Uncertain Forecasts Research Articles

Transferability of ecological forecasting models to novel biotic conditions in a long-term experimental study.

Ecological forecasting models play an increasingly important role for managing natural resources and assessing our fundamental knowledge of processes driving ecological dynamics. As global environmental change pushes ecosystems beyond their historical conditions, the utility of these models may depend on their transferability to novel conditions. Because species interactions can alter resource use, timing of reproduction, and other aspects of a species' realized niche, changes in biotic conditions, which can arise from community reorganization events in response to environmental change, have the potential to impact model transferability. Using a long-term experiment on desert rodents, we assessed model transferability under novel biotic conditions to better understand the limitations of ecological forecasting. We show that ecological forecasts can be less accurate when the models generating them are transferred to novel biotic conditions and that the extent of model transferability can depend on the species being forecast. We also demonstrate the importance of incorporating uncertainty into forecast evaluation with transferred models generating less accurate and more uncertain forecasts. These results suggest that how a species perceives its competitive landscape can influence model transferability and that when uncertainties are properly accounted for, transferred models may still be appropriate for decision making. Assessing the extent of the transferability of forecasting models is a crucial step to increase our understanding of the limitations of ecological forecasts.

A hybrid robust SBM-DEA, multiple regression, and MCDM-GIS model for airport site selection: Case study of Sistan and Baluchestan Province, Iran

This study focuses on the strategic decision-making process for selecting airport locations in developing countries, where investment constraint is a significant concern. Recognizing that airport location decisions are influenced by a multitude of factors, often in the absence of comprehensive data and amidst uncertain forecasts, there is a need for a methodology capable of adeptly handling various factors under uncertainty. The goal is to provide solutions that remain feasible and near-optimal, even with some variations in input parameters, ensuring robustness. To this end, this research introduces a decision tool incorporating Slack-Based Measurement in Robust Data Envelopment Analysis (SBM-RDEA). The Slack-based method is beneficial in cases with multiple inputs and outputs where their relationships are not strictly proportional, as in the airport location selection problem. DEA, in conjunction with Multiple Regression analysis, leverages available data on the attributes of operational regional airports to compute the significance of these criteria in shaping the success factors of these facilities. Furthermore, these weightings can be employed to evaluate the suitability of airport locations currently under development and assess their potential for contributing to regional development. Additionally, to address the uncertainty of input data, a Robust optimization approach is employed to ensure a reliable response for this strategic decision-making process. This weighting framework is utilized twice within the research methodology: first, to assess the potential of different counties in the state for hosting a new regional airport, and second, to identify the optimal location for the airport in an MCDM-GIS analysis. This methodology has been applied to a case study in Sistan and Baluchistan, Iran. The result of the proposed method has been compared with one of the most common existing methodologies. This method identifies Zahedan County as having the highest potential and selects the location (29.48° N, 60.90° E), in the east of Zahedan city, as the optimal site for airport construction. Validation results confirm the efficacy of this solution.

Storage management in a rolling horizon Dynamic Real-Time Optimization (DRTO) methodology for a non-concentrating solar thermal plant for low temperature heat production

The intermittency and uncertain forecasts of solar irradiation complicate the operation of a solar thermal plant with thermal storage for heat production. In this work, a rolling horizon Dynamic Real-Time Optimization (DRTO) methodology is proposed to determine the economic optimal operation of a non-concentrating solar thermal plant for low temperature heat production, using a planning phase to improve storage management. The methodology is tested online on a detailed simulation model representing a large-scale solar thermal plant in case studies, using variable heat demand and real data for the weather forecasts and measurements. It was shown that DRTO performs better than offline Dynamic Optimization thanks to the use of updated weather forecasts and the regular re-initialization of the system state using measurements. An increase up to 57% in supplied energy and a decrease up to 35% in operating costs were achieved with DRTO compared to DO. Guidelines on the best storage management policy at the DRTO level, using the planning phase, are formulated. While storing the maximum energy possible for later use is the best option when overheating is not a risk, following the planned storage state helps to prevent overheating when the solar irradiation is high and the heat demand low.

