Identifying major drivers of daily streamflow from large-scale atmospheric circulation with machine learning DOI Creative Commons
Jenny Sjåstad Hagen, Étienne Leblois,

Deborah Lawrence

et al.

Journal of Hydrology, Journal Year: 2021, Volume and Issue: 596, P. 126086 - 126086

Published: Feb. 23, 2021

Previous studies linking large-scale atmospheric circulation and river flow with traditional machine learning techniques have predominantly explored monthly, seasonal or annual streamflow modelling for applications in direct downscaling hydrological climate-impact studies. This paper identifies major drivers of daily from using two reanalysis datasets six catchments Norway representing various Köppen-Geiger climate types flood-generating processes. A nested loop roughly pruned random forests is used feature extraction, demonstrating the potential automated retrieval physically consistent interpretable input variables. Random forest (RF), support vector (SVM) regression multilayer perceptron (MLP) neural networks are compared to multiple-linear assess role model complexity utilizing identified reconstruct streamflow. The models were trained on 31 years aggregated data distinct moving windows each catchment, reflecting catchment-specific forcing-response relationships between atmosphere rivers. results show that accuracy improves some extent complexity. In all but smallest, rainfall-driven most complex model, MLP, gives a Nash-Sutcliffe Efficiency (NSE) ranging 0.71 0.81 testing spanning five years. poorer performance by smallest catchment discussed relation characteristics, sub-grid topography local variability. intra-model differences also viewed consistency automatically retrieved selections datasets. study provides benchmark future development deep variables Norway.

Language: Английский

Artificial Neural Networks Based Optimization Techniques: A Review DOI Open Access
Maher G. M. Abdolrasol, S. M. Suhail Hussain, Taha Selim Ustun

et al.

Electronics, Journal Year: 2021, Volume and Issue: 10(21), P. 2689 - 2689

Published: Nov. 3, 2021

In the last few years, intensive research has been done to enhance artificial intelligence (AI) using optimization techniques. this paper, we present an extensive review of neural networks (ANNs) based algorithm techniques with some famous techniques, e.g., genetic (GA), particle swarm (PSO), bee colony (ABC), and backtracking search (BSA) modern developed lightning (LSA) whale (WOA), many more. The entire set such is classified as algorithms on a population where initial randomly created. Input parameters are initialized within specified range, they can provide optimal solutions. This paper emphasizes enhancing network via by manipulating its tuned or training obtain best structure pattern dissolve problems in way. includes results for improving ANN performance PSO, GA, ABC, BSA respectively, parameters, number neurons hidden layers learning rate. obtained net used solving energy management virtual power plant system.

Language: Английский

Citations

424
A comprehensive review of deep learning applications in hydrology and water resources DOI Open Access
Muhammed Sit, Bekir Zahit Demiray, Zhongrun Xiang

et al.

Water Science & Technology, Journal Year: 2020, Volume and Issue: 82(12), P. 2635 - 2670

Published: Aug. 5, 2020

Abstract The global volume of digital data is expected to reach 175 zettabytes by 2025. volume, variety and velocity water-related are increasing due large-scale sensor networks increased attention topics such as disaster response, water resources management, climate change. Combined with the growing availability computational popularity deep learning, these transformed into actionable practical knowledge, revolutionizing industry. In this article, a systematic review literature conducted identify existing research that incorporates learning methods in sector, regard monitoring, governance communication resources. study provides comprehensive state-of-the-art approaches used industry for generation, prediction, enhancement, classification tasks, serves guide how utilize available future challenges. Key issues challenges application techniques domain discussed, including ethics technologies decision-making management governance. Finally, we provide recommendations directions models hydrology

Language: Английский

Citations

398
COVID-19 Outbreak Prediction with Machine Learning DOI Creative Commons
Sina Ardabili,

Amir Mosavi,

Pedram Ghamisi

et al.

Algorithms, Journal Year: 2020, Volume and Issue: 13(10), P. 249 - 249

Published: Oct. 1, 2020

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed decisions and enforce relevant control measures. Among standard global pandemic prediction, simple epidemiological statistical have received more attention authorities, these popular in media. Due a high level of uncertainty lack essential data, shown low accuracy long-term prediction. Although literature includes several attempts address this issue, generalization robustness abilities existing need be improved. This paper presents comparative analysis machine learning soft computing predict as an alternative susceptible–infected–recovered (SIR) susceptible-exposed-infectious-removed (SEIR) models. wide range investigated, two showed promising results (i.e., multi-layered perceptron, MLP; adaptive network-based fuzzy inference system, ANFIS). Based on reported here, due highly complex nature variation its behavior across nations, study suggests effective tool model outbreak. provides initial benchmarking demonstrate potential future research. further that genuine novelty can realized integrating SEIR

Language: Английский

Citations

321
COVID-19 Pandemic Prediction for Hungary; A Hybrid Machine Learning Approach DOI Creative Commons
Gergő Pintér, Imre Felde,

Amir Mosavi

et al.

