Performance analysis of mathematical methods used to forecast the 2022 New York City Mpox outbreak.

In mid-2022, New York City (NYC) became the epicenter of the US mpox outbreak. We provided real-time mpox case forecasts to the NYC Department of Health and Mental Hygiene to aid in outbreak response. Forecasting methodologies evolved as the epidemic progressed. Initially, lacking knowledge of at-risk population size, we used exponential growth models to forecast cases. Once exponential growth slowed, we used a Susceptible-Exposed-Infectious-Recovered (SEIR) model. Retrospectively, we explored if forecasts could have been improved using an SEIR model in place of our early exponential growth model, with or without knowing the case detection rate. Early forecasts from exponential growth models performed poorly, as 2-week mean absolute error (MAE) grew from 53 cases/week (July 1-14) to 457 cases/week (July 15-28). However, when exponential growth slowed, providing insight into susceptible population size, an SEIR model was able to accurately predict the remainder of the outbreak (7-week MAE: 13.4 cases/week). Retrospectively, we found there was not enough known about the epidemiological characteristics of the outbreak to parameterize an SEIR model early on. However, if the at-risk population and case detection rate were known, an SEIR model could have improved accuracy over exponential growth models early in the outbreak.

Forecasting rheumatoid arthritis patient arrivals by including meteorological factors and air pollutants.

The burden of rheumatoid arthritis (RA) has gradually elevated, increasing the need for medical resource redistribution. Forecasting RA patient arrivals can be helpful in managing medical resources. However, no relevant studies have been conducted yet. This study aims to construct a long short-term memory (LSTM) model, a deep learning model recently developed for novel data processing, to forecast RA patient arrivals considering meteorological factors and air pollutants and compares this model with traditional methods. Data on RA patients, meteorological factors and air pollutants from 2015 to 2022 were collected and normalized to construct moving average (MA)- and autoregressive (AR)-based and LSTM models. After data normalization, the root mean square error (RMSE) was adopted to evaluate models' forecast ability. A total of 2422 individuals were enrolled. Not using the environmental data, the RMSEs of the MA- and AR-based models' test sets are 0.131, 0.132, and 0.117 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they are 0.110, 0.130, and 0.112 for the univariate LSTM models. Considering meteorological factors and air pollutants, the RMSEs of the MA- and AR-based model test sets were 0.142, 0.303, and 0.164 when the training set: test set ratio is 2:1, 3:1, and 7:1, while they were 0.108, 0.119, and 0.109 for the multivariable LSTM models. Our study demonstrated that LSTM models can forecast RA patient arrivals more accurately than MA- and AR-based models for datasets of all three sizes. Considering the meteorological factors and air pollutants can further improve the forecasting ability of the LSTM models. This novel method provides valuable information for medical management, the optimization of medical resource redistribution, and the alleviation of resource shortages.

Developing a transit desert interactive dashboard: Supervised modeling for forecasting transit deserts.

Transit deserts refer to regions with a gap in transit services, with the demand for transit exceeding the supply. This study goes beyond merely identifying transit deserts to suggest actionable solutions. Using a multi-class supervised machine learning framework, we analyzed factors leading to transit deserts, distinguishing demand by gender. Our focus was on peak-time periods. After assessing the Support Vector Machine, Decision Tree, Random Forest, and K-nearest Neighbor, we settled on the Random Forest method, supported by Diverse Counterfactual Explanation and SHapley Additive Explanation in our analysis. The ranking of feature importance in the trained Random Forest model revealed that factors such as density, design, distance to transit, diversity in the built environment, and sociodemographic characteristics significantly contribute to the classification of transit deserts. Diverse Counterfactual Explanation suggested that a reduction in population density and an increase in the proportion of green open spaces would likely facilitate the transformation of transit deserts into transit oases. SHapley Additive Explanation highlighted the differential impact of various features on each identified transit desert. Our analysis results indicate that identifying transit deserts can vary depending on whether the data is aggregated or separated by demographics. We found areas that have unique transit needs based on gender. The disparity in transit services was particularly pronounced for women. Our model pinpointed the core elements that define a transit desert. Broadly, to address transit deserts, strategies should prioritize the needs of disadvantaged groups and enhance the design and accessibility of transit in the built environment. Our research extends existing analyses of transit deserts by leveraging machine learning to develop a predictive model. We developed a machine learning-powered interactive dashboard. Integrating participatory planning approaches with the development of an interactive interface could enhance ongoing community engagement. Planning practices can evolve with AI in the loop.

