Development of Deep Learning Hybrid Models for Hydrological Predictions

PhD by Publication


Ahmed, Abul Abrar Masrur. 2022. Development of Deep Learning Hybrid Models for Hydrological Predictions. PhD by Publication Doctor of Philosophy. University of Southern Queensland. https://doi.org/10.26192/q7q5z
Title

Development of Deep Learning Hybrid Models for Hydrological Predictions

TypePhD by Publication
Authors
AuthorAhmed, Abul Abrar Masrur
Supervisor
1. FirstProf Ravinesh Deo
2. SecondDr Afshin Ghahramani
2. SecondDr Nawin Raj
Feng Qi
3. ThirdZhenliang Yin
3. ThirdLinshan Yang
Institution of OriginUniversity of Southern Queensland
Qualification NameDoctor of Philosophy
Number of Pages289
Year2022
PublisherUniversity of Southern Queensland
Place of PublicationAustralia
Digital Object Identifier (DOI)https://doi.org/10.26192/q7q5z
Abstract

Forecasting hydrologic phenomena are critical for strategic environmental planning, designing the hydrologic structures, and managing agricultural practices and water resources. Physical models are the mainstream method that helps understand the physical mechanisms and dynamics used in hydrological predictions. They are used for addressing the characteristics of hydrological phenomena while considering the initial conditions and spatial-temporal resolution of the model inputs. Data-driven models, on the other hand, are based on artificial intelligence and are designed as alternatives to discover the relationships between a set of predictors and a target variable without considering any of the initial conditions or underlying assumptions. These methods are relatively new and are becoming state-of-the-art to address different prediction problems.

This doctoral thesis, with its five primary objectives, aims to build a set of deep learning hybrid models and evaluate for their predictive skills in forecasting hydrological variables such as soil moisture (SM), evapotranspiration (ETo), and streamflow water levels (SWL) within Australian Murray-Darling Basin. The first objective establishes the significance of feature selection to predict the monthly SWL at six study sites. The BRF-LSTM hybrid method integrated with the long-short term memory (LSTM) model with a Boruta-Random forest optimizer (BRF) is used to demonstrate the importance of feature selection for SWL forecasting problems. The second objective is to develop a CNN-GRU hybrid model using the ant colony optimization to screen the most correlated features from a diversified set of inputs using convolutional neural network (CNN) and gated recurrent unit (GRU) networks for evapotranspiration (ETo) forecasting. The results show that the CNNGRU model integrated with the ACO method has outperformed the benchmark models over multi-step forecast horizons, and it has also captured the complex and non-linear relationships between predictors and daily ETo. The third objective employs the BRF feature selection method to identify the global climate model (GCM)-simulated variables for an LSTM model, aiming to estimate upper-layer surface soil moisture (SM) under RCP4.5 and 8.5 warming scenarios. The results demonstrate that the proposed BRF-LSTM model is more accurate than benchmark models, and this objective has established a new approach that can deal with GCM-simulated variables.

The fourth objective develops a CEEMDAN-CNN-GRU hybrid model to forecast daily surface soil moisture (SSM) by using neighbourhood component analysis (NCA), complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), convolutional neural networks (CNN), and gated recurrent units (GRU). The CEEMDAN-CNN-GRU hybrid model outperforms all benchmark and standalone models in simulating surface soil moisture. The fifth objective is to develop the CBILSTM hybrid model, coupled with CEEMDAN and a variational mode decomposition (VMD) to build the CVMD-CBiLSTM hybrid model for streamflow water level forecasting. This proposed model reveals that the CVMD-CBiLSTM hybrid model had outperformed the benchmark models.

The artificial intelligence (AI) methodologies developed in this PhD project are expected to be a significant step forward in developing AI-based data-driven decision support systems that will enable hydrologists and climate specialists to design water resource management strategies. Though this work focuses on soil moisture, evapotranspiration, and streamflow water level forecasting, the developed methodologies can also contribute significantly to other areas, such as flood forecasting, irrigation scheduling, and sustainable management of water resources. Overall, the doctoral study establishes significant scientific pathways for water resources management and smart farming using AI-based decision support systems.

KeywordsHydrological forecasting, Deep Learning, Hybrid Models, soil moisture, evapotranspiration, and streamflow water level
Related Output
Has partDeep learning hybrid model with Boruta-Random forest optimiser algorithm for streamflow forecasting with climate mode indices, rainfall, and periodicity
Has partHybrid deep learning method for a week-ahead evapotranspiration forecasting
Has partLSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios
Has partDeep Learning Forecasts of Soil Moisture: Convolutional Neural Network and Gated Recurrent Unit Models Coupled with Satellite-Derived MODIS, Observations and Synoptic-Scale Climate Index Data
Has partNew double decomposition deep learning methods for river water level forecasting
Has partKernel Ridge Regression Hybrid Method for Wheat Yield Prediction with Satellite-Derived Predictors
ANZSRC Field of Research 2020460207. Modelling and simulation
370704. Surface water hydrology
Public Notes

File reproduced in accordance with the copyright policy of the publisher/author.

