Framework For Forecasting Research Articles

A Hybrid Framework for Multivariate Time Series Forecasting of Daily Urban Water Demand Using Attention-Based Convolutional Neural Network and Long Short-Term Memory Network

Urban water demand forecasting is beneficial for reducing the waste of water resources and enhancing environmental protection in sustainable water management. However, it is a challenging task to accurately predict water demand affected by a range of factors with nonlinear and uncertainty temporal patterns. This paper proposes a new hybrid framework for urban daily water demand with multiple variables, called the attention-based CNN-LSTM model, which combines convolutional neural network (CNN), long short-term memory (LSTM), attention mechanism (AM), and encoder-decoder network. CNN layers are used to learn the representation and correlation between multivariate variables. LSTM layers are utilized as the building blocks of the encoder-decoder network to capture temporal characteristics from the input sequence, while AM is introduced to the encoder-decoder network to assign corresponding attention according to the importance of water demand multivariable time series at different times. The new hybrid framework considers correlation between multiple variables and neglects irrelevant data points, which helps to improve the prediction accuracy of multivariable time series. The proposed model is contrasted with the LSTM model, the CNN-LSTM model, and the attention-based LSTM to predict the daily water demand time series in Suzhou, China. The results show that the hybrid model achieves higher prediction performance with the smallest mean absolute error (MAE), root mean squared error (RMSE), and mean absolute percentage error (MAPE), and largest correlation coefficient (R2).

A Fully Unsupervised Machine Learning Framework for Algal Bloom Forecasting in Inland Waters Using MODIS Time Series and Climatic Products

Progressively monitoring water quality is crucial, as aquatic contaminants can pose risks to human health and other organisms. Machine learning can support the development of new effective tools for water monitoring, including the detection of algal blooms from remotely sensed image series. Therefore, in this paper, we introduce the Algal Bloom Forecast (ABF) framework, a fully automated framework for algal bloom prediction in inland water bodies. Our approach combines machine learning, time series of remotely sensed products (i.e., Moderate-Resolution Imaging Spectroradiometer (MODIS) images), environmental data and spectral indices to build anomaly detection models that can predict the occurrence of algal bloom events in the posterior period. Our assessments focused on the application of the ABF framework equipped with the support vector machine (SVM), random forest (RF), and long short-term memory (LSTM) methods, the outcomes of which were compared through different evaluation metrics such as global accuracy, the kappa coefficient, F1-Score and R2-Score. Case studies covering the Erie (USA), Chilika (India) and Taihu (China) lakes are presented to demonstrate the effectiveness and flexibility of our learning approach. Based on comprehensive experimental tests, we found that the best algal bloom predictions were achieved by bringing together the ABF design with the RF model.

Stepwise decomposition-integration-prediction framework for runoff forecasting considering boundary correction

Predicting river runoff accurately is of substantial significance for flood control, water resource allocation, and basin ecological dispatching. To explore the reasonable and effective application of time series decomposition in runoff forecasting, this study proposed a novel stepwise decomposition-integration-prediction considering boundary correction (SDIPBC) framework by using the stepwise decomposition sampling method and multi-input neural network. On this basis, we implemented a hybrid forecasting model combining seasonal-trend decomposition procedures based on loess (STL) with the long short-term memory (LSTM) network called STL-LSTM (SDIPBC) to estimate mid-long term river runoff. The reliability of the method was assessed using the historical runoff series of the Lianghekou and Jinping I Reservoirs in the Yalong River Basin, China, and developed several single models and hybrid models for comparative experiments. The results show that the existing decomposition-based hybrid forecasting frameworks are not suitable for practical runoff forecasting. The proposed SDIPBC framework can avoid using future information and improve the prediction accuracy of the single prediction model. For the Nash-Sutcliffe efficiency coefficient (NSE), the ten-day runoff forecasting accuracy of STL-LSTM (SDIPBC) in Lianghekou reservoir and Jinping I Reservoirs reached 0.845 and 0.862 respectively, which improved 1.81 % and 2.38 % than the single LSTM model, indicating that this is a practical and reliable decomposition-based hybrid runoff forecasting method.

