Nkanyiso Mbatha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nkanyiso Mbatha has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Hassan Bencherif
Université de La Réunion, France
3 shared publications - Felix Silwimba
Department of Mathematical Sciences, University of Zululand, Private Bag X1001, Kwa-Dlangezwa 3886, South Africa
2 shared publications - Mohamed Abdoulwahab Toihir
Agence Nationale de l’Aviation Civile et de la Météorologie, Moroni 84646, Comoros
2 shared publications - Nelson Bègue
Laboratoire de l’Atmosphère et des Cyclones, UMR 8105 CNRS, Université de la Réunion, Reunion Island, France
2 shared publications - Shaun Ramroop
University of KwaZulu-Natal
2 shared publications - Sileshi Fanta Melesse
School of Mathematics, Statistics, and Computer Science, University of KwaZulu-Natal, Pietermaritzburg Campus, Private Bag X01, Scottsville 3209, South Africa
2 shared publications
Latest Publications
- Open Access
Forecasting of Standardized Precipitation Index Using Hybrid Models: A Case Study of Cape Town, South Africa
Droughts have negative impacts on agricultural productivity and economic growth. Effective monitoring and accurate forecasting of drought occurrences and trends are crucial for minimizing drought losses and mitigating their spatial and temporal effects. In this study, trend dynamics in monthly total rainfall time series measured at Cape Town International Airport were analyzed using the Mann–Kendall (MK) test, Modified Mann–Kendall (MMK) test and innovative trend analysis (ITA). Additionally, we utilized a hybrid prediction method that combined the model with the complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique, the autoregressive integrated moving average (ARIMA) model, and the long short-term memory (LSTM) network (i.e., CEEMDAN-ARIMA-LSTM) to forecast SPI values of 6-, 9-, and 12-months using rainfall data between 1995 and 2020 from Cape Town International Airport meteorological rainfall stations. In terms of trend analysis of the monthly total rainfall, the MK and MMK tests detected a significant decreasing trend with negative z-scores of −3.7541 and −4.0773, respectively. The ITA also indicated a significant downward trend of total monthly rainfall, especially for values between 10 and 110 mm/month. The SPI forecasting results show that the hybrid model (CEEMDAN-ARIMA-LSTM) had the highest prediction accuracy of the models at all SPI timescales. The Root Mean Square Error (RMSE) values of the CEEMDAN-ARIMA-LSTM hybrid model are 0.121, 0.044, and 0.042 for SPI-6, SPI-9, and SPI-12, respectively. The directional symmetry for this hybrid model is 0.950, 0.917, and 0.950, for SPI-6, SPI-9, and SPI-12, respectively. This indicates that this is the most suitable model for forecasting long-term drought conditions in Cape Town. Additionally, models that use a decomposition step and those that are built by combining independent models seem to produce improved SPI prediction accuracy.
Open AccessForecasting of Standardized Precipitation Index Using Hybrid Models: A Case Study of Cape Town, South Africa
Droughts have negative impacts on agricultural productivity and economic growth. Effective monitoring and accurate forecasting of drought occurrences and trends are crucial for minimizing drought losses and mitigating their spatial and temporal effects. In this study, trend dynamics in monthly total rainfall time series measured at Cape Town International Airport were analyzed using the Mann–Kendall (MK) test, Modified Mann–Kendall (MMK) test and innovative trend analysis (ITA). Additionally, we utilized a hybrid prediction method that combined the model with the complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique, the autoregressive integrated moving average (ARIMA) model, and the long short-term memory (LSTM) network (i.e., CEEMDAN-ARIMA-LSTM) to forecast SPI values of 6-, 9-, and 12-months using rainfall data between 1995 and 2020 from Cape Town International Airport meteorological rainfall stations. In terms of trend analysis of the monthly total rainfall, the MK and MMK tests detected a significant decreasing trend with negative z-scores of −3.7541 and −4.0773, respectively. The ITA also indicated a significant downward trend of total monthly rainfall, especially for values between 10 and 110 mm/month. The SPI forecasting results show that the hybrid model (CEEMDAN-ARIMA-LSTM) had the highest prediction accuracy of the models at all SPI timescales. The Root Mean Square Error (RMSE) values of the CEEMDAN-ARIMA-LSTM hybrid model are 0.121, 0.044, and 0.042 for SPI-6, SPI-9, and SPI-12, respectively. The directional symmetry for this hybrid model is 0.950, 0.917, and 0.950, for SPI-6, SPI-9, and SPI-12, respectively. This indicates that this is the most suitable model for forecasting long-term drought conditions in Cape Town. Additionally, models that use a decomposition step and those that are built by combining independent models seem to produce improved SPI prediction accuracy.