A multi-variable hybrid system for port container throughput deterministic and uncertain forecasting

Container transport is the most environmentally friendly and sustainable way to transport bulk cargo currently. The accurate prediction of container throughput is of great significance to the operation of the port. It is directly related to the healthy development of the entire logistics system, and also serves as a reference for decision makers in the construction of port infrastructure. However, the container throughput sequence contains the influence and restriction of a variety of superimposed factors, and has the characteristics of nonlinear and non-stationary. Traditional technology cannot effectively capture the changes of external related factors. To make up for the deficiencies, a multi-variable hybrid deterministic and uncertain forecasting framework based on improved preprocessing technique and swarm intelligence optimizer is constructed. It not only considers the impact of port hinterland economic indicators, port transport system and transport capacity factors, but also calculates the upper and lower limits of container throughput under different probabilities. The results and tests show that mean absolute percentage errors obtained by the presented forecast system are 1.1551%, 2.0936% and 2.5546% respectively, and the prediction interval coverage probability values of 1 can be achieved. The hybrid system is effective, stable and has reasonable running time, which can be widely popularized. And it is conducive to the orderly operation of transportation industry and the development of container port cities.

Mitigating stochastic uncertainty from weather routing for ships with wind propulsion

Reducing the shipping sector's contribution to climate change requires urgent emission reductions this decade. Both weather routing and wind propulsion offer immediate solutions, where combining sails with efficient routing amplifies the performance of each technology. However, while large emission savings are theoretically available, the impact of stochastic uncertainty from wind forecasts is unknown. Here, we present a novel approach that exploits fuel consumption calculations from over a thousand departures across three routes to characterise stochastic uncertainty. We show that routes with ideal wind conditions and long voyage times are most sensitive to uncertain forecast inputs, reducing savings from Flettner rotors and weather routing by up to 44% when a priori weather routing strategies are used. This paper further shows how an adaptive weather routing strategy can be used as an accurate prediction tool to reduce uncertainty on all routes investigated, reliably amplifying carbon savings from Flettner rotors by between 1.16 and 2.48 times typical great circle route savings. Overall, this paper provides greater assurance around the previously estimated carbon savings that serves to strengthen confidence in a wind-assisted decarbonisation strategy and its potential to provide essential emission reductions this decade.

Forecast-based action for conservation.

Extreme weather events pose an immediate threat to biodiversity, but existing conservation strategies have limitations. Advances in meteorological forecasting and innovation in the humanitarian sector provide a possible solution-forecast-based action (FbA). The growth of ecological forecasting demonstrates the huge potential to anticipate conservation outcomes, but a lack of operational examples suggests a new approach is needed to translate forecasts into action. FbA provides such a framework, formalizing the use of meteorological forecasts to anticipate and mitigate the impacts of extreme weather. Based on experience from the humanitarian sector, I suggest how FbA could work in conservation, demonstrating key concepts using the theoretical example of heatwave impacts on sea turtle embryo mortality, and address likely challenges in realizing FbA for conservation, including establishing a financing mechanism, allocating funds to actions, and decision-making under uncertainty. FbA will demand changes in conservation research, practice, and governance. Researchers must increase efforts to understand the impacts of extreme weather at more immediate and actionable timescales and should coproduce forecasts of such impacts with practitioners. International conservation funders should establish systems to fund anticipatory actions based on uncertain forecasts.

Risk-Aware Stochastic Energy Management of Microgrid with Battery Storage and Renewables

This paper deals with optimization-based control of real microgrids with uncertain forecasts of renewable energy production and local consumption. To achieve maximum economic benefits, these uncertainties need to be accounted for in a systematic fashion. Conventionally, this task is approached by employing stochastic model predictive control. While doing so allows to account for uncertainties in the forecasts, the downside is high computational complexity that hinders implementation in real time. In this paper we therefore propose an alternative method that decreases the computational burden by an order of magnitude without inducing significant suboptimality. The approach is based on splitting the stochastic model predictive control problem into two stages, one that employs multiple realizations of the uncertainties combines with a low-fidelity prediction model, and one that uses only the risk-aware realization, combined with a high-fidelity model. The theoretical development is then showcased on a real microgrid to confirm viability of our approach.

