transfer function for building hourly heating load calculation, this study proposes an idea that comprehensively selects physical variables affecting the hourly dynamic changes of the building heating load as features, which enhances the persuasiveness of selecting datasets features. Then we use the deep learning method to build short-term heating load forecasting models, and explore the influence of different feature combinations and time steps on the model forecasting performance. Combining the physical property of building heat gains, we divide the features into external heat gains, internal heat gains and historical heating load and then show their performance of models at different time steps. It is shown that the two-hour data of external heat gains and internal heat gains, the three-hour data of past heat load have the highest value. The best model can achieve a mean absolute error of 0.153 kW and a mean absolute percentage error of 6.2 %. These findings are helpful for researchers to select more relevant features to forecast heating load in buildings and improve their models through physical aspect.

Real Estate Price Prediction using ANN

This report explores the use of machine learning to predict real estate prices, addressing challenges such as market dynamics and data complexity. Through extensive data analysis and feature engineering, the study implements decision trees, random forests, and neural networks to capture the intricate factors affecting property values. The performance of these models is rigorously evaluated, providing stakeholders with reliable forecasts and insights into key price determinants. This research enhances decision-making in the real estate sector by improving the accuracy and transparency of price predictions. A Graphical User Interface is also developed to enter required information and display the predicted price. Keywords—Machine Learning, Price Prediction, Artificial Neural Network

A Neural Network Forecasting Approach for the Smart Grid Demand Response Management Problem

Demand response management (DRM) plays a crucial role in the prospective development of smart grids. The precise estimation of electricity demand for individual houses is vital for optimizing the operation and planning of the power system. Accurate forecasting of the required components holds significance as it can substantially impact the final cost, mitigate risks, and support informed decision-making. In this paper, a forecasting approach employing neural networks for smart grid demand-side management is proposed. The study explores various enhanced artificial neural network (ANN) architectures for forecasting smart grid consumption. The performance of the ANN approach in predicting energy demands is evaluated through a comparison with three statistical models: a time series model, an auto-regressive model, and a hybrid model. Experimental results demonstrate the ability of the proposed neural network framework to deliver accurate and reliable energy demand forecasts.

Elevation dependent climate assessment and its influence on snow cover variability in Hindu Kush Himalayan region using Google Earth Engine for the period of 2003–2021

The Hindu Kush Himalayan (HKH) regions are taken for this study, which is predominantly characterized by amplified climatic uncertainty and rapid snow melting. Because at the present there is a lack of studies estimating the elevation dependent and climate influenced snow cover variability in the HKH region. This present study examines elevation-dependent (2003–2021) distribution and trends in precipitation, temperature, and snow cover area (SCA) by employing numerous non-parametric statistical applications using the Google Earth Engine (GEE). The Modified Moderate Resolution Imaging Spectroradiometer (MODIS) Terra and Aqua snow cover data is employed to estimate SCA along with the Climate Hazards Group Infrared Precipitation with Station Data version 2.0 (CHIRPS-V2.0) for precipitation and MODIS land surface temperature (LST). The study reveals statistically significant decreasing annual, seasonal, and monthly trends of SCA in most of the elevation zones typically during winter season (−0.256%/year), whereas temperature and precipitation exhibit strong spatial variability. Inclusive investigation portrays maximum mean annual and seasonal increased precipitation at the low-elevated regions, whereas seasonal disparities in temperature ostensible marginal decreased at high-elevation, albeit increased at lowland. Moreover, topographic importance on SCA distribution showcases maximum snow (43.4%) at north-facing less surface inclination with flat topography (14.6%). The comprehensive elevation wise analysis improves our understanding of the overall hydrological challenge and assist in the development of more reliable flood forecasting and water resource management.

Hyper-Flophet: A neural Prophet-based model for traffic flow forecasting in transportation systems

Nowadays, an accurate and reliable traffic forecast is meaningful in making the right decisions for traffic management systems in vehicular environments. Nevertheless, traffic flow prediction is a significant challenge in Vehicular Ad Hoc Networks (VANETs) that has taken much attention. Therefore, in this paper, we propose a hybrid traffic prediction model based on Prophet model and Long Short-Term Memory neural network (LSTM), called Hyper-Flophet, to predict next traffic flow. Hyper-Flophet model adopts the traditional neural prophet model but with major parameter tuning. First, we propose an efficient algorithm for predicting the traffic flow trend then, we develop an interactive LSTM (I-LSTM) model for auto-regression components. After that, we implement a new future regressor component called network mobility and finally, we enhance the event and holiday component by introducing exponential growth term. Through simulations with real VANET data, we show that the proposed hybrid approach can achieve superior forecasting performance over other models.

