38 results
Search Results
2. Predicting Energy Generation in Large Wind Farms: A Data-Driven Study with Open Data and Machine Learning.
- Author
-
Paula, Matheus, Casaca, Wallace, Colnago, Marilaine, da Silva, José R., Oliveira, Kleber, Dias, Mauricio A., and Negri, Rogério
- Subjects
WIND power plants ,MACHINE learning ,WIND power ,ARTIFICIAL intelligence ,WIND forecasting ,RANDOM forest algorithms ,WIND speed - Abstract
Wind energy has become a trend in Brazil, particularly in the northeastern region of the country. Despite its advantages, wind power generation has been hindered by the high volatility of exogenous factors, such as weather, temperature, and air humidity, making long-term forecasting a highly challenging task. Another issue is the need for reliable solutions, especially for large-scale wind farms, as this involves integrating specific optimization tools and restricted-access datasets collected locally at the power plants. Therefore, in this paper, the problem of forecasting the energy generated at the Praia Formosa wind farm, an eco-friendly park located in the state of Ceará, Brazil, which produces around 7% of the state's electricity, was addressed. To proceed with our data-driven analysis, publicly available data were collected from multiple Brazilian official sources, combining them into a unified database to perform exploratory data analysis and predictive modeling. Specifically, three machine-learning-based approaches were applied: Extreme Gradient Boosting, Random Forest, and Long Short-Term Memory Network, as well as feature-engineering strategies to enhance the precision of the machine intelligence models, including creating artificial features and tuning the hyperparameters. Our findings revealed that all implemented models successfully captured the energy-generation trends, patterns, and seasonality from the complex wind data. However, it was found that the LSTM-based model consistently outperformed the others, achieving a promising global MAPE of 4.55%, highlighting its accuracy in long-term wind energy forecasting. Temperature, relative humidity, and wind speed were identified as the key factors influencing electricity production, with peak generation typically occurring from August to November. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
3. Tri-XGBoost model improved by BLSmote-ENN: an interpretable semi-supervised approach for addressing bankruptcy prediction.
- Author
-
Smiti, Salima, Soui, Makram, and Ghedira, Khaled
- Subjects
BANKRUPTCY ,ARTIFICIAL intelligence ,RECEIVER operating characteristic curves ,DATA science ,FORECASTING - Abstract
Bankruptcy prediction is considered one of the most important research topics in the field of finance and accounting. The rapid increase of data science, artificial intelligence, and machine learning has led researchers to build an accurate bankruptcy prediction model. Recent studies show that ensemble methods perform better than traditional machine learning models for predicting corporate failure, especially with highly imbalanced datasets. However, the black box property of these techniques remains challenging to interpret the result and generate corporate classes without any explanation. To this end, we propose to build an accurate and interpretable classification model that generates a set of prediction rules for output. Tri-eXtreme Gradient Boosting (Tri-XGBoost), a semi-supervised technique, is recommended in this paper. The proposed method combines Borderline-Smote (BLSmote) based on Edited Nearest Neighbor (ENN) sampling techniques with three different XGBoost methods as weak classifiers (gbtree, gblinear, and dart). First, the resampling techniques are used to produce more representative synthetic data and balance the distribution of the datasets. To this end, BLSmote is applied to increase the proportion of instances in the minority class (bankrupt data). Then, ENN is used to eliminate the noisy samples from both classes. In addition, the most crucial features that increase predictive accuracy are chosen using XGBoost. Finally, in order to make the model more understandable for both applicants and experts, our result is presented as "IF–THEN" rules. Our proposed model is validated using the imbalanced Polish and Taiwan bankruptcy datasets. Our obtained results demonstrate that our suggested model performs better than the existing models based on the area under the ROC curve (AUC), F1-score, and G-mean performance measures. Our proposed model significantly improves classification accuracy, which is greater than 95% for Polish datasets and more than 93% for Taiwanese dataset in terms of AUC, G-mean and F1-score. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. A Machine Learning-Based Ensemble Framework for Forecasting PM 2.5 Concentrations in Puli, Taiwan.
- Author
-
Yin, Peng-Yeng, Yen, Alex Yaning, Chao, Shou-En, Day, Rong-Fuh, and Bhanu, Bir
- Subjects
PLANT mortality ,PLANT species ,CLIMATE change ,AUTOREGRESSION (Statistics) ,PREDICTION models ,FORECASTING - Abstract
Forecasting of PM
2.5 concentration is a global concern. Evidence has shown that the ambient PM2.5 concentrations are harmful to human health, climate change, plant species mortality, etc. PM2.5 concentrations are caused by natural and anthropogenic activities, and it is challenging to predict them due to many uncertain factors. Current research has focused on developing a new model while overlooking the fact that every single model for PM2.5 prediction has its own strengths and weaknesses. This paper proposes an ensemble framework which combines four diverse learning models for PM2.5 forecasting in Puli, Taiwan. It explores the synergy between parametric and non-parametric learning, and short-term and long-term learning. The feature set covers periodic, meteorological, and autoregression variables which are selected by a spiral validation process. The experimental dataset, spanning from 1 January 2008 to 31 December 2019, from Puli Township in central Taiwan, is used in this study. The experimental results show the proposed multi-model framework can synergize the advantages of the embedded models and obtain an improved forecasting result. Further, the benefit obtained by blending short-term learning with long-term learning is validated, in surpassing the performance obtained by using just single type of learning. Our multi-model framework compares favorably with deep-learning models on Puli dataset. It also shows high adaptivity, such that our multi-model framework is comparable to the leading methods for PM2.5 forecasting in Delhi, India. [ABSTRACT FROM AUTHOR]- Published
- 2022
- Full Text
- View/download PDF
5. A parallel-series hybridization of seasonal intelligent based statistical model for demand forecasting.
- Author
-
Bahrami, Maryam, Khashei, Mehdi, and Amindoust, Atefeh
- Subjects
DEMAND forecasting ,STATISTICAL models ,BOX-Jenkins forecasting ,SEASONS ,TIME series analysis - Abstract
Purpose: The purpose of this paper, because of the complexity of demand time series and the need to construct a more accurate hybrid model that can model all relationships in data, is to propose a parallel-series hybridization of seasonal neural networks and statistical models for demand time series forecasting. Design/methodology/approach: The main idea of proposed model is centered around combining parallel and series hybrid methodologies to use the benefit of unique advantages of both hybrid strategies as well as intelligent and classic seasonal time series models simultaneously for achieving results that are more accurate for the first time. In the proposed model, in contrast of traditional parallel and series hybrid strategies, it can be generally shown that the performance of the proposed model will not be worse than components. Findings: Empirical results of forecasting two well-known seasonal time series data sets, including the total production value of the Taiwan machinery industry and the sales volume of soft drinks, indicate that the proposed model can effectively improve the forecasting accuracy achieved by either of their components used in isolation. In addition, the proposed model can achieve more accurate results than parallel and series hybrid model with same components. Therefore, the proposed model can be used as an appropriate alternative model for seasonal time series forecasting, especially when higher forecasting accuracy is needed. Originality/value: To the best of the authors' knowledge, the proposed model, for first time and in contrast of traditional parallel and series hybrid strategies, is developed. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
