Spatio-temporal deep learning model for accurate streamflow prediction with multi-source data fusion

Environmental Modelling & Software, Год журнала: 2024, Номер 178, С. 106091 - 106091

Опубликована: Май 28, 2024

Язык: Английский

---

A compound approach for ten-day runoff prediction by coupling wavelet denoising, attention mechanism, and LSTM based on GPU parallel acceleration technology

Earth Science Informatics, Год журнала: 2024, Номер 17(2), С. 1281 - 1299

Опубликована: Янв. 10, 2024

Язык: Английский

---

A comparative study of data-driven models for runoff, sediment, and nitrate forecasting

Journal of Environmental Management, Год журнала: 2023, Номер 341, С. 118006 - 118006

Опубликована: Май 8, 2023

Язык: Английский

---

Robust Runoff Prediction With Explainable Artificial Intelligence and Meteorological Variables From Deep Learning Ensemble Model

Water Resources Research, Год журнала: 2023, Номер 59(9)

Опубликована: Сен. 1, 2023

Abstract Accurate runoff forecasting plays a vital role in issuing timely flood warnings. Whereas, previous research has primarily focused on historical and precipitation variability while disregarding other factors' influence. Additionally, the prediction process of most machine learning models is opaque, resulting low interpretability model predictions. Hence, this study develops an ensemble deep to forecast from three hydrological stations. Initially, time‐varying filtered based empirical mode decomposition employed decompose series into several internal functions (IMFs). Subsequently, complexity each IMF component evaluated by multi‐scale permutation entropy, IMFs are classified high‐ low‐frequency portions entropy values. Considering high‐frequency still exhibit great volatility, robust local mean adopted perform secondary portions. Then, meteorological variables processed Relief algorithm variance inflation factor features as inputs, individual subsequences preliminary outputs bidirectional gated recurrent unit extreme models. Random forests (RF) introduced nonlinear predicted sub‐models obtain final results. The proposed outperforms various evaluation metrics. Meanwhile, due opaque nature models, shapley assess contribution selected variable long‐term trend runoff. could serve essential reference for precise warning.

Язык: Английский

---

Improving the forecasting accuracy of monthly runoff time series of the Brahmani River in India using a hybrid deep learning model

Journal of Water and Climate Change, Год журнала: 2023, Номер 15(1), С. 139 - 156

Опубликована: Дек. 15, 2023

Abstract Accurate prediction of monthly runoff is critical for effective water resource management and flood forecasting in river basins. In this study, we developed a hybrid deep learning (DL) model, Fourier transform long short-term memory (FT-LSTM), to improve the accuracy discharge time series Brahmani basin at Jenapur station. We compare performance FT-LSTM with three popular DL models: LSTM, recurrent neutral network, gated unit, considering different lag periods (1, 3, 6, 12). The period, representing interval between observed data points predicted points, crucial capturing temporal relationships identifying patterns within hydrological data. results study show that model consistently outperforms other models across all terms error metrics. Furthermore, demonstrates higher Nash–Sutcliffe efficiency R2 values, indicating better fit actual values. This work contributes growing field forecasting. proves improving forecasts offers promising solution decision-making processes.

Язык: Английский

---

Prediction of agricultural drought index in a hot and dry climate using advanced hybrid machine learning

Ain Shams Engineering Journal, Год журнала: 2024, Номер 15(5), С. 102686 - 102686

Опубликована: Фев. 16, 2024

Drought monitoring and forecasting are essential for efficient water resources management. The present research aims to provide a reliable prediction of the effective Reconnaissance Index (eRDI) based on seven evaporation stations in southern Baluchestan sub-basin Iran. To achieve this purpose, artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR) machine learning methods used combined with marine predator optimization algorithm (MPA) enhance efficiency. have been performed time scales 1-, 3-, 6-months intervals. results demonstrated superiority ANFIS-MPA over SVR-MPA ANN-MPA approaches. In addition, as scale increased, accuracy all models improved. best were eRDI 6-month at Kajdar Sarbaz station by (MAE = 0.33, NSE 0.83, R2 0.99), 0.36, 0.78, 0.85) 0.37, 0.72, 0.83).

Язык: Английский

---

Runoff prediction using a multi-scale two-phase processing hybrid model

Stochastic Environmental Research and Risk Assessment, Год журнала: 2025, Номер unknown

Опубликована: Янв. 19, 2025

Язык: Английский

---

Advanced Framework for Predicting Rainfall-Runoff: Comparative Evaluation of AI Models for Enhanced Forecasting Accuracy

Water Resources Management, Год журнала: 2025, Номер unknown

Опубликована: Янв. 17, 2025

Язык: Английский

---

A novel application of transformer neural network (TNN) for estimating pan evaporation rate

Applied Water Science, Год журнала: 2022, Номер 13(2)

Опубликована: Дек. 30, 2022

Abstract For decision-making in farming, the operation of dams and irrigation systems, as well other fields water resource management hydrology, evaporation, a key activity throughout universal hydrological processes, entails efficient techniques for measuring its variation. The main challenge creating accurate dependable predictive models is evaporation procedure's non-stationarity, nonlinearity, stochastic characteristics. This work examines, first time, transformer-based deep learning architecture prediction four different Malaysian regions. effectiveness proposed (DL) model, signified TNN, evaluated against two competitive reference DL models, namely Convolutional Neural Network Long Short-Term Memory, with regards to various statistical indices using monthly-scale dataset collected from meteorological stations 2000–2019 period. Using variety input variable combinations, impact every data on E p forecast also examined. performance assessment metrics demonstrate that compared benchmark frameworks examined this work, developed TNN technique was more precise modelling monthly loss owing evaporation. In terms effectiveness, enhanced self-attention mechanism, outperforms demonstrating potential use forecasting Relating application, model created projection offers estimate due can thus be used management, agriculture planning based irrigation, decrease fiscal economic losses farming related industries where consistent supervision estimation are considered necessary viable living economy.

Язык: Английский

---

Hydrological model parameter regionalization: Runoff estimation using machine learning techniques in the Tha Chin River Basin, Thailand

MethodsX, Год журнала: 2024, Номер 13, С. 102792 - 102792

Опубликована: Июнь 7, 2024

Understanding hydrological processes necessitates the use of modeling techniques due to intricate interactions among environmental factors. Estimating model parameters remains a significant challenge in runoff for ungauged catchments. This research evaluates Soil and Water Assessment Tool's capacity simulate behaviors Tha Chin River Basin with an emphasis on predictions from regionalization gauged basin, Mae Khlong Basin. Historical data 1993 2017 were utilized calibration, followed by validation using 2018 2022.•Calibration results showed SWAT model's reasonable accuracy, R² = 0.85, 0.64, indicating satisfactory match between observed simulated runoff.•Utilizing Machine Learning (ML) parameter revealed nuanced differences performance. The Random Forest (RF) exhibited 0.60 Artificial Neural Networks (ANN) slightly improved upon RF, showing 0.61 while Support Vector (SVM) demonstrated highest overall performance, 0.63.•This study highlights effectiveness ML predicting catchments, emphasizing their potential enhance accuracy. Future should focus integrating these methodologies various basins improving collection better

Язык: Английский

---