Deriving optimal operating rules for flood control considering pre-release based on forecast information

Pre-releasing before a flood can increase reservoir flood control storage capacity to effectively improve the flood disaster prevention and mitigation effects, but also might bring water shortage risk due to the uncertain forecasts. This paper proposes a framework to determine the optimal operating rules for flood control considering pre-release based on uncertain forecasts. The framework includes three models: a pre-release model at the early stage of the flood to enlarge the flood control storage capacity; a multi-objective optimization model with resilience and risk as objectives at the flood regulating stage to optimize the flood control operating rules; a fuzzy optimum selecting model to determine the satisfied operating rule considering forecast uncertainty and decision-maker's preferences. In the framework, forecast uncertainty has been considered from the perspective of the forecast error distribution. Nierji Reservoir in Northeast China is taken as a case study. Results show that compared with the existing operating rule, the recommended operating rule considering pre-release releases water more evenly and can not only decrease the peak flow at the downstream protection point but also improve the downstream flood resilience without increasing reservoir risk. The proposed framework that considers forecast error distribution provides higher superiority degrees of the rules than the traditional framework that considers the maximum and minimum forecast errors in the real-time operation of the 1969 and 2013 flood hydrographs.

Application of the Intensity Normalization Indicators method for predicting occupational morbidity in leading industries

Introduction. Identification of risk factors for the occurrence of occupational diseases by comparing various prognostic criteria is one of the most important tasks of hygiene and occupational health. The purpose of the study is to develop a prognostic matrix of occupational morbidity (OM) in the leading industries of the Irkutsk region for a set of main predictor factors using the method of intensity normalization indicators (INI). Materials and methods. There was used an information array of long-term OM in the leading industries of the Irkutsk region. The method of calculating weight indices was used to assess the strength of the influence of OM predictor factors and the INI method was used to calculate the prognostic significance of the factors. Results. The risk of occupational disease (OD) has been established to be associated with belonging to a certain occupation (OR=61.8), combined exposure to harmful factors in the working environment (OR=23.8), due to the imperfection of the technological process and equipment. The work experience with a harmful occupational factor, the age of employee, the industry are also significant, but the degree of their influence on the occurrence of OD is much lower. Based on the predictor factors, the risk of OD was calculated, its possible range (0.019-0.412 conventional units) with three subranges (favourable, uncertain and unfavourable prognosis) was determined. The risks of OD in persons with a work experience of 1-4 years, under the age of 40, exposed to the combined effects of physical factors, working as excavator driver and an assembler-riveter, were 0.269 and 0.226 (uncertain forecast). The risk values of OD in workers of these occupations increase by 24.4% and 29.1%, respectively, with an increase in length of service and age, reaching a maximum at the age of 50-59 years with an work experience of 30 or more years (0.334 and 0.292, unfavourable prognosis). The limitations of this INI model include the non-inclusion of clinical, functional, biochemical and socio-psychological indicators of workers among the predictor factors. Limitations. An analysis of one thousand eight hundred sixty two cases of newly diagnosed occupational diseases over a 10-year period, 11 main predictor factors, which is a sufficient reference sample, was made to study occupational morbidity in the leading industries of the Irkutsk region and developing a prognostic matrix. Conclusion. The use of INI makes it possible to give an integrated risk assessment of the OD both for individual factors and for their complex, and to determine risk groups.

Iterative multilevel assimilation of inverted seismic data

In ensemble-based data assimilation (DA), the ensemble size is usually limited to around one hundred. Straightforward application of ensemble-based DA can therefore result in significant Monte Carlo errors, often manifesting themselves as severe underestimation of parameter uncertainties. Localization is the conventional remedy for this problem. Assimilation of large amounts of simultaneous data enhances the negative effects of Monte Carlo errors. Use of lower-fidelity models reduces the computational cost per ensemble member and therefore renders the possibility to reduce Monte Carlo errors by increasing the ensemble size, but it also adds to the modeling error. Multilevel data assimilation (MLDA) uses a selection of models forming hierarchies of both computational cost and computational accuracy, and tries to balance between Monte Carlo errors and modeling errors. In this work, we assess a recently developed MLDA algorithm, the Multilevel Hybrid Ensemble Smoother (MLHES), and introduce and assess an iterative version of this algorithm, the Iterative Multilevel Hybrid Ensemble Smoother (IMLHES). In our assessments, we compare these algorithms with conventional single-level DA algorithms with localization. To this end, a typical example of large amount of spatially distributed data, i.e. inverted seismic data, is considered and three data sets of this kind are assimilated in three different petroleum reservoir models. Qualitatively evaluating the DA outcomes, it is found that multilevel algorithms outperform their conventional single-level counterparts in obtaining the posterior statistics of both uncertain parameters and model forecasts. Additionally, it is observed that IMLHES performs better than MLHES in the same regard, and also successfully converges to the proximity of solution in a case where the considered iterative single-level algorithm did not converge to the global optimum.

