Long-term precipitation prediction in different climate divisions of California using remotely sensed data and machine learning DOI

Shabnam Majnooni,

Mohammad Reza Nikoo, Banafsheh Nematollahi

et al.

Hydrological Sciences Journal, Journal Year: 2023, Volume and Issue: 68(14), P. 1984 - 2008

Published: Aug. 21, 2023

ABSTRACTThis study presented a novel paradigm for forecasting 12-step-ahead monthly precipitation at 126 California gauge stations. First, the satellite-based time series from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), TerraClimate, ECMWF Reanalysis V5 (ERA5), and Estimation Remotely Sensed Information using Artificial Neural Networks-Climate Data Record (PERSIANN-CDR) products were bias-corrected historical data. Four methods tested, quantile mapping (QM) was best. After pre-processing data, 19 machine-learning models developed. random forest, Extreme Gradient Boosting (XGBoost), extreme gradient boosting, support vector machine, multi-layer perceptron, K-nearest-neighbours chosen as best based on Complex Proportional Assessment (COPRAS) measurement. hyperparameter adjustment, Bayesian back-propagation regularization algorithm fused results. The superior models' predictions considered inputs, target's initial step labeled. next 11 steps each station followed this approach, fusion accurately predicted all steps. 12th step's average Nash-Sutcliffe efficiency (NSE), mean square error (MSE), coefficient of determination (R2), correlation (R) 0.937, 52.136, 0.880, 0.869, respectively, demonstrating framework's effectiveness high horizons to help policymakers manage water resources.KEYWORDS: bias correctionhyperparameterslong-term predictionmachine learning (ML)quantile (QM)satellite-based Editor A Castellarin; Associate F-J. ChangEditor ChangDisclosure statementNo potential conflict interest reported by authors.Supplementary materialSupplemental article can be accessed online https://doi.org/10.1080/02626667.2023.2248112.

Language: Английский

Modeling Various Drought Time Scales via a Merged Artificial Neural Network with a Firefly Algorithm DOI Creative Commons
Babak Mohammadi

Hydrology, Journal Year: 2023, Volume and Issue: 10(3), P. 58 - 58

Published: Feb. 27, 2023

Drought monitoring and prediction have important roles in various aspects of hydrological studies. In the current research, standardized precipitation index (SPI) was monitored predicted Peru between 1990 2015. The study proposed a hybrid model, called ANN-FA, for SPI time scales (SPI3, SPI6, SPI18, SPI24). A state-of-the-art firefly algorithm (FA) has been documented as powerful tool to support modeling issues. ANN-FA uses an artificial neural network (ANN) which is coupled with FA Lima via other stations. Through intelligent utilization series from neighbors’ stations model inputs, suggested approach might be used forecast at meteorological station insufficient data. To conduct this, SPI3, SPI24 were modeled using stations’ datasets Peru. Various error criteria employed investigate performance model. Results showed that effective promising drought also multi-station strategy lack results can help predict mean absolute = 0.22, root square 0.29, Pearson correlation coefficient 0.94, agreement 0.97 testing phase best estimation (SPI3).

Language: Английский

Citations

50
Assessment and prediction of meteorological drought using machine learning algorithms and climate data DOI Creative Commons

Khalid En-Nagre,

Mourad Aqnouy, Ayoub Ouarka

et al.

Climate Risk Management, Journal Year: 2024, Volume and Issue: 45, P. 100630 - 100630

Published: Jan. 1, 2024

Monitoring drought in semi-arid regions due to climate change is of paramount importance. This study, conducted Morocco's Upper Drâa Basin (UDB), analyzed data spanning from 1980 2019, focusing on the calculation indices, specifically Standardized Precipitation Index (SPI) and Evapotranspiration (SPEI) at multiple timescales (1, 3, 9, 12 months). Trends were assessed using statistical methods such as Mann-Kendall test Sen's Slope estimator. Four significant machine learning (ML) algorithms, including Random Forest, Voting Regressor, AdaBoost K-Nearest Neighbors evaluated predict SPEI values for both three 12-month periods. The algorithms' performance was measured indices. study revealed that distribution within UDB not uniform, with a discernible decreasing trend values. Notably, four ML algorithms effectively predicted specified demonstrated highest Nash-Sutcliffe Efficiency (NSE) values, ranging 0.74 0.93. In contrast, algorithm produced range 0.44 0.84. These research findings have potential provide valuable insights water resource management experts policymakers. However, it imperative enhance collection methodologies expand measurement sites improve representativeness reduce errors associated local variations.

