Accuracy Of Forecasting Models Research Articles

A novel hybrid model based on multi-objective Harris hawks optimization algorithm for daily PM2.5 and PM10 forecasting

High levels of air pollution can severely affect the living environment and even endanger the human lives. To reduce air pollution concentrations, and warn the public regarding the occurrence of hazardous air pollutants, an accurate and reliable air pollutant forecasting model must be designed. However, previous studies had numerous deficiencies, such as ignoring the importance of predictive stability and poor initial parameters; these deficiencies significantly affected the air pollution prediction performance. Therefore, in this study a novel hybrid model is proposed to address these issues. Powerful data preprocessing techniques are applied to decompose the original time series into different modes from low frequency to high frequency, and a new multi-objective Harris hawks optimization algorithm is developed to tune the parameters of the extreme learning machine (ELM) model with high forecasting accuracy and stability for prediction air pollution. The optimized ELM model is then used to predict a time-series of air pollution. Finally, a scientific and robust evaluation system with several error criteria, benchmark models, and experiments conducted using twelve air pollutant concentration time series from three cities in China is designed to assess the presented hybrid forecasting model. The experimental results indicate that the proposed hybrid model can achieve a more stable and higher predictive performance than other models, and its superior prediction ability may aid in developing effective plans for mitigating air pollutant emissions and preventing the health issues caused by air pollution.

Estimation of Chilling and Heat Accumulation Periods Based on the Timing of Olive Pollination

Research Highlights: This paper compares the thermal requirements in three different olive-growing areas in the Mediterranean region (Toledo, central Spain; Lecce, southeastern Italy; Chaal, central Tunisia). A statistical method using a partial least square regression for daily temperatures has been applied to study the chilling and heat requirements over a continuous period. Background and Objectives: The olive is one of the main causes of pollen allergy for the population of Mediterranean cities. The physiological processes of the reproductive cycle that governs pollen emission are associated with temperature, and thermal requirements strongly regulate the different phases of the plant’s life cycle. However, the point when several specific processes occur—Such as the phases within the dormancy period—Is unclear, and the transition between endodormancy and ecodormancy is not easily distinguishable from an empirical point of view. This work focuses on defining the thermal accumulation periods related to the temperature balance needed to meet the chilling and heat requirements for the metabolic activation and budbreak in olive trees. Results and Conclusions: Thermal accumulation patterns in olive trees are strongly associated with the bioclimatic conditions of olive-growing areas, and the olive flowering start dates showed significant differences between the three studied stations. Our results show that the chilling requirements were fulfilled between late autumn and early winter, although the chilling accumulation period was more evident in the coldest and most continental bioclimatic areas (central Spain). The heat accumulation period (forcing period) was clearly defined and showed a close relationship with the timing of olive flowering. Heat requirements were therefore used to generate accurate forecasting models to predict the beginning of the olive bloom and subsequent olive pollen emission. A forecasting model considering both the chilling and heat requirements was generated in Toledo, where the estimated days displayed an error of 2.0 ± 1.8 days from the observed dates. For Lecce, the error was 2.7 ± 2.5 days and for Chaal, 4.2 ± 2.4 days.

When Managers Meet Models: Integrating Human Judgment and Analytics

Data analytics and machine learning are increasingly prevalent in emerging forecasting practice. Despite the growth in model-based forecasting, practitioners continue to employ human judgment to incorporate contextual information to improve the accuracy of model forecasts. Our research uses an experiment to examine how human judgment and statistical models may be best integrated to improve forecast accuracy within heterogeneous forecasting environments. Our findings suggest that human judgment provides a significant benefit to forecasting. Specifically, integrated forecasts (i.e., forecasts that combine human judgment with computational analytics) can substantially improve forecast accuracy compared to non-integrated forecasts. We find however that this improvement in accuracy is dependent on the method of integration. Human guided machine learning is the most effective method of integration in comparison to other methods commonly used in practice and studied in the academic literature. In keeping with theory, we call for further empirical testing of forecasting methods that leverage the strengths of human judgment and the strengths of models, and urge study of implementation issues in practice.