6. Interactive tool for clustering and forecasting patterns of Taiwan COVID-19 spread.
- Author
-
Ashouri, Mahsa and Phoa, Frederick Kin Hing
- Subjects
STATISTICAL smoothing ,COVID-19 ,WEB-based user interfaces ,MEDICAL research personnel ,DEMAND forecasting ,HIERARCHICAL clustering (Cluster analysis) ,FORECASTING - Abstract
The COVID-19 data analysis is essential for policymakers to analyze the outbreak and manage the containment. Many approaches based on traditional time series clustering and forecasting methods, such as hierarchical clustering and exponential smoothing, have been proposed to cluster and forecast the COVID-19 data. However, most of these methods do not scale up with the high volume of cases. Moreover, the interactive nature of the application demands further critically complex yet compelling clustering and forecasting techniques. In this paper, we propose a web-based interactive tool to cluster and forecast the available data of Taiwan COVID-19 confirmed infection cases. We apply the Model-based (MOB) tree and domain-relevant attributes to cluster the dataset and display forecasting results using the Ordinary Least Square (OLS) method. In this OLS model, we apply a model produced by the MOB tree to forecast all series in each cluster. Our user-friendly parametric forecasting method is computationally cheap. A web app based on R's Shiny App makes it easier for practitioners to find clustering and forecasting results while choosing different parameters such as domain-relevant attributes. These results could help in determining the spread pattern and be utilized by medical researchers. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
7. The Effects of CSR Report Mandatory Policy on Analyst Forecasts: Evidence from Taiwan.
- Author
-
Tseng, Tzu-Yun and Shih, Nien-Su
- Subjects
SOCIAL responsibility of business ,DISCLOSURE laws ,FORECASTING ,SOCIAL accounting - Abstract
The Taiwanese government altered its corporate social responsibility (CSR) report management policy from voluntary disclosure and assurance of CSR reports to partial mandatory disclosure and partial mandatory assurance. This paper examines this policy's effects on analyst forecast. The empirical results showed that the mandatory disclosure policy on CSR reports significantly increased analyst forecast accuracy and reduced analyst forecast dispersion. Furthermore, the study found that analyst forecast accuracy was further increased when CSR reports were forced to undergo accountant assurance than those without mandatory accountant assurance which means that the mandatory assurance policy on CSR reports significantly further increased analyst forecast accuracy. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
8. Financial Distress Prediction of Cooperative Financial Institutions—Evidence for Taiwan Credit Unions.
- Author
-
Kang, Chien-Min, Wang, Ming-Chieh, and Lin, Lin
- Subjects
CREDIT unions ,FINANCIAL institutions ,BUSINESS forecasting ,MARKET volatility ,FORECASTING - Abstract
In response to relatively little evidence on the determinants of the financial distress in cooperative financial institutions (e.g., Credit Unions), this paper proposes a distress indicator of Merton Distance to default (Merton DD), which was constructed with a z-score, possessed improved predictive capability, but reducing equity volatility. This model possesses the advantages of both hazard and modified Merton DD model, which could timely reflect market volatility and predict when distress would occur. As a demonstration, we applied this model to forecast the financial distress of credit unions in Taiwan. The results can provide more information to researchers. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
9. Model Establishment of Cross-Disease Course Prediction Using Transfer Learning.
- Author
-
Ying, Josh Jia-Ching, Chang, Yen-Ting, Chen, Hsin-Hua, and Chao, Wen-Cheng
- Subjects
DEEP learning ,MEDICAL technology ,ARTIFICIAL intelligence ,TIME series analysis ,PREDICTION models ,FORECASTING - Abstract
In recent years, the development and application of artificial intelligence have both been topics of concern. In the medical field, an important direction of medical technology development is the extraction and use of applicable information from existing medical records to provide more accurate and helpful diagnosis suggestions. Therefore, this paper proposes using the development of diseases with easily discernible symptoms to predict the development of other medically related but distinct diseases that lack similar data. The aim of this study is to improve the ease of assessing the development of diseases in which symptoms are difficult to detect, and to improve the utilization of medical data. First, a time series model was used to capture the continuous manifestations of diseases with symptoms that could be easily found at different time intervals. Then, through transfer learning and attention mechanism, the general features captured were applied to the predictive model of the development of diseases with insufficient data and symptoms that are difficult to detect. Finally, we conducted a comprehensive experimental study based on a dataset collected from the National Health Insurance Research Database in Taiwan. The results demonstrate that the effectiveness of our transfer learning approach outperforms state-of-the-art deep learning prediction models for disease course prediction. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
10. Performance Evaluation and Forecasting for High School Admission Through School-Based Assessment in Taiwan.
- Author
-
Wen-Tsung Lai
- Subjects
SCHOOL admission ,FORECASTING ,HIGH schools ,HIGH school seniors ,TIME series analysis - Abstract
Purpose: The purpose of this study is to evaluate why school-based assessment cannot be considered to compare the sequence of senior high school admissions that exceed the quota. Method: The study sample comprises 1,650 graduates whose Basic Competency Test (BCTEST) were considered for their high school admission in Taiwan during 2009--2013. The statistical forecasting methods used are fuzzy time series and self-regression. Result: The result is that the development trend of every student is considered by using the forecasting scores of fuzzy time series with the 17 stages of interval fuzzy scores. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
11. Transportation energy demand forecasting in Taiwan based on metaheuristic algorithms.
- Author
-
Lashgari, Ali, Hosseinzadeh, Hasan, Khalilzadeh, Mohammad, Milani, Bahar, Ahmadisharaf, Amin, and Rashidi, Shima
- Subjects
DEMAND forecasting ,ENERGY consumption ,CURVE fitting ,ENERGY futures ,GROWTH rate - Abstract
A new methodology is suggested in this study to provide optimum forecasting of the future transportation energy demand in Taiwan. The paper introduces a new improved version of Emperor Penguin Optimizer (IEPO) to provide an optimal and suitable forecasting model. The forecasting was based on three different models including linear, exponential, and quadratic where their coefficients have been optimized using the suggested IEPO algorithm which is based on considering the population, the GDP growth rate, and the total annual vehicle-km. The study considers two different scenarios based on curve fitting and projection data. The results indicate that the RMS value for the TED forecasting based on the proposed IEPO algorithm applied to the linear, exponential, and Quadratic for training are 0.0452, 0.0461, and 0.0492, respectively and for testing are 0.0456, 0.0596, and 0.0642, respectively. This shows better results of the optimized exponential method's efficiency. Simulation results showed high efficiency for the proposed IEPO-based transportation energy demand forecasting based on all of the employed models for decision-making in ROC. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