- Open Access
- 24 July 2024
- Published by MDPI AG in Preprints.org
Forecasting of Standardized Precipitation Index using Hybrid Models: A Case Study of Cape Town, South Africa
Droughts have negative impacts on agricultural productivity and economic growth. Effective monitoring and accurate forecasting of drought occurrences and trends are crucial for minimizing drought losses and mitigating their spatial and temporal effects. In this study, trend dynamics in monthly total rainfall time series measured at Cape Town International Airport were analyzed using Mann-Kendall (MK) test, Modified Mann-Kendall (MMK) and innovative trend analysis (ITA) were examined. Additionally, we utilized hybrid prediction method that combined the model with the complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique, the autoregressive integrated moving average (ARIMA) model, the long short-term memory (LSTM) network (i.e. CEEMDAN-ARIMA-LSTM) to forecast SPI values of 6-, 9-, and 12-months using rainfall data between 1995 and 2020 from Cape Town International Airport meteorological rainfall stations. The results demonstrate the following essential points: (1) The trend analysis results of the total monthly rainfall values indicate a significant decreasing trend with the negative z-score (MK= -3.7541 and MMK= - 4.0773). ITA also indicated a significant downwards trend of rainfall in the study area. (2) As the forecasting horizon increases, the prediction accuracy of the models and CEEMDAN-combined models gradually improves, reaching their optimum performance at the 12-month horizon. (3) CEEMDAN efficiently stabilizes time-series data, resulting in greater prediction accuracy in the hybrid model compared to individual models at all timescales. (4) The RMSE and R2 values for the hybrid CEEMDAN-ARIMA-LSTM model at a 12-month forecasting horizon are 0.042 and 0.995, demonstrating the applicability of this hybrid approach for drought forecasting.
- 24 July 2024
- Published by MDPI AG in Preprints.org
Open AccessForecasting of Standardized Precipitation Index using Hybrid Models: A Case Study of Cape Town, South Africa
Droughts have negative impacts on agricultural productivity and economic growth. Effective monitoring and accurate forecasting of drought occurrences and trends are crucial for minimizing drought losses and mitigating their spatial and temporal effects. In this study, trend dynamics in monthly total rainfall time series measured at Cape Town International Airport were analyzed using Mann-Kendall (MK) test, Modified Mann-Kendall (MMK) and innovative trend analysis (ITA) were examined. Additionally, we utilized hybrid prediction method that combined the model with the complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique, the autoregressive integrated moving average (ARIMA) model, the long short-term memory (LSTM) network (i.e. CEEMDAN-ARIMA-LSTM) to forecast SPI values of 6-, 9-, and 12-months using rainfall data between 1995 and 2020 from Cape Town International Airport meteorological rainfall stations. The results demonstrate the following essential points: (1) The trend analysis results of the total monthly rainfall values indicate a significant decreasing trend with the negative z-score (MK= -3.7541 and MMK= - 4.0773). ITA also indicated a significant downwards trend of rainfall in the study area. (2) As the forecasting horizon increases, the prediction accuracy of the models and CEEMDAN-combined models gradually improves, reaching their optimum performance at the 12-month horizon. (3) CEEMDAN efficiently stabilizes time-series data, resulting in greater prediction accuracy in the hybrid model compared to individual models at all timescales. (4) The RMSE and R2 values for the hybrid CEEMDAN-ARIMA-LSTM model at a 12-month forecasting horizon are 0.042 and 0.995, demonstrating the applicability of this hybrid approach for drought forecasting.
- Open Access
- 21 November 2023
- Published by MDPI AG in Preprints.org
Observations, Remote Sensing and Model Simulation to Ana-lyze Southern Brazil Antarctic Ozone Hole Influence
The paper presents the observational, remote sensing and model simulation to analyze Southern Brazil Antarctic Ozone Hole influence (SBAOHI) events occurred between 2005 and 2014. To an-alyze it we use Total Ozone Column (TOC) data provide by Brewer Spectrophotometer (BS) and OMI (Ozone Monitoring Instrument) instrument satellite, besides the AURA/MLS (Microwave Limb Sounder) instrument satellite ozone profiles was utilized with DYBAL (Dynamical Barrier Localization) code in MIMOSA (Modélisation Isentrope du transport Mésoéchelle de l’Ozone Stratosphérique par Advection) model Potential Vorticity (PV) fields. TOC has 7.0 ± 2.9 DU re-ductions average in 62 events. October have more events (30.7%). Polar Tongue events are 19.3% of total, being in October more frequently observed (50% of cases), with medium intensity (58.2%) and in stratosphere medium levels (55.0%). Already Polar Filament events (80.7%) are more frequent in September (32.0%), medium intensity (42.0%) and in stratosphere medium lev-els (40.7%). ENSO index positive phase influenced 61.3% of events, having dominance in all in-tensity categories (minor 57.9%, medium 51.6%, major 58.3%), while the equilibrium dominate the QBO influence with 50% of total cases in positive phase and 50 % in negative phase.
