Daily Streamflow Forecasting Using Networks of Real-Time Monitoring Stations and Hybrid Machine Learning Methods DOI Open Access
Yue Zhang, Zimo Zhou, Ying Deng

et al.

Water, Journal Year: 2024, Volume and Issue: 16(9), P. 1284 - 1284

Published: April 30, 2024

Considering the increased risk of urban flooding and drought due to global climate change rapid urbanization, imperative for more accurate methods streamflow forecasting has intensified. This study introduces a pioneering approach leveraging available network real-time monitoring stations advanced machine learning algorithms that can accurately simulate spatial–temporal problems. The Spatio-Temporal Attention Gated Recurrent Unit (STA-GRU) model is renowned its computational efficacy in events with forecast horizon 7 days. novel integration groundwater level, precipitation, river discharge as predictive variables offers holistic view hydrological cycle, enhancing model’s accuracy. Our findings reveal 7-day period, STA-GRU demonstrates superior performance, notable improvement mean absolute percentage error (MAPE) values R-square (R2) alongside reductions root squared (RMSE) (MAE) metrics, underscoring generalizability reliability. Comparative analysis seven conventional deep models, including Long Short-Term Memory (LSTM), Convolutional Neural Network LSTM (CNNLSTM), (ConvLSTM), (STA-LSTM), (GRU), GRU (CNNGRU), STA-GRU, confirms power STA-LSTM models when faced long-term prediction. research marks significant shift towards an integrated deep-learning forecasting, emphasizing importance spatially temporally encompassing variability within watershed’s stream network.

Language: Английский

A Comprehensive Survey of Machine Learning Methodologies with Emphasis in Water Resources Management DOI Creative Commons

Maria Drogkoula,

Konstantinos Kokkinos, Nicholas Samaras

et al.

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(22), P. 12147 - 12147

Published: Nov. 8, 2023

This paper offers a comprehensive overview of machine learning (ML) methodologies and algorithms, highlighting their practical applications in the critical domain water resource management. Environmental issues, such as climate change ecosystem destruction, pose significant threats to humanity planet. Addressing these challenges necessitates sustainable management increased efficiency. Artificial intelligence (AI) ML technologies present promising solutions this regard. By harnessing AI ML, we can collect analyze vast amounts data from diverse sources, remote sensing, smart sensors, social media. enables real-time monitoring decision making applications, including irrigation optimization, quality monitoring, flood forecasting, demand enhance agricultural practices, distribution models, desalination plants. Furthermore, facilitates integration, supports decision-making processes, enhances overall sustainability. However, wider adoption faces challenges, heterogeneity, stakeholder education, high costs. To provide an management, research focuses on core fundamentals, major (prediction, clustering, reinforcement learning), ongoing issues offer new insights. More specifically, after in-depth illustration algorithmic taxonomy, comparative mapping all specific tasks. At same time, include tabulation works along with some concrete, yet compact, descriptions objectives at hand. leveraging tools, develop plans address world’s supply concerns effectively.

Language: Английский

Citations

51
Alternate pathway for regional flood frequency analysis in data-sparse region DOI
Nikunj K. Mangukiya, Ashutosh Sharma

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 629, P. 130635 - 130635

Published: Jan. 17, 2024

Language: Английский

Citations

25
Novel approach for the LULC change detection using GIS & Google Earth Engine through spatiotemporal analysis to evaluate the urbanization growth of Ahmedabad city DOI Creative Commons
Anant Patel,