Correction: Nonparametric conditional density estimation in a deep learning framework for short-term forecasting

Correction: Nonparametric conditional density estimation in a deep learning framework for short-term forecasting

Probabilistic photovoltaic power forecasting using a calibrated ensemble of model chains

Physical model chain is a step-by-step modeling framework for the conversion of irradiance to photovoltaic (PV) power. When a model chain is fed with irradiance forecasts, it provides the corresponding PV power forecasts. Despite its advantages, forecasting with model chains has yet to receive the attention that it deserves. In several recent works, however, the idea of model-chain-based solar forecasting has been formally modernized, though the framework was restricted to deterministic forecasting. In this work, the model-chain-based forecasting framework is extended to the probability space, in that, a calibrated ensemble of model chains is used to generate probabilistic PV power forecasts. Using two-year data from eight PV plants in Hungary, alongside professional weather forecasts issued by the Hungarian Meteorological Services, it is empirically shown that the raw model-chain ensemble forecasts tend to be underdispered, but adequate post-processing is able to improve calibration and reduce the continuous ranked probability score of raw ensembles by 20%. Given the fact that uncertainty quantification has a cardinal importance to grid integration, this probabilistic extension of the model-chain-based solar forecasting framework is thought beneficial.

Development of a wind power ramp forecasting system via meteorological pattern analysis

AbstractRamp phenomena caused by abrupt changes in wind speed may confound the stable operation of correlated electrical power supply systems, yet accurate numerical predictions are challenging, as the wind is affected by complex interactions between large‐scale weather patterns and local geographical conditions. Further, optimal numerical weather prediction (NWP) methods and physics schemes vary as a function of weather patterns. The present study proposed a new real‐time wind power ramp forecast framework based on the flexible selection of optimal NWP models, which were derived via principal component analysis (PCA). The novelty of this analysis lies in that statistical methods were employed for NWP optimization, compared with their more conventional use during an NWP postprocessing. Here, a weather pattern was classified by PCA using outcomes from the global‐scale prediction models, and the optimum regional NWP system settings were acquired according to the weather patterns for further wind field dynamical downscaling. The performance of the developed prediction system was verified with wind power at wind turbine hub‐heights for three areas in eastern Japan, and the Critical Success Index (CSI) indicated an improvement of prediction accuracy over benchmark predictions by ≤0.184 for ramp‐up events and ≤0.127 for ramp‐down events (both observed in Tohoku area). Higher CSI values were consistently seen in three wind farm areas, indicative of the improvement in detection probability for actual ramp events compared with benchmark.

Integrating the Accuracy and Time Dimension of Foresight

Judgmental forecasting research has demonstrated that forecasters differ in their foresight––their ability to consistently forecast future states of the world accurately. However, the conceptualization of foresight underlying this research stream focuses exclusively on accuracy and thereby, neglects the time dimension of foresight. We develop a reconceptualization of foresight that integrates the dimensions of accuracy and time. To provide the theoretical basis for this integration, we propose a forecasting framework suggesting that forecasting future states of the world becomes easier over time as the availability of signals, which enable forecasters to forecast future states of the world more accurately, increases over time. Therefore, we reconceptualize foresight as the ability to forecast future states of the world accurately and early. To operationalize this reconceptualization of foresight in forecasting tournaments, we propose the time-weighted Brier score (TWBS), which weights errors made closer to the event horizon more heavily. We prove analytically that the TWBS is a strictly proper scoring rule that represents a mathematical generalization of the Brier score (BS). Furthermore, we show in a simulation study that the linear and square root TWBS, which weight the forecast errors over time heavier according to the linear and square root function, measure the true foresight of persons better than the BS under various theoretical signal trajectories. Taken together, we contribute to the emergent literature on foresight by providing a theoretical framework, reconceptualization, and generalized operationalization of foresight that integrate the dimensions of accuracy and time.