Medium-term forecasting of global horizontal solar radiation in Brazil using machine learning-based methods

The generation of electric energy through renewable sources, such as solar photovoltaic (PV) systems, has emerged as one solution to the climate change crisis. To avoid fluctuations in energy generation on the electricity grid, reliable and accurate forecasts are required. Statistical downscaling methodologies often rely on data from General Circulation Model (GCM) to provide information on the local level. In contrast to traditional downscaling approaches, the present study focuses on a data-driven approach using the Global Data Assimilation System (GDAS) database in three different ways to feed the machine learning (ML) models, based on boosting and bagging, to provide medium-term Global Horizontal Irradiance (GHI) forecasts, i.e. up to seven days ahead. In addition, feature selection and feature augmentation techniques are also applied. The results showed that Extra Trees method outperformed the other tested in the present study, with a RMSE of 99.6 and 137.6 W/m2, and correlation 0.31 and 0.52 for June and October, respectively. Thus far, this work marks the initial suggestion of incorporating GDAS analysis data into a data-driven forecasting approach employing bagging and boosting models. This innovative approach demonstrates the potential for integrating global-scale data assimilation systems with local measurements using ML techniques. The outcomes of this research contribute to advancing the field of traditional downscaling methods and provides more robust and specialized forecasting.

Constraining Parameter Uncertainties in the Coulomb Rate–State Approach: A Case Study of Seismicity in the Longmenshan Region after the 2008 Mw 7.9 Wenchuan Earthquake, China

Abstract The rate–state frictional law, coupled with the Coulomb failure stress changes (ΔCFS), is one of the most popular physics-based models to forecast seismicity rate changes following a major earthquake. However, its effectiveness is hampered by parameter uncertainties. To seek possible solutions for such uncertainties, this article carried out retrospective forecasts of the decade-long seismicity in the Longmenshan region, China, after the 2008 Mw 7.9 Wenchuan earthquake, and proposed methods to constrain parameter uncertainties. First, we derived spatially variable ta and Aσ from fault-slip rates. This method not only provides observational constraints for these two parameters but also reflects spatial variations of fault rate–state properties. Second, although both complete and declustered background catalogs are common in Coulomb rate–state forecasts, this study demonstrated that declustering avoids false alerts of seismicity rate increase that resulted from temporary seismicity fluctuations in the background catalog. Finally, we extended the model from its typical application based on a stress step (the coseismic stress change) to a calculation that allows a more complex stress evolution (the postseismic viscoelastic stress change). With these methods to constrain parameter uncertainties, we are able to obtain more reliable forecasts.

Predicting Traffic Flow with Neural Networks

The monitoring and analysis of traffic flow has become crucial for transportation planners to best schedule road infrastructure repair projects as well as for people to better plan and manage their daily commutes. Therefore, one of the most crucial needs of traffic management systems is the capacity to precisely predict the type of traffic stream. In this study, we will give an intelligent approach to traffic flow prediction using actual data from the Central Road Research Institute (CRRI), India for the years 2018 and 2019. The suggested method is to train a neural network model to predict traffic flow on an hourly basis in the future. The simulation's conclusions provided a reliable forecast for the traffic statistics

ST-TransNet: A Spatiotemporal Transformer Network for Uncertainty Estimation from a Single Deterministic Precipitation Forecast

