Evaluating Performances of LSTM, SVM, GPR, and RF for Drought Prediction in Norway: A Wavelet Decomposition Approach on Regional Forecasting DOI Open Access
Sertaç Oruç, Mehmet Ali Hınıs, Türker Tuğrul

et al.

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3465 - 3465

Published: Dec. 2, 2024

A serious natural disaster that poses a threat to people and their living spaces is drought, which difficult notice at first can quickly spread wide areas through subtle progression. Numerous methods are being explored identify, prevent, mitigate distinct metrics have been developed. In order contribute the research on measures be taken against Standard Precipitation Evaporation Index (SPEI), one of drought indices has developed accepted in recent years includes more comprehensive definition, was chosen this study. Machine learning deep algorithms, including support vector machine (SVM), random forest (RF), long short-term memory (LSTM), Gaussian process regression (GPR), were used model droughts six regions Norway: Bodø, Karasjok, Oslo, Tromsø, Trondheim, Vadsø. Four architectures employed for goal, as novel approach, models’ output enhanced by using discrete wavelet decomposition/transformation (WT). The outputs evaluated correlation coefficient (r), Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE) performance evaluation criteria. When findings analyzed, GPR (W-GPR), acquired after WT, typically produced best results. Furthermore, it discovered that, out all recognized models, M04 had most effective structure. Consequently, successful outcomes obtained with W-SVM-M04 Bodø W-GPR-M04 Oslo region results across (r: 0.9983, NSE: 0.9966 RMSE:0.0539).

Language: Английский

A generalised hydrological model for streamflow prediction using wavelet Ensembling DOI
Chinmaya Panda, Kanhu Charan Panda,

Ram Mandir Singh

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 132883 - 132883

Published: Feb. 1, 2025

Language: Английский

Citations

0
Probabilistic linkages of propagation from meteorological to agricultural drought in the North African semi-arid region DOI Creative Commons

Younes Dahhane,

Victor Ongoma, Abdessamad Hadri

et al.

Frontiers in Water, Journal Year: 2025, Volume and Issue: 7

Published: April 8, 2025

Understanding the probability of drought occurrence in agricultural areas is important for designing effective adaptation strategies to impacts on agriculture and food security. This knowledge critical, especially arid semi-arid Morocco, which are prone vulnerable droughts. study examines linkage between meteorological (MD) (AD) a critical region Morocco. Different indexes [NDVI anomaly, vegetation condition index (VCI), temperature (TCI), health (VHI)], [Standardized Precipitation Evapotranspiration Index (SPEI) different time scales (3, 6, 9, 12 months)] assessed period 2000–2022. Statistical measures such as Spearman correlation ( R ), root mean square error (RMSE), absolute (MAE), utilized assess performance detect drought. The propagation from was identified, probabilistic linkages two types droughts were investigated using copula function Bayesian network. Results show that combination SPEI3 VHI has highest coefficient 0.65 lowest RMSE MAE 1.5 1.5, respectively. 39 days scale months, seasonally, it 29, 32, 82 days, autumn, winter, spring, network results have high occur whenever there severe extreme drought, with probabilities mild moderate findings significant applications water resource management planning, usage security based likelihood occurence.

Language: Английский

Citations

0
Federated transfer learning for distributed drought stage prediction DOI Creative Commons

Muhammad Owais Raza,

Aqsa Umar,

Jawad Rasheed

et al.

Discover Artificial Intelligence, Journal Year: 2025, Volume and Issue: 5(1)

Published: May 11, 2025

Language: Английский

Citations

0
Evaluating Performances of LSTM, SVM, GPR, and RF for Drought Prediction in Norway: A Wavelet Decomposition Approach on Regional Forecasting DOI Open Access
Sertaç Oruç, Mehmet Ali Hınıs, Türker Tuğrul

et al.

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3465 - 3465

Published: Dec. 2, 2024

A serious natural disaster that poses a threat to people and their living spaces is drought, which difficult notice at first can quickly spread wide areas through subtle progression. Numerous methods are being explored identify, prevent, mitigate distinct metrics have been developed. In order contribute the research on measures be taken against Standard Precipitation Evaporation Index (SPEI), one of drought indices has developed accepted in recent years includes more comprehensive definition, was chosen this study. Machine learning deep algorithms, including support vector machine (SVM), random forest (RF), long short-term memory (LSTM), Gaussian process regression (GPR), were used model droughts six regions Norway: Bodø, Karasjok, Oslo, Tromsø, Trondheim, Vadsø. Four architectures employed for goal, as novel approach, models’ output enhanced by using discrete wavelet decomposition/transformation (WT). The outputs evaluated correlation coefficient (r), Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE) performance evaluation criteria. When findings analyzed, GPR (W-GPR), acquired after WT, typically produced best results. Furthermore, it discovered that, out all recognized models, M04 had most effective structure. Consequently, successful outcomes obtained with W-SVM-M04 Bodø W-GPR-M04 Oslo region results across (r: 0.9983, NSE: 0.9966 RMSE:0.0539).

Language: Английский

Citations

2