A Multi-Variable Hybrid System for Port Container Throughput Deterministic and Uncertain Forecasting

A Multi-Variable Hybrid System for Port Container Throughput Deterministic and Uncertain Forecasting

Comparison of two model predictive control methods that can deal with ensemble forecasts

In this work we numerically implement tree-based model predictive control (TB-MPC) to a Dutch water system. The TB-MPC is compared to deterministic control (MPC) and ensemble model predictive control (ENS-MPC). The comparison is done using synthetic ensembles with different dispersions. For example, in the deterministic runs, members from the ensembles with different percentiles are used. In total 44 closed-loop experiments were performed: the control action is calculated based on a linear model and sent to a linear model combined with non-linear pre-processing as simulation model. Using ensembles leads to a more robust control of the water system as ensemble approaches are able to control the water system even in case of uncertain forecast. In this case study TB-MPC shows better performance for larger uncertainties while ENS-MPC performs better for smaller uncertainties. This can be beneficial when extreme events are expected, but for day-to-day forecast TB-MPC shows a great potential.

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

Abstract. Streamflow forecasts are traditionally effective in mitigating water scarcity and flood defense. This study developed an artificial intelligence (AI)-based management methodology that integrated multi-step streamflow forecasts and multi-objective reservoir operation optimization for water resource allocation. Following the methodology, we aimed to assess forecast quality and forecast-informed reservoir operation performance together due to the influence of inflow forecast uncertainty. Varying combinations of climate and hydrological variables were input into three AI-based models, namely a long short-term memory (LSTM), a gated recurrent unit (GRU), and a least-squares support vector machine (LSSVM), to forecast short-term streamflow. Based on three deterministic forecasts, the stochastic inflow scenarios were further developed using Bayesian model averaging (BMA) for quantifying uncertainty. The forecasting scheme was further coupled with a multi-reservoir optimization model, and the multi-objective programming was solved using the parameterized multi-objective robust decision-making (MORDM) approach. The AI-based management framework was applied and demonstrated over a multi-reservoir system (25 reservoirs) in the Zhoushan Islands, China. Three main conclusions were drawn from this study: (1) GRU and LSTM performed equally well on streamflow forecasts, and GRU might be the preferred method over LSTM, given that it had simpler structures and less modeling time; (2) higher forecast performance could lead to improved reservoir operation, while uncertain forecasts were more valuable than deterministic forecasts, regarding two performance metrics, i.e., water supply reliability and operating costs; (3) the relationship between the forecast horizon and reservoir operation was complex and depended on the operating configurations (forecast quality and uncertainty) and performance measures. This study reinforces the potential of an AI-based stochastic streamflow forecasting scheme to seek robust strategies under uncertainty.

Point and interval prediction for non-ferrous metals based on a hybrid prediction framework

As a bulk product with huge international circulation, non-ferrous metals have frequent and severe price fluctuations, which have attracted great attention from academia and industry. However, the non-ferrous metal price series has strong volatility and nonlinear characteristics, which makes the realization of high-precision forecasts still a difficult and challenging problem. In this paper, a hybrid point prediction system is constructed to achieve high precision point prediction results. Moreover, uncertain forecasts contain more information and can provide market participants with more detailed guidance, but uncertainty forecasting is often ignored in practice. Based on the high precision point prediction system, the uncertainty prediction framework is proposed in this paper. Different distribution functions were used to analyze the distribution characteristics of the data, and the uncertainty prediction at different levels was successfully realized according to point prediction results. To verify prediction performance of the proposed prediction framework, multiple contrast experiments have been carried out using the London Metal Exchange daily future prices of Zinc, Copper and Lead. The empirical results show that the developed prediction framework has better predictive power for non-ferrous metals price prediction.

