scholarly journals SPI-Based Hybrid Hidden Markov–GA, ARIMA–GA, and ARIMA–GA–ANN Models for Meteorological Drought Forecasting

2021 ◽  
Vol 13 (22) ◽  
pp. 12576
Author(s):  
Mohammed Alquraish ◽  
Khaled Ali. Abuhasel ◽  
Abdulrahman S. Alqahtani ◽  
Mosaad Khadr
Keyword(s):  
Genetic Algorithm ◽  
Performance Evaluation ◽  
Hidden Markov ◽  
Moving Average ◽  
Area Under The Curve ◽  
Meteorological Drought ◽  
Hybrid Models ◽  
Economic Damage ◽  
Drought Forecasting ◽  
Auto Regressive

Drought is a severe environmental disaster that results in significant social and economic damage. As such, efficient mitigation plans must rely on precise modeling and forecasting of the phenomenon. This study was designed to enhance drought forecasting through developing and evaluating the applicability of three hybrid models—the hidden Markov model–genetic algorithm (HMM–GA), the auto-regressive integrated moving average–genetic algorithm (ARIMA–GA), and a novel auto-regressive integrated moving average–genetic algorithm–ANN (ARIMA–GA–ANN)—to forecast the standard precipitation index (SPI) in the Bisha Valley, Saudi Arabia. The accuracy of the models was investigated and compared with that of classical HMM and ARIMA based on a performance evaluation and visual inspection. Furthermore, the multi-class Receiver Operating Characteristic-based Area under the Curve (ROC–AUC) was applied to evaluate the ability of the hybrid model to forecast drought events. We used data from 1968 to 2008 to train the models and data from 2009 to 2019 for validation. The performance evaluation results confirmed that the hybrid models provided superior results in forecasting the SPI one month in advance. Furthermore, the results demonstrated that the GA-induced improvement in the HMM forecasts was matched by an approximate 16.40% and 23.46% decrease in the RMSE in the training and testing results, respectively, compared to the classical HMM model. Consequently, the RMSE values of the ARIMA–GA model were reduced by an average of 10.06% and 9.36% for the training and testing processes, respectively. Finally, the ARIMA–GA–ANN, which combined the strengths of the linear stochastic model ARIMA and a non-linear ANN, achieved a greater reduction values in RMSE by an average of 32.82% and 27.47% in comparison with ARIMA in the training and testing phases, respectively. The ROC–AUC results confirmed the capability of the developed models to distinguish between events and non-events with reasonable accuracy, implying the appropriateness of these models as a tool for drought mitigation and warning systems.

Forecasting of meteorological drought using ARIMA model

2017 ◽  
Author(s):  
K. Karthika ◽  
Krishnaveni . ◽  
V. Thirunavukkarasu
Keyword(s):  
Moving Average ◽  
Arima Model ◽  
Meteorological Drought ◽  
Information Criterion ◽  
Mitigation Strategies ◽  
Model Parameters ◽  
Drought Forecasting ◽  
Contributing Factors ◽  
Bayesian Criterion ◽  
Semi Arid Region

Drought is a global phenomenon that occurs virtually in all landscapes causing significant damage. Due to the random nature of contributing factors, occurrence and severity of droughts can be treated as stochastic in nature. Early indication of possible drought can help to set out drought mitigation strategies and measures in advance. Therefore drought forecasting plays an important role in the planning and management of water resource systems. The principal objective of the study is to carryout short-term annual forecasting of meteorological drought using Auto Regressive Integrated Moving Average (ARIMA) model in Lower Thirumanimuthar Sub-basin located in semi-arid region of Tamilnadu, India is chosen as the study area which is predominantly affected by drought over few decades. Suitable linear stochastic model, non seasonal autoregressive integrated moving average (ARIMA) was developed to predict drought. The best model was selected based on minimum Akaike Information Criterion (AIC) and Schwarz Bayesian Criterion (SBC). Parameter estimation step indicates that the estimated model parameters are significantly different from zero. The predicted data using the best ARIMA model were compared to the observed data for model validation purpose in which the predicted data show reasonably good agreement with the actual data. Hence the models were applied to forecast drought in the Lower Thirumanimuthar sub-basin region up to 2 years in advance with good accuracy.