12. Significant wave height forecasting using WRF-CLSF model in Taiwan strait.
- Author
-
Ma, Jinshan, Xue, Honghui, Zeng, Yindong, Zhang, Zhenchang, and Wang, Qicong
- Subjects
NUMERICAL weather forecasting ,STRAITS ,WIND forecasting ,WAVES (Fluid mechanics) ,CONVOLUTIONAL neural networks ,COASTAL engineering ,FORECASTING - Abstract
Short-term hourly reliable prediction of significant wave height is an important research topic in coastal engineering. Many researchers have carried out in-depth studies in many ocean regions. Generally, most of this work is implemented through numerical models. However, as for numerical models, with the increase of hourly prediction duration, the accumulation of wave randomness leads to the poor prediction effect. In this paper, four buoy stations in the Taiwan Strait are taken as the research objects. We propose a significant wave height prediction algorithm, which combines numerical weather prediction model WRF and deep-learning model, called WRF-CLSF(Convolution-LSTM-FC). WRF can forecast 24-h wind speed in real-time, based on a variety of interpretable physical mechanisms. CLSF aims to extract the information of historical wind-wave interaction scale and the trend of wind-wave coherence, with the help of convolution operation and the time series model(LSTM), respectively. In the experiment, the proposed model was compared with the state-of-the-art prediction model. The results show that WRF-CLSF has an outstanding prediction effect at four buoy observation stations along with the Taiwan Strait. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
13. Initiative climate, psychological safety and knowledge sharing as predictors of team creativity: A multilevel study of research and development project teams.
- Author
-
Liu, Yuwen, Keller, Robert T., and Bartlett, Kenneth R.
- Subjects
INFORMATION sharing ,RESEARCH & development projects ,FORECASTING ,ORGANIZATIONAL learning ,INDIVIDUALIZED instruction - Abstract
This paper examines from a multilevel perspective the contributions of initiative climate, psychological safety and knowledge sharing to team creativity in research and development (R&D) project teams. We propose and test an organizational learning contingency model of creativity, reflecting on how initiative climate interacts with employees' psychological safety in influencing knowledge sharing and teams' creative performance, by collecting data from 352 employees comprising 88 R&D teams in Taiwan at two time points and from two sources, team members and team leaders. Results indicated that knowledge sharing acts as a mediator in the relationship between initiative climate and team creativity. Results also supported the cross‐level moderation effect of initiative climate on the relationship between psychological safety and knowledge sharing behaviour. We also made the interesting but unhypothesized findings that tenure differentiation and education diversity both negatively influenced team creativity and go on to discuss both theoretical and practical implications of our research. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
14. Week-ahead daily peak load forecasting using genetic algorithm-based hybrid convolutional neural network.
- Author
-
Ying-Yi Hong, Yu-Hsuan Chan, Yung-Han Cheng, Yih-Der Lee, Jheng-Lun Jiang, and Shen-Szu Wang
- Subjects
- *
PEAK load , *CONVOLUTIONAL neural networks , *RECURRENT neural networks , *CASCADE connections , *BIDDING strategies , *FORECASTING - Abstract
Daily peak load forecasting is crucial for the operation of bulk power systems, including economic dispatch and unit commitment. It is also essential for peak load shaving and load management in distribution systems. In power markets, peak load forecasting helps participants develop bidding strategies. This paper proposes a new method, using a hybrid convolutional neural network (CNN) that is cascaded with a fully-connected network, for making week-ahead daily peak load forecasts. The proposed method uses three loops to obtain the optimal CNN: The outer loop performs crossover/mutation operations and tournament selection to produce chromosomes to optimize the network topology and hyperparameters (such as kernel size) of the hybrid CNN by genetic algorithms; the middle loop deals with the order of chromosomes; the inner loop optimizes the synaptic weights and parameters (e.g. values of a kernel) using Adam optimizer. Daily peak load data and corresponding meteorological data for Taiwan are explored. Simulation results show that the proposed method outperforms the traditional CNN, multi-layer neural network, recurrent neural network, support vector regression and vector autoregressive moving average model. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
15. Forecasting Trading-Session Return Volatility in Taiwan Futures Market: A Periodic Regime Switching with Jump Approach.
- Author
-
Lai, Yi-Hao, Wang, Yi-Chiuan, and Chang, Yu-Ching
- Subjects
VOLATILITY (Securities) ,MARKET volatility ,FUTURES market ,FORECASTING ,INVESTMENT risk ,INVESTMENT management ,JUMP processes - Abstract
This study develops a novel periodic regime-switching model (the PRS model) to improve the forecasting of stock market volatility by accounting for the information from non-trading and trading periods, including regular trading and after-hour trading. Empirical analysis of the Taiwan Futures Exchange (TAIFEX) demonstrates the significant improvements of the PRS model in both in-sample and out-of-sample periods. Our results also show that the introduction of after-hour trading sessions has provided valuable information for volatility forecasting in subsequent regular trading sessions, emphasizing the importance of considering diverse information flows across different trading and non-trading times. The PRS model effectively captures the dynamics of non-trading and trading sessions and the influence of unusual news arrivals and jumps on market volatility, contributing to investment and risk management strategies. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
16. Hypothesis testing for performance evaluation of probabilistic seasonal rainfall forecasts.
- Author
-
Cheng, Ke-Sheng, Yu, Gwo‑Hsing, Tai, Yuan-Li, Huang, Kuo-Chan, Tsai, Sheng‑Fu, Wu, Dong‑Hong, Lin, Yun-Ching, Lee, Ching-Teng, and Lo, Tzu-Ting
- Subjects
DISTRIBUTION (Probability theory) ,SEASONS ,SUMMER ,FORECASTING ,RAINFALL ,HYPOTHESIS - Abstract
A hypothesis testing approach, based on the theorem of probability integral transformation and the Kolmogorov–Smirnov one-sample test, for performance evaluation of probabilistic seasonal rainfall forecasts is proposed in this study. By considering the probability distribution of monthly rainfalls, the approach transforms the tercile forecast probabilities into a forecast distribution and tests whether the observed data truly come from the forecast distribution. The proposed approach provides not only a quantitative measure for performance evaluation but also a cumulative probability plot for insightful interpretations of forecast characteristics such as overconfident, underconfident, mean-overestimated, and mean-underestimated. The approach has been applied for the performance evaluation of probabilistic season rainfall forecasts in northern Taiwan, and it was found that the forecast performance is seasonal dependent. Probabilistic seasonal rainfall forecasts of the Meiyu season are likely to be overconfident and mean-underestimated, while forecasts of the winter-to-spring season are overconfident. A relatively good forecast performance is observed for the summer season. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