Probabilistic Multi-Step-Ahead Short-Term Water Demand Forecasting with Lasso

Water demand is a highly important variable for operational control and decision making. Hence, the development of accurate forecasts is a valuable field of research to further improve the efficiency of water utilities. Focusing on probabilistic multi-step-ahead forecasting, a time series model is introduced, to capture typical autoregressive, calendar and seasonal effects, to account for time-varying variance, and to quantify the uncertainty and path-dependency of the water demand process. To deal with the high complexity of the water demand process a high-dimensional feature space is applied, which is efficiently tuned by an automatic shrinkage and selection operator (lasso). It allows to obtain an accurate, simple interpretable and fast computable forecasting model, which is well suited for real-time applications. The complete probabilistic forecasting framework allows not only for simulating the mean and the marginal properties, but also the correlation structure between hours within the forecasting horizon. For practitioners, complete probabilistic multi-step-ahead forecasts are of considerable relevance as they provide additional information about the expected aggregated or cumulative water demand, so that a statement can be made about the probability with which a water storage capacity can guarantee the supply over a certain period of time. This information allows to better control storage capacities and to better ensure the smooth operation of pumps. To appropriately evaluate the forecasting performance of the considered models, the energy score (ES) as a strictly proper multidimensional evaluation criterion, is introduced. The methodology is applied to the hourly water demand data of a German water supplier.

An optimized conformable fractional non-homogeneous gray model and its application

Developing a robust, accurate forecasting model and improving the prediction abilities of the limited historical data that lacks statistical rules has become a top priority. To address this problem, an improved conformable fractional non-homogeneous gray model, namely CFONGM(1,1,k,c), is proposed. Combining the dynamic background-value and particle swarm optimization algorithm to further improve forecasting ability of the existing gray model. In which matrix perturbation theory is employed to prove that the novel model conforms the principle of new information priority and has a smaller perturbation bound of solution. The two empirical examples of educational funds and new students enrollment of regular institutions of higher education of China are employed to examine the prediction accuracy of the novel model. The results show that the novel model has a better prediction performance compared with other competitive models.

The Development of Rice Field Area in Special Region of Yogyakarta

In general, the development of agricultural land usage change was illustrated through linear trend analysis without comparing it first with other trend analysis. As a consequence, it was assumed that the data will be in a straight line with a tendency for constant numbers over a period of time. However, the facts on the ground proved that the area of ??agricultural land converted into non-agricultural land was not always the same from year to year. The novelty of this research was to do a comparison between linear and non-linear trends to predict the development of rice fields, so that an accurate forecasting model was obtained. The aim of this research were: 1) knowing the development of rice fields area in the Special Region of Yogyakarta, 2) determining the appropriate forecasting model for the development of rice fields area in the Special Region of Yogyakarta, and 3) forecasting the area of ??rice fields in the Special Region of Yogyakarta. The data that used came from BPS (Central Bureau of Statistics) from 1996 to 2017. The trend models being compared were linear trends, quadratic trends, and exponential trends. The results showed that the area of ??rice fields in the Special Region of Yogyakarta tended to decrease from year to year. The best forecasting model was an exponential trend. In 2017 to 2021, it was estimated that there will be a decrease in rice field area of ??221 hectares or 0.41 percent per year.

Assessment of stacked unidirectional and bidirectional long short-term memory networks for electricity load forecasting

Electricity load forecasting has been a substantial problem in the electric power system management process. An accurate forecasting model is essential to avoid imprecise predictions that can negatively affect system efficiency, economy, and sustainability. Among several prediction techniques, deep learning methods, especially the Long Short-Term Memory (LSTM), have been shown to have a superior performance in predicting the electricity load consumption. However, the consequences of using these methods have not fully been explored in terms of the various hidden layer structures, the depth of the model architecture, and the impact of tuning the model hyperparameters. In this paper, a systematic experimental methodology has been conducted to investigate the impact of using deep-stacked unidirectional (Uni-LSTM) and bidirectional (Bi-LSTM) networks on predicting electricity load consumption. In particular, two stacked configurations, which include two and three LSTM layers, are compared with the single-layered LSTM for both types to show the significant importance of adding the stacked layers. Moreover, for each proposed configuration, a hyperparameter optimization tool has been implemented to obtain the best model. The results indicate that the deep-stacked LSTM layers have no significant improvement in the prediction accuracy; nevertheless, they consume almost twice the time of the single-layered models. Also, the Bi-LSTM networks outperform the Uni-LSTM networks by 76.25%, 75.49%, and 75.35% in terms of Root Mean Square Error (RMSE), with respect to one, two, and three-layer model configurations, respectively. Furthermore, regarding the prediction accuracy comparison over the total tested period, the optimized Bi-LSTM model outperforms both the optimized Uni-LSTM model by 75.98%, 89.1%, and 89.37%, and the Support Vector Regression (SVR) model by 82.54%, 92.59%, and 92.89% in terms of (RMSE), the Mean Average Percentage Error (MAPE), and Mean Absolute Errors (MAE).

