Improved of Forecasting Sea Surface Temperature based on Hybrid ARIMA and Support Vector Machines Models

Nawi, Wan Imanul Aisyah Wan Mohamad; Lola, Muhamad Safiih; Zakariya, Razak; Zainuddin, Nurul Hila; Hamid, Abd. Aziz K. Abd; Aruchunan, Elayaraja

doi:10.11113/mjfas.v17n5.2356

Cited by 9 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various research has been done to predict and estimate the ocean surface temperature or SST to analyze thermal interchanges between oceans, atmosphere, behavior patterns of aquatic animals, and ocean or sea currents [7]. Ocean surface temperature has historically been estimated using linear regression and statistical approaches, such as the "Autoregressive Integrated Moving Average (ARIMA)" models [8], Machine learning techniques such as "support vector machines (SVMs)" have been employed in several types of research to predict SST [9] [10]. The "particle swarm optimization (PSO)" is also used for SST predictions in [11].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Approach for Predicting Ocean Surface Temperature

Mishra,

Sharda,

Vyas

et al. 2024

Preprint

View full text Add to dashboard Cite

The sea surface temperature (SST) is an essential parameter for the investigation of sea and ocean ecosystems owing to its interaction with water quality, organisms, and hydrological events including floods and droughts. This is because the SST is a measure of how hot the water is at the surface of the ocean. SST forecasting is the technique for estimating future SST values, based on historical SST data, which is useful for analyzing and tracking changes in hydroclimatic variables. Most earlier studies have used complex neural network-based architectures for SST prediction. These models have low accuracy due to high variance. In this paper, a new approach based on Random Forest (RF) of machine learning has been proposed to predict the surface temperature of the global ocean using hydrographic sea surface parameters. The hydrographic datasets provided by California Cooperative Oceanic Fisheries Investigations (CalCOFI) are used in this research. The results indicated that STheta, Salnty, O2ml_L, O2Sat, and Oxy_µmol/Kg are useful parameters for predicting thermal information accurately. The suggested technique achieves an R2 score of 0.986 while having a Mean Absolute Error of 0.08°C, which is a significant improvement above the performance shown by the previous research.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Approach for Predicting Ocean Surface Temperature

Mishra,

Sharda,

Vyas

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The experimental results revealed that the ARIMA model performs better forecasting linear time series, while [24,32], the remaining service life of aircraft engines prediction [31], and the P M 2 . 5 concentrations time series data set (a heterogeneous data set mixed one-dimension series data) [41], temperature [29]. The researchers also publish the combination methods that were used to forecast climate change by machine learning methods such as support vector regression, random forest, and K-nearest neighbors [36].…”

Section: Introductionmentioning

confidence: 99%

Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment

Tran,

Senkerik,

et al. 2023

mendel

View full text Add to dashboard Cite

This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.

show abstract

“…In this scenario, a few researchers predict COVID-19 pattern using ARIMA [8][9][10][11][12][13][14][15]. However, ARIMA model have a limitation where it's normally only can handle a linear time series data structure [16]. However, approximations by ARIMA models are inadequate in representing a barrier in time series forecasting for researchers particularly for nonlinear pattern [17].…”

Section: Introductionmentioning

confidence: 99%

“…The SVMs, which were first introduced by Vladimir Vapnik in 1995 [19] in the domain of statistical learning theory and structural risk minimization, have been shown to operate well on a variety of forecasting and classification issues. The SVMs could also cope with or address difficulties like nonlinearity, local minimum, and high dimension in which ARIMA model [16,[20][21][22]. SVMs models have recently been used to handle issues such as nonlinear, local minimum, and high dimension.…”

Section: Introductionmentioning

confidence: 99%

“…This approach is crucial due to issues that arise in time series forecasting where almost all real-world time series contain both linear and nonlinear correlation patterns between the data. Recently, the hybridization of forecasting methods has been used with great achievement to reach enhanced forecasting accuracy [16,17,[20][21][22][23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Developing forecasting model for future pandemic applications based on COVID-19 data 2020–2022

et al. 2023

Self Cite

View full text Add to dashboard Cite

Improving forecasting particularly time series forecasting accuracy, efficiency and precisely become crucial for the authorities to forecast, monitor, and prevent the COVID-19 cases so that its spread can be controlled more effectively. However, the results obtained from prediction models are inaccurate, imprecise as well as inefficient due to linear and non-linear patterns exist in the data set, respectively. Therefore, to produce more accurate and efficient COVID-19 prediction value that is closer to the true COVID-19 value, a hybrid approach has been implemented. Thus, aims of this study is (1) to propose a hybrid ARIMA-SVM model to produce better forecasting results. (2) to investigate in terms of the performance of the proposed models and percentage improvement against ARIMA and SVM models. statistical measurements such as MSE, RMSE, MAE, and MAPE then conducted to verify that the proposed models are better than ARIMA and SVM models. Empirical results with three real datasets of well-known cases of COVID-19 in Malaysia show that, compared to the ARIMA and SVM models, the proposed model generates the smallest MSE, RMSE, MAE and MAPE values for the training and testing datasets, means that the predicted value from the proposed model is closer to the actual value. These results prove that the proposed model can generate estimated values more accurately and efficiently. As compared to ARIMA and SVM, our proposed models perform much better in terms of error reduction percentages for all datasets. This is demonstrated by the maximum scores of 73.12%, 74.6%, 90.38%, and 68.99% in the MAE, MAPE, MSE, and RMSE, respectively. Therefore, the proposed model can be the best and effective way to improve prediction performance with a higher level of accuracy and efficiency in predicting cases of COVID-19.

show abstract

Improved of Forecasting Sea Surface Temperature based on Hybrid ARIMA and Support Vector Machines Models

Cited by 9 publications

References 19 publications

Machine Learning-Based Approach for Predicting Ocean Surface Temperature

Machine Learning-Based Approach for Predicting Ocean Surface Temperature

Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment

Developing forecasting model for future pandemic applications based on COVID-19 data 2020–2022

Contact Info

Product

Resources

About