17. Impact of the COVID-19 Pandemic on the Revenue of the Catering Industry: Taiwan as an Example.
- Author
-
Hsin-Chieh Wu, Tin-Chih Toly Chen, and Syuan Yu Wang
- Subjects
COVID-19 pandemic ,CATERING services ,BUSINESS revenue ,BUSINESS planning ,RANDOM forest algorithms - Abstract
Due to the impact of the COVID-19 pandemic, people have reduced eating out, resulting in a severe drop in the revenue of the catering industry. Health risks have become a major factor affecting the revenue of this industry. Predicting the revenue of the catering industry during the COVID-19 pandemic will not only allow practitioners to adjust their business strategies, but also provide a reference for governments to formulate relief measures. To this end, this study proposes a fuzzy big data analytics approach in which random forests, recursive feature elimination, fuzzy c-means, and deep neural networks are jointly applied. First, random forests and recursive feature elimination are used to select the most influential factors. The data is then divided into clusters by fuzzy c-means. Subsequently, a deep neural network is built for each cluster to make predictions. The prediction results of individual clusters are then aggregated to improve prediction accuracy. The proposed methodology has been applied to forecast the revenue of the catering industry in Taiwan. The results of the experiment showed that the impact of new deaths on the revenue of the catering industry was far greater than the number of newly diagnosed COVID-19 cases. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
18. Bayesian Forecasting of Bounded Poisson Distributed Time Series.
- Author
-
Liu, Feng-Chi, Chen, Cathy W. S., and Ho, Cheng-Ying
- Subjects
AIR quality indexes ,FORECASTING ,CREDIT ratings ,POISSON distribution ,BAYESIAN field theory - Abstract
This research models and forecasts bounded ordinal time series data that can appear in various contexts, such as air quality index (AQI) levels, economic situations, and credit ratings. This class of time series data is characterized by being bounded and exhibiting a concentration of large probabilities on a few categories, such as states 0 and 1. We propose using Bayesian methods for modeling and forecasting in zero-one-inflated bounded Poisson autoregressive (ZOBPAR) models, which are specifically designed to capture the dynamic changes in such ordinal time series data. We innovatively extend models to incorporate exogenous variables, marking a new direction in Bayesian inferences and forecasting. Simulation studies demonstrate that the proposed methods accurately estimate all unknown parameters, and the posterior means of parameter estimates are robustly close to the actual values as the sample size increases. In the empirical study we investigate three datasets of daily AQI levels from three stations in Taiwan and consider five competing models for the real examples. The results exhibit that the proposed method reasonably predicts the AQI levels in the testing period, especially for the Miaoli station. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
19. A novel rainfall forecast model using GNSS observations and CAPE in Singapore.
- Author
-
Liu, Zhuoya, Wen, Yi, Zhang, Xun, Wang, Mian, Xiao, Shuzhou, Chen, Yuan, and He, Lin
- Subjects
- *
GLOBAL Positioning System , *PRECIPITABLE water , *RAINFALL , *STANDARD deviations , *FORECASTING - Abstract
Precipitable water vapor (PWV) and zenith total delay (ZTD) are highly correlated indicators used for forecasting rainfall effectively. These two factors are widely used when establishing qualitative and quantitative rainfall forecast models. Another indicator, however, convective available potential energy (CAPE), is also highly correlated with the occurrence of rainfall, but has not been combined with PWV or ZTD in previous studies. Therefore, a novel rainfall forecast model based on support vector regression that combines CAPE and Global Navigation Satellite System (GNSS)-derived PWV is proposed in this paper. Moreover, annual, seasonal scales, and hourly autocorrelation for predictors were also considered, and wavelet coherence (WTC) was introduced to further reveal the correlation relationships between CAPE, PWV and rainfall in both time and frequency domains. Hourly PWV, CAPE, temperature (T) and rainfall over a time span of three years were collected from four stations in Singapore and Taiwan to evaluate the performance of the proposed model. The root mean square error (RMSE) and mean absolute error (MAE) between the measured and forecasted rainfall were calculated for each year and averaged. Subsequently, the average RMSE and MAE were determined for the annual seasonal rainfall. The annual average RMSE value was 0.71 mm and the average annual seasonal RMSE value was 0.69 mm. The annual average MAE value was 0.21 mm and the annual seasonal was 0.22 mm. The average correlation coefficient (R2) for the annual value was 0.94 and the annual seasonal R2 value was 0.93. These results indicate that the forecast accuracy at the seasonal scale is basically consistent with annual scale. Additionally, a measure called comparable RMSE (CRMS) was introduced to evaluate the forecasting accuracy across all grades of rainfall. This analysis showed that the accuracy of moderate rainfall (MR) and heavy rainfall (HR) forecasts is similar, but slight rainfall (SR) forecasts are the most accurate among seasons and schemes. • A short-term rainfall forecast method is proposed using convective available potential energy (CAPE) and GNSS-derived PWV. • The forecast accuracy of seasonal scales is consistent with annual scale. • Results showed that the forecast accuracy of moderate rainfall and heavy rainfall were comparable while that of slight rainfall was highest. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
20. A Global Solar Radiation Forecasting System Using Combined Supervised and Unsupervised Learning Models.
- Author
-
Wei, Chih-Chiang and Yang, Yen-Chen
- Subjects
SOLAR radiation ,GLOBAL radiation ,MACHINE learning ,SUPERVISED learning ,SOLAR energy ,SOLAR technology ,FORECASTING ,FUZZY neural networks ,EARTH stations - Abstract
One of the most important sources of energy is the sun. Taiwan is located at a 22–25° north latitude. Due to its proximity to the equator, it experiences only a small angle of sunlight incidence. Its unique geographical location can obtain sustainable and stable solar resources. This study uses research on solar radiation forecasts to maximize the benefits of solar power generation, and it develops methods that can predict future solar radiation patterns to help reduce the costs of solar power generation. This study built supervised machine learning models, known as a deep neural network (DNN) and a long–short-term memory neural network (LSTM). A hybrid supervised and unsupervised model, namely a cluster-based artificial neural network (k-means clustering- and fuzzy C-means clustering-based models) was developed. After establishing these models, the study evaluated their prediction results. For different prediction periods, the study selected the best-performing model based on the results and proposed combining them to establish a real-time-updated solar radiation forecast system capable of predicting the next 12 h. The study area covered Kaohsiung, Hualien, and Penghu in Taiwan. Data from ground stations of the Central Weather Administration, collected between 1993 and 2021, as well as the solar angle parameters of each station, were used as input data for the model. The results of this study show that different models offer advantages and disadvantages in predicting different future times. The hybrid prediction system can predict future solar radiation more accurately than a single model. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
21. Hybrid Post-Processing on GEFSv12 Reforecast for Summer Maximum Temperature Ensemble Forecasts with an Extended-Range Time Scale over Taiwan.