Advances in Hydrologic Forecasts and Water Resources Management

The impacts of climate change on water resources management as well as the increasing severe natural disasters over the last decades have caught global attention. Reliable and accurate hydrological forecasts are essential for efficient water resources management and the mitigation of natural disasters. While the notorious nonlinear hydrological processes make accurate forecasts a very challenging task, it requires advanced techniques to build accurate forecast models and reliable management systems. One of the newest techniques for modelling complex systems is artificial intelligence (AI). AI can replicate the way humans learn and has the great capability to efficiently extract crucial information from large amounts of data to solve complex problems. The fourteen research papers published in this Special Issue contribute significantly to the uncertainty assessment of operational hydrologic forecasting under changing environmental conditions and the promotion of water resources management by using the latest advanced techniques, such as AI techniques. The fourteen contributions across four major research areas: (1) machine learning approaches to hydrologic forecasting; (2) uncertainty analysis and assessment on hydrological modelling under changing environments; (3) AI techniques for optimizing multi-objective reservoir operation; and (4) adaption strategies of extreme hydrological events for hazard mitigation. The papers published in this issue can not only advance water sciences but can also support policy makers toward more sustainable and effective water resources management.

Symbiotic organisms search-optimized deep learning technique for mapping construction cash flow considering complexity of project

Abstract Accurate construction cash flow forecasting is very important in successfully managing cost during execution of building projects. Despite many research efforts, it still remains a difficult issue in attaining an accurate forecast model of cash flows due to the risk factors and characteristic of the project. Additionally, cash flow of the construction projects is strongly impacted by sequence and non-sequence factors. Hence, this study proposed a novel artificial intelligence(AI)-based inference model, named symbiotic organisms search-optimized neural network-long short-term memory (SOS-NN-LSTM), which employs symbiotic organisms search (SOS) algorithm to obtain the suitable hyperparameters of the neural network (NN) and long short-term memory (LSTM) for establishing a robust hybridization model. In the proposed model, the LSTM technique addresses time series problem with considering the complexity of projects while the NN technique aims at tackling non-sequence factors. The experimental results on 13 construction projects have supported the SOS-NN-LSTM as the best model in forecasting the cash flow by achieving the greatest values of (2.55%), MAPE (5.71%), MAE (2.07%), and R2 (0.983). The statistical result further reveals that accuracy of cash flow forecasting can be improved at least 13.4% and 12.0% in terms of RMSE and MAE, respectively, in comparison with other comparative AI-based inference models. The SOS-NN-LSTM model is thus a useful tool to help managers forecast and control cash flow of construction projects.

Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series

ABSTRACT Accurate runoff forecasting plays a key role in catchment water management and water resources system planning. To improve the prediction accuracy, one needs to strive to develop a reliable and accurate forecasting model for streamflow. In this study, the novel combination of the adaptive neuro-fuzzy inference system (ANFIS) model with the shuffled frog-leaping algorithm (SFLA) is proposed. Historical streamflow data of two different rivers were collected to examine the performance of the proposed model. To evaluate the performance of the proposed ANFIS-SFLA model, six different scenarios for the model input–output architecture were investigated. The results show that the proposed ANFIS-SFLA model (R2 = 0.88; NS = 0.88; RMSE = 142.30 (m3/s); MAE = 88.94 (m3/s); MAPE = 35.19%) significantly improved the forecasting accuracy and outperformed the classic ANFIS model (R2 = 0.83; NS = 0.83; RMSE = 167.81; MAE = 115.83 (m3/s); MAPE = 45.97%). The proposed model could be generalized and applied in different rivers worldwide.