Short- and long-term weather prediction based on a hybrid of CEEMDAN, LMD, and ANN.

Agriculture is one of the major economic sectors in Africa, and it predominantly depends on the climate. However, extreme climate changes do have a negative impact on agricultural production. The damage resulting from extreme climate change can be mitigated if farmers have access to accurate weather forecasts, which can enable them to make the necessary adjustments to their farming practices. To improve weather prediction amidst extreme climate change, we propose a novel prediction model based on a hybrid of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), local mean decomposition (LMD), and artificial neural networks (NN). A detailed comparison of the performance metrics for the short- and long-term prediction results with other prediction models reveals that the three-phase hybrid CEEMDAN-LMD-NN model is optimal in terms of the evaluation metrics used. The study's findings demonstrate the efficiency of the three-phase hybrid CEEMDAN-LMD-NN prediction model in decision-system design, particularly for large-scale commercial farmers, small-holder farmers, and the agricultural index insurance industry that require reliable forecasts generated at multi-step horizons.

Research on short-term power load forecasting based on VMD and GRU.

The traditional method for power load forecasting is susceptible to various factors, including holidays, seasonal variations, weather conditions, and more. These factors make it challenging to ensure the accuracy of forecasting results. Additionally, there is a limitation in extracting meaningful physical signs from power data, which ultimately reduces prediction accuracy. This paper aims to address these issues by introducing a novel approach called VCAG (Variable Mode Decomposition-Convolutional Neural Network-Attention Mechanism-Gated Recurrent Unit) for combined power load forecasting. In this approach, we integrate Variable Mode Decomposition (VMD) with Convolutional Neural Network (CNN). VMD is employed to decompose power load data, extracting valuable time-frequency features from each component. These features then serve as input for the CNN. Subsequently, an attention mechanism is applied to give importance to specific features generated by the CNN, enhancing the weight of crucial information. Finally, the weighted features are fed into a Gated Recurrent Unit (GRU) network for time series modeling, ultimately yielding accurate load forecasting results.To validate the effectiveness of our proposed model, we conducted experiments using two publicly available datasets. The results of these experiments demonstrate that our VCAG method achieves high accuracy and stability in power load forecasting, effectively overcoming the limitations associated with traditional forecasting techniques. As a result, this approach holds significant promise for broad applications in the field of power load forecasting.

Study on carbon emission driving factors and carbon peak forecasting in power sector of Shanxi province.

The realisation of the low-carbon transition of the energy system in resource-intensive regions, as embodied by Shanxi Province, depends on a thorough understanding of the factors impacting the power sector's carbon emissions and an accurate prediction of the peak trend. Because of this, the power industry's carbon emissions in Shanxi province are measured in this article from 1995 to 2020 using data from the Intergovernmental Panel on Climate Change (IPCC). To obtain a deeper understanding of the factors impacting carbon emissions in the power sector, factor decomposition is performed using the Logarithmic Mean Divisia Index (LMDI). Second, in order to precisely mine the relationship between variables and carbon emissions, the Sparrow Search Algorithm (SSA) aids in the optimisation of the Long Short-Term Memory (LSTM). In order to implement SSA-LSTM-based carbon peak prediction in the power industry, four development scenarios are finally built up. The findings indicate that: (1) There has been a fluctuating upward trend in Shanxi Province's total carbon emissions from the power industry between 1995 and 2020, with a cumulative growth of 372.10 percent. (2) The intensity of power consumption is the main factor restricting the rise of carbon emissions, contributing -65.19%, while the per capita secondary industry contribution factor, contributing 158.79%, is the main driver of the growth in emissions. (3) While the baseline scenario and the rapid development scenario fail to peak by 2030, the low carbon scenario and the green development scenario peak at 243,991,100 tonnes and 258,828,800 tonnes, respectively, in 2025 and 2028. (4) Based on the peak performance and the decomposition results, resource-intensive cities like Shanxi's power industry should concentrate on upgrading and strengthening the industrial structure, getting rid of obsolete production capacity, and encouraging the faster development of each factor in order to help the power sector reach peak carbon performance.

