Applications of XGBoost in water resources engineering: A systematic literature review (Dec 2018–May 2023)

Environmental Modelling & Software, Год журнала: 2024, Номер 174, С. 105971 - 105971

Опубликована: Фев. 10, 2024

Язык: Английский

---

Future trends of reference evapotranspiration in Sicily based on CORDEX data and Machine Learning algorithms

Agricultural Water Management, Год журнала: 2023, Номер 280, С. 108232 - 108232

Опубликована: Фев. 15, 2023

In years of increasing impact climate change effects, a reliable characterization the spatiotemporal evolutionary dynamics evapotranspiration can enable significant improvement in water resource management, especially as regards irrigation activities. Sicily, an insular region Southern Italy, has exceptionally valuable agricultural production and high needs. this study, ETo reference Sicily was first evaluated on basis historical future parameters, referring for values to two scenarios characterized by different Representative Concentration Pathways: RCP 4.5 8.5. Then, Hierarchical algorithm used divide into three homogeneous regions, each specific features. addition, some Machine Learning (ML) algorithms were develop forecasting models based only data. Support Vector Regression (SVR) predict Tmin Tmax, while ensemble model Multilayer Perceptron (MLP) M5P Tree developed forecasting. Predictions made with MLP-M5P compared computed 8.5 scenarios. During forecast period, from 2001 2091, increases observed all clusters. For cluster C1, along coast, percentage 7.52%, 14.64% 10.78%, 4.5, 8.5, MLP-M5P, respectively, while, C3, inland, higher equal 8.12%, 16.71%, 14.98%, respectively. The led intermediate trends between showing correlation latter (R2 0.93 0.98). approach, both clustering algorithms, provided comprehensive analysis evapotranspiration, detection regions and, at same time, evaluation trends, coastal inland areas.

Язык: Английский

---

Ensemble learning using multivariate variational mode decomposition based on the Transformer for multi-step-ahead streamflow forecasting

Journal of Hydrology, Год журнала: 2024, Номер 636, С. 131275 - 131275

Опубликована: Май 7, 2024

Язык: Английский

---

A multi-scale analysis method with multi-feature selection for house prices forecasting

Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 112779 - 112779

Опубликована: Янв. 1, 2025

Язык: Английский

---

A review of the Artificial Intelligence (AI) based techniques for estimating reference evapotranspiration: Current trends and future perspectives

Computers and Electronics in Agriculture, Год журнала: 2023, Номер 209, С. 107836 - 107836

Опубликована: Апрель 28, 2023

Язык: Английский

---

Development of wavelet-based Kalman Online Sequential Extreme Learning Machine optimized with Boruta-Random Forest for drought index forecasting

Engineering Applications of Artificial Intelligence, Год журнала: 2022, Номер 117, С. 105545 - 105545

Опубликована: Ноя. 10, 2022

Язык: Английский

---

Short-term prediction of reference crop evapotranspiration based on machine learning with different decomposition methods in arid areas of China

Agricultural Water Management, Год журнала: 2023, Номер 279, С. 108175 - 108175

Опубликована: Фев. 7, 2023

This paper established hybrid prediction models based on variational mode decomposition (VMD), empirical (EMD), and ensemble (EEMD) combined with the backpropagation neural network model (BPNN) to improve accuracy of reference crop evapotranspiration (ET0) time series characteristics nonlinearity instability. The daily ET0 data 11 representative stations in Xinjiang from 1993 2016 were selected for training testing compared results support vector regression (SVR) gradient boosting tree (GBRT) as two machine learning models. indicated superiority VMD-BPNN EMD-BPNN EEMD-BPNN terms stability, root mean square error (RMSE) = 0.405 mm/d, absolute (MAE) 0.268 coefficient determination (R2) 0.979. When employing forecast seven days, RMSE Nash-Sutcliffe efficiency (NSE) 0.588 mm/d 0.952, respectively, high precision reliability. was significantly higher than that single models, such BPNN, SVR, GBRT. MAE values more 60% smaller GBRT R2 NSE approximately 18% respectively. demonstrates effectiveness VMD method reducing non-stationarity original data. BPNN predicted decomposed series, stability enhanced. indicates reliability its capability Xinjiang.

Язык: Английский

---

Metaheuristic approaches for prediction of water quality indices with relief algorithm-based feature selection

Ecological Informatics, Год журнала: 2023, Номер 75, С. 102122 - 102122

Опубликована: Май 9, 2023

Язык: Английский

---

Monthly sodium adsorption ratio forecasting in rivers using a dual interpretable glass-box complementary intelligent system: Hybridization of ensemble TVF-EMD-VMD, Boruta-SHAP, and eXplainable GPR

Expert Systems with Applications, Год журнала: 2023, Номер 237, С. 121512 - 121512

Опубликована: Сен. 13, 2023

Язык: Английский

---

Quantitative improvement of streamflow forecasting accuracy in the Atlantic zones of Canada based on hydro-meteorological signals: A multi-level advanced intelligent expert framework

Ecological Informatics, Год журнала: 2024, Номер 80, С. 102455 - 102455

Опубликована: Янв. 4, 2024

Developing reliable streamflow forecasting models is critical for hydrological tasks such as improving water resource management, analyzing river patterns, and flood forecasting. In this research, the first time, an emerging multi-level TOPSIS (technique order preference by similarity to ideal solution) based hybridization comprised of Boruta classification regression tree (Boruta-CART) feature selection, multivariate variational mode decomposition (MVMD), a hybrid Convolutional Neural Network (CNN) Bidirectional Gated Recurrent Unit (CNN-BiGRU) deep learning was adopted multi-temporal (one three days ahead) forecast daily in Rivers Prince Edward Island, Canada. For aim, step, Boruta-CART selection technique determines most effective lagged components among all antecedent two-day information (i.e., t-1 t-2) hydro-meteorological features (from 2015 2020), including level, mean air temperature, heat degree days, total precipitation, dew point relative humidity Bear Winter Afterwards, (MVMD) decomposes input time series decrease complexity non-linearity non-stationary ones before feeding (DL) models. Here, CNN-GRU employed primary DL model, along with kernel extreme machine method (KELM), random function link (RVFL), CNN bidirectional recurrent neural network (CNN-BiRNN) comparative A scheme applying several performance measures like correlation coefficient (R), root square error (RMSE), reliability designed robustness assessment (MVM-CNN-BiGRU, MVM-CNN-BiRNN, MVM-RVFL, MVM-KELM) standalone The computational outcomes revealed that River, MVM-CNN-BiGRU, owing its best day ahead: score 1, R = 0.960, RMSE 0.098, 65.082; 0.999, 0.924, 0.33) outperformed other models, followed MVM-KELM, respectively. Moreover, MVM-CNN-BiGRU terms (one-day 0.890, 0.955, 0.274, 34.004; three-days 0.686, 0.330) superior provided expert system could be vital local decision-making process, absence modeling, during seasons reduce damage residential areas.

Язык: Английский

---