scholarly journals FORECASTING DROUGHT WITH ARIMA MODEL AND STANDARDIZED PRECIPITATION INDEX (SPI)

2019 ◽  
Vol 1 (2) ◽  
pp. 32-34
Author(s):  
ALFA MOHAMMED SALISU
Keyword(s):  
Moving Average ◽  
Arima Model ◽  
Standardized Precipitation Index ◽  
Precipitation Index ◽  
Data Series ◽  
Drought Forecasting ◽  
Data Set ◽  
Forecasting Accuracy ◽  
Diagnostic Checking ◽  
Auto Regressive

Drought forecasting is an important forecasting procedure for preparing and managing water resources for all creatures. Natural disasters across the regions such as flooding, earthquakes, droughts etc. have caused damages to life as a result of which numerous researches have been conducted to assist in reducing the phenomenon. Consequently, therefore, this study considered using Auto-Regressive Integrated Moving Average (ARIMA) model in forecasting drought using Standardized Precipitation Index (SPI) as a forecasting tool which was used to measure and classify drought. The models are developed to forecast the SPI series. Results indicated the forecasting ability of the ARIMA models which increases as the timescales. The study is aimed at using ARIMA method for modeling SPI data series. The studies used data set made up of 624 months, obtained from 1954 to 2008. In the analysis only SPI3 series was non-seasonal while others have seasonality and Seasonal ARIMA was carried out, SPI12 was significant compared with the forecasting accuracy alongside the diagnostic checking having a minimum error of RMSE and MAE in both testing and training phases. The research contributes to the discovering of feasible forecasting of drought and demonstrates that the established model is good and appropriate for forecasting drought.

scholarly journals Forecasting Drought Using Modified Empirical Wavelet Transform-ARIMA with Fuzzy C-Means Clustering

2018 ◽  
Vol 11 (3) ◽  
pp. 1152
Author(s):  
Muhammad Akram Shaari ◽  
Ruhaidah Samsudin ◽  
Ani Shabri Ilman
Keyword(s):  
Wavelet Transform ◽  
Moving Average ◽  
Daily Rainfall ◽  
Rainfall Data ◽  
Intrinsic Mode Functions ◽  
Drought Forecasting ◽  
Fuzzy C Means ◽  
Empirical Wavelet Transform ◽  
Fuzzy C Means Clustering ◽  
Auto Regressive

Drought forecasting is important in preparing for drought and its mitigation plan. This study focuses on the investigating the performance of Auto Regressive Integrated Moving Average (ARIMA) and Empirical Wavelet Transform (EWT)-ARIMA based on clustering analysis in forecasting drought using Standard Precipitation Index (SPI). Daily rainfall data from Arau, Perlis from 1956 to 2008 was used in this study. SPI data of 3, 6, 9, 12 and 24 months were then calculated using the rainfall data. EWT is employed to decompose the time series into several finite modes. The EWT is used to create Intrinsic Mode Functions (IMF) which are used to create ARIMA models. Fuzzy c-means clustering is used on the instantaneous frequency given by Hilbert Transform of the IMF to create several clusters. The objective of this study is to compare the effectiveness of the methods in accurately forecasting drought in Arau, Malaysia. It was found that the proposed model performed better compared to ARIMA and EWT-ARIMA.

scholarly journals A Comparative Analysis of Hidden Markov Model, Hybrid Support Vector Machines, and Hybrid Artificial Neural Fuzzy Inference System in Reservoir Inflow Forecasting (Case Study: The King Fahd Dam, Saudi Arabia)

Water ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1236
Author(s):  
Mohammed M. Alquraish ◽  
Khaled A. Abuhasel ◽  
Abdulrahman S. Alqahtani ◽  
Mosaad Khadr
Keyword(s):  
Genetic Algorithm ◽  
Performance Evaluation ◽  
Fuzzy Inference ◽  
Hidden Markov ◽  
Support Vector ◽  
Inference System ◽  
Inflow Forecasting ◽  
Reservoir Inflow ◽  
Two Hybrid ◽  
Neural Fuzzy