Spatiotemporal information enhanced multi-feature short-term traffic flow prediction.

Accurately predicting traffic flow is crucial for optimizing traffic conditions, reducing congestion, and improving travel efficiency. To explore spatiotemporal characteristics of traffic flow in depth, this study proposes the MFSTBiSGAT model. The MFSTBiSGAT model leverages graph attention networks to extract dynamic spatial features from complex road networks, and utilizes bidirectional long short-term memory networks to capture temporal correlations from both past and future time perspectives. Additionally, spatial and temporal information enhancement layers are employed to comprehensively capture traffic flow patterns. The model aims to directly extract original temporal features from traffic flow data, and utilizes the Spearman function to extract hidden spatial matrices of road networks for deeper insights into spatiotemporal characteristics. Historical traffic speed and lane occupancy data are integrated into the prediction model to reduce forecasting errors and enhance robustness. Experimental results on two real-world traffic datasets demonstrate that MFSTBiSGAT successfully extracts and captures spatiotemporal correlations in traffic networks, significantly improving prediction accuracy.

Modeling epidemic dynamics using Graph Attention based Spatial Temporal networks.

The COVID-19 pandemic and influenza outbreaks have underscored the critical need for predictive models that can effectively integrate spatial and temporal dynamics to enable accurate epidemic forecasting. Traditional time-series analysis approaches have fallen short in capturing the intricate interplay between these factors. Recent advancements have witnessed the incorporation of graph neural networks and machine learning techniques to bridge this gap, enhancing predictive accuracy and providing novel insights into disease spread mechanisms. Notable endeavors include leveraging human mobility data, employing transfer learning, and integrating advanced models such as Transformers and Graph Convolutional Networks (GCNs) to improve forecasting performance across diverse geographies for both influenza and COVID-19. However, these models often face challenges related to data quality, model transferability, and potential overfitting, highlighting the necessity for more adaptable and robust approaches. This paper introduces the Graph Attention-based Spatial Temporal (GAST) model, which employs graph attention networks (GATs) to overcome these limitations by providing a nuanced understanding of epidemic dynamics through a sophisticated spatio-temporal analysis framework. Our contributions include the development and validation of the GAST model, demonstrating its superior forecasting capabilities for influenza and COVID-19 spread, with a particular focus on short-term, daily predictions. The model's application to both influenza and COVID-19 datasets showcases its versatility and potential to inform public health interventions across a range of infectious diseases.

Forecasting the rheological state properties of self-compacting concrete mixes using the response surface methodology technique for sustainable structural concreting.

It is structurally pertinent to understudy the important roles the self-compacting concrete (SCC) yield stress and plastic viscosity play in maintaining the rheological state of the concrete to flow. It is also important to understand that different concrete mixes with varying proportions of fine to coarse aggregate ratio and their nominal sizes produce different and corresponding flow- and fill-abilities, which are functions of the yield stress/plastic viscosity state conditions of the studied concrete. These factors have necessitated the development of regression models, which propose optimal rheological state behavior of SCC to ensure a more sustainable concreting. In this research paper on forecasting the rheological state properties of self-compacting concrete (SCC) mixes by using the response surface methodology (RSM) technique, the influence of nominal sizes of the coarse aggregate has been studied in the concrete mixes, which produced experimental mix entries. A total of eighty-four (84) concrete mixes were collected, sorted and split into training and validation sets to model the plastic viscosity and the yield stress of the SCC. In the field applications, the influence of the sampling sizes on the rheological properties of the concrete cannot be overstretched due to the importance of flow consistency in SCC in order to achieve effective workability. The RSM is a symbolic regression analysis which has proven to exercise the capacity to propose highly performable engineering relationships. At the end of the model exercise, it was found that the RSM proposed a closed-form parametric relationship between the outputs (plastic viscosity and yield stress) and the studied independent variables (the concrete components). This expression can be applied in the design and production of SCC with performance accuracies of above 95% and 90%, respectively. Also, the RSM produced graphical prediction of the plastic viscosity and yield stress at the optimized state conditions with respect to the measured variables, which could be useful in monitoring the performance of the concrete in practice and its overtime assessment. Generally, the production of SCC for field applications are justified by the components in this study and experimental entries beyond which the parametric relations and their accuracies are to be reverified.