Abstract The forecast uncertainty, particularly for precipitation, serves as a crucial indicator of the reliability of deterministic forecasts. Traditionally, forecast uncertainty is estimated by ensemble forecasting, which is computationally expensive since the forecast model is run multiple times with perturbations. Recently, deep learning methods have been explored to learn the statistical properties of ensemble prediction systems due to their low computational costs. However, accurately and effectively capturing the uncertainty information in precipitation forecasts remains challenging. In this study, we present a novel spatiotemporal transformer network (ST-TransNet) as an alternative approach to estimate uncertainty with ensemble spread and probabilistic forecasts, by learning from historical ensemble forecasts. ST-TransNet features a hierarchical structure for extracting multiscale features and incorporates a spatiotemporal transformer module with window-based attention to capture correlations in both spatial and temporal dimensions. Additionally, window-based attention can not only extract local precipitation patterns but also reduce computational costs. The proposed ST-TransNet is evaluated on the TIGGE ensemble forecast dataset and Global Precipitation Measurement (GPM) precipitation products. Results show that ST-TransNet outperforms both traditional and deep learning methods across various metrics. Case studies further demonstrate its ability to generate reasonable and accurate spread and probability forecasts from a single deterministic precipitation forecast. It demonstrates the capacity and efficiency of neural networks in estimating precipitation forecast uncertainty.

Research on optimization of improved short-term load composite forecasting model based on AM–CNN–Bi–LSTM

Accurate load prediction is a prerequisite for the design, operation, scheduling, and management of energy systems. In the context of the development of smart grids, the extensive integration of highly volatile distributed energy generation into the power system has brought new challenges to the accuracy, reliability, real-time performance, and intelligence of short-term load forecasting. Therefore, this article proposes a novel short-term power load composite prediction model based on AM–CNN–Bi–LSTM. First, CNN is used to extract relevant feature quantities of power load coupling characteristics. Then, AM is used to evaluate the importance of the feature data, highlighting the features that have a greater impact on the prediction results. Finally, the Bi-LSTM network captures bidirectional temporal information from multiple time steps for prediction. Taking one year of measured data as an example, the error comparison of the prediction results of the composite prediction model overlay shows that compared with other models, the composite prediction model has improved prediction accuracy, feature extraction, generalization ability, and other aspects. The research results improve the accuracy of short-term power load forecasting while providing effective model references for decision-making in power system optimization scheduling, safe operation, and reasonable pricing.

Research on short-term load forecasting based on clustering and deep learning

In power systems, power load forecasting is essential to ensure the reliability and efficiency of power supply. Since power load is affected by many factors, including weather, seasonality, and social activities, its patterns and changes are complex and diverse, and traditional forecasting methods may make it difficult to meet demand. In this background, this study combines the K-means clustering algorithm and deep learning model. First, through K-means clustering, we grouped historical load data, dates, and temperatures to identify different load patterns. This grouping helps adapt to different load changes, thereby improving the adaptability of the forecast. Then, a deep learning model is applied, combining a convolutional neural network (CNN) and a two-layer bidirectionally gated recurrent unit (BIGRU). These two models are used to deal with spatiotemporal characteristics and sequence dependence in load data respectively. CNN is used to capture the spatial features in the load data, while BIGRU processes the time series information in the data to effectively capture the complex dynamic nature of the load. K-means clustering information is entered as additional data into the CNN and BIGRU models. The experimental results of the study show that by fully considering different load patterns and data characteristics. Reducing load demand and providing more reliable short-term load forecasts improve the efficiency of the power supply, reduce energy waste, and reduce the burden on the power system.

Testing the Forecasting Power of Statistical Models for Intercity Rail Passenger Flows in Turkey

While going through a major rail transformation, it is important to develop reliable estimation models for rail passenger flows (RPFs) in Turkey. There are two main approaches in RPF estimation, regressions and autoregressive integrated moving-average (ARIMA) models, both of which were in this study developed using the daily RPF data for the period 2011–2015. The ARIMA models (with some variations) were used to forecast first the daily flows in 2016, during which travel restrictions for summer resulted in reduced volumes, successfully captured in the updated ARIMA model. The regression models predicted the expected demand during the restrictions, enabling evaluation of the impact of restrictions, which also showed the models’ power over the longer term. The forecasts were extended to 2017, 2018, and 2019 data. The regression results produced more reliable forecasts over the long term, whereas more accurate predictions were obtained by ARIMA-Sliding (FA-Sld) for short-term planning purposes.