Byline AffiliationsSchool of Mathematics, Physics and Computing
Permalink -

https://research.usq.edu.au/item/q7q5z/development-of-deep-learning-hybrid-models-for-hydrological-predictions

Download files


Published Version
  • 119
    total views
  • 400
    total downloads
  • 29
    views this month
  • 23
    downloads this month

Export as

Related outputs

Cloud cover bias correction in numerical weather models for solar energy monitoring and forecasting systems with kernel ridge regression
Deo, Ravinesh C., Ahmed, A.A. Masrur, Casillas-Perez, David, Pourmousavi, S. Ali, Segal, Gary, Yu, Yanshan and Salcedo-sanz, Sancho. 2023. "Cloud cover bias correction in numerical weather models for solar energy monitoring and forecasting systems with kernel ridge regression." Renewable Energy. 203, pp. 113-130. https://doi.org/10.1016/j.renene.2022.12.048
Introductory Engineering Mathematics Students’ Weighted Score Predictions Utilising a Novel Multivariate Adaptive Regression Spline Model
Ahmed, Abul Abrar Masrur, Deo, Ravinesh C., Ghimire, Sujan, Downs, Nathan J., Devi, Aruna, Barua, Prabal D. and Yaseen, Zaher M.. 2022. "Introductory Engineering Mathematics Students’ Weighted Score Predictions Utilising a Novel Multivariate Adaptive Regression Spline Model." Sustainability. 14 (17), pp. 1-27. https://doi.org/10.3390/su141711070
Kernel Ridge Regression Hybrid Method for Wheat Yield Prediction with Satellite-Derived Predictors
Ahmed, A. A. Masrur, Sharma, Ekta, Jui, S. Janifer Jabin, Deo, Ravinesh C., Nguyen-Huy, Thong and Ali, Mumtaz. 2022. "Kernel Ridge Regression Hybrid Method for Wheat Yield Prediction with Satellite-Derived Predictors." Remote Sensing. 14 (5), pp. 1-24. https://doi.org/10.3390/rs14051136
Assessment and Prediction of Sea Level Trend in the South Pacific Region
Raj, Nawin, Gharineiat, Zahra, Ahmed, Abul Abrar Masrur and Stepanyants, Yury. 2022. "Assessment and Prediction of Sea Level Trend in the South Pacific Region." Remote Sensing. 14 (4), pp. 1-25. https://doi.org/10.3390/rs14040986
New double decomposition deep learning methods for river water level forecasting
Ahmed, A. A. Masrur, Deo, Ravinesh C., Ghahramani, Afshin, Feng, Qi, Raj, Nawin, Yin, Zhenliang and Yang, Linshan. 2022. "New double decomposition deep learning methods for river water level forecasting." Science of the Total Environment. 831, pp. 1-21. https://doi.org/10.1016/j.scitotenv.2022.154722
Spatiotemporal Hybrid Random Forest Model for Tea Yield Prediction Using Satellite-Derived Variables
Jui, S. Janifer Jabin, Ahmed, A. A. Masrur, Bose, Aditi, Raj, Nawin, Sharma, Ekta, Soar, Jeffrey and Chowdhury, Md Wasique Islam. 2022. "Spatiotemporal Hybrid Random Forest Model for Tea Yield Prediction Using Satellite-Derived Variables." Remote Sensing. 14 (3), pp. 1-18. https://doi.org/10.3390/rs14030805
Optimization algorithms as training approach with hybrid deep learning methods to develop an ultraviolet index forecasting model
Ahmed, A. A. Masrur, Ahmed, Mohammad Hafez, Saha, Sanjoy Kanti, Ahmed, Oli and Sutradhar, Ambica. 2022. "Optimization algorithms as training approach with hybrid deep learning methods to develop an ultraviolet index forecasting model." Stochastic Environmental Research and Risk Assessment. 36 (10), pp. 3011-3039. https://doi.org/10.1007/s00477-022-02177-3
Hybrid deep learning method for a week-ahead evapotranspiration forecasting
Ahmed, A. A. Masrur, Deo, Ravinesh C., Feng, Qi, Ghahramani, Afshin, Raj, Nawin, Yin, Zhenliang and Yang, Linshan. 2022. "Hybrid deep learning method for a week-ahead evapotranspiration forecasting." Stochastic Environmental Research and Risk Assessment. 36 (3), pp. 831-849. https://doi.org/10.1007/s00477-021-02078-x
Deep Learning Forecasts of Soil Moisture: Convolutional Neural Network and Gated Recurrent Unit Models Coupled with Satellite-Derived MODIS, Observations and Synoptic-Scale Climate Index Data
Ahmed, A. A. Masrur, Deo, Ravinesh C., Raj, Nawin, Ghahramani, Afshin, Feng, Qi, Yin, Zhenliang and Yang, Linshan. 2021. "Deep Learning Forecasts of Soil Moisture: Convolutional Neural Network and Gated Recurrent Unit Models Coupled with Satellite-Derived MODIS, Observations and Synoptic-Scale Climate Index Data." Remote Sensing. 13 (4), pp. 1-30. https://doi.org/10.3390/rs13040554
LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios
Ahmed, A. A. Masrur, Deo, Ravinesh C., Ghahramani, Afshin, Raj, Nawin, Feng, Qi, Yin, Zhenliang and Yang, Linshan. 2021. "LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4.5 and RCP8.5 global warming scenarios." Stochastic Environmental Research and Risk Assessment. 35, pp. 1851-1881. https://doi.org/10.1007/s00477-021-01969-3
Deep learning hybrid model with Boruta-Random forest optimiser algorithm for streamflow forecasting with climate mode indices, rainfall, and periodicity
Ahmed, A. A. Masrur, Deo, Ravinesh C., Feng, Qi, Ghahramani, Afshin, Raj, Nawin, Yin, Zhenliang and Yang, Linshan. 2021. "Deep learning hybrid model with Boruta-Random forest optimiser algorithm for streamflow forecasting with climate mode indices, rainfall, and periodicity." Journal of Hydrology. 599, pp. 1-23. https://doi.org/10.1016/j.jhydrol.2021.126350