Daivee Vyas,

Nirali Chaudhari

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101788 - 101788

Published: Jan. 12, 2024

Changes in Land Use and Cover (LULC) have a significant impact on both urban environmental planning, especially the context of rapidly urbanising areas. The largest city state Gujarat, Ahmedabad, has experienced substantial growth. Utilising powerful tools Geographic Information System (GIS) Google Earth Engine (GEE), this study uses thorough methodology to track examine changes LULC over last ten years. Modifications light fast urbanisation cycle. This comprehensive approach monitor analyze Landsat imagery past years, leveraging capabilities GIS. Important insights into patterns are revealed by analysing from Ahmedabad 2013 2023. Pre-processing with GIS GEE, accuracy evaluation, classification satellite images all included methodology. With notable 0.85 Kappa 89 % classification, resulting classifications cover settlements, vegetation, water bodies, arid land, other relevant features. Results show that previous seen noteworthy decrease agricultural lands 13.74 reduction barren areas 4.78 %. Meanwhile, total shown expansion 23.56 is because it highlights how reduces vegetation cover. results will helpful for planning strategies take changing dynamics account.

Language: Английский

Citations

23
Optimizing feature selection with gradient boosting machines in PLS regression for predicting moisture and protein in multi-country corn kernels via NIR spectroscopy DOI Creative Commons
Runyu Zheng, Yuyao Jia,

Chidanand Ullagaddi

et al.

Food Chemistry, Journal Year: 2024, Volume and Issue: 456, P. 140062 - 140062

Published: June 12, 2024

Differences in moisture and protein content impact both nutritional value processing efficiency of corn kernels. Near-infrared (NIR) spectroscopy can be used to estimate kernel composition, but models trained on a few environments may underestimate error rates bias. We assembled samples from diverse international NIR with chemometrics partial least squares regression (PLSR) determine protein. The potential five feature selection methods improve prediction accuracy was assessed by extracting sensitive wavelengths. Gradient boosting machines (GBMs), particularly CatBoost LightGBM, were found effectively select crucial wavelengths for (1409, 1900, 1908, 1932, 1953, 2174 nm) (887, 1212, 1705, 1891, 2097, 2456 nm). SHAP plots highlighted significant wavelength contributions model prediction. These results illustrate GBMs' effectiveness engineering agricultural food sector applications, including developing multi-country global calibration

Language: Английский

Citations

22
River stream flow prediction through advanced machine learning models for enhanced accuracy DOI Creative Commons
Naresh Kedam, Deepak Kumar Tiwari, Vijendra Kumar

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102215 - 102215

Published: May 4, 2024

The Narmada River basin, a significant water resource in central India, plays crucial role supporting agricultural, industrial, and domestic supply. Effective management of this basin requires accurate streamflow forecasting, which has become increasingly important. This study delves into forecasting using historical data from five major river stations, covering the upper reaches East middle sections. dataset spans 1978 to 2020 undergoes rigorous screening preparation, including normalization StandardScaler. research adopts comprehensive approach, developing models for training on 70% data, validation most current 15%, testing against future targets with another 15% data. To achieve precise predictions, suite machine learning is employed, CatBoost, LGBM (Light Gradient Boosting Machine), Random Forest, XGBoost. Performance evaluation these relies key indices such as mean squared error (MSE), absolute (MAE), root square (RMSE), percent (RMSPE), normalized (NRMSE), R-squared (R2). Notably, among models, Forest emerges robust prediction, showcasing its effectiveness handling complexities hydrological forecasting. contributes significantly field by providing insights performance various models. findings not only enhance our understanding watershed dynamics but also highlight pivotal that can play improving sustainable management.

Language: Английский

Citations

20
Reconstructing Long-Term Daily Streamflow Data at the Discontinuous Monitoring Station in the Ungauged Transboundary Basin Using Machine Learning DOI
Vinh Ngoc Tran, Thi Thuy Hang Nguyen,

Hai Van Khuong

et al.

Water Resources Management, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 17, 2025

Language: Английский

Citations

3
Improving flood forecasting in Narmada river basin using hierarchical clustering and hydrological modelling DOI Creative Commons
Darshan Mehta,

Jay Dhabuwala,

S. M. Yadav

et al.

