Forecasting, Volume 6, Issue 2 (June 2024) – 13 articles

Transportation significantly influences greenhouse gas emissions—particularly carbon dioxide (CO₂)—thereby affecting climate, health, and various socioeconomic aspects. Therefore, in developing and implementing targeted and effective policies to mitigate the environmental impacts of transportation-related carbon dioxide emissions, governments and decision-makers have focused on identifying methods for the accurate and reliable forecasting of carbon emissions in the transportation sector. This study evaluates these policies’ impacts on CO₂ emissions using three forecasting models: ANN, SVR, and ARIMAX. Data spanning the years 1993–2022, including those on population, GDP, and vehicle kilometers, were analyzed. The results indicate the superior performance of the ANN model, which yielded the lowest mean absolute percentage error (MAPE = 6.395). Moreover, the results highlight the limitations of the ARIMAX model; particularly its susceptibility to disruptions, such as the COVID-19 pandemic, due to its reliance on historical data. Leveraging the ANN model, a scenario analysis of trends under the “30@30” policy revealed a reduction in CO₂ emissions from fuel combustion in the transportation sector to 14,996.888 kTons in 2030. These findings provide valuable insights for policymakers in the fields of strategic planning and sustainable transportation development. Full article

Minimum trace reconciliation, developed by Wickramasuriya et al., 2019, is an innovation in the literature on forecast reconciliation. The proof, however, has a gap, and the idea is not easy to extend to more general situations. This paper fills the gap by providing an alternative proof based on the first-order condition in the space of a non-square matrix and arguing that it is not only simpler but also can be extended to incorporate more general results on minimum weighted trace reconciliation in Panagiotelis et al., 2021. Thus, our alternative proof not only has pedagogical value but also connects the results in the literature from a unified perspective. Full article

Forecasting returns in financial markets is notoriously challenging due to the resemblance of price changes to white noise. In this paper, we propose novel methods to address this challenge. Employing high-frequency Brazilian stock market data at one-minute granularity over a full year, we apply various statistical and machine learning algorithms, including Bidirectional Long Short-Term Memory (BiLSTM) with attention, Transformers, N-BEATS, N-HiTS, Convolutional Neural Networks (CNNs), and Temporal Convolutional Networks (TCNs) to predict changes in the price ratio of closely related stock pairs. Our findings indicate that a combination of reversion and machine learning-based forecasting methods yields the highest profit-per-trade. Additionally, by allowing the model to abstain from trading when the predicted magnitude of change is small, profits per trade can be further increased. Our proposed forecasting approach, utilizing a blend of methods, demonstrates superior accuracy compared to individual methods for high-frequency data. Full article

In this article, we document the use of hail cannons in Mexico to dispel or suppress heavy rain episodes, a common practice among farmers, without scientific evidence to support its effectiveness. This study uses two rain databases: one compiled from the Global Precipitation Measurement (GPM) mission and the other generated with the implementation of the Weather Research and Forecasting (WRF) model. The aim is to explore the association between heavy rain episodes and hail cannon locations. The analysis includes two geographic features: a pair of coordinates and a 3 km radius area of influence around each hail cannon. This dimension is based on the size and distribution of the heavy rainfall events. This study analyzes four years of half-hourly rain data using the Python ecosystem environment with machine learning libraries. The results show no relationship between the operation of hail cannons and the dissipation or attenuation of heavy rainfall events. However, this study highlights that the significant differences between the GPM and WRF databases in registering heavy rain events may be attributable to their own uncertainty. Despite the unavailability of ground-based observations, the inefficiency of hail cannons in affecting the occurrence of heavy rain events is evident. Overall, this study provides scientific evidence that hail cannons are inefficient in preventing the occurrence of heavy rain episodes. Full article

Deep learning has recently demonstrated the ability to predict long-term patient risk and its stratification when trained on imaging data such as chest radiographs. However, existing methods formulate estimating patient risk as a binary classification, typically ignoring or limiting the use of temporal information, and not accounting for the loss of patient follow-up, which reduces the fidelity of estimation and limits the prediction to a certain time horizon. In this paper, we demonstrate that deep survival and time-to-event prediction models can outperform binary classifiers at predicting mortality and risk of adverse health events. In our study, deep survival models were trained to predict risk scores from chest radiographs and patient demographic information in the Prostate, Lung, Colorectal, and Ovarian (PLCO) cancer screening trial (25,433 patient data points used in this paper) for 2-, 5-, and 10-year time horizons. Binary classification models that predict mortality at these time horizons were built as baselines. Compared to the considered alternative, deep survival models improve the Brier score (5-year: 0.0455 [95% CI, 0.0427–0.0482] vs. 0.0555 [95% CI, (0.0535–0.0575)], p < 0.05) and expected calibration error (ECE) (5-year: 0.0110 [95% CI, 0.0080–0.0141] vs. 0.0747 [95% CI, 0.0718–0.0776], p < 0.05) for those fixed time horizons and are able to generate predictions for any time horizon, without the need to retrain the models. Our study suggests that deep survival analysis tools can outperform binary classification in terms of both discriminative performance and calibration, offering a potentially plausible solution for forecasting risk in clinical practice. Full article