Incorporating weather forecasts into risk-based irrigation decision-making

ABSTRACT Irrigation decision-making is complex. It requires balancing multiple risks . We examined if incorporation of weather forecasts into irrigation decision-making improved environmental and economic outcomes on dairy farms in Canterbury, New Zealand. We focused on understanding how farmers can manage irrigation decision-making with uncertain weather forecasts, and the associated impacts on drainage, pasture growth and economics. Previous work had demonstrated that weather conditions were not used in irrigation decision-making as much as desirable and that weather forecast uncertainty was not explicitly considered. , We incorporated weather forecasts as a perfect forecast and the best available forecast. We used probability percentiles to incorporate forecast uncertainty into decision-making. The research hypothesis was that through utilising risk profiles of factors that influence environmental and economic outcomes of irrigation decisions, farmers could improve decison-makingwhen faced with uncertain future weather states. When weather forecasts were integrated into irrigation decision-making, there were environmental and economic benefits relative to a simple deficit-based irrigation decision rule. Based on a case study, we predicted 5% additional profit (approximately, $200 per hectare) may be possible when the best available forecasts was used relative to a simple deficit-based decision rule, and a further 1% profit if forecast uncertainty was considered.

Short-term apartment-level load forecasting using a modified neural network with selected auto-regressive features

Residential electricity load profiles and their diversity have become increasingly important to realize the benefits of Smart or Transactive Energy Networks (TENs). An important element of TENs will be practical, accurate, and implementable residential load forecasting techniques. While there have been many approaches to short-term load forecasting, few have included forecasting for individual households, partly because the high volatility and idiosyncrasies present in individual household load data can pose significant challenges. In this study, we develop a Convolutional Long Short-Term Memory-based neural network with Selected Autoregressive Features (termed a CLSAF model) to improve short-term household electricity load forecasting accuracy by employing three strategies: autoregressive features selection, exogenous features selection, and a “default” state to avoid overfitting at times of high load volatility. We include aggregations of apartments to floor and building level, because utilities may favor transactive approaches that rely on aggregator models, e.g., a cluster of consumers as opposed to an individual. We demonstrate that the CLSAF model, by virtue of its enhanced feature representation and modest computational resources, can accomplish load forecasting in a multi-family residential building across three spatial granularities (individual apartment/household, floor, and building levels), with an accuracy improvement of up to 25% compared to a persistence model. We propose a data screening technique to characterize time-series electricity-load data. This technique is suitable for integration into a TEN ecosystem and allows one to estimate confidence levels of the load forecasts to optimize computational resources and the risks associated with uncertain forecasts.

Noncomputerised Circadian Interventions for Improving Working Memory Performance among Children

Working Memory provides a mental workspace for tasks requiring both processing and storage. Working memory is a cognitive system whose essential function is to facilitate and beautify the potential of encoding, storage, and retrieval functions that are imperative for gaining knowledge and processing of facts. It has been prompted that various mediations applied within day-to-day contexts of children have the potential to improve working memory and generate transfer to real-world skills, anyway little is known about the effectiveness of these interventions among children. This review focuses to detect deliberately the adequacy of intervention or interventional package on working memory performance of children to identify their effects on Working Memory, advantages extended to near-and far-transfer capability of interventions, and gains sustained overtime and dosage of it. Literature searches were conducted across 10 electronic data bases using consistent keywords. Papers were screened by title and abstract (n=964) and judged against predefined eligibility criteria (n=63). Eighteen papers were included in the appraisal. Different working memory interventional approaches were included such as adapting the surroundings to decrease working memory loads; direct working memory training with and without tactics mandate and coaching competencies which circuitously effect on working memory (athletics, lexical apprehension, astonishing man-made play, and self-possession). Both direct training on working memory undertakings and rehearsing certain abilities that may likewise affect randomly on working memory which delivered refinement on working memory errands. Hardly, any research articulated dosage impact, estimated outlying shift of outcomes (n=4), or tried the solidness of valid statements after added time (n=4). The absence of an unmistakable hypothetical structure brought about uncertain forecasts about instructing and switch impacts. Methodological difficulties likewise compel the intensity of the proof, including: small-scale sample sizes; oversight of blinding of members and result assessors; and shortfall of active control group

COVID-19. WHO CAN HELP US?