- Author
-
Nageswararao, Malasala Murali, Zhu, Yuejian, Tallapragada, Vijay, and Chen, Meng-Shih
- Subjects
ARTIFICIAL neural networks ,LONG-range weather forecasting ,SUMMER ,FORECASTING ,ATMOSPHERIC temperature ,DEEP learning ,GLOBAL warming - Abstract
Taiwan is highly susceptible to global warming, experiencing a 1.4 °C increase in air temperature from 1911 to 2005, which is twice the average for the Northern Hemisphere. This has potentially led to higher rates of respiratory and cardiovascular mortality. Accurately predicting maximum temperatures during the summer season is crucial, but numerical weather models become less accurate and more uncertain beyond five days. To enhance the reliability of a forecast, post-processing techniques are essential for addressing systematic errors. In September 2020, the NOAA NCEP implemented the Global Ensemble Forecast System version 12 (GEFSv12) to help manage climate risks. This study developed a Hybrid statistical post-processing method that combines Artificial Neural Networks (ANN) and quantile mapping (QQ) approaches to predict daily maximum temperatures (T
max ) and their extremes in Taiwan during the summer season. The Hybrid technique, utilizing deep learning techniques, was applied to the GEFSv12 reforecast data and evaluated against ERA5 reanalysis. The Hybrid technique was the most effective among the three techniques tested. It had the lowest bias and RMSE and the highest correlation coefficient and Index of Agreement. It successfully reduced the warm bias and overestimation of Tmax extreme days. This led to improved prediction skills for all forecast lead times. Compared to ANN and QQ, the Hybrid method proved to be more effective in predicting daily Tmax , including extreme Tmax during summer, on extended-range time-scale deterministic and ensemble probabilistic forecasts over Taiwan. [ABSTRACT FROM AUTHOR]- Published
- 2023
- Full Text
- View/download PDF
22. Assessing the Impact of Dropsonde Data on Rain Forecasts in Taiwan with Observing System Simulation Experiments.
- Author
-
Chien, Fang-Ching and Chiu, Yen-Chao
- Subjects
TROPICAL cyclones ,SIMULATION methods & models ,FORECASTING - Abstract
This paper presents an observing system simulation experiment (OSSE) study to examine the impact of dropsonde data assimilation (DA) on rainfall forecasts for a heavy rain event in Taiwan. The rain event was associated with strong southwesterly flows over the northern South China Sea (SCS) after a weakening tropical cyclone (TC) made landfall over southeastern China. With DA of synthetic dropsonde data over the northern SCS, the model reproduces more realistic initial fields and a better simulated TC track that can help in producing improved low-level southwesterly flows and rainfall forecasts in Taiwan. Dropsonde DA can also aid the model in reducing the ensemble spread, thereby producing more converged ensemble forecasts. The sensitivity studies suggest that dropsonde DA with a 12-h cycling interval is the best strategy for deriving skillful rainfall forecasts in Taiwan. Increasing the DA interval to 6 h is not beneficial. However, if the flight time is limited, a 24-h interval of DA cycling is acceptable, because rainfall forecasts in Taiwan appear to be satisfactory. It is also suggested that 12 dropsondes with a 225-km separation distance over the northern SCS set a minimum requirement for enhancing the model regarding rainfall forecasts. Although more dropsonde data can help the model to obtain better initial fields over the northern SCS, they do not provide more assistance to the forecasts of the TC track and rainfall in Taiwan. These findings can be applied to the future field campaigns and model simulations in the nearby regions. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
23. Tourism combination forecasting using a dynamic weighting strategy with change-point analysis.
- Author
-
Hu, Yi-Chung
- Subjects
FORECASTING ,FUZZY integrals ,INBOUND tourism ,PREDICTION models ,TOURISM - Abstract
Combination forecasting is an important in the literature on tourism. This study considers three important issues to develop a more accurate combination forecasting method for tourism forecasting. We address the unrealistic requirement related to the statistical properties of the collected data for model fitting, assign changing rather than fixed weights to single models, and incorporate nonlinear relationships among single-model forecasts into forecast combinations. This leads us to develop a three-stage procedure for combination forecasting that consists of generating single-model forecasts with grey prediction models, detecting significant changes in the time series to determine when to update the weights for combining the forecasts, and nonlinearly combining individual forecasts based on a dynamic weighting strategy. In contrast with commonly used fixed weighting, the dynamic weighting used here involves the use of change points to identify the period for which the weights need to be re-estimated. The inbound demand for tourism in Taiwan was used as an empirical case to assess the performance of the proposed framework for forecast combinations. The results show that the nonlinear fuzzy integral with the proposed dynamic weighting strategy significantly outperforms that with the fixed weighting strategy, and has a superior forecasting accuracy than other combined models. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
24. Eight-Day Typhoon Quantitative Precipitation Forecasts in Taiwan by the 2.5 km CReSS Model, Part II: Reduced Control of Track Errors on Rainfall Prediction Quality for Typhoons Associated with Southwesterly Flow.
- Author
-
Wang, Chung-Chieh, Soong, Wei-Kuo, Chien, Chih-Wei, Chang, Chih-Sheng, and Huang, Shin-Yi
- Subjects
TYPHOONS ,PRECIPITATION forecasting ,RAINFALL ,STORMS ,TOPOGRAPHY ,FORECASTING - Abstract
Due to the enhancement by its steep mesoscale topography, the overall rainfall amount and distribution in Taiwan from typhoons, to a first degree, are determined by the storm track relative to the island. Therefore, the quality of typhoon quantitative precipitation forecasts (QPFs) from numerical models is often controlled by track errors, with better quality from those with smaller track errors. However, the present work demonstrates that in daily QPFs over Taiwan made by a cloud-resolving model during five seasons of 2012–2016, targeted for 84 days during 27 typhoons and at ranges of day one (0–24 h) to day eight (168–192 h), the control of track errors on QPF quality is reduced for typhoons associated with southwesterly flow, compared to those without, and decent QPFs could still be obtained with large track errors in some cases. Subsequently, the circumstances and reasons for good (or bad) QPFs in selected examples are further investigated to deepen our understanding of typhoon QPFs in Taiwan. Some common ingredients are found in three cases where good QPFs were produced at a longer range (day 7 or 8) without a good track: these typhoons passed near northern Taiwan and the southwesterly flow prevailed over much of the island during the accumulation period. Responsible for much of the rainfall in Taiwan, the southwesterly flow was reasonably captured, resulting in good QPFs. In another example where the typhoon moved across southern Taiwan, on the contrary, the rainfall was produced by the storm's circulation, and the QPF was degraded without a good enough track prediction. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
25. Performance of a Convective-Scale Ensemble Prediction System on 2017 Warm-Season Afternoon Thunderstorms over Taiwan.
