Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala Headworks
This study, under the context of a global perspective, focuses on the Indus Basin Irrigation System (IBIS) of Pakistan specifically the Jhelum and Chenab rivers inflows. The IBIS operation relies on seasonal planning strategies, informed by forecasts of river inflows at key stations by the Indus Riv...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Environmental Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenvs.2025.1590346/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849468929078984704 |
|---|---|
| author | Muhammad Muneeb Khan Muhammad Kaleem Sarwar Muhammad Awais Zafar Muhammad Rashid Muhammad Atiq Ur Rehman Tariq Saif Haider Abdelaziz M. Okasha Ahmed Z. Dewidar Mohamed A. Mattar Ali Salem Ali Salem |
| author_facet | Muhammad Muneeb Khan Muhammad Kaleem Sarwar Muhammad Awais Zafar Muhammad Rashid Muhammad Atiq Ur Rehman Tariq Saif Haider Abdelaziz M. Okasha Ahmed Z. Dewidar Mohamed A. Mattar Ali Salem Ali Salem |
| author_sort | Muhammad Muneeb Khan |
| collection | DOAJ |
| description | This study, under the context of a global perspective, focuses on the Indus Basin Irrigation System (IBIS) of Pakistan specifically the Jhelum and Chenab rivers inflows. The IBIS operation relies on seasonal planning strategies, informed by forecasts of river inflows at key stations by the Indus River System Authority (IRSA). In this study, Artificial Intelligence (AI) models including Generalized Regression Neural Network (GRNN), and Multi-Layer Feedforward Neural Network (MLFN) along with the statistical model Autoregressive Integrated Moving Average (ARIMA) were used to forecast the inflows of both rivers for 5 years (2020–2024) with a lead time of 1 year. Historic flow data of 59 years (10 daily from 1966 to 2024) were collected from IRSA. The collected data from 1966 to 2014 are used for calibration/training and from 2015 to 2020 are used for validation/testing of selected models for both study locations. The results of correlation and error estimation depicted that Artificial Neural Network (ANN) models predicted better inflows than the ARIMA model. The average RMSE and R2 of ANN models is 9.68 and 0.92 and the average RMSE and R2 of ARIMA Model is 10.17 and 0.88, this results in improvement of average RMSE and R2 by 4.82% and 4.35% in case of ANN Models when compared with ARIMA Model. Qualitative analysis shows that ANN techniques better predicted the high and low flows when compared with statistical methods. Specifically, the application of the ANN models has enhanced the precision of forecasted inflows assessment compared to the probabilistic inflow forecasting methods used by IRSA. The average RMSE and R2 in case of IRSA forecast is 11.47 and 0.88 and the average RMSE and R2 in case of ANN Models is 10.30 and 0.92, this results in improvement of average RMSE and R2 by 10.20% and 4.35% in case of ANN Models when compared with IRSA forecast. This study highlights the need for utilization of ANN models in place of probabilistic inflow forecasting methods to improve the accuracy of time series inflow forecasts. |
| format | Article |
| id | doaj-art-8acc7e604cde4f6cb4368bc0cf31d5ff |
| institution | Kabale University |
| issn | 2296-665X |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Environmental Science |
| spelling | doaj-art-8acc7e604cde4f6cb4368bc0cf31d5ff2025-08-20T03:25:42ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2025-06-011310.3389/fenvs.2025.15903461590346Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala HeadworksMuhammad Muneeb Khan0Muhammad Kaleem Sarwar1Muhammad Awais Zafar2Muhammad Rashid3Muhammad Atiq Ur Rehman Tariq4Saif Haider5Abdelaziz M. Okasha6Ahmed Z. Dewidar7Mohamed A. Mattar8Ali Salem9Ali Salem10Centre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanCentre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanCentre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanDepartment of Earth and Geoenvironmental Sciences, University of Bari Aldo Moro, Bari, ItalyCentre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanCentre of Excellence in Water Resources Engineering, University of Engineering and Technology, Lahore, PakistanDepartment of Agricultural Engineering, Faculty of Agriculture, Kafrelsheikh University, Kafr El-Sheikh, EgyptPrince Sultan Bin Abdulaziz International Prize for Water Chair, Prince Sultan Institute for Environmental, Water and Desert Research, King Saud University, Riyadh, Saudi ArabiaPrince Sultan Bin Abdulaziz International Prize for Water Chair, Prince