Improving short-term sea ice concentration forecasts using deep learning

Abstract. Reliable short-term sea ice forecasts are needed to support maritime operations in polar regions. While sea ice forecasts produced by physically based models still have limited accuracy, statistical post-processing techniques can be applied to reduce forecast errors. In this study, post-processing methods based on supervised machine learning have been developed for improving the skill of sea ice concentration forecasts from the TOPAZ4 prediction system for lead times from 1 to 10 d. The deep learning models use predictors from TOPAZ4 sea ice forecasts, weather forecasts, and sea ice concentration observations. Predicting the sea ice concentration for the next 10 d takes about 4 min (including data preparation), which is reasonable in an operational context. On average, the forecasts from the deep learning models have a root mean square error 41 % lower than TOPAZ4 forecasts and 29 % lower than forecasts based on persistence of sea ice concentration observations. They also significantly improve the forecasts for the location of the ice edges, with similar improvements as for the root mean square error. Furthermore, the impact of different types of predictors (observations, sea ice, and weather forecasts) on the predictions has been evaluated. Sea ice observations are the most important type of predictors, and the weather forecasts have a much stronger impact on the predictions than sea ice forecasts.

Forecasting US Inflation Trends: Insights from Time Series Analysis

Abstract: In our research, we dive into the world of forecasting US inflation using the ARIMA (Auto-Regressive Integrated Moving Average) model. We crafted a predictive framework by meticulously analyzing data, conducting tests like the Augmented Dickey-Fuller, and crunching metrics such as RMSE and MSE. Our meticulous model selection procedures involve carefully examining many ARIMA configurations to identify the ideal parameters, ensuring robustness and accuracy in forecasting inflation trends over the study period. Our findings show that the ARIMA (0,1,2) model outperforms others, offering reliable forecasts. These results not only showcase the model's effectiveness but also provide valuable insights for both policymakers and market players. By understanding potential inflationary trends, they can confidently navigate risks and make informed decisions, ultimately fostering stability and growth in the economy.

Evaluation of debris-flow building damage forecasts

Abstract. Reliable forecasts of building damage due to debris flows may provide situational awareness and guide land and emergency management decisions. Application of debris-flow runout models to generate such forecasts requires combining hazard intensity predictions with fragility functions that link hazard intensity with building damage. In this study, we evaluated the performance of building damage forecasts for the 9 January 2018 Montecito postfire debris-flow runout event, in which over 500 buildings were damaged. We constructed forecasts using either peak debris-flow depth or momentum flux as the hazard intensity measure and applied each approach using three debris-flow runout models (RAMMS, FLO-2D, and D-Claw). Generated forecasts were based on averaging multiple simulations that sampled a range of debris-flow volume and mobility, reflecting typical sources and magnitude of pre-event uncertainty. We found that only forecasts made with momentum flux and the D-Claw model could correctly predict the observed number of damaged buildings and the spatial patterns of building damage. However, the best forecast only predicted 50 % of the observed damaged buildings correctly and had coherent spatial patterns of incorrectly predicted building damage (i.e., false positives and false negatives). These results indicate that forecasts made at the building level reliably reflect the spatial pattern of damage but do not support interpretation at the individual building level. We found the event size strongly influences the number of damaged buildings and the spatial pattern of debris-flow depth and velocity. Consequently, future research on the link between precipitation and the volume of sediment mobilized may have the greatest effect on reducing uncertainty in building damage forecasts. Finally, because we found that both depth and velocity are needed to predict building damage, comparing debris-flow models against spatially distributed observations of building damage is a more stringent test for model fidelity than comparison against the extent of debris-flow runout.

Two-stage short-term wind power probabilistic prediction using natural gradient boosting combined with neural network

Accurate wind power probabilistic prediction reflects the uncertainty information of wind power generation, which is the foundation for optimal scheduling of power systems. This study proposes a two-stage probabilistic prediction model combining natural gradient boosting and neural network for accurate uncertainty estimation of short-term output in a wind farm. In the first stage, the selected input features containing historical and future information are fed into a neural network for representation learning. In the second stage, the extracted abstract features are concatenated with the original features, and a natural gradient boosting model is employed to acquire short-term probabilistic forecasts. The experimental results using data from two real wind farms indicate that the proposed hybrid model can generate accurate, sharp, and reliable forecasts. After performing the successive day-ahead prediction task for a month in the first wind farm, the average root mean square error and mean absolute error of the proposed model in the point prediction were 0.1330 and 0.1070, respectively, which were 6.21%–57.29% and 2.96%–62.03% lower than those of comparative models. In addition, the model’s forecasting probability density curves demonstrate high reliability; its coverage probability and the mean width percentage of the interval prediction results under the 90% confidence level were 0.9094 and 0.3696, respectively, which were more suitable than those of five other probabilistic prediction models.