- Author
-
I-HAN CHEN, YI-JUI SU, HSIAO-WEI LAI, JING-SHAN HONG, CHIH-HSIN LI, PAO-LIANG CHANG, and YING-JHANG WU
- Subjects
METEOROLOGICAL services ,THUNDERSTORMS ,PRECIPITATION forecasting ,LEAD time (Supply chain management) ,TYPHOONS ,FORECASTING ,DATA analysis - Abstract
A 16-member convective-scale ensemble prediction system (CEPS) developed at the Central Weather Bureau (CWB) of Taiwan is evaluated for probability forecasts of convective precipitation. To address the issues of limited predictability of convective systems, the CEPS provides short-range forecasts using initial conditions from a rapid-updated ensemble data assimilation system. This study aims to identify the behavior of the CEPS forecasts, especially the impact of different ensemble configurations and forecast lead times. Warm-season afternoon thunderstorms (ATs) from 30 June to 4 July 2017 are selected. Since ATs usually occur between 1300 and 2000 LST, this study compares deterministic and probabilistic quantitative precipitation forecasts (QPFs) launched at 0500, 0800, and 1100 LST. This study demonstrates that initial and boundary perturbations (IBP) are crucial to ensure good spread–skill consistency over the 18-h forecasts. On top of IBP, additional model perturbations have insignificant impacts on upper-air and precipitation forecasts. The deterministic QPFs launched at 1100 LST outperform those launched at 0500 and 0800 LST, likely because the most-recent data assimilation analyses enhance the practical predictability. However, it cannot improve the probabilistic QPFs launched at 1100 LST due to inadequate ensemble spreads resulting from limited error growth time. This study points out the importance of sufficient initial condition uncertainty on short-range probabilistic forecasts to exploit the benefits of rapid-update data assimilation analyses. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
26. Recurrent Learning on PM 2.5 Prediction Based on Clustered Airbox Dataset.
- Author
-
Lo, Chia-Yu, Huang, Wen-Hsing, Ho, Ming-Feng, Sun, Min-Te, Chen, Ling-Jyh, Sakai, Kazuya, and Ku, Wei-Shinn
- Subjects
AIR pollutants ,STEAM power plants ,AIR pollution ,NUCLEAR power plants ,FORECASTING ,PREDICTION models - Abstract
The progress of industrial development naturally leads to the demand for more electrical power. Unfortunately, due to the fear of the safety of nuclear power plants, many countries have relied on thermal power plants, which will cause more air pollutants during the process of coal burning. This phenomenon as well as increased vehicle emissions around us, have constituted the primary factors of serious air pollution. Inhaling too much particulate air pollution may lead to respiratory diseases and even death, especially PM $_{2.5}$ 2. 5 . By predicting the air pollutant concentration, people can take precautions to avoid overexposure to air pollutants. Consequently, accurate PM $_{2.5}$ 2. 5 prediction becomes more important. In this study, we propose a PM $_{2.5}$ 2. 5 prediction system, which utilizes the dataset from EdiGreen Airbox and Taiwan EPA. Autoencoder and Linear interpolation are adopted for solving the missing value problem. Spearman’s correlation coefficient is used to identify the most relevant features for PM $_{2.5}$ 2. 5 . Two prediction models (i.e., LSTM and LSTM based on K-means) are implemented which predict PM $_{2.5}$ 2. 5 value for each Airbox device. To assess the performance of the model prediction, the daily average error and the hourly average accuracy for the duration of a week are calculated. The experimental results show that LSTM based on K-means has the best performance among all methods. Therefore, LSTM based on K-means is chosen to provide real-time PM $_{2.5}$ 2. 5 prediction through the Linebot. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
27. Forecasting Hourly Intermittent Rainfall by Deep Belief Networks with Simple Exponential Smoothing.
- Author
-
Huang, Guo-Yu, Lai, Chi-Ju, and Pai, Ping-Feng
- Subjects
RAINFALL ,STATISTICAL smoothing ,DEMAND forecasting ,FORECASTING ,DEEP learning ,GENETIC algorithms - Abstract
Accurate rainfall forecasting is essential in planning and managing water resource systems efficiently. However, intermittent rainfall patterns increase the difficulty of accurately forecasting rainfall values. Deep learning techniques have recently been popular and powerful in forecasting. Thus, this study employed deep belief networks with a simple exponential smoothing procedure (DBNSES) to forecast hourly intermittent rainfall values in Taiwan. Weather factors were used as independent variables to forecast rainfall volume. The simple exponential smoothing data preprocessing procedure was used to deal with the intermittent data patterns. The other three forecasting models, namely the least squares support vector regression (LSSVR), the generalized regression neural network (GRNN), and the backpropagation neural network (BPNN), were employed to forecast rainfall using the same data sets. In addition, genetic algorithms were utilized to determine the parameters of four forecasting models. The empirical results indicate that the developed DBNSES models are superior to the other forecasting models in terms of forecasting accuracy. In addition, the DBNSES can obtain smaller values of RMSE than those in the previous studies. Therefore, the DBNSES model is a suitable and effective way of forecasting rainfall with intermittent data patterns. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
28. Microphysical Perturbation Experiments and Ensemble Forecasts on Summertime Heavy Rainfall over Northern Taiwan.
- Author
-
Chen, Jen-Ping, Tsai, Tzu-Chin, Tzeng, Min-Duan, Liao, Chi-Shuin, Kuo, Hung-Chi, and Hong, Jing-Shan
- Subjects
WEATHER forecasting ,RAINFALL probabilities ,SUMMER ,FORECASTING ,AUTUMN ,TROPICAL cyclones ,RAINFALL - Abstract
Microphysical perturbation experiments were conducted to investigate the sensitivity of convective heavy rain simulation to cloud microphysical parameterization and its feasibility for ensemble forecasts. An ensemble of 20 perturbation members differing in either the microphysics package or process treatments within a single scheme was applied to simulate 10 summer-afternoon heavy-rain convection cases. The simulations revealed substantial disagreements in the location and amplitude of peak rainfall among the microphysics-package and single-scheme members, with an overall spread of 57%–161%, 66%–161%, and 65%–149% of the observed average rainfall, maximum rainfall, and maximum intensity, respectively. The single-scheme members revealed that the simulation of heavy convective precipitation is quite sensitive to factors including ice-particle fall speed parameterization, aerosol type, ice particle shape, and size distribution representation. The microphysical ensemble can derive reasonable probability of occurrence for a location-specific heavy-rain forecast. Spatial-forecast performance indices up to 0.6 were attained by applying an optimal fuzzy radius of about 8 km for the warning-area coverage. The forecasts tend to be more successful for more organized convection. Spectral mapping methods were further applied to provide ensemble forecasts for the 10 heavy rainfall cases. For most cases, realistic spatial patterns were derived with spatial correlation up to 0.8. The quantitative performance in average rainfall, maximum rainfall, and maximum intensity from the ensembles reached correlations of 0.83, 0.84, and 0.51, respectively, with the observed values. Significance Statement: Heavy rainfall from summer convections is stochastic in terms of intensity and location; therefore, an accurate deterministic forecast is often challenging. We designed perturbation experiments to explore weather forecasting models' sensitivity to cloud microphysical parameterizations and the feasibility of application to ensemble forecast. Promising results were obtained from simulations of 10 real cases. The cloud microphysical ensemble approach may provide reasonable forecasts of heavy rainfall probability and convincing rainfall spatial distribution, particularly for more organized convection. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
29. The impact of Google Trends index and encompassing tests on forecast combinations in tourism.
- Author
-
Hu, Yi-Chung and Wu, Geng
- Subjects
FORECASTING ,PREDICTION models ,TOURISM ,INTERNET searching ,COVID-19 pandemic - Abstract
Copyright of Tourism Review is the property of Emerald Publishing Limited and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2022
- Full Text
- View/download PDF
30. Assessing the effective spatial characteristics of input features through physics-informed machine learning models in inundation forecasting during typhoons.