The modeling and simulation of societies requires identifying the spatio-temporal patterns of people’s activities. In urban areas, it is key to effective urban planning; it can be used in real estate projects to predict their future impacts on behavior in surrounding accessible areas. The work presented here aims at developing a method for making it possible to model the potential visits of the various equipment and public spaces of a district under construction by mobilizing data from census at the regional level and the layout of shops and activities as defined by the real estate project. This agent-based model takes into account the flow of external visitors, estimated realistically based on the pre-occupancy movements in the surrounding cities. To perform this evaluation, we implemented a multi-agent-based simulation model (MATSim) at the regional scale and at the scale of the future district. In its design, the district is physically open to the outside and will offer services that will be of interest to other residents or users of the surrounding area. To know the effect of this opening on a potential transit of visitors in the district, as well as the places of interest for the inhabitants, it is necessary to predict the flows of micro-trips within the district once it is built. We propose an attraction model to estimate the daily activities and trips of the future residents based on the attractiveness of the facilities and the urbanistic potential of the blocks. This transportation model is articulated in conjunction with the regional model in order to establish the flow of outgoing and incoming visitors. The impacts of the future district on the mobility of its surrounding area is deduced by implementing a simulation in the projection situation. Full article

This study introduces a novel adjustment to the firefly algorithm (FA) through the integration of rare instances of cannibalism among fireflies, culminating in the development of the honeybee mating-based firefly algorithm (HBMFA). The IEEE Congress on Evolutionary Computation (CEC) 2005 benchmark functions served as a rigorous testing ground to evaluate the efficacy of the new algorithm in diverse optimization scenarios. Moreover, thorough statistical analyses, including two-sample t-tests and fitness function evaluation analysis, the algorithm’s optimization capabilities were robustly validated. Additionally, the coefficient of determination, used as an objective function, was utilized with real-world wind speed data from the SR-25 station in Brazil to assess the algorithm’s applicability in modeling wind speed parameters. Notably, HBMFA achieved superior solution accuracy, with enhancements averaging 0.025% compared to conventional FA, despite a moderate increase in execution time of approximately 18.74%. Furthermore, this dominance persisted when the algorithm’s performance was compared with other common optimization algorithms. However, some limitations exist, including the longer execution time of HBMFA, raising concerns about its practical applicability in scenarios where computational efficiency is critical. Additionally, while the new algorithm demonstrates improvements in fitness values, establishing the statistical significance of these differences compared to FA is not consistently achieved, which warrants further investigation. Nevertheless, the added value of this work lies in advancing the state-of-the-art in optimization algorithms, particularly in enhancing solution accuracy for critical engineering applications. Full article

Evaluation of water quality and accurate prediction of water pollution indicators are key components in water resource management and water pollution control. The use of biological early warning systems (BEWS), in which living organisms are used as biosensors, allows for a comprehensive assessment of the aquatic environment state and a timely response in the event of an emergency. In this paper, we examine three machine learning algorithms (Theta, Croston and Prophet) to forecast bivalves’ activity data obtained from the BEWS developed by the authors. An algorithm for anomalies detection in bivalves’ activity data was developed. Our results showed that for one of the anomalies, Prophet was the best method, and for the other two, the anomaly detection time did not differ between the methods. A comparison of methods in terms of computational speed showed the advantage of the Croston method. This anomaly detection algorithm can be effectively incorporated into the software of biological early warning systems, facilitating rapid responses to changes in the aquatic environment. Full article

