Real-time Forecasting Research Articles

Ensemble Predictability of Week 3/4 Precipitation and Temperature over the United States via Cluster Analysis of the Large-Scale Circulation

Abstract Forecasting the week 3/4 period presents many challenges, resulting in a need for improvements to forecast skill. At this distance from initial conditions, numerical models struggle to present skillful forecasts of temperature, precipitation, and associated extremes. One approach to address this is to utilize more predictable large-scale circulation regimes to make forecasts of temperature and precipitation anomalies, using the association between the regimes and surface weather obtained from reanalysis products. This study explores the utility of k-means cluster analysis on geopotential heights and their ability to make skillful regime predictions in the week 3/4 period. Using 14-day running means of European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5) 500-hPa geopotential heights for the wintertime December–February (DJF) period, circulation regimes are identified using k-means clustering. Each period is assigned a cluster number, allowing the compositing of any reanalysis or observation variable to form cluster maps. Maps of 500-hPa height, 2-m temperature, precipitation, and storm-track anomalies are some of the variables composited. The utility of these relationships in a dynamical forecast setting is tested via Global Ensemble Forecast System v12 (GEFSv12) hindcasts and real-time ensemble suite forecasts. Week 3/4 deterministic and probabilistic experimental forecasts are then derived from cluster assignments using several methods. We find, via a conditional skill analysis, forecasts strongly correlated with a cluster exhibit greater skill for both dynamical model and cluster-derived forecasts. Our preliminary results represent a step forward to aid forecasters make more skillful assessments of the circulation regime and its associated surface weather for this challenging forecast time scale. Significance Statement Our paper links the local statistics of 14-day precipitation and temperature within the United States to very broad preferred patterns of winds and pressure over the wide Pacific–North American region. Such patterns, known as “circulation regimes,” provide the background that heavily influences local surface conditions. We find that forecasts for which midatmospheric anomalies are closely aligned with one or more circulation regimes are better at predicting the U.S. weather probabilities than other week 3–4 forecasts. A tool based on this finding identifies forecasts for which confidence is higher. Future work will be designed to further exploit the links between circulation regimes and weather to improve the accuracy of week 3–4 forecasts.

An AI-driven Approach to Traffic Congestion Prediction in Port Harcourt City Using Naïve Bayes

Four important intersections Location Junction, Rumuokoro Junction, GRA Junction, and Rumuokwuta Junction will be the focus of this study's investigation into the persistent problem of traffic congestion in Port Harcourt, Nigeria. In order to provide insights for improved traffic management, the project also aims to construct a predictive model that forecasts traffic congestion on certain routes using the Naïve Bayes algorithm. The study used both exploratory and descriptive research techniques to gather information about Port Harcourt's traffic congestion. Field surveys were carried out at the four intersections between 7 a.m. and 7 p.m. to collect traffic counts and vehicle footage. The investigation also included data from Rivers State Command, a division of the Federal Road Safety Corps (FRSC). Using this data to find patterns and trends in traffic flow, a Naïve Bayes algorithm was developed to classify and predict the degree of traffic congestion. With a 97% accuracy rate, the algorithm accurately classified 1164 out of 1200 traffic data points, predicting traffic congestion. The predictive algorithm used bar charts to show the traffic conditions; tall, moderate, and tiny bars, respectively, indicated high, medium, and low traffic congestion. The model's efficacy in real-time traffic forecasting was reinforced by the close match between the forecasts and observed traffic patterns. According to the study's findings, the Naïve Bayes algorithm can accurately forecast traffic congestion and provides road users and urban planners with useful information. The model can greatly enhance road efficiency by lowering travel times, relieving congestion, and improving traffic management on Port Harcourt's major arteries by accurately predicting traffic conditions.

Assessment of the extent of community preparedness to flood risk in Jigawa State, Nigeria

Jigawa State faces annual flood disasters that have resulted in significant loss of life and property, putting many communities at risk. This study aim to evaluate the preparedness for flood risk in Jigawa State, Nigeria. A sample of 666 respondents was selected for a self-administered questionnaire, with 601 fully completed. The collected data were analyzed descriptively to determine the preparedness index. (PI). From the result of the findings, a majority (77.7%) of the respondents agreed that the community is aware of flood risks. There was also a provision of a neighborhood directory (97.8%), local shelter (75.9%) and emergency contacts (55.4%) during floods. The PI (92.6%, 98.6% 84.1% and 85.1% respectively), are above the 65% threshold and hence considered ‘prepared’ in this regard; but, ‘somewhat prepared’ (PI of 61.7%) regarding awareness of flood disaster risk management strategies; ‘and unprepared’ (PI of 55.5%, 50.5%, 50.5%, 50.8% and 54.3% respectively) in terms of community organization of public education and training of flood risk reduction (66.6%); engagement on rehearsals/emergency drills (51.6%); good community-based warning system (51.4%); and a standalone system for property protection measures during floods (52.4%); as well as an active recovery plan (62.9%). It was recommended that proper embankment protection and water regulation outlets be established. Additionally, real-time flood forecasting and effective early warning systems should be developed. Communities should be assessed to identify flood risk zones before construction activities begin, or alternatively, resettlement to safer areas should be considered for those living in flood-prone regions.

