A Review of Deep Learning Applications for Sustainable Water Resource Management DOI Creative Commons
Tipon Tanchangya, Asif Raihan, Junaid Rahman

et al.

Global Sustainability Research, Journal Year: 2024, Volume and Issue: unknown, P. 48 - 73

Published: Nov. 24, 2024

Deep learning (DL) techniques and algorithms have the capacity to significantly impact world economies, ecosystems, communities. DL technologies been utilized in development administration of urban structures. However, there exists a dearth literature reviewing present level these applications exploring potential directions which can address water challenges. This study aims review demand projections, leakage detection localization, drainage defect blockage, cyber security wealth surveillance, wastewater recycling management, safety prediction, rainfall conversation, irrigation regulation. The application is currently its early stages. Most studies adopted standard networks, simulated information, experimental or prototype settings evaluate efficacy approaches. no reported instances practical adoption. Compared other reviewed problems, being implemented practically daily operations handling facilities. major challenges for deployment management include algorithmic development, multi-agent platforms, virtual clones, data quality availability, security, context-aware analysis, training efficiency. We validate our by using several case that employ treatment. Prospective exploration systems are anticipated advance toward increased cognition flexibility. research encourage further utilizing feasible usage digitalization global sector.

Language: Английский

Advanced Temporal Deep Learning Framework for Enhanced Predictive Modeling in Industrial Treatment Systems DOI Creative Commons

S Ramya,

S Srinath,

Pushpa Tuppad

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104158 - 104158

Published: Jan. 1, 2025

Language: Английский

Citations

1
CNN vs. LSTM: A Comparative Study of Hourly Precipitation Intensity Prediction as a Key Factor in Flood Forecasting Frameworks DOI Creative Commons
Isa Ebtehaj, Hossein Bonakdari

Atmosphere, Journal Year: 2024, Volume and Issue: 15(9), P. 1082 - 1082

Published: Sept. 6, 2024

Accurate precipitation intensity forecasting is crucial for effective flood management and early warning systems. This study evaluates the performances of convolutional neural network (CNN) long short-term memory (LSTM) models in predicting hourly using data from Sainte Catherine de la Jacques Cartier station near Québec City. The predict levels one to six hours ahead, which are categorized into slight, moderate, heavy, very heavy intensities. Our methodology involved gathering data, defining input combinations multistep ahead forecasting, employing CNN LSTM models. these were assessed through qualitative quantitative evaluations. key findings reveal that model excelled (1HA 2HA) long-term (3HA 6HA) with higher R2 (up 0.999) NSE values 0.999), while was more computationally efficient, lower AICc (e.g., −16,041.1 1HA). error analysis shows demonstrated precision categories, a relative error, whereas performed better slight moderate categories. outperformed minor- high-intensity events, but exhibited performance significant events shorter lead times. Overall, both adequate, providing accuracy extended forecasts offering efficiency immediate predictions, highlighting their complementary roles enhancing systems strategies.

Language: Английский

Citations

3
Spatial-Temporal Evaluation and Prediction of Water Resources Carrying Capacity in the Xiangjiang River Basin Using County Units and Entropy Weight TOPSIS-BP Neural Network DOI Open Access
Jiacheng Wang, Zhixiang Wang,

Zeding Fu

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(18), P. 8184 - 8184

Published: Sept. 19, 2024

To improve the water resources carrying capacity of Xiangjiang River Basin and achieve sustainable development, this article evaluates predicts Basin’s level based on county-level units. This takes 44 units in as evaluation target, selects TOPSIS entropy weight method to determine weights, calculates sample, uses a BP neural network model calculate predicted for next 5 years, adds GIS spatiotemporal analysis.(1) The has remained relatively stable long period, with overloaded areas being majority. (2) There are significant spatial differences resources: Zixing City, located upstream tributary, is far ahead due its possession Dongjiang Reservoir; middle lower reaches (northern region) generally higher than that upper (southern region). (3) According prediction, will maintain development trend 2022, while such Changsha City be critical state, other counties cities an state.This study important references value early warning work related research, providing scientific systematic strong support resource management planning Hunan Province regions.

Language: Английский

Citations

3
Carbonaceous adsorbents in wastewater treatment: From mechanism to emerging application DOI
Xiao Liu, Qinglan Hao,

Maohong Fan

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 955, P. 177106 - 177106

Published: Nov. 1, 2024

Language: Английский

Citations

2
Smart Water Management and Resource Conservation DOI
Rajeev Kumar, Arti Saxena

Advances in electronic government, digital divide, and regional development book series, Journal Year: 2024, Volume and Issue: unknown, P. 235 - 262

Published: Nov. 15, 2024

Water is essential to every living being. management and resource conservation very important provide safe clean water all. Resources of have been polluted contaminated due increasing population urbanization. Irrigation hydropower reservoir are other sources responsible for stress on earth. The main aim smart cities urban development everyone at low cost in sustainable ways. Thus, it necessary conserve resources manage the smartly. Use non-conventional irrigation, aquaculture aquifer recharge one solutions decrease use fresh these purposes. Machine learning solution managing conserving resources. Various machine models applied prediction tasks. However, deep categorization regression task. chapter objective cities.

Language: Английский

Citations

1
A Review of Deep Learning Applications for Sustainable Water Resource Management DOI Creative Commons
Tipon Tanchangya, Asif Raihan, Junaid Rahman

et al.

Global Sustainability Research, Journal Year: 2024, Volume and Issue: unknown, P. 48 - 73

Published: Nov. 24, 2024

Deep learning (DL) techniques and algorithms have the capacity to significantly impact world economies, ecosystems, communities. DL technologies been utilized in development administration of urban structures. However, there exists a dearth literature reviewing present level these applications exploring potential directions which can address water challenges. This study aims review demand projections, leakage detection localization, drainage defect blockage, cyber security wealth surveillance, wastewater recycling management, safety prediction, rainfall conversation, irrigation regulation. The application is currently its early stages. Most studies adopted standard networks, simulated information, experimental or prototype settings evaluate efficacy approaches. no reported instances practical adoption. Compared other reviewed problems, being implemented practically daily operations handling facilities. major challenges for deployment management include algorithmic development, multi-agent platforms, virtual clones, data quality availability, security, context-aware analysis, training efficiency. We validate our by using several case that employ treatment. Prospective exploration systems are anticipated advance toward increased cognition flexibility. research encourage further utilizing feasible usage digitalization global sector.

Language: Английский

Citations

0