Application of multiple spatial interpolation approaches to annual rainfall data in the Wadi Cheliff basin (north Algeria) DOI Creative Commons
Mohammed Achite, Paraskevas Tsangaratos, Gaetano Pellicone

et al.

Ain Shams Engineering Journal, Journal Year: 2023, Volume and Issue: 15(3), P. 102578 - 102578

Published: Nov. 25, 2023

This study addresses a challenging problem of predicting mean annual precipitation across arid and semi-arid areas in northern Algeria, utilizing deterministic, geostatistical (GS), machine learning (ML) models. Through the analysis data spanning nearly five decades encompassing 150 monitoring stations, result Random Forest showed highest training performance, with R square value (of 0.9524) Root Mean Square Error 24.98). Elevation emerges as critical factor, enhancing prediction accuracy mountainous complex terrains when used an auxiliary variable. Cluster further refines our understanding station distribution characteristics, identifying four distinct clusters, each exhibiting unique patterns elevation zones. helps for better prediction, encouraging integration additional variables exploration climate change impacts, thereby contributing to informed environmental management adaptation strategies diverse climatic terrain scenarios.

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
Innovative approach for predicting daily reference evapotranspiration using improved shallow and deep learning models in a coastal region: A comparative study DOI

Hussam Eldin Elzain,

Osman Abdalla, Mohammed Abdallah

et al.

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 354, P. 120246 - 120246

Published: Feb. 14, 2024

Language: Английский

Citations

18
A coupled extreme gradient boosting-MPA approach for estimating daily reference evapotranspiration DOI
Mohammed Achite, Hamid Nasiri, Okan Mert Katipoğlu

et al.

Theoretical and Applied Climatology, Journal Year: 2025, Volume and Issue: 156(2)

Published: Jan. 16, 2025

Language: Английский

Citations

3
A novel hybrid modeling approach based on empirical methods, PSO, XGBoost, and multiple GCMs for forecasting long-term reference evapotranspiration in a data scarce-area DOI
Ali El Bilali, Abdessamad Hadri, Abdeslam Taleb

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 232, P. 110106 - 110106

Published: Feb. 12, 2025

Language: Английский

Citations

2
A review of the Artificial Intelligence (AI) based techniques for estimating reference evapotranspiration: Current trends and future perspectives DOI
Pooja Goyal, Sunil Kumar, Rakesh Sharda

et al.

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 209, P. 107836 - 107836

Published: April 28, 2023

Language: Английский

Citations

41
Optimization of computational intelligence approach for the prediction of glutinous rice dehydration DOI
Kabiru Ayobami Jimoh, Norhashila Hashim, Rosnah Shamsudin

et al.

Journal of the Science of Food and Agriculture, Journal Year: 2024, Volume and Issue: 104(10), P. 6208 - 6220

Published: March 7, 2024

Five computational intelligence approaches, namely Gaussian process regression (GPR), artificial neural network (ANN), decision tree (DT), ensemble of trees (EoT) and support vector machine (SVM), were used to describe the evolution moisture during dehydration glutinous rice. The hyperparameters models optimized with three strategies: Bayesian optimization, grid search random search. To understand parameters that facilitate model adaptation process, global sensitivity analysis (GSA) was compute impact input variables on output.

Language: Английский

Citations

10
Double-layer home energy management strategy for increasing PV self-consumption and cost reduction through appliances scheduling, EV, and storage DOI Creative Commons
Modawy Adam Ali Abdalla, Min Wang, Bing Wang

et al.

Energy Reports, Journal Year: 2023, Volume and Issue: 10, P. 3494 - 3518

Published: Oct. 13, 2023

Maximizing self-consumption of the photovoltaic (PV) generation is an important factor to increase penetration PV in residential grid. It can improve system profitability, save energy and reduce grid stress. This study proposes a double-layer home management strategy household electricity costs. The first layer involves rescheduling shiftable appliances operate during surplus hours, while second employs multi-objective based on Jaya particle swarm optimization (PSO) algorithms optimize power exchange between storage (ESS) electric vehicle (EV), with smart home. Six different scenarios are simulated investigate role appliances, ESS, EV technology increasing self-consumption. Results scheduling showed that proposed consumption by 17–41% 27–78%, respectively, depending scenarios. found be more effective than single-layer approach, significant economic benefits. method provides efficient solution for improving saving energy, reducing Thus, this contributes development sustainable systems, paving way future research area.