Sultan Institute for Environmental, Water and Desert Research, King Saud University, Riyadh, Saudi ArabiaCivil Engineering Department, Faculty of Engineering, Minia University, Minia, EgyptStructural Diagnostics and Analysis Research Group, Faculty of Engineering and Information Technology, University of Pécs, Pécs, HungaryThis study, under the context of a global perspective, focuses on the Indus Basin Irrigation System (IBIS) of Pakistan specifically the Jhelum and Chenab rivers inflows. The IBIS operation relies on seasonal planning strategies, informed by forecasts of river inflows at key stations by the Indus River System Authority (IRSA). In this study, Artificial Intelligence (AI) models including Generalized Regression Neural Network (GRNN), and Multi-Layer Feedforward Neural Network (MLFN) along with the statistical model Autoregressive Integrated Moving Average (ARIMA) were used to forecast the inflows of both rivers for 5 years (2020–2024) with a lead time of 1 year. Historic flow data of 59 years (10 daily from 1966 to 2024) were collected from IRSA. The collected data from 1966 to 2014 are used for calibration/training and from 2015 to 2020 are used for validation/testing of selected models for both study locations. The results of correlation and error estimation depicted that Artificial Neural Network (ANN) models predicted better inflows than the ARIMA model. The average RMSE and R2 of ANN models is 9.68 and 0.92 and the average RMSE and R2 of ARIMA Model is 10.17 and 0.88, this results in improvement of average RMSE and R2 by 4.82% and 4.35% in case of ANN Models when compared with ARIMA Model. Qualitative analysis shows that ANN techniques better predicted the high and low flows when compared with statistical methods. Specifically, the application of the ANN models has enhanced the precision of forecasted inflows assessment compared to the probabilistic inflow forecasting methods used by IRSA. The average RMSE and R2 in case of IRSA forecast is 11.47 and 0.88 and the average RMSE and R2 in case of ANN Models is 10.30 and 0.92, this results in improvement of average RMSE and R2 by 10.20% and 4.35% in case of ANN Models when compared with IRSA forecast. This study highlights the need for utilization of ANN models in place of probabilistic inflow forecasting methods to improve the accuracy of time series inflow forecasts.https://www.frontiersin.org/articles/10.3389/fenvs.2025.1590346/fullANNARIMAGRNNinflow forecastMLFNneural networks |
| spellingShingle | Muhammad Muneeb Khan Muhammad Kaleem Sarwar Muhammad Awais Zafar Muhammad Rashid Muhammad Atiq Ur Rehman Tariq Saif Haider Abdelaziz M. Okasha Ahmed Z. Dewidar Mohamed A. Mattar Ali Salem Ali Salem Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala Headworks Frontiers in Environmental Science ANN ARIMA GRNN inflow forecast MLFN neural networks |
| title | Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala Headworks |
| title_full | Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala Headworks |
| title_fullStr | Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala Headworks |
| title_full_unstemmed | Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala Headworks |
| title_short | Comparative analysis of inflow forecasting using machine learning and statistical techniques: case study of Mangla reservoir and Marala Headworks |
| title_sort | comparative analysis of inflow forecasting using machine learning and statistical techniques case study of mangla reservoir and marala headworks |
| topic | ANN ARIMA GRNN inflow forecast MLFN neural networks |
| url | https://www.frontiersin.org/articles/10.3389/fenvs.2025.1590346/full |
| work_keys_str_mv | AT muhammadmuneebkhan comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT muhammadkaleemsarwar comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT muhammadawaiszafar comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT muhammadrashid comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT muhammadatiqurrehmantariq comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT saifhaider comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT abdelazizmokasha comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT ahmedzdewidar comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT mohamedamattar comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT alisalem comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks AT alisalem comparativeanalysisofinflowforecastingusingmachinelearningandstatisticaltechniquescasestudyofmanglareservoirandmaralaheadworks |