Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory
Predicting daily reference evapotranspiration (ETo) plays a significant role in numerous environmental and agricultural applications. It aids in optimizing agricultural practices, enhancing drought resilience, supporting environmental conservation efforts, and providing critical data for research. B...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125000044 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595381501820928 |
|---|---|
| author | Mumtaz Ali Jesu Vedha Nayahi Erfan Abdi Mohammad Ali Ghorbani Farzan Mohajeri Aitazaz Ahsan Farooque Salman Alamery |
| author_facet | Mumtaz Ali Jesu Vedha Nayahi Erfan Abdi Mohammad Ali Ghorbani Farzan Mohajeri Aitazaz Ahsan Farooque Salman Alamery |
| author_sort | Mumtaz Ali |
| collection | DOAJ |
| description | Predicting daily reference evapotranspiration (ETo) plays a significant role in numerous environmental and agricultural applications. It aids in optimizing agricultural practices, enhancing drought resilience, supporting environmental conservation efforts, and providing critical data for research. By leveraging advanced technologies and accurate modeling techniques, stakeholders can make informed decisions that promote sustainability and resilience in the face of changing climatic conditions. The main purpose of this investigation was to forecast the daily ETo trends at Melbourne and Sydney stations in Australia, where several cutting-edge machine learning methodologies were employed. The modeling approach encompassed the implementation of Neural Network (NN), Deep Learning (DL), Recurrent Neural Networks (RNN), RNN based Long Short-Term Memory (RNN-LSTM), and Convolutional Neural Network based LSTM (CNN-LSTM) to forecast daily ETo using historical meteorology data. During the model development stage, the optimal variables were determined successfully via heatmaps for precise assessment of ETo in both stations. The predictive models were built by incorporating both the training subset (80 %, covering the years 2009 to 2020) and the testing subset (20 %, ranging from 2021 to 2024) independently to forecast ETo. The results confirmed that the RNN-LSTM attained higher prediction accuracy as compared to NN, DL, RNN, and CNN-LSTM models. Conversely, based on the visual representations and assessments, one can grasp the significant resemblance between the forecasts of the RNN-LSTM model and the actual data. By combining RNNs with LSTM units, models can leverage the strengths of both approaches to improve their ability to process sequential data effectively. This integration allows for better capturing of both short-term and long-term dependencies in the input sequences. Upon careful evaluation, it became clear that the error values associated with the RNN-LSTM models were negligible at the designated stations during the testing phase, with an RMSE of 0.0011 mm for Melbourne, and 0.022 mm for Sydney, followed by RNN, DL, and NN respectively. The proposed modeling approach can be beneficial in monitoring and managing water and crop planning which relies on precise ETo predictions. |
| format | Article |
| id | doaj-art-29551274a983495aa993d04c3c138ec2 |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-29551274a983495aa993d04c3c138ec22025-01-19T06:24:45ZengElsevierEcological Informatics1574-95412025-03-0185102995Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memoryMumtaz Ali0Jesu Vedha Nayahi1Erfan Abdi2Mohammad Ali Ghorbani3Farzan Mohajeri4Aitazaz Ahsan Farooque5Salman Alamery6UniSQ College, University of Southern Queensland 4305 QLD, Australia; Scientific Research Center, Al-Ayen University, Thi-Qar, Nasiriyah 64001, Iraq; Corresponding authors at: UniSQ College, University of Southern Queensland, 4305, QLD, Australia.Anna University Regional Campus –, Tirunelveli, India,Department of water engineering, University of Tabriz, Tabriz, IranDepartment of water engineering, University of Tabriz, Tabriz, Iran; Corresponding authors at: UniSQ College, University of Southern Queensland, 4305, QLD, Australia.UniSQ College, University of Southern Queensland 4305 QLD, Australia; Anna University Regional Campus –, Tirunelveli, India,; Department of water engineering, University of Tabriz, Tabriz, Iran; Canadian Centre for Climate Change and Adaptation, University of Prince Edward Island, St Peters, PE, Canada; Department of Biochemistry, College of Science, King Saud University, Saudi Arabia; Scientific Research Center, Al-Ayen University, Thi-Qar, Nasiriyah 64001, Iraq; Faculty of Sustainable Design Engineering, University of