- Author
-
Jhong, Bing-Chen, Lin, Chung-Yi, Jhong, You-Da, Chang, Hsiang-Kuan, Chu, Jung-Lien, and Fang, Hsi-Ting
- Subjects
TYPHOONS ,VORONOI polygons ,MACHINE learning ,FLOODS ,SUPPORT vector machines ,FORECASTING ,GENETIC algorithms - Abstract
This study aimed to assess the effective spatial characteristics of input features by using physics-informed, machine learning (ML)-based inundation forecasting models. To achieve this aim, inundation depth data were simulated using a numerical hydrodynamic model to obtain training and testing data for these ML-based models. Effective spatial information was identified using a back-propagation neural network, an adaptive neuro-fuzzy inference system, support vector machine, and a hybrid model combining support vector machine and a multi-objective genetic algorithm. The conventional average rainfall determined using the Thiessen polygon method, raingauge observations, radar-based rainfall data, and typhoon characteristics were used as the inputs of the aforementioned ML models. These models were applied in inundation forecasting for Yilan County, Taiwan, and the hybrid model had the best forecasting performance. The results show that the hybrid model with crucial features and appropriate lag lengths gave the best performance. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
31. Deep-Learning Model Selection and Parameter Estimation from a Wind Power Farm in Taiwan †.
- Author
-
Lin, Wen-Hui, Wang, Ping, Chao, Kuo-Ming, Lin, Hsiao-Chung, Yang, Zong-Yu, and Lai, Yu-Huang
- Subjects
WIND power ,PARAMETER estimation ,WIND power plants ,FARM mechanization ,RECURRENT neural networks ,REINFORCEMENT learning ,FORECASTING - Abstract
Deep learning networks (DLNs) use multilayer neural networks for multiclass classification that exhibit better results in wind-power forecasting applications. However, improving the training process using proper parameter hyperisations and techniques, such as regularisation and Adam-based optimisation, remains a challenge in the design of DLNs for processing time-series data. Moreover, the most appropriate parameter for the DLN model is to solve the wind-power forecasting problem by considering the excess training algorithms, such as the optimiser, activation function, batch size, and dropout. Reinforcement learning (RN) schemes constitute a smart approach to explore the proper initial parameters for the developed DLN model, considering a balance between exploration and exploitation processes. Therefore, the present study focuses on determining the proper hyperparameters for DLN models using a Q-learning scheme for four developed models. To verify the effectiveness of the developed temporal convolution network (TCN) models, experiments with five different sets of initial parameters for the TCN model were determined by the output results of Q-learning computation. The experimental results showed that the TCN accuracy for 168 h wind power prediction reached a mean absolute percentage error of 1.41%. In evaluating the effectiveness of selection of hyperparameters for the proposed model, the performance of four DLN-based prediction models for power forecasting—TCN, long short-term memory (LSTM), recurrent neural network (RNN), and gated recurrence unit (GRU) models—were compared. The overall detection accuracy of the TCN model exhibited higher prediction accuracy compared to canonical recurrent networks (i.e., the GRU, LSTM, and RNN models). [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
32. Short-Term PV Power Forecasting Using a Regression-Based Ensemble Method.
- Author
-
Lateko, Andi A. H., Yang, Hong-Tzer, and Huang, Chao-Ming
- Subjects
SMART power grids ,PHOTOVOLTAIC power generation ,RECURRENT neural networks ,RENEWABLE energy sources ,SUPPORT vector machines ,LOAD forecasting (Electric power systems) ,FORECASTING ,RANDOM forest algorithms ,WEATHER forecasting - Abstract
One of the most critical aspects of integrating renewable energy sources into the smart grid is photovoltaic (PV) power generation forecasting. This ensemble forecasting technique combines several forecasting models to increase the forecasting accuracy of the individual models. This study proposes a regression-based ensemble method for day-ahead PV power forecasting. The general framework consists of three steps: model training, creating the optimal set of weights, and testing the model. In step 1, a Random forest (RF) with different parameters is used for a single forecasting method. Five RF models (RF
1 , RF2 , RF3 , RF4 , and RF5 ) and a support vector machine (SVM) for classification are established. The hyperparameters for the regression-based method involve learners (linear regression (LR) or support vector regression (SVR)), regularization (least absolute shrinkage and selection operator (LASSO) or Ridge), and a penalty coefficient for regularization (λ). Bayesian optimization is performed to find the optimal value of these three hyperparameters based on the minimum function. The optimal set of weights is obtained in step 2 and each set of weights contains five weight coefficients and a bias. In the final step, the weather forecasting data for the target day is used as input for the five RF models and the average daily weather forecasting data is also used as input for the SVM classification model. The SVM output selects the weather conditions, and the corresponding set of weight coefficients from step 2 is combined with the output from each RF model to obtain the final forecasting results. The stacking recurrent neural network (RNN) is used as a benchmark ensemble method for comparison. Historical PV power data for a PV site in Zhangbin Industrial Area, Taiwan, with a 2000 kWp capacity is used to test the methodology. The results for the single best RF model, the stacking RNN, and the proposed method are compared in terms of the mean relative error (MRE), the mean absolute error (MAE), and the coefficient of determination (R2 ) to verify the proposed method. The results for the MRE show that the proposed method outperforms the best RF method by 20% and the benchmark method by 2%. [ABSTRACT FROM AUTHOR]- Published
- 2022
- Full Text
- View/download PDF
33. Combination forecasting using multiple attribute decision making in tourism demand.
- Author
-
Hu, Yi-Chung
- Subjects
DECISION making ,FORECASTING ,INBOUND tourism ,PREDICTION models ,TOURISM ,PUBLIC sector - Abstract
Copyright of Tourism Review is the property of Emerald Publishing Limited and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2022
- Full Text
- View/download PDF
34. Improving the Forecasting Performance of Taiwan Car Sales Movement Direction Using Online Sentiment Data and CNN-LSTM Model.