Functional data-driven framework for fast forecasting of electrode slurry rheology simulated by molecular dynamics

The computational simulation of the manufacturing process of lithium-ion battery composite electrodes based on mechanistic models allows capturing the influence of manufacturing parameters on electrode properties. However, ensuring that these properties match with experimental data is typically computationally expensive. In this work, we tackled this costly procedure by proposing a functional data-driven framework, aiming first to retrieve the early numerical values calculated from a molecular dynamics simulation to predict if the observable being calculated is prone to match with our range of experimental values, and in a second step, recover additional values of the ongoing simulation to predict its final result. We demonstrated this approach in the context of the calculation of electrode slurries viscosities. We report that for various electrode chemistries, the expected mechanistic simulation results can be obtained 11 times faster with respect to the complete simulations, while being accurate with a {R}_{rm{score}}^{2} equals to 0.96.

A novel framework for carbon price forecasting with uncertainties

Carbon price prediction is a key issue in the field of carbon market research. However, the existing methods of carbon price forecasting mostly regard carbon price series as a certain time series, but pay less attention to the uncertainty implied by carbon price series. Based on this, this paper proposes a forecasting model framework considering the uncertainty of carbon price series, which represents the carbon price series as a time series of probability density function to deal with the uncertainty. A prediction model based on the probability density recurrence network of carbon price is constructed with the help of the recurrence network construction technology of data and link prediction, and the advantages of the model are verified by numerical simulation. The empirical analysis is made by using the EU carbon price data. In the whole sample interval, we build 123 time windows. The results indicate that our prediction model has better level forecasting precision in 90.69% time windows and directional prediction accuracy in 67.82% time windows than the prediction model built based on deterministic network, which can improve the level prediction accuracy and directional prediction accuracy by 25.76% and 5.09% on average. By comparing with the accuracy results of existing carbon price prediction models, we discuss the feasibility of improving the prediction effect by increasing the number of similar nodes.

The BSP's Forecasting and Policy Analysis System

The Bangko Sentral ng Pilipinas (BSP) subscribes to the Forecasting and Policy Analysis System (FPAS) as the framework for macroeconomic forecasting and analysis in support of monetary policy formulation. FPAS is a standard framework, adopted by many in"ation-targeting central banks, that organizes the generation, consolidation, and analysis of economic information relavant to monetary policy formulation. This paper aims to describe how macroeconomic forecasts and policy simulations are generated to support monetary policy analysis and formulation at the BSP. To this end, this article summarizes the main features of the process involved in generating the baseline forecasts, alternative scenarios, and policy simulations. We highlight the complementary roles played by the BSP’s suite of models and the expert judgement from the sector specialists as well as the importance of forecast communication in the transmission of monetary policy. Finally, we present a systematic evaluation of the forecasting performance of the BSP from 2010 to 2020 together with some of the lessons in forecasting during the COVID-19 pandemic and the recent efforts to improve the BSP’s FPAS.

COVID-19 contagion forecasting framework based on curve decomposition and evolutionary artificial neural networks: A case study in Andalusia, Spain

Many types of research have been carried out with the aim of combating the COVID-19 pandemic since the first outbreak was detected in Wuhan, China. Anticipating the evolution of an outbreak helps to devise suitable economic, social and health care strategies to mitigate the effects of the virus. For this reason, predicting the SARS-CoV-2 transmission rate has become one of the most important and challenging problems of the past months. In this paper, we apply a two-stage mid and long-term forecasting framework to the epidemic situation in eight districts of Andalusia, Spain. First, an analytical procedure is performed iteratively to fit polynomial curves to the cumulative curve of contagions. Then, the extracted information is used for estimating the parameters and structure of an evolutionary artificial neural network with hybrid architectures (i.e., with different basis functions for the hidden nodes) while considering single and simultaneous time horizon estimations. The results obtained demonstrate that including polynomial information extracted during the training stage significantly improves the mid- and long-term estimations in seven of the eight considered districts. The increase in average accuracy (for the joint mid- and long-term horizon forecasts) is 37.61% and 35.53% when considering the single and simultaneous forecast approaches, respectively.