- 21 November 2023
- Published by MDPI AG in Preprints.org
Open AccessObservations, Remote Sensing and Model Simulation to Ana-lyze Southern Brazil Antarctic Ozone Hole Influence
The paper presents the observational, remote sensing and model simulation to analyze Southern Brazil Antarctic Ozone Hole influence (SBAOHI) events occurred between 2005 and 2014. To an-alyze it we use Total Ozone Column (TOC) data provide by Brewer Spectrophotometer (BS) and OMI (Ozone Monitoring Instrument) instrument satellite, besides the AURA/MLS (Microwave Limb Sounder) instrument satellite ozone profiles was utilized with DYBAL (Dynamical Barrier Localization) code in MIMOSA (Modélisation Isentrope du transport Mésoéchelle de l’Ozone Stratosphérique par Advection) model Potential Vorticity (PV) fields. TOC has 7.0 ± 2.9 DU re-ductions average in 62 events. October have more events (30.7%). Polar Tongue events are 19.3% of total, being in October more frequently observed (50% of cases), with medium intensity (58.2%) and in stratosphere medium levels (55.0%). Already Polar Filament events (80.7%) are more frequent in September (32.0%), medium intensity (42.0%) and in stratosphere medium lev-els (40.7%). ENSO index positive phase influenced 61.3% of events, having dominance in all in-tensity categories (minor 57.9%, medium 51.6%, major 58.3%), while the equilibrium dominate the QBO influence with 50% of total cases in positive phase and 50 % in negative phase.
- Open Access
- 11 November 2020
- Published by MDPI AG in Atmosphere
- Vol. 11 (11) , 1216
Ozone Variability and Trend Estimates from 20-Years of Ground-Based and Satellite Observations at Irene Station, South Africa
While the stratospheric ozone protects the biosphere against ultraviolet (UV) radiation, tropospheric ozone acts like a greenhouse gas and an indicator of anthropogenic pollution. In this paper, we combined ground-based and satellite ozone observations over Irene site (25.90° S, 28.22° E), one of the most ancient ozone-observing stations in the southern tropics. The dataset is made of daily total columns and weekly profiles of ozone collected over 20 years, from 1998 to 2017. In order to fill in some missing data and split the total column of ozone into a tropospheric and a stratospheric column, we used satellite observations from TOMS (Total Ozone Mapping Spectrometer), OMI (Ozone Monitoring Instrument), and MLS (Microwave Limb Sounder) experiments. The tropospheric column is derived by integrating ozone profiles from an ozonesonde experiment, while the stratospheric column is obtained by subtracting the tropospheric column from the total column (recorded by the Dobson spectrometer), and by assuming that the mesospheric contribution is negligible. Each of the obtained ozone time series was then analyzed by applying the method of wavelet transform, which permitted the determination of the main forcings that contribute to each ozone time series. We then applied the multivariate Trend-Run model and the Mann–Kendall test for trend analysis. Despite the different analytical approaches, the obtained results are broadly similar and consistent. They showed a decrease in the stratospheric column (−0.56% and −1.7% per decade, respectively, for Trend-Run and Mann–Kendall) and an increase in the tropospheric column (+2.37% and +3.6%, per decade, respectively, for Trend-Run and Mann–Kendall). Moreover, the results presented here indicated that the slowing down of the total ozone decline is somewhat due to the contribution of the tropospheric ozone concentration.
- 11 November 2020
- Published by MDPI AG in Atmosphere
- Vol. 11 (11) , 1216
Open AccessOzone Variability and Trend Estimates from 20-Years of Ground-Based and Satellite Observations at Irene Station, South Africa
While the stratospheric ozone protects the biosphere against ultraviolet (UV) radiation, tropospheric ozone acts like a greenhouse gas and an indicator of anthropogenic pollution. In this paper, we combined ground-based and satellite ozone observations over Irene site (25.90° S, 28.22° E), one of the most ancient ozone-observing stations in the southern tropics. The dataset is made of daily total columns and weekly profiles of ozone collected over 20 years, from 1998 to 2017. In order to fill in some missing data and split the total column of ozone into a tropospheric and a stratospheric column, we used satellite observations from TOMS (Total Ozone Mapping Spectrometer), OMI (Ozone Monitoring Instrument), and MLS (Microwave Limb Sounder) experiments. The tropospheric column is derived by integrating ozone profiles from an ozonesonde experiment, while the stratospheric column is obtained by subtracting the tropospheric column from the total column (recorded by the Dobson spectrometer), and by assuming that the mesospheric contribution is negligible. Each of the obtained ozone time series was then analyzed by applying the method of wavelet transform, which permitted the determination of the main forcings that contribute to each ozone time series. We then applied the multivariate Trend-Run model and the Mann–Kendall test for trend analysis. Despite the different analytical approaches, the obtained results are broadly similar and consistent. They showed a decrease in the stratospheric column (−0.56% and −1.7% per decade, respectively, for Trend-Run and Mann–Kendall) and an increase in the tropospheric column (+2.37% and +3.6%, per decade, respectively, for Trend-Run and Mann–Kendall). Moreover, the results presented here indicated that the slowing down of the total ozone decline is somewhat due to the contribution of the tropospheric ozone concentration.
