Development of deep learning approaches for drought forecasting: a comparative study in a cold and semi-arid region DOI
Amin Gharehbaghi, Redvan Ghasemlounıa, Babak Vaheddoost

et al.

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 18(1)

Published: Dec. 19, 2024

Language: Английский

Evolution of drought characteristics using a new combined joint multivariate index based on the copula function DOI

Narjes Shahbeygi,

Bahareh Pirzadeh, Jamshid Piri

et al.

Natural Hazards, Journal Year: 2025, Volume and Issue: unknown

Published: March 11, 2025

Language: Английский

Citations

0
Drought prediction in Jilin Province based on deep learning and spatio-temporal sequence modeling DOI

Zhaojun Hou,

Beibei Wang, Yichen Zhang

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 642, P. 131891 - 131891

Published: Aug. 27, 2024

Language: Английский

Citations

3
LSTM Model Integrated Remote Sensing Data for Drought Prediction: A Study on Climate Change Impacts on Water Availability in the Arid Region DOI Open Access
Haitham Abdulmohsin Afan, Atheer Saleem Almawla, Basheer Al-Hadeethi

et al.

Water, Journal Year: 2024, Volume and Issue: 16(19), P. 2799 - 2799

Published: Oct. 1, 2024

Climate change is one of the trending terms in world nowadays due to its profound impact on human health and activity. Extreme drought events desertification are some results climate change. This study utilized power AI tools by using long short-term memory (LSTM) model predict index for Anbar Province, Iraq. The data from standardized precipitation evapotranspiration (SPEI) 118 years have been used current study. proposed employed seven different optimizers enhance prediction performance. Based performance indicators, show that RMSprop Adamax achieved highest accuracy (90.93% 90.61%, respectively). Additionally, models forecasted next 40 SPEI area, where all showed an upward trend SPEI. In contrast, best expected no increase severity drought. research highlights vital role machine learning remote sensing forecasting significance these applications providing accurate better water resources management, especially arid regions like province.

Language: Английский

Citations

2
A novel feature extraction-selection technique for long lead time agricultural drought forecasting DOI
Mehdi Mohammadi Ghaleni, Mansour Moradi, Mahnoosh Moghaddasi

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: unknown, P. 132332 - 132332

Published: Nov. 1, 2024

Language: Английский

Citations

1
Advance drought prediction through rainfall forecasting with hybrid deep learning model DOI Creative Commons
Brij B. Gupta, Akshat Gaurav, Razaz Waheeb Attar

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 13, 2024

Drought is a natural disaster that can affect larger area over time. Damage caused by the drought only be reduced through its accurate prediction. In this context, we proposed hybrid stacked model for rainfall prediction, which crucial effective forecasting and management. first layer of models, Bi-directional LSTM used to extract features, then in second layer, will make predictions. The captures complex temporal dependencies processing multivariate time series data both forward backward directions using bi-directional layers. Trained with Mean Squared Error loss Adam optimizer, demonstrates improved accuracy, offering significant potential proactive

Language: Английский

Citations

1
Prediction of Meteorological Drought in Xinjiang at Multiple Temporal Scales Based on GWO-SA-ConvBiLSTM DOI Creative Commons
Lei Gu, Wen Yu,

MeiShuang Yu

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 22, 2024

Abstract Drought is one of the most serious climatic disasters affecting human society. Effective drought prediction can provide a reliable basis for formulation anti-drought measures. According to characteristics, we construct multi-time scale GWO-SA-ConvBiLSTM network. In this model, combine Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Networks (CNN), add self-attention mechanism (SA). On basis, grey Wolf optimizer(GWO) added make model choose optimal hyperparameter faster. We selected Atel region Xinjiang as research object, sorted out meteorological data 5 stations in study area from 1960 2018, imported their SPEI values 1, 3, 6, 12 24 months into training. Compared with other models, our has better performance scenario prediction.

Language: Английский

Citations

0
Utilizing InVEST ecosystem services model combined with deep learning and fallback bargaining for effective sediment retention in Northern Iran DOI
Ali Nasiri Khiavi,

Hamid Khodamoradi,

Fatemeh Sarouneh

et al.

Environmental Science and Pollution Research, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 14, 2024

Language: Английский

Citations

0
Development of deep learning approaches for drought forecasting: a comparative study in a cold and semi-arid region DOI
Amin Gharehbaghi, Redvan Ghasemlounıa, Babak Vaheddoost

et al.

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 18(1)

Published: Dec. 19, 2024

Language: Английский

Citations

0