The COVID-19 pandemic has disrupted the usual rhythm of our lives, becoming a surprise, a serious problem and a great challenge for all segments of society, but the prospects for overcoming this situation and returning to previous social standards remain unclear. Cautious and uncertain forecasts of specialists even for the near future and daily updates in the media of the number of infected and dead sow a sense of anxiety, and medical confessions about the lack of effective treatment create a sense of insecurity.

Multiobjective stochastic programming with recourses for real-time flood water conservation of a multireservoir system under uncertain forecasts

Flood water conservation realized through real-time multireservoir operations is effective in mitigating water scarcity. Owing to the influence of real-time inflow forecast uncertainty, determining an informed operation plan necessitates resolution of the conflict between upstream flood risk, downstream flood risk, and water scarcity risk. This study developed a multiobjective stochastic programming with recourses (MOSP) model to seek robust risk-averse plans under multiple risks. In the proposed approach, inflow forecast errors are modeled and sampled as spatially and temporally correlated stochastic processes using a copula function. The multiobjective stochastic programming is solved using the epsilon constraint method based on explicit formulation of multiple risk objectives with discretized inflow scenarios, and a rolling horizon with recourses for real-time operational updating is modeled to address the dynamic decision-making characteristics. The proposed methodologies were applied to the multireservoir system of the Pi River Basin (China), and comparisons with model results of a traditional coupled simulation and a deterministic single objective optimization model were conducted. Results indicated that capturing spatial and temporal dependencies of forecast uncertainty provides informative forecast support. Moreover, noninferior solutions obtained from MOSP dominate the deterministic optimal solution, which could either conserve 4.86 million m3 (12%) more water without increase in flood risk, or reduce the upstream flood risk by 3.1% without increase in either water scarcity or downstream flood risk during a typical receding flood. The proposed methodology provides a dynamic decision-making modeling tool that could reduce overall risk and determine a compromise for flood water conservation under uncertainty.

Nature of the forecast depending on the level of cytokines and the prevalence of AA and AG haplotypes in patients with sporadic and family forms of multiple sclerosis

The relationships between the nature of the prognosis, normal and elevated levels of pro-inflammatory (INF-γ, IL-1β) and anti-inflammatory cytokines (IL-10, IL-12), the prevalence of haplotypes AA and AG in 105 patients with sporadic form (recurrent course (RС) — 72, progressive types of course (PTС) — 33) and in 33 patients with family form (RС — 15, PTС — 18) of multiple sclerosis. Studies have shown that with RС, a favorable and uncertain prognosis in patients with a sporadic form of MS was significantly more likely to occur with a normal level of anti-inflammatory cytokines (IL-10, IL-12), while in a familial form, a normal level of IL-10 was associated with a favorable and IL-12 — with an uncertain forecast. With PTС in patients with a sporadic form, the normal INF-γ content was more likely to occur with an unfavorable prognosis, while its increased content was characteristic of an uncertain prognosis. In the family form, an unfavorable prognosis was more common with an elevated level of the pro-inflammatory cytokine INF-γ and a normal level of anti-inflammatory cytokine IL-10. This suggests that a complex and differentiated interaction of pro- and anti-inflammatory cytokines occurs with the participation of various pathogenetic mechanisms for different forms and types of course. Uncertain prognosis in familial form of RT, unlike sporadic, was more common in patients with AA haplotype. A comparative assessment of the relationship between AA and AG haplotypes revealed the predominance of AA haplotype with an uncertain prognosis in patients with familial form of RT. Haplotype AG was significantly more common in the family form of PTT and did not depend on the nature of the prognosis. Thus, the prevalence of AA and AG haplotypes in both sporadic and familial forms revealed a close relationship with the nature of the prognosis and the type of course. Key words: multiple sclerosis, sporadic and familial form, prognosis, type of course, cytokines, haplotype