- Open Access
- 30 April 2020
- Published by MDPI AG in Atmosphere
- Vol. 11 (5) , 457
Time Series Analysis and Forecasting Using a Novel Hybrid LSTM Data-Driven Model Based on Empirical Wavelet Transform Applied to Total Column of Ozone at Buenos Aires, Argentina (1966–2017)
Total column of ozone (TCO) time series analysis and accurate forecasting is of great significance in monitoring the status of the Chapman Mechanism in the stratosphere, which prevents harmful UV radiation from reaching the Earth’s surface. In this study, we performed a detailed time series analysis of the TCO data measured in Buenos Aires, Argentina. Moreover, hybrid data-driven forecasting models, based on long short-term memory networks (LSTM) recurrent neural networks (RNNs), are developed. We extracted the updated trend of the TCO time series by utilizing the singular spectrum analysis (SSA), empirical wavelet transform (EWT), empirical mode decomposition (EMD), and Mann-Kendall. In general, the TCO has been stable since the mid-1990s. The trend analysis shows that there is a recovery of ozone during the period from 2010 to 2017, apart from the decline of ozone observed during 2015, which is presumably associated with the Calbuco volcanic event. The EWT trend method seems to have effective power for trend identification, compared with others. In this study, we developed a robust data-driven hybrid time series-forecasting model (named EWT-LSTM) for the TCO time series forecasting. Our model has the advantage of utilizing the EWT technique in the decomposition stage of the LSTM process. We compared our model with (1) an LSTM model that uses EMD, namely EMD-LSTM; (2) an LSTM model that uses wavelet denoising (WD) (WD-LSTM); (3) a wavelet denoising EWT-LSTM (WD-EWT-LSTM); and (4) a wavelet denoising noise-reducing sequence called EMD-LSTM (WD-EMD-LSTM). The model that uses the EWT decomposition process (EWT-LSTM) outperformed the other five models developed here in terms of various forecasting performance evaluation criteria, such as the root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R).
- 30 April 2020
- Published by MDPI AG in Atmosphere
- Vol. 11 (5) , 457
Open AccessTime Series Analysis and Forecasting Using a Novel Hybrid LSTM Data-Driven Model Based on Empirical Wavelet Transform Applied to Total Column of Ozone at Buenos Aires, Argentina (1966–2017)
Total column of ozone (TCO) time series analysis and accurate forecasting is of great significance in monitoring the status of the Chapman Mechanism in the stratosphere, which prevents harmful UV radiation from reaching the Earth’s surface. In this study, we performed a detailed time series analysis of the TCO data measured in Buenos Aires, Argentina. Moreover, hybrid data-driven forecasting models, based on long short-term memory networks (LSTM) recurrent neural networks (RNNs), are developed. We extracted the updated trend of the TCO time series by utilizing the singular spectrum analysis (SSA), empirical wavelet transform (EWT), empirical mode decomposition (EMD), and Mann-Kendall. In general, the TCO has been stable since the mid-1990s. The trend analysis shows that there is a recovery of ozone during the period from 2010 to 2017, apart from the decline of ozone observed during 2015, which is presumably associated with the Calbuco volcanic event. The EWT trend method seems to have effective power for trend identification, compared with others. In this study, we developed a robust data-driven hybrid time series-forecasting model (named EWT-LSTM) for the TCO time series forecasting. Our model has the advantage of utilizing the EWT technique in the decomposition stage of the LSTM process. We compared our model with (1) an LSTM model that uses EMD, namely EMD-LSTM; (2) an LSTM model that uses wavelet denoising (WD) (WD-LSTM); (3) a wavelet denoising EWT-LSTM (WD-EWT-LSTM); and (4) a wavelet denoising noise-reducing sequence called EMD-LSTM (WD-EMD-LSTM). The model that uses the EWT decomposition process (EWT-LSTM) outperformed the other five models developed here in terms of various forecasting performance evaluation criteria, such as the root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R).