Design and Development of Efficient Model to Predict Neurodegenerative Disorders Using Advanced LSTM: A Review of Literature

Purpose: A continuous Nervous system illness that influences development is known as neurodegenerative sickness. Side effects show up continuously, and may start with a scarcely distinguishable quake in just a single hand. Quakes are normal, but they are frequently joined by firmness or eased back versatility. The emphasis is on Parkinson's infection specifically (PD). The signs and results of Parkinson's contamination shift starting with one individual then onto the next. Early reprimand markers could be subtle and go unnoticed. Regardless, when aftereffects start to influence the different sides of your body, secondary effects normally jump on single side of your body and decay on that side. Parkinson's illness is brought about by the demise of nerve cells in the substantia nigra, a portion of the cerebrum. The exactness of a few fake brain network approaches, for example, Convolutional Neural Network, Recurrent Neural Network, Long-Short term Memory network have been concentrated on to analyze Parkinson's illnesses. This record inspects a synopsis of a portion of the examination and concentrates on that have been directed in the field of clinical diagnostics. In light of the audit, research holes are featured, as well as examination needs for future review. Approach: A thorough study on the algorithms used in analysis of handwritten and vocal to distinguish and anticipate Parkinson's illness. Findings: The review showed that the majority of the AI and deep learning strategy can order neurodegenerative illness in view of vocal, transcribed and walk investigation in light of the clinical datasets. The new crossover philosophy proposed will be more exact as the model will actually want to foresee and distinguish neurodegenerative sickness in view of eye development. Originality: The sort of information expected for forecast and discovery framework are considered and the design and portrayal outline of a proposed model are incorporated. Paper Type: Literature Review.

An explainable framework for load forecasting of a regional integrated energy system based on coupled features and multi-task learning

To extract strong correlations between different energy loads and improve the interpretability and accuracy for load forecasting of a regional integrated energy system (RIES), an explainable framework for load forecasting of an RIES is proposed. This includes the load forecasting model of RIES and its interpretation. A coupled feature extracting strategy is adopted to construct coupled features between loads as the input variables of the model. It is designed based on multi-task learning (MTL) with a long short-term memory (LSTM) model as the sharing layer. Based on SHapley Additive exPlanations (SHAP), this explainable framework combines global and local interpretations to improve the interpretability of load forecasting of the RIES. In addition, an input variable selection strategy based on the global SHAP value is proposed to select input feature variables of the model. A case study is given to verify the effectiveness of the proposed model, constructed coupled features, and input variable selection strategy. The results show that the explainable framework intuitively improves the interpretability of the prediction model.

Hyperparameter Optimization of Bayesian Neural Network Using Bayesian Optimization and Intelligent Feature Engineering for Load Forecasting.

This paper proposes a new hybrid framework for short-term load forecasting (STLF) by combining the Feature Engineering (FE) and Bayesian Optimization (BO) algorithms with a Bayesian Neural Network (BNN). The FE module comprises feature selection and extraction phases. Firstly, by merging the Random Forest (RaF) and Relief-F (ReF) algorithms, we developed a hybrid feature selector based on grey correlation analysis (GCA) to eliminate feature redundancy. Secondly, a radial basis Kernel function and principal component analysis (KPCA) are integrated into the feature-extraction module for dimensional reduction. Thirdly, the Bayesian Optimization (BO) algorithm is used to fine-tune the control parameters of a BNN and provides more accurate results by avoiding the optimal local trapping. The proposed FE-BNN-BO framework works in such a way to ensure stability, convergence, and accuracy. The proposed FE-BNN-BO model is tested on the hourly load data obtained from the PJM, USA, electricity market. In addition, the simulation results are also compared with other benchmark models such as Bi-Level, long short-term memory (LSTM), an accurate and fast convergence-based ANN (ANN-AFC), and a mutual-information-based ANN (ANN-MI). The results show that the proposed model has significantly improved the accuracy with a fast convergence rate and reduced the mean absolute percent error (MAPE).

A real-time data assimilative forecasting system for animal tracking.