Language: Английский

Citations

22
A novel regenerative braking energy recuperation system for electric vehicles based on driving style DOI

Chengqun Qiu,

Xinshan Wan,

Na Wang

et al.

Energy, Journal Year: 2023, Volume and Issue: 283, P. 129055 - 129055

Published: Sept. 12, 2023

Language: Английский

Citations

19
The projected futures of water resources vulnerability under climate and socioeconomic change in the Yangtze River Basin, China DOI Creative Commons

Xiu Zhang,

Yuqing Tian,

Na Dong

et al.

Ecological Indicators, Journal Year: 2023, Volume and Issue: 147, P. 109933 - 109933

Published: Jan. 25, 2023

Despite being one of the most abundant water resources globally, Yangtze River Basin (YRB) region is facing substantial risks aggravated by climatic and anthropogenic changes. Here, we adopted an integrated framework to investigate plausible futures resource provisioning in YRB under current future conditions on sub-watershed level: (i) a process-based model (InVEST) was used project yield whole nearest (2040–2060) distant (2080–2100) (ii) socio-ecological index developed assess spatio-temporal patterns vulnerability (WRV). Model projections indicated that several water-rich areas southeastern would suffer declining future. While projected increase some drier regions northwest. Future changes basin-level were decrease low emissions scenarios (RCP2.6) combined with sustainability socioeconomic scenario (SSP1). The greatest medium-to-high end (RCP7.0) rather than high-end (RCP8.5) climate change scenario. high WRV distributed sub-watersheds near Taihu Lake source River. Climate have different roles shaping dynamics WRV, precipitation reduction consumption likely result increased levels lower reaches middle reaches, respectively. Our study added new spatial data for vital ecological economic importance Asia. prone should be prioritised management practices. assessment approach this concurrent measures from both subjective objective perspectives could relevant studies exploring how respond environmental

Language: Английский

Citations

15
Exploring the Applicability of Regression Models and Artificial Neural Networks for Calculating Reference Evapotranspiration in Arid Regions DOI Open Access
Mohamed K. Abdel-Fattah, Sameh Kotb Abd‐Elmabod, Zhenhua Zhang

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(21), P. 15494 - 15494

Published: Oct. 31, 2023

Reference evapotranspiration (ET0) is critical in agriculture and irrigation water management, particularly arid semi-arid regions. Our study aimed to develop an accurate efficient model for estimating ET0 using various climatic variables as predictors. This research evaluated two techniques, i.e., stepwise regression artificial neural networks (ANNs), identify the most effective calculating ET0. The models were developed tested based on climate data obtained from whole station of Egypt. CLIMWAT 2.0 program was used acquire Egypt a total 32 stations. software dedicated meteorological database created specifically work with CROPWAT computer program. average spanning 29 years, 1991 2020. utilized compute reference 8, Penman–Monteith equation. results showed that ANN demonstrated superior performance calculations compared other methods, achieving coefficient determination (R2) 0.99 mean absolute percentage error (MAPE) 2.7%. In contrast, yielded R2 0.95 MAPE 8.06. On hand, influential maximum temperature, humidity, solar radiation, wind speed. findings this could be applied fields, such agriculture, irrigation, crop requirements, optimize growth under limited resources global environmental changes. Furthermore, our identifies limitations challenges applying these regions, availability constraints complexity. We discuss need more extensive reliable datasets suggest future directions, including ensemble modeling, remote sensing integration, evaluating change’s impact estimation. Overall, contributes understanding estimation regions provides valuable insights into applicability ANNs. ANNs offers potential advancements resource management agricultural planning, enabling informed decision-making processes.

Language: Английский

Citations

14