Results in Engineering, Journal Year: 2023, Volume and Issue: 20, P. 101571 - 101571

Published: Nov. 7, 2023

The purpose of the study was to use hierarchical clustering and Thiessen polygon algorithms identify significant rain gauge stations for flood forecasting at Sardar Sarovar Dam. Rainfall data from 2010 2018 utilized analyze catchment region between Omkareshwar Dam identified two clusters with similar rainfall patterns divided area into seventeen regions using polygons. land map showed that mostly covered by crop lands, soil three types sedimentary claystone soil. A hydrological model, Hydrologic Engineering Center – Modelling System (HEC-HMS), used rainfall-runoff modeling, computed runoff compared observed discharge inflow Regression analysis performed assess performance results a good correlation estimated values 2012 2016. concludes existing network is sufficient forecasting, developed model along method can provide more accurate predictions flow. highlights importance selecting suitable reliable in flood-prone basins. findings be useful future prediction area.

Language: Английский

Citations

36
Simulating the Hydrological Processes under Multiple Land Use/Land Cover and Climate Change Scenarios in the Mahanadi Reservoir Complex, Chhattisgarh, India DOI Open Access
Shashikant Verma, Mani Kant Verma, A. D. Prasad

et al.

Water, Journal Year: 2023, Volume and Issue: 15(17), P. 3068 - 3068

Published: Aug. 27, 2023

Land use/land cover (LULC) and climate are two crucial environmental factors that impact watershed hydrology worldwide. The current study seeks to comprehend how the evolving LULC patterns impacting of Mahanadi Reservoir catchment. A semi-distributed Soil Water Assessment Tool (SWAT) model was utilized simulate various water balance elements. Twelve distinct scenarios were developed by combining three different climatic data periods (1985–1996, 1997–2008, 2009–2020) with four sets land use maps (1985, 1995, 2005, 2014). SWAT demonstrated strong performance in simulating monthly stream flows throughout calibration validation phases. reveals changes have a effect on environment. Specifically, lead heightened streamflow reduced evapotranspiration (ET). These mainly attributed amplified urbanization diminished presence bodies, forest cover, barren within combined change shifts complex interactions. Therefore, present offers an understanding over past few decades influenced hydrological behavior catchment Chhattisgarh. findings this potential offer advantages governmental policymakers, resource engineers, planners seeking effective strategies for management. would be particularly relevant context ecological regions similar those In addition, rational regulatory framework is essential assisting stakeholders managing resources appropriately developing entire

Language: Английский

Citations

32
An integration of geospatial and fuzzy-logic techniques for multi-hazard mapping DOI Creative Commons

Mausmi Gohil,

Darshan Mehta, Mohamedmaroof Shaikh

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101758 - 101758

Published: Jan. 10, 2024

A hazard is a natural occurrence that might harm humans, animals or the environment. It may cause loss of life, illness other health consequences, property damage, social and economic crisis environmental degradation. Many places world are at risk from one more disasters. Although many studies have concentrated on single hazards, there need for integrated evaluations multi-hazards effective land management. selection datasets methods, such as meteorological data, satellite images, GIS, were used to create assessment maps. The parameters multi-hazard mainly considered rainfall, slope, elevation, use/land cover map in GIS For particular region, can be produced by integrating maps several assessments. objective this study an integration geospatial fuzzy-logic techniques mapping. Extensive parts Gujarat state (India) experience wide range hazards: floods, soil erosion, drought, earthquakes. This research creates evaluates individual group visualize spatial variation hazards state, India. calculated four been categorised into five classes: very-low, low, moderate, high, very high. multi has classified sixteen classes using unsupervised. aims improve disaster preparedness, enhance management, guide decision-making reduction. helpful future engineers, planners, local governments field planning

Language: Английский

Citations

16
Long-term streamflow forecasting in data-scarce regions: Insightful investigation for leveraging satellite-derived data, Informer architecture, and concurrent fine-tuning transfer learning DOI
Fatemeh Ghobadi, Zaher Mundher Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬,

Doosun Kang

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 631, P. 130772 - 130772

Published: Feb. 2, 2024

Language: Английский

Citations

16