Article
Thermodynamics
Ruan Luzia, Lihki Rubio, Carlos E. Velasquez
Summary: Several studies have focused on improving forecasting techniques for capturing multiple patterns in time series. The advancement in computing hardware has made it possible to solve complex equations using large amounts of data, such as neural networks. However, time series methods like ARIMA can also provide good approximations with low computational resources. To enhance ARIMA approximations, they can be combined with techniques like Wavelet Transform or Fourier Transform. This study evaluates the suitability of using artificial neural networks, ARIMA combined with Wavelet Transform, or Fourier Transform to make predictions for different time horizons and frequencies. The results indicate that artificial neural networks perform better for short-term horizons, ARIMA with Fourier Transform provides the best approximation for monthly time series and any time horizon, and ARIMA with Wavelet Transform offers the best approximation for medium-term and long-term periods at any time frequency.
Article
Environmental Sciences
Muhammad Tariq Khan, Muhammad Shoaib, Raffaele Albano, Muhammad Azhar Inam, Hamza Salahudin, Muhammad Hammad, Shakil Ahmad, Muhammad Usman Ali, Sarfraz Hashim, Muhammad Kaleem Ullah
Summary: The science of hydrological modeling has evolved with advancements in software and hardware technologies. Researchers focus on accurately converting rainfall into runoff and assessing uncertainty. Alternative data-driven methods, such as coupling machine learning models with wavelet transformation, have gained attention in hydrology.
Article
Chemistry, Multidisciplinary
Zongyu Li, Zhilin Sun, Jing Liu, Haiyang Dong, Wenhua Xiong, Lixia Sun, Hanyu Zhou
Summary: This paper explores the problem of sediment variation in rivers. Traditional research methods require significant human and material resources, while this study utilizes intelligent approaches combining wavelet transforms and neural networks for predicting sediment models. The results demonstrate the effectiveness of this method in improving prediction accuracy, providing a reference basis for river sediment prediction.
APPLIED SCIENCES-BASEL
(2022)
Article
Ecology
Celso Augusto Guimaraes Santos, Gleycielle Rodrigues do Nascimento, Camilo Allyson Simoes de Farias, Richarde Marques da Silva, Manoranjan Mishra
Summary: This study presents a methodology that improves streamflow forecasting by using wavelet neural networks to relate streamflows with rainfall data. The methodology performs well in long-term forecasts, especially in the Mahanadi River basin, and can be applied in other catchments.
ECOLOGICAL INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Samuel Vitor Saraiva, Frede de Oliveira Carvalho, Celso Augusto Guimaraes Santos, Lucas Costa Barreto, Paula Karenina de Macedo Machado Freire
Summary: This study conducted a comparative analysis of a set of machine learning models, including an ANN and an SVM coupled with wavelet transform and data resampling. Results showed that the ANN outperformed the SVM in terms of accuracy, with the best performing combination being the BWNN method. The BWNN method yielded lower mean square error and higher R-2 and MAE coefficients for streamflow forecasting 3 to 15 days ahead.
APPLIED SOFT COMPUTING
(2021)
Article
Construction & Building Technology
Ruihua Liang, Weifeng Liu, Sakdirat Kaewunruen, Hougui Zhang, Zongzhen Wu
Summary: In this study, advanced hybrid models of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network were built to accurately and efficiently classify and evaluate the impact of multiple external vibration sources on sensitive buildings such as laboratories and heritage buildings. The proposed optimal model achieved an accuracy of over 97% for identifying external vibration sources by utilizing extensive data recorded in Beijing. A real-world case study was conducted, demonstrating the necessity and feasibility of this study for engineering applications.
STRUCTURAL CONTROL & HEALTH MONITORING
(2023)
Article
Engineering, Civil
Thien Huy Truong Nguyen, Bree Bennett, Michael Leonard
Summary: Stochastic rainfall models are important for evaluating hydrological risks, but there are discrepancies between rainfall metrics and flow metrics. The performance of different models varies depending on the strictness of the flow-based comparison and the region analyzed.
JOURNAL OF HYDROLOGY
(2023)
Article
Chemistry, Multidisciplinary
Bishwajit Roy, Maheshwari Prasad Singh, Mosbeh R. Kaloop, Deepak Kumar, Jong-Wan Hu, Radhikesh Kumar, Won-Sup Hwang
Summary: This paper proposes an integrated model EO-ELM and a deep neural network DNN for one day-ahead rainfall-runoff modeling, validated at two benchmark stations in the UK. The experimental results show the efficiency and robustness of EO-ELM and DNN compared to other models for daily R-R modeling.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Civil
Amir Molajou, Vahid Nourani, Abbas Afshar, Mina Khosravi, Adam Brysiewicz
Summary: Rainfall-runoff modeling at different time scales is a significant issue in hydro-environmental planning. In this study, a hybrid GA-EANN model was proposed and showed better performance compared to sole ANN and EANN models. The hybrid model achieved up to 19% and 35% improvement in testing suitability criteria for the Aji Chai and Murrumbidgee catchments, respectively.