Mathematics, Journal Year: 2020, Volume and Issue: 8(6), P. 890 - 890

Published: June 2, 2020

Several epidemiological models are being used around the world to project number of infected individuals and mortality rates COVID-19 outbreak. Advancing accurate prediction is utmost importance take proper actions. Due lack essential data uncertainty, have been challenged regarding delivery higher accuracy for long-term prediction. As an alternative susceptible-infected-resistant (SIR)-based models, this study proposes a hybrid machine learning approach predict COVID-19, we exemplify its potential using from Hungary. The methods adaptive network-based fuzzy inference system (ANFIS) multi-layered perceptron-imperialist competitive algorithm (MLP-ICA) proposed time series rate. that by late May, outbreak total morality will drop substantially. validation performed 9 days with promising results, which confirms model accuracy. It expected maintains as long no significant interruption occurs. This paper provides initial benchmarking demonstrate future research.

Language: Английский

Citations

230
Advances in Machine Learning Modeling Reviewing Hybrid and Ensemble Methods DOI
Sina Ardabili,

Amir Mosavi,

Annamária R. Várkonyi-Kóczy

et al.

Lecture notes in networks and systems, Journal Year: 2020, Volume and Issue: unknown, P. 215 - 227

Published: Jan. 1, 2020

Language: Английский

Citations

171
Estimation of daily maize transpiration using support vector machines, extreme gradient boosting, artificial and deep neural networks models DOI
Junliang Fan, Jing Zheng, Lifeng Wu

et al.

Agricultural Water Management, Journal Year: 2020, Volume and Issue: 245, P. 106547 - 106547

Published: Oct. 8, 2020

Language: Английский

Citations

167
A novel intelligent deep learning predictive model for meteorological drought forecasting DOI
Ali Danandeh Mehr, Amir Rikhtehgar Ghiasi, Zaher Mundher Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬

et al.

Journal of Ambient Intelligence and Humanized Computing, Journal Year: 2022, Volume and Issue: 14(8), P. 10441 - 10455

Published: Jan. 24, 2022

Language: Английский

Citations

139
Comparison of Deep Learning Techniques for River Streamflow Forecasting DOI Creative Commons
Xuan-Hien Le, Duc Hai Nguyen, Sungho Jung

et al.

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 71805 - 71820

Published: Jan. 1, 2021

Recently, deep learning (DL) models, especially those based on long short-term memory (LSTM), have demonstrated their superior ability in resolving sequential data problems. This study investigated the performance of six models that belong to supervised category evaluate DL terms streamflow forecasting. They include a feed-forward neural network (FFNN), convolutional (CNN), and four LSTM-based models. Two standard with just one hidden layer-LSTM gated recurrent unit (GRU)-are used against two more complex models-the stacked LSTM (StackedLSTM) model Bidirectional (BiLSTM) model. The Red River basin-the largest river basin north Vietnam-was adopted as case because its geographic relevance since Hanoi city-the capital Vietnam-is located downstream River. Besides, input these are observed at seven hydrological stations three main branches system. indicates exhibited considerably better maintained stability than FFNN CNN However, complexity StackedLSTM BiLSTM is not accompanied by improvement results comparison illustrate respective higher models-LSTM GRU. findings this present can reach impressive forecasts even presence upstream dams reservoirs. For streamflow-forecasting problem, GRU simple architecture (one layer) sufficient produce highly reliable while minimizing computation time.

Language: Английский

Citations

117
Integrating Machine Learning and AI for Improved Hydrological Modeling and Water Resource Management DOI
Djabeur Mohamed Seifeddine Zekrifa,

Megha Kulkarni,

A. Bhagyalakshmi

et al.

Advances in environmental engineering and green technologies book series, Journal Year: 2023, Volume and Issue: unknown, P. 46 - 70

Published: June 9, 2023

The hydrological cycle is an important process that controls how and where water distributed on Earth. It includes processes including transpiration, evaporation, condensation, precipitation, runoff, infiltration. However, there are obstacles to understanding modelling the cycle, such as a lack of data, ambiguity, fluctuation, impact human activity natural balance. Techniques for accurate essential managing resources risk reduction. With potential uses in rainfall forecasting, streamflow flood modelling, machine learning artificial intelligence (AI) effective tools modelling. Case studies real-world examples show solutions problems like data quality, interpretability, scalability may be applied situations. Discussions future directions challenges emphasise new developments areas need more investigation cooperation.

Language: Английский

Citations

61
A critical review of machine learning algorithms in maritime, offshore, and oil & gas corrosion research: A comprehensive analysis of ANN and RF models DOI
Md Mahadi Hasan Imran, Shahrizan Jamaludin, Ahmad Faisal Mohamad Ayob

et al.

Ocean Engineering, Journal Year: 2024, Volume and Issue: 295, P. 116796 - 116796

Published: Jan. 30, 2024

Language: Английский

Citations

21