Load forecasting method based on CEEMDAN and TCN-LSTM.

Aiming at the problems of high stochasticity and volatility of power loads as well as the difficulty of accurate load forecasting, this paper proposes a power load forecasting method based on CEEMDAN (Completely Integrated Empirical Modal Decomposition) and TCN-LSTM (Temporal Convolutional Networks and Long-Short-Term Memory Networks). The method combines the decomposition of raw load data by CEEMDAN and the spatio-temporal modeling capability of TCN-LSTM model, aiming to improve the accuracy and stability of forecasting. First, the raw load data are decomposed into multiple linearly stable subsequences by CEEMDAN, and then the sample entropy is introduced to reorganize each subsequence. Then the reorganized sequences are used as inputs to the TCN-LSTM model to extract sequence features and perform training and prediction. The modeling prediction is carried out by selecting the electricity compliance data of New South Wales, Australia, and compared with the traditional prediction methods. The experimental results show that the algorithm proposed in this paper has higher accuracy and better prediction effect on load forecasting, which can provide a partial reference for electricity load forecasting methods.

Predicting Future Birth Rates with the Use of an Adaptive Machine Learning Algorithm: A Forecasting Experiment for Scotland.

The total fertility rate is influenced over an extended period of time by shifts in population socioeconomic characteristics and attitudes and values. However, it may be impacted by macroeconomic trends in the short term, although these effects are likely to be minimal when fertility is low. With the objective of forecasting monthly deliveries, this study concentrates on the analysis of registered births in Scotland. Through this approach, we examine the significance of precisely forecasting fertility trends, which can subsequently aid in the anticipation of demand in diverse sectors by allowing policymakers to anticipate changes in population dynamics and customize policies to tackle emerging demographic challenges. Consequently, this has implications for fiscal stability, national economic accounts and the environment. In conducting our analysis, we incorporated non-linear machine learning methods alongside traditional statistical approaches to forecast monthly births in an out-of-sample exercise that occurs one step in advance. The outcomes underscore the efficacy of machine learning in generating precise predictions within this particular domain. In sum, this research will comprehensively demonstrate a cutting-edge model of machine learning that utilizes several attributes to assist in clinical decision-making, predict potential complications during pregnancy and choose the appropriate delivery method, as well as help in medical diagnosis and treatment.

COVID-19 trends across borders: Identifying correlations among countries.

OBJECTIVES: To enhance the accuracy of forecasting future coronavirus disease 2019 (COVID-19) cases and trends by identifying and analyzing correlations between the daily case counts of different countries reported between January 2020 and January 2023, to uncover significant links in COVID-19 patterns between nations, allowing for real-time, precise predictions of disease spread based on observed trends in correlated countries. METHODS: Daily COVID-19 cases for each country were tracked between January 2020 and January 2023 to identify correlations between nations. Current case data were obtained from reliable sources, such as Johns Hopkins University and the World Health Organization. Data were analyzed in Microsoft Excel using Pearson's correlation coefficient to assess the strength of connections. RESULTS: Strong correlations (r > 0.80) were revealed between the daily reported COVID-19 case counts of numerous countries across various continents. Specifically, 62 nations showed significant correlations with at least one correlated (connected) country per nation. These correlations indicate a similarity in COVID-19 trends over the past 3 or more years. CONCLUSION: This study addresses the gap in country-specific correlations within COVID-19 forecasting methodologies. The proposed method offers essential real-time insights to aid effective government and organizational planning in response to the pandemic.

Emergence of the reproduction matrix in epidemic forecasting.