Electric load forecasting based on deep learning and optimized by heuristic algorithm in smart grid

Accurate electric load forecasting is important due to its application in the decision making and operation of the power grid. However, the electric load profile is a complex signal due to the non-linear and stochastic behavior of consumers. Despite much research conducted in this area; still, accurate forecasting models are needed. In this article, a novel hybrid short-term electric load forecasting model is proposed. The proposed model is an integrated framework of data pre-processing and feature selection module, training and forecasting module, and an optimization module. The data pre-processing and feature selection module is based on modified mutual information (MMI) technique, which is an improved version of the mutual information technique, used to select abstractive features from historical data. The training and forecasting module is based on factored conditional restricted Boltzmann machine (FCRBM), which is a deep learning model, empowered via learning to forecast the future electric load. The optimization module is based on our proposed genetic wind-driven (GWDO) optimization algorithm, which is used to fine-tune the adjustable parameters of the model. The accuracy of the proposed framework is evaluated through historical hourly load data of three USA power grids, taken from publicly available PJM electricity market. The proposed model is validated by comparing it with four recent forecasting models like Bi-level, mutual information-based artificial neural network (MI-ANN), ANN-based accurate and fast converging (AFC-ANN), and long short-term memory (LSTM) in terms of accuracy and convergence rate.

A Novel Accurate and Fast Converging Deep Learning-Based Model for Electrical Energy Consumption Forecasting in a Smart Grid

Energy consumption forecasting is of prime importance for the restructured environment of energy management in the electricity market. Accurate energy consumption forecasting is essential for efficient energy management in the smart grid (SG); however, the energy consumption pattern is non-linear with a high level of uncertainty and volatility. Forecasting such complex patterns requires accurate and fast forecasting models. In this paper, a novel hybrid electrical energy consumption forecasting model is proposed based on a deep learning model known as factored conditional restricted Boltzmann machine (FCRBM). The deep learning-based FCRBM model uses a rectified linear unit (ReLU) activation function and a multivariate autoregressive technique for the network training. The proposed model predicts future electrical energy consumption for efficient energy management in the SG. The proposed model is a novel hybrid model comprising four modules: (i) data processing and features selection module, (ii) deep learning-based FCRBM forecasting module, (iii) genetic wind driven optimization (GWDO) algorithm-based optimization module, and (iv) utilization module. The proposed hybrid model, called FS-FCRBM-GWDO, is tested and evaluated on real power grid data of USA in terms of four performance metrics: mean absolute percentage deviation (MAPD), variance, correlation coefficient, and convergence rate. Simulation results validate that the proposed hybrid FS-FCRBM-GWDO model has superior performance than existing models such as accurate fast converging short-term load forecasting (AFC-STLF) model, mutual information-modified enhanced differential evolution algorithm-artificial neural network (MI-mEDE-ANN)-based model, features selection-ANN (FS-ANN)-based model, and Bi-level model, in terms of forecast accuracy and convergence rate.

Short-term wind speed forecasting based on the Jaya-SVM model

Wind energy is an emerging environmentally friendly energy source. However, due to the uncertainty and volatility of wind speed, wind energy cannot be effectively exploited, and it is essential to build an accurate wind speed forecasting model. In this paper, a Jaya algorithm-based support vector machine (Jaya-SVM) model is proposed for short-term wind speed forecasting. Different from the typical SVM regression, the most representative features of input data are selected and the hyper-parameters of SVM are optimized by using the Jaya optimization algorithm. To examine the performance of the Jaya-SVM model, seven other wind speed forecasting models, Least Absolute Shrinkage and Selection Operator, Extreme Gradient Boosting model, Multi-Layer Perceptron Regression model, Deep Belief Network, Gaussian Process Regression, Stacked Sparse Autoencoder and Granular Computing method are employed for comparison. The wind speed data collected in Jilin, China is fully utilized. The computational results demonstrate that the Jaya-SVM model generates the best results among all eight models in terms of MAE, MSE, MAPE, R2 and reliability, having the capacity of accurate wind speed forecasting.