Convective storms represent a dangerous atmospheric phenomenon, particularly for the heavy and concentrated precipitation they can trigger. Given their high velocity and variability, their prediction is challenging, though it is crucial to issue reliable alarms. The paper presents a neural network approach to forecast the convective cell trajectory and intensity, using, as an example, a region in northern Italy that is frequently hit by convective storms in spring and summer. The predictor input is constituted by radar-derived information about the center of gravity of the cell, its reflectivity (a proxy for the intensity of the precipitation), and the area affected by the storm. The essential characteristic of the proposed approach is that the neural network directly forecasts the evolution of the convective cell position and of the other features for the following hour at a 5-min temporal resolution without a relevant loss of accuracy in comparison to predictors trained for each specific variable at a particular time step. Besides its accuracy ($R^2$ of the position is about 0.80 one hour in advance), this machine learning approach has clear advantages over the classical numerical weather predictors since it runs at orders of magnitude more rapidly, thus allowing for the implementation of a real-time early-warning system. Full article

The objective of this work is to predict the impact of technology on employment demand by profession in Spain between 2023 and 2035. The evaluation of this effect involved the comparison of two scenarios: a trend scenario obtained by predicting the evolution of occupations in demand and a technological scenario anticipated in the case of technological progress. To accomplish this goal, a new approach was developed in the present study based on previous research. Thus, we estimated the proportion of jobs likely to be automated using a task-based approach. Each occupation was examined based on its components to determine the degree to which these tasks could be automated. The results suggest that technology may influence job demand but with low percentages (between 3% and 5% for both low- and high-qualified workers) in the long term. However, job losses are greater in absolute difference in low-skilled professions, where a great share of the labor force is engaged. Full article

Since cryptocurrencies are among the most extensively traded financial instruments globally, predicting their price has become a crucial topic for investors. Our dataset, which includes fluctuations in Bitcoin’s hourly prices from 15 May 2018 to 19 January 2024, was gathered from Crypto Data Download. It is made up of over 50,000 hourly data points that provide a detailed view of the price behavior of Bitcoin over a five-year period. In this study, we used potent algorithms, including gradient descent, attention mechanisms, long short-term memory (LSTM), and artificial neural networks (ANNs). Furthermore, to estimate the price of Bitcoin, we first merged two deep learning algorithms, LSTM and attention mechanisms, and then combined LSTM-Attention with gradient-specific optimization to increase our model’s performance. Then we integrated ANN-LSTM and included gradient-specific optimization for the same reason. Our results show that the hybrid model with gradient-specific optimization can be used to anticipate Bitcoin values with better accuracy. Indeed, the hybrid model combines the best features of both approaches, and gradient-specific optimization improves predictive performance through frequent analysis of pricing data changes. Full article

All-Terrain Vehicles (ATVs) are popular off-road vehicles in the United States, with a staggering 10.5 million households reported to own at least one ATV. Despite their popularity, ATVs pose a significant risk of severe injuries, leading to substantial healthcare expenses and raising public health concerns. As such, gaining insights into the patterns of ATV-related hospitalizations and accurately predicting these injuries is of paramount importance. This knowledge can guide the development of effective prevention strategies, ultimately mitigating ATV-related injuries and the associated healthcare costs. Therefore, we performed an in-depth analysis of ATV-related hospitalizations from 2010 to 2021. Furthermore, we developed and assessed the performance of three forecasting models—Neural Prophet, SARIMA, and LSTM—to predict ATV-related injuries. The performance of these models was evaluated using the Root Mean Square Error (RMSE) accuracy metric. As a result, the LSTM model outperformed the others and could be used to provide valuable insights that can aid in strategic planning and resource allocation within healthcare systems. In addition, our findings highlight the urgent need for prevention programs that are specifically targeted toward youth and timed for the summer season. Full article

The scheduled maintenance of industrial equipment is usually performed with a low frequency, as it usually leads to unpredicted downtime in business operations. Nevertheless, this confers a risk of failure in individual modules of the equipment, which may diminish its performance or even lead to its breakdown, rendering it non-operational. Lately, predictive maintenance methods have been considered for industrial systems, such as power generation stations, as a proactive measure for preventing failures. Such methods use data gathered from industrial equipment and Machine Learning (ML) algorithms to identify data patterns that indicate anomalies and may lead to potential failures. However, industrial equipment exhibits specific behavior and interactions that originate from its configuration from the manufacturer and the system that is installed, which constitutes a great challenge for the effectiveness of ML model maintenance and failure predictions. In this article, we propose a novel method for tackling this challenge based on the development of a digital twin for industrial equipment known as a Remote Terminal Unit (RTU). RTUs are used in electrical systems to provide the remote monitoring and control of critical equipment, such as power generators. The method is applied in an RTU that is connected to a real power generator within a Public Power Corporation (PPC) facility, where operational anomalies are forecasted based on measurements of its processing power, operating temperature, voltage, and storage memory. Full article