Machine Learning Forecast of Dust Storm Frequency in Saudi Arabia Using Multiple Features

Dust storms are significant atmospheric events that impact air quality, public health, and visibility, especially in arid Saudi Arabia. This study aimed to develop dust storm frequency predictions for Riyadh, Jeddah, and Dammam by integrating meteorological and environmental variables. Our models include multiple linear regression, support vector machine, gradient boosting regression tree, long short-term memory (LSTM), and temporal convolutional network (TCN). This study highlights the effectiveness of LSTM and TCN models in capturing the complex temporal dynamics of dust storms and demonstrates that they outperform traditional methods, as evidenced by their lower mean absolute error (MAE) and root mean square error (RMSE) values and higher R2 score. In Riyadh, the TCN model demonstrates its remarkable performance, with an R2 score of 0.51, an MAE of 2.80, and an RMSE of 3.48, highlighting its precision, adaptability, and responsiveness to changes in dust storm frequency. Conversely, in Dammam, the LSTM model proved to be the most accurate, achieving an MAE of 3.02, RMSE of 3.64, and R2 score of 0.64. In Jeddah, the LSTM model also exhibited an MAE of 2.48 and an RMSE of 2.96. This research shows the potential of using deep learning models to improve the accuracy and reliability of dust storm frequency forecasts.

Wind-Speed Multi-Step Forecasting Based on Variational Mode Decomposition, Temporal Convolutional Network, and Transformer Model

Reliable and accurate wind-speed forecasts significantly impact the efficiency of wind power utilization and the safety of power systems. In addressing the performance enhancement of transformer models in short-term wind-speed forecasting, a multi-step prediction model based on variational mode decomposition (VMD), temporal convolutional network (TCN), and a transformer is proposed. Initially, the Dung Beetle Optimizer (DBO) is utilized to optimize VMD for decomposing non-stationary wind-speed series data. Subsequently, the TCN is used to extract features from the input sequences. Finally, the processed data are fed into the transformer model for prediction. The effectiveness of this model is validated by comparison with six other prediction models across three datasets, demonstrating its superior accuracy in short-term wind-speed forecasting. Experimental findings from three distinct datasets reveal that the developed model achieves an average improvement of 52.1% for R2. To the best of our knowledge, this places our model at the leading edge of wind-speed prediction for 8 h and 12 h forecasts, demonstrating MSEs of 1.003 and 0.895, MAEs of 0.754 and 0.665, and RMSEs of 1.001 and 0.946, respectively. Therefore, this research offers significant contributions through a new framework and demonstrates the utility of the transformer in effectively predicting short-term wind speed.

Short‐term predictions of PM10 and NO2 concentrations in urban environments based on ARIMA search grid modeling

AbstractAir pollution poses a persistent challenge for urban management departments and policymakers due to its significant health and economic impacts. Various cities worldwide have implemented diverse strategies and initiatives to enhance air quality monitoring and modeling standards. However, the outcomes of these efforts often manifest over the long term, leading to a preference for short‐term statistical methods. The autoregressive integrated moving average (ARIMA) search grid modeling approach has gained widespread use for forecasting air quality. This paper presents a comprehensive time series analysis conducted to predict air quality in urban areas of Budapest, Hungary, with a focus on nitrogen dioxide (NO2) and particulate matter (PM10), using air quality data spanning from 2018 to 2022 for four monitoring categories: Urban traffic, industrial background, urban background, and suburban background. The study employs the ARIMA search grid method to forecast concentrations of these pollutants at multiple air quality monitoring stations based on Akaike information criteria (AIC) and the Bayesian information criteria (BIC) criteria along with the results of augmented Dickey–Fuller (ADF) test. The results demonstrate varying levels of forecast accuracy across different stations, indicating the model's effectiveness in short‐term predicting of air quality. These findings are essential for assessing the reliability of air quality forecasts in Budapest and can inform decisions regarding air quality management and the development of strategies to address air pollution and particulate matter concerns in the region.