During the recent COVID-19 pandemic, the instantaneous reproduction number, R(t), has surged as a widely used measure to target public health interventions aiming at curbing the infection rate. In analogy with the basic reproduction number that arises from the linear stability analysis, R(t) is typically interpreted as a threshold parameter that separates exponential growth (R(t) > 1) from exponential decay (R(t) < 1). In real epidemics, however, the finite number of susceptibles, the stratification of the population (e.g. by age or vaccination state), and heterogeneous mixing lead to more complex epidemic courses. In the context of the multidimensional renewal equation, we generalize the scalar R(t) to a reproduction matrix, [Formula: see text], which details the epidemic state of the stratified population, and offers a concise epidemic forecasting scheme. First, the reproduction matrix is computed from the available incidence data (subject to some a priori assumptions), then it is projected into the future by a transfer functional to predict the epidemic course. We demonstrate that this simple scheme allows realistic and accurate epidemic trajectories both in synthetic test cases and with reported incidence data from the COVID-19 pandemic. Accounting for the full heterogeneity and nonlinearity of the infection process, the reproduction matrix improves the prediction of the infection peak. In contrast, the scalar reproduction number overestimates the possibility of sustaining the initial infection rate and leads to an overshoot in the incidence peak. Besides its simplicity, the devised forecasting scheme offers rich flexibility to be generalized to time-dependent mitigation measures, contact rate, infectivity and vaccine protection.

Research on China insurance demand forecasting: Based on mixed frequency data model.

In this paper, we introduce the mixed-frequency data model (MIDAS) to China's insurance demand forecasting. We select the monthly indicators Consumer Confidence Index (CCI), China Economic Policy Uncertainty Index (EPU), Consumer Price Index (PPI), and quarterly indicator Depth of Insurance (TID) to construct a Mixed Data Sampling (MIDAS) regression model, which is used to study the impact and forecasting effect of CCI, EPU, and PPI on China's insurance demand. To ensure forecasting accuracy, we investigate the forecasting effects of the MIDAS models with different weighting functions, forecasting windows, and a combination of forecasting methods, and use the selected optimal MIDAS models to forecast the short-term insurance demand in China. The experimental results show that the MIDAS model has good forecasting performance, especially in short-term forecasting. Rolling window and recursive identification prediction can improve the prediction accuracy, and the combination prediction makes the results more robust. Consumer confidence is the main factor influencing the demand for insurance during the COVID-19 period, and the demand for insurance is most sensitive to changes in consumer confidence. Shortly, China's insurance demand is expected to return to the pre-COVID-19 level by 2023Q2, showing positive development. The findings of the study provide new ideas for China's insurance policymaking.

MGLEP: Multimodal Graph Learning for Modeling Emerging Pandemics with Big Data.

Accurate forecasting and analysis of emerging pandemics play a crucial role in effective public health management and decision-making. Traditional approaches primarily rely on epidemiological data, overlooking other valuable sources of information that could act as sensors or indicators of pandemic patterns. In this paper, we propose a novel framework, MGLEP, that integrates temporal graph neural networks and multi-modal data for learning and forecasting. We incorporate big data sources, including social media content, by utilizing specific pre-trained language models and discovering the underlying graph structure among users. This integration provides rich indicators of pandemic dynamics through learning with temporal graph neural networks. Extensive experiments demonstrate the effectiveness of our framework in pandemic forecasting and analysis, outperforming baseline methods across different areas, pandemic situations, and prediction horizons. The fusion of temporal graph learning and multi-modal data enables a comprehensive understanding of the pandemic landscape with less time lag, cheap cost, and more potential information indicators.

Predicting the epidemiological trend of acute hemorrhagic conjunctivitis in China using Bayesian structural time-series model.

This study aims to explore the application value of the Bayesian Time Structure Sequence (BSTS) model in estimating the acute hemorrhagic conjunctivitis (AHC) epidemics. The reported AHC cases spanning from January 2011 to October 2022 in China were collated. Utilizing R software, the BSTS and Autoregressive Integrated Moving Average (ARIMA) models were constructed using the data from January 2011 to December 2021. The prediction effect of both models was compared using the data from January to October 2022, and finally the AHC incidence from November 2022 to December 2023 was predicted. The results indicated that forecast errors under the BSTS model were lower than those under the ARIMA model. The actual AHC incidence in July 2022 from the ARIMA model deviated from the 95% confidence interval (CI) of the predicted value. However, the observed AHC incidence from the BSTS model fell within the 95% CI of the predicted value. Notably, the BSTS model predicted 26,474 new AHC cases in China from November 2022 to December 2023, exhibiting better prediction performance compared to the ARIMA model. This indicates that the BSTS model possesses a high application value for forecasting the epidemic trends of AHC, making it a valuable tool for disease surveillance and prevention strategies.