The precise prediction of the streamflow of reservoirs is of considerable importance for many activities relating to water resource management, such as reservoir operation and flood and drought control and protection. This study aimed to develop and evaluate the applicability of a hidden Markov model (HMM) and two hybrid models, i.e., the support vector machine-genetic algorithm (SVM-GA) and artificial neural fuzzy inference system-genetic algorithm (ANFIS-GA), for reservoir inflow forecasting at the King Fahd dam, Saudi Arabia. The results obtained by the HMM model were compared with those for the two hybrid models ANFIS-GA and SVM-GA, and with those for individual SVM and ANFIS models based on performance evaluation indicators and visual inspection. The results of the comparison revealed that the ANFIS-GA model and ANFIS model provided superior results for forecasting monthly inflow with satisfactory accuracy in both training (R2 = 0.924, 0.857) and testing (R2 = 0.842, 0.810) models. The performance evaluation results for the developed models showed that the GA-induced improvement in the ANFIS and SVR forecasts was matched by an approximately 25% decrease in RMSE and around a 13% increase in Nash–Sutcliffe efficiency. The promising accuracy of the proposed models demonstrates their potential for applications in monthly inflow forecasting in the present semiarid region.

Prognosticating the spread of covid-19 pandemic based on optimal arima estimators

2020 ◽  
Vol 20 ◽  
Author(s):  
Venuka Sandhir ◽  
Vinod Kumar ◽  
Vikash Kumar
Keyword(s):  
South Africa ◽  
Statistical Analysis ◽  
Moving Average ◽  
Arima Model ◽  
Information Criterion ◽  
Stable Case ◽  
Johns Hopkins University ◽  
Modelling Techniques ◽  
Auto Regressive ◽  
Global Threat

Background: COVID-19 cases have been reported as a global threat and several studies are being conducted using various modelling techniques to evaluate patterns of disease dispersion in the upcoming weeks. Here we propose a simple statistical model that could be used to predict the epidemiological extent of community spread of COVID-19from the explicit data based on optimal ARIMA model estimators. Methods: Raw data was retrieved on confirmed cases of COVID-19 from Johns Hopkins University (https://github.com/CSSEGISandData/COVID-19) and Auto-Regressive Integrated Moving Average (ARIMA) model was fitted based on cumulative daily figures of confirmed cases aggregated globally for ten major countries to predict their incidence trend. Statistical analysis was completed by using R 3.5.3 software. Results: The optimal ARIMA model having the lowest Akaike information criterion (AIC) value for US (0,2,0); Spain (1,2,0); France (0,2,1); Germany (3,2,2); Iran (1,2,1); China (0,2,1); Russia (3,2,1); India (2,2,2); Australia (1,2,0) and South Africa (0,2,2) imparted the nowcasting of trends for the upcoming weeks. These parameters are (p, d, q) where p refers to number of autoregressive terms, d refers to number of times the series has to be differenced before it becomes stationary, and q refers to number of moving average terms. Results obtained from ARIMA model showed significant decrease cases in Australia; stable case for China and rising cases has been observed in other countries. Conclusion: This study tried their best at predicting the possible proliferate of COVID-19, although spreading significantly depends upon the various control and measurement policy taken by each country.

scholarly journals End-to-end convolutional neural network enables COVID-19 detection from breath and cough audio: a pilot study

2021 ◽  
Vol 7 (2) ◽  
pp. 356-362
Author(s):  
Harry Coppock ◽  
Alex Gaskell ◽  
Panagiotis Tzirakis ◽  
Alice Baird ◽  
Lyn Jones ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Low Cost ◽  
Area Under The Curve ◽  
Alternative Form ◽  
Economic Damage ◽  
Audio Signals ◽  
Operating Characteristics ◽  
Data Set ◽  
Empirical Performance