Streamflow forecasting using extreme gradient boosting model coupled with Gaussian mixture model

The establishment of an accurate and reliable forecasting model is important for water resource planning and management. In this study, we developed a hybrid model (namely GMM-XGBoost), coupling extreme gradient boosting (XGBoost) with Gaussian mixture model (GMM), for monthly streamflow forecasting. The proposed model is based on the principle of modular model, where a complex problem is divided into several simple ones. GMM was applied to cluster streamflow into several groups, using the features selected by a tree-based method. Then, each group was used to fit several single XGBoosts. And the prediction is a weighted average of the single models. Monthly streamflow data at Cuntan and Hankou stations on Yangtze River Basin were used to evaluate the performance of the proposed model. To compare the forecasting efficiency, support vector machine (SVM) and standalone XGBoost were selected as the benchmark models. The results indicated that although all three models yielded quite good performance on one-month ahead forecasting with high Nash-Sutclitte efficiency coefficient (NSE) and low root mean squared error (RMSE), GMM-XGBoost provided the best accuracy with significant improvement of forecasting accuracy. It can be inferred from the results that (1) XGBoost is applicable for streamflow forecasting, and in general, performs better than SVM; (2) the cluster analysis-based modular model is helpful in improving accuracy and capturing the complicated patterns of hydrological process; (3) the proposed GMM-XGBoost model is a superior alternative, which can provide accurate and reliable predictions for optimal water resources management.

RETRACTED ARTICLE: Monitoring the quality of water in shrimp ponds and forecasting of dissolved oxygen using Fuzzy C means clustering based radial basis function neural networks

The success of shrimp farming lies in the proper monitoring of water quality in the pond. Of all the water quality parameters the dissolved oxygen plays a vital role in the proper growth of shrimps and influences mortality to a great extent. Traditional methods of sensing the water quality especially dissolved oxygen is done in laboratories far away from the actual pond site and it is often time consuming. Hence an accurate forecasting model which predicts the changes in the DO content is quintessential to decrease mortality, yield export quality shrimps and reduce operational costs. Water quality datasets are collected by using devices fabricated with wireless water quality sensors which floats in the ponds. Fuzzy C means was chosen as the clustering method based on the dataset collected and radial basis functions neural networks were constructed with accurate number of hidden neurons to predict the changes in the dissolved oxygen. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Correlation Coefficient (R) and Willmott index of agreement (WIA) were used as the evaluation parameters in comparison with the Multilayer Perceptron based Backpropagation Neural Network and Standard Radial Basis Function Neural Network for prediction of the DO content. The results show that the proposed method is effective with reduced errors and correlation coefficient close to unity. This accurate prediction of the dissolved oxygen helps the farmers to take corrective action when required and decrease the operational costs and produce export quality shrimps.

Прогнозування постпірогенного відпаду в сосняках, пошкоджених літніми низовими пожежами, у Лівобережному Лісостепу України

Пожежі є одними із найнебезпечніших чинників дестабілізації лісів. У зв’язку зі зростанням посушливості клімату ризик збільшення частоти й масштабів лісових пожеж залишається високим, тому актуальним є розроблення науково обґрунтованих заходів із пом’якшення екологічних, економічних та соціальних наслідків лісових пожеж. Удосконалено та уточнено показники, що характеризують візуальні прояви пошкодження дерев після низових пожеж, та показники вогнестійкості середньовікових дерев сосни звичайної (Pinus sylvestris L.). Виявлено, що в міру збільшення середньої висоти нагару на стовбурах зростає частка відпаду в досліджуваних групах дерев (r = 0,87, tф = 5,80, t0,01 = 3,17). Встановлено, що вогнестійкість дерев збільшується зі збільшенням природного ступеня товщини дерева в насадженні (виявлено обернений достовірний кореляційний зв’язок між природним ступенем товщини (ПСТ) і категорією санітарного стану пошкоджених дерев: (r = -0,54; р = 0,05). Розроблено прогностичну модель для встановлення ймовірності відпаду дерев, пошкоджених низовими стійкими літніми пожежами, яка як предиктори включає середню висоту нагару на стовбурах та ПСТ (точність прогностичної моделі становить понад 78 %).