Forecasting daily total pollen concentrations on a global scale.

BACKGROUND: There is evidence that global anthropogenic climate change may be impacting floral phenology and the temporal and spatial characteristics of aero-allergenic pollen. Given the extent of current and future climate uncertainty, there is a need to strengthen predictive pollen forecasts. METHODS: The study aims to use CatBoost (CB) and deep learning (DL) models for predicting the daily total pollen concentration up to 14 days in advance for 23 cities, covering all five continents. The model includes the projected environmental parameters, recent concentrations (1, 2 and 4 weeks), and the past environmental explanatory variables, and their future values. RESULTS: The best pollen forecasts include Mexico City (R2(DL_7) ≈ .7), and Santiago (R2(DL_7) ≈ .8) for the 7th forecast day, respectively; while the weakest pollen forecasts are made for Brisbane (R2(DL_7) ≈ .4) and Seoul (R2(DL_7) ≈ .1) for the 7th forecast day. The global order of the five most important environmental variables in determining the daily total pollen concentrations is, in decreasing order: the past daily total pollen concentration, future 2 m temperature, past 2 m temperature, past soil temperature in 28-100 cm depth, and past soil temperature in 0-7 cm depth. City-related clusters of the most similar distribution of feature importance values of the environmental variables only slightly change on consecutive forecast days for Caxias do Sul, Cape Town, Brisbane, and Mexico City, while they often change for Sydney, Santiago, and Busan. CONCLUSIONS: This new knowledge of the ecological relationships of the most remarkable variables importance for pollen forecast models according to clusters, cities and forecast days is important for developing and improving the accuracy of airborne pollen forecasts.

Title evaluation of FluSight influenza forecasting in the 2021-22 and 2022-23 seasons with a new target laboratory-confirmed influenza hospitalizations.

Accurate forecasts can enable more effective public health responses during seasonal influenza epidemics. For the 2021-22 and 2022-23 influenza seasons, 26 forecasting teams provided national and jurisdiction-specific probabilistic predictions of weekly confirmed influenza hospital admissions for one-to-four weeks ahead. Forecast skill is evaluated using the Weighted Interval Score (WIS), relative WIS, and coverage. Six out of 23 models outperform the baseline model across forecast weeks and locations in 2021-22 and 12 out of 18 models in 2022-23. Averaging across all forecast targets, the FluSight ensemble is the 2nd most accurate model measured by WIS in 2021-22 and the 5th most accurate in the 2022-23 season. Forecast skill and 95% coverage for the FluSight ensemble and most component models degrade over longer forecast horizons. In this work we demonstrate that while the FluSight ensemble was a robust predictor, even ensembles face challenges during periods of rapid change.

A compartmental model for smoking dynamics in Italy: a pipeline for inference, validation, and forecasting under hypothetical scenarios.

We propose a compartmental model for investigating smoking dynamics in an Italian region (Tuscany). Calibrating the model on local data from 1993 to 2019, we estimate the probabilities of starting and quitting smoking and the probability of smoking relapse. Then, we forecast the evolution of smoking prevalence until 2043 and assess the impact on mortality in terms of attributable deaths. We introduce elements of novelty with respect to previous studies in this field, including a formal definition of the equations governing the model dynamics and a flexible modelling of smoking probabilities based on cubic regression splines. We estimate model parameters by defining a two-step procedure and quantify the sampling variability via a parametric bootstrap. We propose the implementation of cross-validation on a rolling basis and variance-based Global Sensitivity Analysis to check the robustness of the results and support our findings. Our results suggest a decrease in smoking prevalence among males and stability among females, over the next two decades. We estimate that, in 2023, 18% of deaths among males and 8% among females are due to smoking. We test the use of the model in assessing the impact on smoking prevalence and mortality of different tobacco control policies, including the tobacco-free generation ban recently introduced in New Zealand.