BackgroundSince the emergence of COVID-19 in December 2019, multidisciplinary research teams have wrestled with how best to control the pandemic in light of its considerable physical, psychological and economic damage. Mass testing has been advocated as a potential remedy; however, mass testing using physical tests is a costly and hard-to-scale solution.MethodsThis study demonstrates the feasibility of an alternative form of COVID-19 detection, harnessing digital technology through the use of audio biomarkers and deep learning. Specifically, we show that a deep neural network based model can be trained to detect symptomatic and asymptomatic COVID-19 cases using breath and cough audio recordings.ResultsOur model, a custom convolutional neural network, demonstrates strong empirical performance on a data set consisting of 355 crowdsourced participants, achieving an area under the curve of the receiver operating characteristics of 0.846 on the task of COVID-19 classification.ConclusionThis study offers a proof of concept for diagnosing COVID-19 using cough and breath audio signals and motivates a comprehensive follow-up research study on a wider data sample, given the evident advantages of a low-cost, highly scalable digital COVID-19 diagnostic tool.

PERFORMANCE EVALUATION OF GENETIC DISTRIBUTED FUZZY CONTROLLERS FOR MULTI-PART-TYPE PRODUCTION LINE

2007 ◽  
Vol 06 (02) ◽  
pp. 115-128
Author(s):  
SEYED MAHDI HOMAYOUNI ◽  
TANG SAI HONG ◽  
NAPSIAH ISMAIL
Keyword(s):  
Genetic Algorithm ◽  
Performance Evaluation ◽  
Objective Function ◽  
Production Rate ◽  
Production Line ◽  
Production Systems ◽  
Membership Functions ◽  
Part Type ◽  
High Penalty ◽  
Single Part

Genetic distributed fuzzy (GDF) controllers are proposed for multi-part-type production line. These production systems can produce more than one part type. For these systems, "production rate" and "priority of production" for each part type is determined by production controllers. The GDF controllers have already been applied to single-part-type production systems. The methodology is illustrated and evaluated using a two-part-type production line. For these controllers, genetic algorithm (GA) is used to tune the membership functions (MFs) of GDF. The objective function of the GDF controllers minimizes the surplus level in production line. The results show that GDF controllers can improve the performance of production systems. GDF controllers show their abilities in reducing the backlog level. In production systems in which the backlog has a high penalty or is not allowed, the implementation of GDF controllers is advisable.

An MEWMA-based segmental multivariate hidden Markov model for degradation assessment and prediction

2021 ◽  
pp. 1748006X2199052
Author(s):  
Yaping Li ◽  
Enrico Zio ◽  
Ershun Pan
Keyword(s):  
Markov Models ◽  
Hidden Markov ◽  
Average Run Length ◽  
Moving Average ◽  
Model Parameters ◽  
Current Time ◽  
Multivariate Processes ◽  
Industrial Systems ◽  
Hidden States ◽  
Multivariate Signals

Degradation is an unavoidable phenomenon in industrial systems. Hidden Markov models (HMMs) have been used for degradation modeling. In particular, segmental HMMs have been developed to model the explicit relationship between degradation signals and hidden states. However, existing segmental HMMs deal only with univariate cases, whereas in real systems, signals from various sensors are collected simultaneously, which makes it necessary to adapt the segmental HMMs to deal with multivariate processes. Also, to make full use of the information from the sensors, it is important to differentiate stable signals from deteriorating ones, but there is no good way for this, especially in multivariate processes. In this paper, the multivariate exponentially weighted moving average (MEWMA) control chart is employed to identify deteriorating multivariate signals. Specifically, the MEWMA statistic is used as a comprehensive indicator for differentiating multivariate observations. Likelihood Maximization is used to estimate the model parameters. To avoid underflow, the forward and backward probabilities are normalized. In order to assess degradation, joint probabilities are defined and derived. Further, the occurrence probability of each degradation state at the current time, as well as in the future, is derived. The Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset of NASA is employed for comparative analysis. In terms of degradation assessment and prediction, the proposed model performs very well in general. By sensitivity analysis, we show that in order to improve further the performance of the method, the weight of the chart should be set relatively small, whereas the method is not sensitive to the change of the in-control average run length (ARL).

Sign in / Sign up

Export Citation Format

Share Document