Monitoring technologies now provide real‐time animal location information, which opens up the possibility of developing forecasting systems to fuse these data with movement models to predict future trajectories. State‐space modeling approaches are well established for retrospective location estimation and behavioral inference through state and parameter estimation. Here we use a state‐space model within a comprehensive data assimilative framework for probabilistic animal movement forecasting. Real‐time location information is combined with stochastic movement model predictions to provide forecasts of future animal locations and trajectories, as well as estimates of key behavioral parameters. Implementation uses ensemble‐based sequential Monte Carlo methods (a particle filter). We first apply the framework to an idealized case using a nondimensional animal movement model based on a continuous‐time random walk process. A set of numerical forecasting experiments demonstrates the workflow and key features, such as the online estimation of behavioral parameters using state augmentation, the use of potential functions for habitat preference, and the role of observation error and sampling frequency on forecast skill. For a realistic demonstration, we adapt the framework to short‐term forecasting of the endangered southern resident killer whale (SRKW) in the Salish Sea using visual sighting information wherein the potential function reflects historical habitat utilization of SRKW. We successfully estimate whale locations up to 2.5 h in advance with a moderate prediction error (<5 km), providing reasonable lead‐in time to mitigate vessel–whale interactions. It is argued that this forecasting framework can be used to synthesize diverse data types and improve animal movement models and behavioral understanding and has the potential to lead to important advances in movement ecology.

Multi-Variables-Driven Model Based on Random Forest and Gaussian Process Regression for Monthly Streamflow Forecasting

Due to the inherent non-stationary and nonlinear characteristics of original streamflow and the complicated relationship between multi-scale predictors and streamflow, accurate and reliable monthly streamflow forecasting is quite difficult. In this paper, a multi-scale-variables-driven streamflow forecasting (MVDSF) framework was proposed to improve the runoff forecasting accuracy and provide more information for decision-making. This framework was realized by integrating random forest (RF) and Gaussian process regression (GPR) with multi-scale variables (hydrometeorological and climate predictors) as inputs and is referred to as RF-GPR-MV. To validate the effectiveness and superiority of the RF-GPR-MV model, it was implemented for multi-step-ahead monthly streamflow forecasts with horizons of 1 to 12 months for two key hydrological stations in the Jinsha River basin, Southwest China. Other MVDSF models based on the Pearson correlation coefficient (PCC) and GPR with/without multi-scale variables or the PCC and a backpropagation neural network (BP) or general regression neural network (GRNN), with only previous streamflow and precipitation, namely, PCC-GPR-MV, PCC-GPR-QP, PCC-BP-QP, and PCC-GRNN-QP, respectively, were selected as benchmarks. Experimental results indicated that the proposed model was superior to the other benchmark models in terms of the Nash–Sutcliffe efficiency (NSE) for almost all forecasting scenarios, especially for forecasting with longer lead times. Additionally, the results also confirmed that the addition of large-scale climate and circulation factors was beneficial for promoting the streamflow forecasting ability, with an average contribution rate of about 15%. The RF in the MVDSF framework improved the forecasting performance, with an average contribution rate of about 25%. This improvement was more pronounced when the lead time exceeded 3 months. Moreover, the proposed model could also provide prediction intervals (PIs) to characterize forecast uncertainty, as supplementary information to further help decision makers in relevant departments to avoid risks in water resources management.

An adaptive deep learning framework for day-ahead forecasting of photovoltaic power generation

Accurate forecasts of photovoltaic power generation (PVPG) are essential to optimize operations between energy supply and demand. Recently, the propagation of sensors and smart meters has produced an enormous volume of data, which supports the data-driven models for PVPG forecasting. Although emerging deep learning (DL) models, such as the long short-term memory (LSTM), based on historical data, have provided effective solutions for PVPG forecasting with great successes, these models utilize offline learning. As a result, DL models cannot take advantage of the opportunity to learn from newly-arrived data, and are unable to handle concept drift caused by installing extra PV units and unforeseen PV unit failures. Consequently, to improve day-ahead PVPG forecasting accuracy, as well as eliminate the impacts of concept drift, this paper proposes an adaptive LSTM (AD-LSTM), which is a DL framework that can not only acquire general knowledge from historical data, but also dynamically learn specific knowledge from newly-arrived data. A two-phase adaptive learning strategy (TP-ALS) is integrated into AD-LSTM, and a sliding window (SDWIN) algorithm is proposed, to detect concept drift in PV systems. Multiple datasets from PV systems are utilized to assess the feasibility and effectiveness of the proposed approaches. The developed AD-LSTM model demonstrates greater forecasting capability than the conventional offline LSTM model, particularly in the presence of concept drift. The forecasting skill of AD-LSTM can be improved up to 73.11%. Additionally, the proposed AD-LSTM model also achieves superior performance in terms of day-ahead PVPG forecasting for individual days and multiple days to other reference models in the literature.