Prince Edward Island, Charlottetown, PE, Canada; Islamic Azad University, Central Tehran Branch, IranCanadian Centre for Climate Change and Adaptation, University of Prince Edward Island, St Peters, PE, CanadaDepartment of Biochemistry, College of Science, King Saud University, Saudi ArabiaPredicting daily reference evapotranspiration (ETo) plays a significant role in numerous environmental and agricultural applications. It aids in optimizing agricultural practices, enhancing drought resilience, supporting environmental conservation efforts, and providing critical data for research. By leveraging advanced technologies and accurate modeling techniques, stakeholders can make informed decisions that promote sustainability and resilience in the face of changing climatic conditions. The main purpose of this investigation was to forecast the daily ETo trends at Melbourne and Sydney stations in Australia, where several cutting-edge machine learning methodologies were employed. The modeling approach encompassed the implementation of Neural Network (NN), Deep Learning (DL), Recurrent Neural Networks (RNN), RNN based Long Short-Term Memory (RNN-LSTM), and Convolutional Neural Network based LSTM (CNN-LSTM) to forecast daily ETo using historical meteorology data. During the model development stage, the optimal variables were determined successfully via heatmaps for precise assessment of ETo in both stations. The predictive models were built by incorporating both the training subset (80 %, covering the years 2009 to 2020) and the testing subset (20 %, ranging from 2021 to 2024) independently to forecast ETo. The results confirmed that the RNN-LSTM attained higher prediction accuracy as compared to NN, DL, RNN, and CNN-LSTM models. Conversely, based on the visual representations and assessments, one can grasp the significant resemblance between the forecasts of the RNN-LSTM model and the actual data. By combining RNNs with LSTM units, models can leverage the strengths of both approaches to improve their ability to process sequential data effectively. This integration allows for better capturing of both short-term and long-term dependencies in the input sequences. Upon careful evaluation, it became clear that the error values associated with the RNN-LSTM models were negligible at the designated stations during the testing phase, with an RMSE of 0.0011 mm for Melbourne, and 0.022 mm for Sydney, followed by RNN, DL, and NN respectively. The proposed modeling approach can be beneficial in monitoring and managing water and crop planning which relies on precise ETo predictions.http://www.sciencedirect.com/science/article/pii/S1574954125000044AgricultureDeep learningEToForecastingRNN-LSTMCNN-LSTM |
| spellingShingle | Mumtaz Ali Jesu Vedha Nayahi Erfan Abdi Mohammad Ali Ghorbani Farzan Mohajeri Aitazaz Ahsan Farooque Salman Alamery Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory Ecological Informatics Agriculture Deep learning ETo Forecasting RNN-LSTM CNN-LSTM |
| title | Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory |
| title_full | Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory |
| title_fullStr | Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory |
| title_full_unstemmed | Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory |
| title_short | Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory |
| title_sort | improving daily reference evapotranspiration forecasts designing ai enabled recurrent neural networks based long short term memory |
| topic | Agriculture Deep learning ETo Forecasting RNN-LSTM CNN-LSTM |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125000044 |
| work_keys_str_mv | AT mumtazali improvingdailyreferenceevapotranspirationforecastsdesigningaienabledrecurrentneuralnetworksbasedlongshorttermmemory AT jesuvedhanayahi improvingdailyreferenceevapotranspirationforecastsdesigningaienabledrecurrentneuralnetworksbasedlongshorttermmemory AT erfanabdi improvingdailyreferenceevapotranspirationforecastsdesigningaienabledrecurrentneuralnetworksbasedlongshorttermmemory AT mohammadalighorbani improvingdailyreferenceevapotranspirationforecastsdesigningaienabledrecurrentneuralnetworksbasedlongshorttermmemory AT farzanmohajeri improvingdailyreferenceevapotranspirationforecastsdesigningaienabledrecurrentneuralnetworksbasedlongshorttermmemory AT aitazazahsanfarooque improvingdailyreferenceevapotranspirationforecastsdesigningaienabledrecurrentneuralnetworksbasedlongshorttermmemory AT salmanalamery improvingdailyreferenceevapotranspirationforecastsdesigningaienabledrecurrentneuralnetworksbasedlongshorttermmemory |