Language: Английский

Citations

21
A novel implementation of pre-processing approaches and hybrid kernel-based model for short- and long-term groundwater drought forecasting DOI
Saman Shahnazi, Kiyoumars Roushangar, Seyed Hossein Hashemi

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: 652, P. 132667 - 132667

Published: Jan. 6, 2025

Language: Английский

Citations

3
Enhancing drought prediction precision with EEMD-ARIMA modeling based on standardized precipitation index DOI Creative Commons
Reza Rezaiy, Ani Shabri

Water Science & Technology, Journal Year: 2024, Volume and Issue: 89(3), P. 745 - 770

Published: Jan. 31, 2024

Abstract This study introduces ensemble empirical mode decomposition (EEMD) coupled with the autoregressive integrated moving average (ARIMA) model for drought prediction. In realm of forecasting, we assess EEMD-ARIMA against traditional ARIMA approach, using monthly precipitation data from January 1970 to December 2019 in Herat province, Afghanistan. Our evaluation spans various timescales standardized index (SPI) 3, SPI 6, 9, and 12. Statistical indicators like root-mean-square error, mean absolute error (MAE), percentage (MAPE), R2 are employed. To comprehend features thoroughly, each series initially computed original time series. Subsequently, undergoes EEMD, resulting intrinsic functions (IMFs) one residual The next step involves forecasting IMF component corresponding model. create an forecast initial series, predicted outcomes modeled IMFs finally added. Results indicate that significantly enhances accuracy compared conventional

Language: Английский

Citations

10
Global reconstruction of gridded aridity index and its spatial and temporal characterization from 2003 to 2022 DOI Creative Commons
Jiaying Lu, Ling Yao, Jun Qin

et al.

International Journal of Digital Earth, Journal Year: 2025, Volume and Issue: 18(1)

Published: March 5, 2025

Aridity index (AI) is an effective estimator of drought status, and spatiotemporally continuous long-term AI dataset critical for assessment applications. Due to the spatial heterogeneity global climate topography, there exist significant uncertainties estimates in areas with sparse ground observations, high-resolution estimation remains a challenge. In this study, we propose LSTM-based approach model nonlinear intra-annual relationship between satellite-derived data enhance performance through ensemble learning by leveraging MODIS at different observation times. A annually gridded generated resolution 0.05° × from 2003 2022. Validation against Global Surface Summary Day database yields biases, root mean squared errors coefficients −0.04 0.02, 0.19 0.86, 0.62 0.83 across continents. Comparisons based on Climatic Research Unit or ERA5-Land datasets further demonstrate high accuracy our estimates. Preliminary analysis reveals wetting trend over past two decades. This offers valuable support research dryland ecosystems, agriculture, change, offering insights address environmental sustainability challenges.

Language: Английский

Citations

1
Spatiotemporal characteristics and forecasting of short-term meteorological drought in China DOI
Qi Zhang, Chiyuan Miao, Jiaojiao Gou

et al.

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 624, P. 129924 - 129924

Published: July 18, 2023

Language: Английский

Citations

21
Spatio-temporal distribution and prediction of agricultural and meteorological drought in a Mediterranean coastal watershed via GIS and machine learning DOI
Siham Acharki, Sudhir Kumar Singh, Edivando Vítor do Couto

et al.

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2023, Volume and Issue: 131, P. 103425 - 103425

Published: June 1, 2023

Language: Английский

Citations

20
Development of a new hybrid ensemble method for accurate characterization of future drought using multiple global climate models DOI

Mahrukh Yousaf,

Zulfiqar Ali, Muhammad Mohsin

et al.

Stochastic Environmental Research and Risk Assessment, Journal Year: 2023, Volume and Issue: 37(12), P. 4567 - 4587

Published: July 27, 2023

Language: Английский

Citations

17
An enhanced drought forecasting in coastal arid regions using deep learning approach with evaporation index DOI
Moteeb Al Moteri, Fadwa Alrowais,

Wafa Mtouaa

et al.

Environmental Research, Journal Year: 2024, Volume and Issue: 246, P. 118171 - 118171

Published: Jan. 10, 2024

Language: Английский

Citations

9
Improving Drought Prediction Accuracy: A Hybrid EEMD and Support Vector Machine Approach with Standardized Precipitation Index DOI
Reza Rezaiy, Ani Shabri

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(13), P. 5255 - 5277

Published: June 29, 2024

Language: Английский

Citations

7