The role of big data technology in project schedule management: the case of Amazon

With the rapid development of the Internet, big data technology has received widespread attention in the field of management. Traditional project schedule management methods cannot adapt to the complex and changing environment, and some researchers believe that big data technology has become a key tool to improve and optimize project management. However, there is a lack of mature theoretical systems and practical experience to guide the application of big data technology. Based on the case of Amazon, this paper analyses how the company uses big data technology to optimize project schedule management. It is found that the application of big data technology in project management brings significant benefits. It is able to provide empirical and innovative support for project schedule management. This paper discusses the application of big data technology in project schedule management, highlighting its capability to enable timely adjustments. Real-time monitoring and forecasting facilitate proactive management of project directions and potential risks. Moreover, it leverages real-time data to optimize resource allocation and enhance resource utilization. Furthermore, the paper addresses the challenges and proposes countermeasures associated with big data technology in this context. To tackle the issue of uneven data quality, a robust data collection mechanism should be established.

AI for Traffic Prediction and Management

Urban traffic congestion is a growing problem in cities across the globe, contributing to long delays, higher fuel consumption, environmental degradation, and economic losses. Conventional traffic management systems often depend on static data and rule-based approaches, which fall short in dealing with the complexity and variability of modern traffic. This paper introduces an AI-based traffic management approach that utilizes machine learning models to provide real-time traffic forecasts. By integrating historical data, live sensor inputs, and machine learning techniques, this system aims to enhance traffic flow, alleviate congestion, and improve travel efficiency. The model is compared against existing systems, demonstrating improved accuracy, flexibility, and scalability. Results indicate that the AI-based system offers significant advantages in managing urban traffic, surpassing traditional methods. The study further elaborates on how AI-powered traffic management can cut travel times by ensuring efficiency and safety, therefore playing a part in environmental sustainability through emission reduction, and the opportunities and challenges it brings to the table in the implementation of AI in traffic systems.

Lessons learnt from a real-time attribution and contextualisation trial in a National Meteorological and Hydrological Service

Abstract When a record hot month occurs, timely and credible attribution and contextualisation information can enhance public understanding and future preparedness. This is particularly effective if provided in real time by a National Meteorological and Hydrological Service (NMHS). Many NMHSs are working to integrate research-based attribution methods into their operational services. In this study, researchers and climate service staff collaborated to assess the feasibility of delivering such information swiftly and aligned with standard NMHS data and procedures. The record warm July (winter) temperatures of Tasmania, Australia in 2023 were chosen to illustrate the trial. Rapid results were available three days after the event. Approximately half of the unusual warmth was attributed to climate change, with the likelihood of breaking the previous record at least 17 times higher in the current climate compared to a stationary pre-industrial climate (14% vs. 0.4%). The warming trend became evident in the 1980s, and by 2060, average July temperatures in Tasmania match the record temperature of July 2023 under a high emissions scenario. However, average July minimum temperatures were not well modelled, necessitating the addition of a higher-resolution forecast-based attribution method. In subsequent analysis, almost all the forecast temperature anomaly, and reduced storm activity, was attributable to climate change. Statistical analysis revealed that a weak El Niño partly offset the unusual warmth. To expedite these additional approaches, information drawn from real-time forecasts could be used. Lessons learnt from this trial include technical improvements to align better with NMHS protocols including using consistent datasets and baselines, and refining and automating the method suite. Logistical and communication enhancements included training staff to run the suite, improving communication materials, and developing delivery channels. These learnings provide key considerations for NMHSs as they move towards providing timely and credible climate attribution and contextualisation information as part of their operational services.