WATER RESOURCES MANAGEMENT
(2021)
Article
Environmental Sciences
K. Lebar, D. Kastelec, S. Rusjan
Summary: This study investigates the interplay between hydrometeorological factors and seasonal forest vegetation in regulating the nitrate-nitrogen (NO3-N) flushing in a forested catchment. The results show that there is no significant difference in NO3-N concentrations based on seasons, but differences exist during baseflow conditions. Additionally, the study finds that the influence of vegetation on NO3-N flushing is not significant during rainfall events.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Computer Science, Interdisciplinary Applications
Georgy Ayzel, Maik Heistermann
Summary: The study systematically compared the performance of the GR4H hydrological model with the LSTM and GRU neural networks in relation to the length of calibration data, revealing significant differences in model performance and convergence speed.
COMPUTERS & GEOSCIENCES
(2021)
Article
Engineering, Multidisciplinary
Subhashree Mohapatra, Girish Kumar Pati, Manohar Mishra, Tripti Swarnkar
Summary: This study proposes an intelligent method using empirical wavelet transform (EWT) and convolutional neural network (CNN) to classify alimentary canal diseases. The method achieves high accuracy and performance metrics in disease classification. A comparative study with other contemporary techniques is conducted to validate the efficacy of the proposed method.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Engineering, Civil
Meysam Ghamariadyan, Monzur A. Imteaz
Summary: The study developed the Wavelet Artificial Neural Networks (WANN) model to forecast seasonal rainfall in Queensland, Australia. The WANN model outperformed other methods in accuracy, especially compared to the ACCESS-S and climatology forecasts, with improvements ranging from 37% to 60%.
WATER RESOURCES MANAGEMENT
(2021)
Article
Water Resources
Farnaz Daneshvar Vousoughi
Summary: Two approaches were used in the Ardabil Plain to determine the relationship between hydrological time-series and the groundwater level. The results show that human activities have a greater impact on the groundwater level than the fluctuation of the hydrological time-series.
JOURNAL OF WATER AND CLIMATE CHANGE
(2022)
Article
Environmental Sciences
Saeideh Samani, Meysam Vadiati, Zohre Nejatijahromi, Behrooz Etebari, Ozgur Kisi
Summary: This study proposed a set of supervised machine learning models and wavelet transform to predict groundwater level changes in the Zarand-Saveh complex aquifer in Iran. The results showed that the hybrid wavelet-machine learning models considerably improved the standalone model results, with the wavelet transform-least square support vector machine model performing the best among all methods.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Environmental Sciences
Amir Molajou, Abbas Afshar, Mina Khosravi, Elham Soleimanian, Masoud Vahabzadeh, Hossein Akbari Variani
Summary: In recent decades, global demands for freshwater, energy, and food have been influenced by population growth, economic development, international trade, and increasing urbanization and food diversity. The lack of integrated management strategies poses a threat to the security of these resources, while climate change exacerbates the adverse impacts. Therefore, understanding and studying the complex interactions and connections between these systems have become crucial.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Interdisciplinary Applications
Elnaz Sharghi, Nardin Jabbarian Paknezhad, Hessam Najafi
Summary: This paper introduces the construction of prediction intervals for Suspended Sediment Load modeling using Emotional Artificial Neural Network (EANN) and classic Neural Network models, comparing their reliability. Results show that EANN has higher reliability with Genetic Algorithm constructed PIs, reducing uncertainty levels. Additionally, the LUBE method outperforms the Bootstrap method in terms of reliability, with EANN showing lower uncertainty levels in Upper Rio Grande River modeling compared to FFNN.
EARTH SCIENCE INFORMATICS
(2021)
Article
Engineering, Civil
Amir Molajou, Vahid Nourani, Abbas Afshar, Mina Khosravi, Adam Brysiewicz
Summary: Rainfall-runoff modeling at different time scales is a significant issue in hydro-environmental planning. In this study, a hybrid GA-EANN model was proposed and showed better performance compared to sole ANN and EANN models. The hybrid model achieved up to 19% and 35% improvement in testing suitability criteria for the Aji Chai and Murrumbidgee catchments, respectively.
WATER RESOURCES MANAGEMENT
(2021)
Article
Engineering, Civil
Vahid Nourani, Hessam Najafi, Elnaz Sharghi, Kiyoumars Roushangar
Summary: This study applies Z-number valued if-then rules to predict dry, wet, and normal periods, leading to more comprehensive and accurate results.