- Author
-
Ou-Yang, Chao, Chou, Shih-Chung, and Juan, Yeh-Chun
- Subjects
AUTOMOBILE sales & prices ,FORECASTING ,DATA modeling ,SALES forecasting ,MACHINE learning ,DEEP learning ,BUSINESS forecasting - Abstract
The automotive industry is the leading producer of machines in Taiwan and worldwide. Developing effective methods for forecasting car sales can allow car companies to arrange their production and sales plans. Capitalizing on the growth of social media and deep learning algorithms, this research aimed to improve the overall performance of the forecasting of Taiwan car sales movement direction forecasting by using online sentiment data and CNN-LSTM method. First, the historical sales volumes and multi-channel online sentiment data for six car brands in Taiwan were collected and preprocessed for labeling of car sales movement direction. Then, three models, namely, the classical, sentimental, and CNN-LSTM models, were constructed and trained/fitted for forecasting car sales movement directions in Taiwan. Finally, the performance of the three prediction models were compared to verify the effects of online sentiment data and the CNN-LSTM model on forecasting performance. The results showed that four forecasting performance indices, i.e., accuracy, precision, recall and F1-score, improved by 27.78% (from 41.67% to 69.45%), 0.39 (from 0.38 to 0.77), 0.27 (from 0.42 to 0.69) and 0.33 (from 0.35 to 0.68), respectively. Therefore, the online sentiment data and CNN-LSTM method can indeed improve the overall performance of car sales movement direction in Taiwan. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
35. Estate price prediction system based on temporal and spatial features and lightweight deep learning model.
- Author
-
Chiu, Sheng-Min, Chen, Yi-Chung, and Lee, Chiang
- Subjects
DEEP learning ,DATA structures ,FORECASTING ,TEMPORAL databases - Abstract
The development of estate price prediction systems is one of the issues that researchers are paying the most attention to. A good estate price prediction system can shorten the time it takes buyers to consider estates and invigorate the estate market. Generally speaking, an estate price prediction system considers the temporal and spatial features of the estate. In addition, the estate price prediction system can also be launched online for users to make instant online queries with, which means that it needs short run time. However, most existing studies only considered either temporal or spatial features and could not consider both, thereby resulting in questionable prediction accuracy. Although deep learning may increase prediction accuracy, it does not meet the short run time requirement. We therefore presented three ideas in this study to overcome these issues: (1) designing a novel spatiotemporal data structure, the Space-Time Influencing Figure (STIF), to quantify the influence of changes in the facilities surrounding each estate on estate price, (2) designing a novel CNN-LSTM model to go with the STIFs for estate price prediction, and (3) designing a new framework to extract the most important features to estate price for certain types of estates and combining these features with a shallow RNN for modeling. The computation cost of this model is far lower than that of a CNN-LSTM model, making it suitable for practical application. Finally, we used actual estate data from Taiwan to verify that the proposed approach can effectively and swiftly predict estate prices. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
36. Process-Based Evaluation of Stochastic Perturbed Microphysics Parameterization Tendencies on Ensemble Forecasts of Heavy Rainfall Events.
- Author
-
Lupo, Kevin M., Torn, Ryan D., and Yang, Shu-Chih
- Subjects
MICROPHYSICS ,BUOYANT ascent (Hydrodynamics) ,METEOROLOGICAL research ,PARAMETERIZATION ,FORECASTING - Abstract
Stochastic model error schemes, such as the stochastic perturbed parameterization tendencies (SPPT) and independent SPPT (iSPPT) schemes, have become an increasingly accepted method to represent model error associated with uncertain subgrid-scale processes in ensemble prediction systems (EPSs). While much of the current literature focuses on the effects of these schemes on forecast skill, this research examines the physical processes by which iSPPT perturbations to the microphysics parameterization scheme yield variability in ensemble rainfall forecasts. Members of three 120-member Weather Research and Forecasting (WRF) Model ensemble case studies, including two distinct heavy rain events over Taiwan and one over the northeastern United States, are ranked according to an area-averaged accumulated rainfall metric in order to highlight differences between high- and low-precipitation forecasts. In each case, high-precipitation members are characterized by a damping of the microphysics water vapor and temperature tendencies over the region of heaviest rainfall, while the opposite is true for low-precipitation members. Physically, the perturbations to microphysics tendencies have the greatest impact at the cloud level and act to modify precipitation efficiency. To this end, the damping of tendencies in high-precipitation forecasts suppresses both the loss of water vapor due to condensation and the corresponding latent heat release, leading to grid-scale supersaturation. Conversely, amplified tendencies in low-precipitation forecasts yield both drying and increased positive buoyancy within clouds. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
37. Sensitivity of Forecast Uncertainty to Different Microphysics Schemes within a Convection-Allowing Ensemble during SoWMEX-IOP8.
- Author
-
Chen, Chin-Hung, Chung, Kao-Shen, Yang, Shu-Chih, Chen, Li-Hsin, Lin, Pay-Liam, and Torn, Ryan D.
- Subjects
MICROPHYSICS ,MESOSCALE convective complexes ,FORECASTING ,NUMERICAL weather forecasting ,SPECTRUM analysis - Abstract
A mesoscale convective system that occurred in southwestern Taiwan on 15 June 2008 is simulated using convection-allowing ensemble forecasts to investigate the forecast uncertainty associated with four microphysics schemes—the Goddard Cumulus Ensemble (GCE), Morrison (MOR), WRF single-moment 6-class (WSM6), and WRF double-moment 6-class (WDM6) schemes. First, the essential features of the convective structure, hydrometeor distribution, and microphysical tendencies for the different microphysics schemes are presented through deterministic forecasts. Second, ensemble forecasts with the same initial conditions are employed to estimate the forecast uncertainty produced by the different ensembles with the fixed microphysics scheme. GCE has the largest spread in most state variables due to its most efficient phase conversion between water species. By contrast, MOR results in the least spread. WSM6 and WDM6 have similar vertical spread structures due to their similar ice-phase formulas. However, WDM6 produces more ensemble spread than WSM6 does below the melting layer, resulting from its double-moment treatment of warm rain processes. The model simulations with the four microphysics schemes demonstrate upscale error growth through spectrum analysis of the root-mean difference total energy (RMDTE). The RMDTE results reveal that the GCE and WDM6 schemes are more sensitive to initial condition uncertainty, whereas the MOR and WSM6 schemes are relatively less sensitive to that for this event. Overall, the diabatic heating–cooling processes connect the convective-scale cloud microphysical processes to the large-scale dynamical and thermodynamical fields, and they significantly affect the forecast error signatures in the multiscale weather system. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
38. Ordinal Time Series Forecasting of the Air Quality Index.
- Author
-
Chen, Cathy W. S. and Chiu, L. M.
- Subjects
AIR quality indexes ,TIME series analysis ,FORECASTING ,DUMMY variables ,SUPPORT vector machines - Abstract
This research models and forecasts daily AQI (air quality index) levels in 16 cities/counties of Taiwan, examines their AQI level forecast performance via a rolling window approach over a one-year validation period, including multi-level forecast classification, and measures the forecast accuracy rates. We employ statistical modeling and machine learning with three weather covariates of daily accumulated precipitation, temperature, and wind direction and also include seasonal dummy variables. The study utilizes four models to forecast air quality levels: (1) an autoregressive model with exogenous variables and GARCH (generalized autoregressive conditional heteroskedasticity) errors; (2) an autoregressive multinomial logistic regression; (3) multi-class classification by support vector machine (SVM); (4) neural network autoregression with exogenous variable (NNARX). These models relate to lag-1 AQI values and the previous day's weather covariates (precipitation and temperature), while wind direction serves as an hour-lag effect based on the idea of nowcasting. The results demonstrate that autoregressive multinomial logistic regression and the SVM method are the best choices for AQI-level predictions regarding the high average and low variation accuracy rates. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.