Hurricane Forecasting: A Novel Multimodal Machine Learning Framework

Abstract This paper describes a novel machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple ML techniques and utilizing diverse data sources. Our multimodal framework, called Hurricast, efficiently combines spatial–temporal data with statistical data by extracting features with deep learning encoder–decoder architectures and predicting with gradient-boosted trees. We evaluate our models in the North Atlantic and eastern Pacific basins in 2016–19 for 24-h lead-time track and intensity forecasts and show they achieve comparable mean absolute error and skill to current operational forecast models while computing in seconds. Furthermore, the inclusion of Hurricast into an operational forecast consensus model could improve upon the National Hurricane Center’s official forecast, thus highlighting the complementary properties with existing approaches. In summary, our work demonstrates that utilizing machine learning techniques to combine different data sources can lead to new opportunities in tropical cyclone forecasting. Significance Statement Machine learning techniques have not been fully explored for improving tropical cyclone movement and intensity changes. This work shows how advanced machine learning techniques combined with routinely available information can be used to improve 24-h tropical cyclone forecasts efficiently. The successes demonstrated for 24-h forecasts provide a recipe for improving predictions for longer lead times, further reducing forecast uncertainties and benefiting society.

Scenario approach to the assessment of development prospects of the Russian regions

The article describes the features of building and assessment of spatial development scenarios in long-term forecasts. The author used the scenario approach for qualitative and quantitative assessment of alternative strategies for regional development within the framework of the macroeconomic forecast for the development of the Russian economy. Further, the author analyzed the experience of developing spatial scenarios for the EU countries and Russia. Next, the longterm regional trends are presented, which, due to the high inertia of space, will determine spatial development in the future. The author also describes modern problems that significantly impact the choice of strategies for the regions. Prospects for spatial development the author assessed in the framework of three forecast scenarios. For two options of the macroeconomic forecast, the author calculated quantitative estimates of the spatial development parameters characterizing the scenarios. Relevant calculations the author performed using macroeconomic and interregional forecasting and analytical models. Finally, the author showed the advantages of the scenario of balanced growth from the standpoint of implementing national goals of social and economic development.

A Flood Forecasting Framework Coupling a High Resolution WRF Ensemble With an Urban Hydrologic Model

Numerical weather prediction (NWP) models such as the Weather Research and Forecasting (WRF) model are increasingly used over the Indian region to forecast extreme rainfall events. However, studies which explore the application of high-resolution rainfall simulations obtained from the WRF model in urban hydrology are limited. In this paper, the utility of a model coupling framework to predict urban floods is explored through the case study of Bangalore city in India. This framework is used to simulate multiple extreme events that occurred over the city for the monsoons of years 2020 and 2021. To address the uncertainty from the WRF model, a 12-member convection permitting ensemble is used. Model configurations using Kain Fritsch and WSM6 parameterization schemes could simulate the spatial and temporal pattern of the selected event. The city is easily flooded with rainfall events above a threshold of 60 mm/day and to capture the response of the urban catchment, the Personal Computer Storm Water Management Model (PCSWMM) is used in this study. Flood forecasts are created using the outputs from the WRF ensemble and the Global Forecasting System (GFS). The high temporal and spatial resolution of the rainfall forecasts (&amp;lt;4 km at 15-min intervals), has proved critical in reproducing the urban flood event. The flood forecasts created using the WRF ensemble indicate that flooding and water levels are comparable to the observed whereas the GFS underestimates these to a large extent. Thus, the coupled WRF–PCSWMM modelling framework is found effective in forecasting flood events over an Indian city.