JOURNAL OF HYDROLOGY
(2021)
Article
Engineering, Civil
Abbas Afshar, Mina Khosravi, Amir Molajou
Summary: The study examines the adaptability of cyclic and non-cyclic conjunctive use of groundwater and surface water resources in improving groundwater sustainability and water allocation sustainability under climate change scenarios. The cyclic operation strategy improves the adaptability of the conjunctive use system, with an improvement of over 27% in groundwater sustainability index compared to the non-cyclic approach.
WATER RESOURCES MANAGEMENT
(2021)
Correction
Engineering, Civil
Amir Molajou, Vahid Nourani, Abbas Afshar, Mina Khosravi, Adam Brysiewicz
WATER RESOURCES MANAGEMENT
(2021)
Article
Engineering, Civil
Amir Molajou, Parsa Pouladi, Abbas Afshar
Summary: The study introduces a conceptual socio-hydrological-based framework for the water-energy-food nexus, aiming to investigate the impact of farmers' dynamic agricultural activities under different socio-economic conditions on the WEF systems. The integrated model reflects the interactions among physical, socio-economic, ecological, and political processes within the WEF nexus, highlighting the need to balance natural resources and social systems for sustainable outcomes. The proposed framework can provide policymakers with insights into the dynamic impacts of agricultural activities on the WEF nexus, emphasizing the importance of understanding bidirectional feedback mechanisms among farmers and WEF systems.
WATER RESOURCES MANAGEMENT
(2021)
Article
Water Resources
Hessam Najafi, Vahid Nourani, Elnaz Sharghi, Kiyoumars Roushangar, Dominika Dabrowska
Summary: The study examined the performance of the Z-number-based model in predicting classified monthly precipitation events at two synoptic stations in Iran, demonstrating accurate predictions and significant improvement compared to traditional fuzzy methods.
HYDROLOGY RESEARCH
(2022)
Article
Green & Sustainable Science & Technology
Abbas Afshar, Elham Soleimanian, Hossein Akbari Variani, Masoud Vahabzadeh, Amir Molajou
Summary: Several models have been proposed to address different aspects of the Water-Energy-Food (WEF) nexus system, with the aim of considering internal and external relationships between subsystems. Gathering extensive data is essential in a holistic model, with classification into non-simulated and simulated data being an important step in simplifying the complexity of the nexus system. This study demonstrates the importance of data classification in accessing and sharing data within a comprehensive nexus simulation model.
ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY
(2022)
Review
Environmental Sciences
Elham Soleimanian, Abbas Afshar, Amir Molajou
Summary: The lack of a comprehensive and user-friendly simulation model is the primary obstacle to adopting the Water, Energy, and Food (WEF) Nexus. Existing integrated WEF Nexus models have significant drawbacks compared to compiled alternatives. This study aims to find the best water simulation model for implementation in the nexus concept and provides a holistic checklist for choosing the preferred water simulation model based on specific needs.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Civil
Mina Khosravi, Abbas Afshar, Amir Molajou
Summary: This study presents decision tree-based conditional operation rules for a distributed conjunctive use system of surface water and groundwater. The conditional operation rules show a significant reduction in relative absolute error compared to single linear regression and project the maximum water shortage for the next ten years.
WATER RESOURCES MANAGEMENT
(2022)
Article
Engineering, Civil
Fatemeh Yavari, Seyyed Ali Salehi Neyshabouri, Jafar Yazdi, Amir Molajou, Adam Brysiewicz
Summary: This study proposes a novel method to predict future floods and probable damage by analyzing the simultaneous impacts of non-stationarity in hydrological time series and land-use changes in urban areas. The results show that the damage in the second period decreases in low return periods, but increases for longer return periods. The non-stationarity of rainfalls has a significant effect on flood intensification.
WATER RESOURCES MANAGEMENT
(2022)
Article
Engineering, Civil
Mina Khosravi, Abbas Afshar, Amir Molajou, Sam Sandoval-Solis
Summary: This paper presents a novel multiobjective optimization model for a cyclic storage system that balances water allocation to irrigated agriculture and energy consumption for groundwater pumping. The results show that the cyclic storage strategy improves the sustainability index and reduces pumping energy. These findings are significant for decision-makers in policy-making and strategy evaluation.
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT
(2022)
Article
Automation & Control Systems
Sana Maleki, Vahid Nourani, Hessam Najafi, Aida Hosseini Baghanam, Chang-Qing Ke
Summary: Groundwater vulnerability assessment systems are developed to protect groundwater resources from contamination. The DRASTIC method is commonly used to determine groundwater susceptibility by considering seven parameters. This study applied the Z-number concept as a new approach to estimate aquifers vulnerability, which incorporates reliability and uncertainty in human knowledge.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Environmental Sciences
Vahid Nourani, Sana Maleki, Hessam Najafi, Aida Hosseini Baghanam
Summary: This study developed a Mamdani fuzzy logic (MFL) in combination with data mining to handle the uncertainty caused by expert opinion in groundwater vulnerability assessment. Results showed that the MFL approach was more reliable and practical than the traditional method.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