Dynamics of real-time forecasting failure and recovery due to data gaps: A study using EnKF-based assimilation with the Lorenz model

Data assimilation-based real-time forecasting is widely used in meteorological and hydrological applications, where continuous data streams are employed to update forecasts and maintain accuracy. However, the reliability of the data source can be compromised due to sensor and communication failures or physical or cyber-attacks, and the impact of data stream failures on the accuracy of the forecasting system is not well understood. This study aims to systematically investigate the process of data stream failure and recovery for the first time. To achieve this, data gaps with varying lengths and timings are introduced to EnKF-based data assimilation system on the Lorenz model operating in both chaotic and periodic modes. Results show that the forecasting error grows exponentially in the chaotic mode but was limited in the periodic mode from the start of the data gap. For chaotic mode, the recovery of the system depends on the length of the data gap if the model error is not saturated; after saturation, the timing of the data stream recovery is important. Moreover, even long after restarting the data assimilation in the chaotic mode, the forecasting system cannot fully restore the original accuracy, while the periodic mode is generally resilient to disruption. This research introduces new metrics for quantifying system resilience and provides crucial insights into the long-term implications of data gaps, advancing our understanding of forecasting system behavior and reliability.

Improving a WRF-Based High-Impact Weather Forecast System for a Northern California Power Utility

We describe enhancements to an operational forecast system based on the Weather Research and Forecasting (WRF) model for the prediction of high-impact weather events affecting power utilities, particularly conditions conducive to wildfires. The system was developed for Pacific Gas and Electric Corporation (PG&E) to forecast conditions in Northern and Central California for critical decision-making such as proactively de-energizing selected circuits within the power grid. WRF forecasts are routinely produced on a 2 km grid, and the results are used as input to wildfire fuel moisture, fire probability, wildfire spread, and outage probability models. This forecast system produces skillful real-time forecasts while achieving an optimal blend of model resolution and ensemble size appropriate for today’s computational resources afforded to utilities. Numerous experiments were performed with different model settings, grid spacing, and ensemble configuration to develop an operational forecast system optimized for skill and cost. Dry biases were reduced by leveraging a new irrigation scheme, while wind skill was improved through a novel approach involving the selection of Global Ensemble Forecast System (GEFS) members used to drive WRF. We hope that findings in this study can help other utilities (especially those with similar weather impacts) improve their own forecast system.

Real-time flood forecasting and uncertainty analysis: a case study of the Krong H’nang hydropower reservoir

ABSTRACT Early and reliable flood forecasting is crucial for mitigating the impacts of floods and ensuring the safe operation of irrigation and hydroelectric facilities. Traditional methods often use a calibrated event-based rainfall-runoff model with a limited number of simulations, making it difficult to measure parameter uncertainties accurately. This paper introduces a new method for estimating the parameters of the HEC-HMS model and evaluating the uncertainties in real-time flood forecasting. First, the Latin Hypercube Sampling (LHS) procedure is used to efficiently sample the parameter values throughout the feasible parameter space. Next, thousands of parameter sets are simulated using a deterministic rainfall-runoff model, generating numerous initial solutions for the Shuffled Complex Evolution (SCE-UA) algorithm to search and evolve. Additional parameter sets are then generated as the search evolves, leading to new simulations until the algorithm reaches the convergence criteria. The optimal solutions are selected based on predefined multiple objective functions. Uncertainty of the forecast results is also computed using the Generalized Likelihood Uncertainty Estimation (GLUE) method and represented as confidence intervals. The method was applied to forecast flood hydrographs at the Krong H’nang hydropower reservoir in Vietnam, using data from 33 flood events from 2016 to 2021. The results demonstrate that the program can effectively forecast the flood hydrograph up to 4 hours in advance (the Kling-Gupta efficiency KGE > 0.8 and the absolute relative volume error |VE| < 10%). The observed values fall within the uncertainty range of Q5%-Q95%. Compared to the conventional method, which uses a fixed parameter set value, this approach is superior and therefore can assist policymakers and operators in more effectively managing reservoir operations.

Quantifying the impact of prevalence-dependent adaptive behavior on COVID-19 transmission: A modeling case study in Maryland

The COVID-19 pandemic highlighted the need for robust epidemic forecasts, projecting health burden over short- and medium-term time horizons. Many COVID-19 forecasting models incorporate information on infection transmission, disease progression, and the effects of interventions, but few combine information on how individuals change their behavior based on altruism, fear, risk perception, or personal economic circumstances. Moreover, early models of COVID-19 produced under- and over-estimates, failing to consider the complexity of human responses to disease threat and prevention measures. In this study, we modeled adaptive behavior during the first year of the COVID-19 pandemic in Maryland, USA. The adapted compartmental model incorporates time-varying transmissibility informed on data of environmental factors (e.g., absolute humidity) and behavioral factors (aggregate mobility and perceived risk). We show that humidity and mobility alone did little to explain transmissibility after the first 100 days. Including adaptive behavior in the form of perceived risk as a function of hospitalizations more effectively explained inferred transmissibility and improved out-of-sample fit, demonstrating the model’s potential in real-time forecasting. These results demonstrate the importance of incorporating endogenous behavior in models, particularly during a pandemic, to produce more accurate projections, which could lead to more impactful and efficient decision making and resource allocation.

