Comparative Analysis of Convolutional Neural Network-Long Short-Term Memory, Sparrow Search Algorithm-Backpropagation Neural Network, and Particle Swarm Optimization-Extreme Learning Machine Models for the Water Discharge of the Buzău River, Romania

Water, Journal Year: 2024, Volume and Issue: 16(2), P. 289 - 289

Published: Jan. 15, 2024

Modeling and forecasting the river flow is essential for management of water resources. In this study, we conduct a comprehensive comparative analysis different models built monthly discharge Buzău River (Romania), measured in upper part river’s basin from January 1955 to December 2010. They employ convolutional neural networks (CNNs) coupled with long short-term memory (LSTM) networks, named CNN-LSTM, sparrow search algorithm backpropagation (SSA-BP), particle swarm optimization extreme learning machines (PSO-ELM). These are evaluated based on various criteria, including computational efficiency, predictive accuracy, adaptability training sets. The obtained applying CNN-LSTM stand out as top performers, demonstrating superior efficiency high especially when set containing data series 1984 (putting Siriu Dam operation) September 2006 (Model type S2). This research provides valuable guidance selecting assessing prediction models, offering practical insights scientific community real-world applications. findings suggest that Model S2 preferred choice forecast predictions due its speed accuracy. S (considering recorded 2006) recommended secondary option. S1 (with period 1955–December 1983) suitable other unavailable. study advances field by presenting precise these their respective strengths

Language: Английский

---

An evolutionary hybrid method based on particle swarm optimization algorithm and extreme gradient boosting for short-term streamflow forecasting

Acta Geophysica, Journal Year: 2024, Volume and Issue: 72(5), P. 3661 - 3681

Published: Feb. 25, 2024

Language: Английский

---

Monthly Runoff Prediction Via Mode Decomposition-Recombination Technique

Water Resources Management, Journal Year: 2023, Volume and Issue: 38(1), P. 269 - 286

Published: Dec. 1, 2023

Language: Английский

---

Extreme learning machine coupled with Heuristic algorithms for daily streamflow modeling at Lake Ziway Watershed, Ethiopia

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133345 - 133345

Published: April 1, 2025

Language: Английский

---

Hybrid deep learning models for multi-ahead river water level forecasting

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(4), P. 3021 - 3037

Published: May 16, 2024

Language: Английский

---

Enhancing the streamflow simulation of a process-based hydrological model using machine learning and multi-source data

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102755 - 102755

Published: Aug. 3, 2024

Streamflow simulation is crucial for flood mitigation, ecological protection, and water resource planning. Process-based hydrological models machine learning algorithms are the mainstream tools streamflow simulation. However, their inherent limitations, such as time-consuming large data requirements, make achieving high-precision simulations challenging. This study developed a hybrid approach to simultaneously improve accuracy computational efficiency of simulation, which integrates Block-wise use TOPMODEL (BTOP) model into eXtreme Gradient Boosting (XGBoost), i.e., BTOP_XGB. In this approach, BTOP generates simulated using Latin hypercube sampling algorithm instead calibration reduce costs. Then, XGBoost combines with multi-source errors. which, serval input variable selection employed choose relevant inputs remove redundant information model. The validated compared standalone at three stations in Jialing River basin, China. results show that performance BTOP_XGB significantly better than models. NSE Beibei, Xiaoheba, Luoduxi increases by 54%, 21%, 83%, respectively. Meanwhile, time saved >90% original calibrated BTOP. less affected parameter sample sizes amounts, demonstrating robustness simplifies complexity enhances stability learning, jointly improving reliability provides potential shortcut over basins areas or limited observed data.

Language: Английский

---

Assessing Objective Functions in Streamflow Prediction Model Training Based on the Naïve Method

Water, Journal Year: 2024, Volume and Issue: 16(5), P. 777 - 777

Published: March 5, 2024

Reliable streamflow forecasting is a determining factor for water resource planning and flood control. To better understand the strengths weaknesses of newly proposed methods in facilitate comparisons different research results, we test simple, universal, efficient benchmark method, namely, naïve short-term prediction. Using assess performance long memory models trained with objective functions, including mean squared error (MSE), root (RMSE), Nash–Sutcliffe efficiency (NSE), Kling–Gupta (KGE), absolute (MAE). The experiments over 273 watersheds show that method attains good (NSE > 0.5) 88%, 65%, 52% at lead times 1 day, 2 days, 3 respectively. Through benchmarking by find LSTM squared-error-based i.e., MSE, RMSE, NSE, KGE, perform poorly low flow forecasting. This because they are more influenced training samples high flows than those during model process. For comprehensive modeling without special demand orientation, recommend application MAE instead metric as function. In addition, it also feasible to logarithmic transformation on data. work underscores critical importance appropriately selecting functions training/calibration, shedding light how effectively evaluate forecast models.

Language: Английский

---

Revisiting the relationship between state governance, employment, water quality and agricultural productivity in N-11 countries

Journal of Agribusiness in Developing and Emerging Economies, Journal Year: 2024, Volume and Issue: unknown

Published: May 22, 2024

Purpose The agriculture sector is crucial for all economies, especially the developing ones. However, agricultural production influenced by government intervention, which outshines significant role of good governance indicators in productivity. In addition to this, major climate changes also posed various challenges and led water shortages yield losses. Thus affecting production. this paper, we address issue determining association between state productivity N-11 countries. Design/methodology/approach Panel data have been collected from 2000 2021 through Governance Indicator, World Development Indicator Bank databases. For analysis, researcher has utilized autoregressive distributed lag (ARDL) estimations. Findings Through ARDL estimations, it suggested that corruption (CC), employment (EAG), political stability violence absence (PS), rule law (RL), regulatory equality (RQ) quality (WQ) significantly impact (AGP) long run. short run, RL on AGP significant. Research limitations/implications This study follows method collection secondary sources, hinders effectiveness as, basis respective data, potential get specific answers research questions affected. Also, examines context countries 2021, exerts a geographical limitation. While exploring productivity, neglects internal aspects implementing policies firms. Originality/value On practical grounds, demonstrated encourages firms keenly consider gain sustainable development. Moreover, efficiently follow efficient outcomes shown infrastructure can enhance Besides, as per results, positively impacts productivity; thus, relevant steps be taken improve water.

Language: Английский

---

Multiple-model based prediction of weekly discharge of the Brahmaputra-Jamuna by assimilating antecedent hydrological regime

Geocarto International, Journal Year: 2024, Volume and Issue: 39(1)

Published: Jan. 1, 2024

Language: Английский

---