Input attributes optimization using the feasibility of genetic nature inspired algorithm: Application of river flow forecasting

In nature, streamflow pattern is characterized with high non-linearity and non-stationarity. Developing an accurate forecasting model for a streamflow is highly essential for several applications in the field of water resources engineering. One of the main contributors for the modeling reliability is the optimization of the input variables to achieve an accurate forecasting model. The main step of modeling is the selection of the proper input combinations. Hence, developing an algorithm that can determine the optimal input combinations is crucial. This study introduces the Genetic algorithm (GA) for better input combination selection. Radial basis function neural network (RBFNN) is used for monthly streamflow time series forecasting due to its simplicity and effectiveness of integration with the selection algorithm. In this paper, the RBFNN was integrated with the Genetic algorithm (GA) for streamflow forecasting. The RBFNN-GA was applied to forecast streamflow at the High Aswan Dam on the Nile River. The results showed that the proposed model provided high accuracy. The GA algorithm can successfully determine effective input parameters in streamflow time series forecasting.

Pathogens which threaten food security: Puccinia striiformis, the wheat stripe rust pathogen

Stripe rust, caused by Puccinia striiformis, is an important disease of wheat worldwide. The disease is old, but often appears as a re-emerging problem and also expands to new areas. Large-scale stripe rust epidemics occur when new races overcoming specific resistance genes develop in the pathogen population and/or when extreme disease-favourable weather conditions occur. Research progress has been made in the understanding of the biology, genomics, and evolution of the pathogen; host-pathogen interaction; and epidemiology and management of the disease. Despite its importance, the complete life cycle of this important pathogen was not known until very recently. The pathogen is now known to have a heteroecious macrocyclic lifecycle, but whether sexual reproduction on alternate hosts plays an important role in generating diverse races and increasing epidemics on crops is largely unknown. The pathogen has a large number of host species in the grass family, but the role of grass hosts in crop epidemics is not clear in many regions of the world. The disease can be controlled by growing resistant cultivars, appropriate use of fungicide, and suitable cultural practices. However, greater effort are needed to develop more cultivars with durable, high level resistance, develop accurate forecast models, and monitor the disease and pathogen virulence for more effective, profitable, and sustainable control of stripe rust.

Modeling stand basal area growth of Cryptomeria japonica D. Don under different planting densities in Taiwan

ABSTRACT Stand basal area (BA) is an important parameter, yet significantly influenced by initial planting density, in describing the developments of plantation forests. The effects of initial density on the growth of sugi (Cryptomeria japonica D. Don), an important plantation tree species in Taiwan, have seldom been studied. The goals of this study are to (1) model sugi stand BA growth under different initial densities, and (2) quantify model forecast accuracy. The data were from a spacing trial established in 1950 at the National Taiwan University Experimental Forest. The initial densities were 2500, 1111, 625, and 400 trees ha−1. Ten measurements were carried out up to stand age 65. Using a mixed-effects modeling approach, we fitted a Gompertz model with the initial density as the covariate to describe stand BA growth trends. Results showed that stand BA was the largest for stands with the highest initial density. The maximum current annual increment of the highest initial density was also the largest and reached earlier in stand development than that of the other spacings. Data up to stand age 60 were needed to yield a forecast accuracy within 6% for BA at stand age 65. This study showed that the fitted Gompertz model could adequately capture the general growth trends in stand BA despite unequal measurement intervals. The results agreed with other spacing trials in other regions and tree species, and the model accuracy was acceptable given the availability of data. The prediction accuracy results underlined the importance of long-term growth monitoring.

Solar irradiance forecasting models without on-site training measurements

Much effort has been made to increase the integration of solar photovoltaic (PV) systems to reduce the environmental impacts of fossil fuels. An essential process in PV systems is the forecasting of solar irradiance to avoid safety and stability problems due to its intermittent nature. Most of the research has been focused on improving the prediction accuracy based on the assumption that enough on-site training data are available. However, in many situations, it is required for the implementation of PV systems in locations where not enough solar irradiance measurements have been collected. Our hypothesis is that measurements from other sites can be used to train accurate forecasting models, given an appropriate definition of site similarity. We propose a methodology that takes information from exogenous variables that are correlated to on-site solar irradiance and constructs a multidimensional space equipped with a metric. Each site is a point in this space, and the learned metric is used to select those sites that can provide measurements to train an accurate forecasting model on an unobserved site. We show through experiments with real data that using the learned metric provides better predictions than using the measurements collected from the whole set of available sites.