FNNGM: A neural-driven fractional-derivative multivariate fusion model for interpretable real-time CPI forecasts

Integrating models from diverse sources has attracted substantial interest in developing advanced time series forecasting technologies. However, current research lacks a comprehensive and deep fusion model to integrate multiple forecasting methodologies. To this end, this paper proposes a neural-driven fractional-derivative multivariate fusion model (FNNGM (p, n)) to assimilate the fractional-derivative dynamical system, the driving factor in grey multivariate models, and the neural network into a cohesive framework. Consequently, this fusion architecture can benefit from the synergy of the target system's dynamics, extensive exogenous information, and non-linear transformation. Additionally, FNNGM (p, n) fosters extra functionalities through its inherent memory layer and sequence decomposition, bolstering model interpretability with the visible memory mechanism and understandable model workflows. To showcase the utility of FNNGM (p, n), this paper conducts real-time monthly consumer price index (CPI) forecasts that span ten years (from 2013:08 to 2023:07), analyzing the interpretable results from FNNGM (p, n) and contrasting it against many prevailing benchmark models. The comparison results reveal FNNGM (p, n)’s highly concentrated error distributions and the minimum mean absolute percentage forecasting error (APFE), squared forecasting error (SFE), and absolute forecasting error (AFE) values of 0.22 %, 0.59, and 0.56, respectively. Furthermore, the ablation experiments are performed to explore the specific effects and compatibilities of the fusion components, validating the effectiveness of the proposed fusion approach.

A novel incremental ensemble learning for real-time explainable forecasting of electricity price

The development of a stable, safe, secure and sustainable energy future is a challenge for all countries these days. In terms of electricity price, its volatile nature makes its prediction a complex task. A precise real-time forecast of the electricity price can have significant consequences for the economy and risks faced. This work presents a new ensemble learning algorithm for making real-time predictions of electricity price in Spain. It combines long and short-term behavior patterns following an online incremental learning approach, keeping the model always up to date. The detection of novelties and unexpected behaviors in the time series streams allows the algorithm to provide more accurate predictions than the reference machine learning algorithms with which it is compared. In addition, the proposed algorithm predicts in real-time and the predictions obtained are interpretable, thus contributing to the Explainable Artificial Intelligence.

The 2023/24 El Niño and the Feasibility of Long-Lead ENSO Forecasting

Abstract Through its atmospheric teleconnections, El Niño–Southern Oscillation (ENSO) shifts and disrupts weather and climate patterns far beyond the equatorial Pacific where it occurs often resulting in catastrophic consequences in many countries of the world. It is also the largest source of seasonal and interannual climate predictability. Despite its huge importance, ENSO forecasting is still not performed operationally at longer leads than about 6 months ahead. At the same time, there is mounting scientific evidence that forecasts are possible even more than a year in advance. Early warning of ENSO events could substantially mitigate some of the most damaging impacts, such as floods, droughts, and harvest failure and help avoid famine, migration, and disease outbreaks. Here, we present forecasts from a statistical ENSO model of the next El Niño predicted to occur in the winter of 2023/24, at lead times between 11 and 17 months ahead of an expected peak in December 2023. We use a statistical unobserved dynamic components model (EDCM) based on subsurface ocean temperatures as well as sea surface temperatures and zonal wind stress. EDCM has been previously validated through hindcasts of the major El Niños since 1970 and through real-time forecasts of the 2015/16 and 2018/19 El Niños. Our statistical framework and results indicate that there is potential for doubling the operational predictive lead time of ENSO to at least 12 months, with additional promise for even earlier anticipation of 19 months. Such longer-lead forecasts could be of high value, because decision-making and management in a number of key socioeconomic sectors could be greatly improved.

Real-Time Forecasting of Intradialytic Hypotension Using Deep Learning and Multimodal Data Integration

Real-Time Forecasting of Intradialytic Hypotension Using Deep Learning and Multimodal Data Integration

Real-time detection and temperature forecasting of large-space building fires using machine learning

Real-time detection and temperature forecasting of large-space building fires using machine learning

An enhanced Standardized Precipitation–Evapotranspiration Index (SPEI) drought-monitoring method integrating land surface characteristics

Abstract. Atmospheric evaporative demand is a key metric for monitoring agricultural drought. Existing ways of estimating evaporative demand in drought indices do not faithfully represent the constraints imposed by land surface characteristics and become less accurate over nonuniform land surfaces. This study proposes incorporating surface vegetation characteristics, such as vegetation dynamics data, aerodynamic parameters, and physiological parameters, into existing potential-evapotranspiration (PET) methods. This approach is implemented across the continental United States (CONUS) for the period from 1981–2017 and is tested using a recently developed drought index, the Standardized Precipitation–Evapotranspiration Index (SPEI). We show that activating realistic maximum surface conductance and aerodynamic conductance could improve the prediction of soil moisture dynamics and drought impacts by 29 %–41 % on average compared to more simple, widely used methods. We also demonstrate that this is especially effective in forests and humid regions, with improvements of 86 %–89 %. Our approach only requires a minimal amount of ancillary data while allowing for both historical reconstruction and real-time drought forecasting. This offers a physically meaningful yet easy-to-implement way to account for vegetation control in drought indices.

Supervised Learning-Based Prediction of Lightning Probability in the Warm Season

The accurate prediction of lightning is crucial for forecasters to respond effectively to its related hazards. The rapid development and confined spatial extent of convective storms, in which lightning frequently occurs, pose considerable challenges for accurately predicting their locations using numerical weather prediction (NWP) models. Lightning occurrence is often prognosed using thermodynamic parameters, convective available potential energy (CAPE), the severe weather threat index (SWEAT), the lifted index (LI), etc. A high-resolution NWP model provides a prediction of these thermodynamic parameters at high spatiotemporal resolution with high accuracy for a few hours. However, a complicated algorithm is required to handle all the useful high-resolution variables from the NWP model. The recently emerging machine learning technique can solve this issue by properly handling these “big data” without any model distributional assumption. In this study, we developed a random forest algorithm for nowcasting and very short-range forecasting (useful for ~6 h), named LightningRF. LightningRF was trained by using lightning occurrence as a response variable and characteristic parameters from the NWP as predictors. It was also applied to analysis and forecast fields, showing a high probability of lightning within the observed lightning regions. This highlights the potential of helping forecasters improve their lightning forecasting skills using real-time probabilistic forecasts from a trained model.

An Urban Flood Model Development Coupling the 1D and 2D Model with Fixed-Time Synchronization

Due to climate change, the frequency and intensity of torrential rainfall in urban areas are increasing, leading to more frequent flood damage. Consequently, there is a need for a rapid and accurate analysis of urban flood response capabilities. The dual-drainage model has been widely used for accurate flood analysis, with minimum time step synchronization being commonly adopted. However, this method has limitations in terms of speed. This study applied the hyper-connected solution for an urban flood (HC-SURF) model with fixed-time step flow synchronization, validated its accuracy using laboratory observation data, and tested its effectiveness in real urban watersheds with various synchronization times. Excellent performance was achieved in simulating real phenomena. In actual urban watersheds, as the synchronization time increased, the errors in surcharge and discharge also increased due to the inability to accurately reflect water level changes within the synchronization time; however, overall, they remained minimal. Therefore, the HC-SURF model is demonstrated as a useful tool for urban flood management that can be used to advantage in real-time flood forecasting and decision-making.

An early-warning forecast model for red tide (Karenia brevis) blooms on the southwest coast of Florida

Karenia brevis blooms occur nearly annually along the southwest coast of Florida, and effective mitigation of ecological, public health, and economic impacts requires reliable real-time forecasting. We present two boosted random forest models that predict the weekly maximum K. brevis abundance category across the Greater Charlotte Harbor estuaries over one-week and four-week forecast horizons. The feature set was restricted to data available in near-real time, consistent with adoption of the models as decision-support tools. Features include current and lagged K. brevis abundance statistics, Loop Current position, sea surface temperature, sea level, and riverine discharges and nitrogen concentrations. During cross-validation, the one-week and four-week forecasts exhibited 73 % and 84 % accuracy, respectively, during the 2010–2023 study period. In addition, we assessed the models’ reliability in forecasting the onset of 10 bloom events on time or in advance; the one-week and four-week models anticipated the onset eight times and five times, respectively.

Augmenting the real-time rainfall forecast skills over odisha using deep learning technique

Augmenting the real-time rainfall forecast skills over odisha using deep learning technique