A Comparative Assessment of Machine Learning and Deep Learning Models for the Daily River Streamflow Forecasting

Water Resources Management, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 29, 2024

Language: Английский

---

A Comparative Approach to Understand the Performance of CMIP6 Models for Maximum Temperature near Tropic of Cancer Using Multiple Machine Learning Ensembles

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

Published: Feb. 11, 2025

Language: Английский

---

Comparability of NARX model to SWAT model in simulating future water resources scenarios using CMIP6 climate model outputs over UASB, Ethiopia

Stochastic Environmental Research and Risk Assessment, Journal Year: 2025, Volume and Issue: unknown

Published: March 24, 2025

Language: Английский

---

Divergent path: isolating land use and climate change impact on river runoff

Frontiers in Environmental Science, Journal Year: 2024, Volume and Issue: 12

Published: Feb. 1, 2024

Water resource management requires a thorough examination of how land use and climate change affect streamflow; however, the potential impacts land-use changes are frequently ignored. Therefore, principal goal this study is to isolate effects anticipated on streamflow at Indus River, Besham, Pakistan, using Soil Assessment Tool (SWAT). The multimodal ensemble (MME) 11 general circulation models (GCMs) under two shared socioeconomic pathways (SSPs) 245 585 was computed Taylor skill score (TSS) rating metric (RM). Future predicted cellular automata artificial neural network (CA-ANN). were assessed various SSPs scenarios. To calibrate validate SWAT model, historical record (1991–2013) divided into following parts: calibration (1991–2006) validation (2007–2013). model performed well in simulating with NSE, R 2 , RSR values during phases, which 0.77, 0.79, 0.48 0.76, 0.78, 0.49, respectively. results show that (97.47%) has greater effect river runoff than (2.53%). Moreover, impact SSP585 (5.84%–19.42%) higher SSP245 (1.58%–4%). recommended be incorporated water policies bring sustainability environment.

Language: Английский

---

Seasonal Monitoring Method for TN and TP Based on Airborne Hyperspectral Remote Sensing Images

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(9), P. 1614 - 1614

Published: April 30, 2024

Airborne sensing images harness the combined advantages of hyperspectral and high spatial resolution, offering precise monitoring methods for local-scale water quality parameters in small bodies. This study employs airborne remote image data to explore estimation total nitrogen (TN) phosphorus (TP) concentrations Lake Dianshan, Yuandang, as well its main inflow outflow rivers. Our findings reveal following: (1) Spectral bands between 700 750 nm show highest correlation with TN TP during summer autumn seasons. reflectance exhibit greater sensitivity compared winter spring (2) Seasonal models developed using Catboost method demonstrate significantly higher accuracy than other machine learning (ML) models. On test set, root mean square errors (RMSEs) are 0.6 mg/L 0.05 concentrations, average absolute percentage (MAPEs) 23.77% 25.14%, respectively. (3) Spatial distribution maps retrieved indicate their dependence on exogenous inputs close association algal blooms. Higher observed near inlet (Jishui Port), reductions outlet (Lanlu particularly concentration. Areas intense blooms shorelines generally concentrations. offers valuable insights processing bodies provides reliable techniques lake management.

Language: Английский

---

Machine learning‐based streamflow forecasting using CMIP6 scenarios: Assessing performance and improving hydrological projections and climate change

Hydrological Processes, Journal Year: 2024, Volume and Issue: 38(6)

Published: June 1, 2024

Abstract Water is essential for humans as well all living organisms to sustain their lives. Therefore, any climate‐driven change in available resources has significant impacts on the environment and life. Global climate models (GCMs) are one of most practical methods evaluate change. Based this, this research evaluated capability GCMs from Coupled Model Intercomparison Project 6 (CMIP6) reproduce historical flow prediction centre data Konya Closed basin project using selected GCMs. based CMIP6 under scenario common socioeconomic pathways (SSP245 SSP 585) were used analyse effect streamflow study area by Bias Correction GCM Models Long Short‐Term Memory (LSTM), Bidirectional LSTM (BiLSTM), AdaBoost, Gradient Boosting, Regression Tree, Random Forest methods. The coefficient determination (R 2 ), mean square error (MSE), absolute (MAE), root (RMSE) assess performance Findings show that consistently outperformed other both testing training phases. A downward volume water flowing through region's rivers streams next decades. It critical enhance climate‐resilient infrastructure financing, establish an early warning system drought, introduce best management practices, implement integrated resource management, public awareness, support alleviate negative consequences drought increase resilience against effects Turkey's resources.

Language: Английский

---

Assessing the impacts of climate and land cover change on groundwater recharge in a semi-arid region of Southern India

Theoretical and Applied Climatology, Journal Year: 2024, Volume and Issue: 155(8), P. 7147 - 7163

Published: June 13, 2024

Language: Английский

---

Predictive Performance of Ensemble Learning Boosting Techniques in Daily Streamflow Simulation

Water Resources Management, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 22, 2024

Language: Английский

---

Assessing the impacts of land use and climate change on streamflow generation in the Nowrangpur catchment based on the SWAT-land-use update tool

Journal of Water and Climate Change, Journal Year: 2024, Volume and Issue: 16(1), P. 70 - 91

Published: Dec. 20, 2024

ABSTRACT Climate change and land-use are two major factors that affect the hydrologic response of a river basin. Soil Water Assessment Tool (SWAT) is reliable method to model hydrology The SWAT–land-use update tool offers user-friendly interface for incorporation dynamic changes into hydrological modeling. This paper evaluates impacts climate on streamflow generation in Nowrangpur catchment encompassing Indravati dam, which water-resources project India. Calibrating SWAT involved updating data from 1985 2015, yielding satisfactory results. future land-use/land-cover were predicted using cellular automata–artificial neural network model. Downscaled general circulation ten models utilized predict climate-change up 2100. Projections indicate increased precipitation during months August December with more pronounced increase mid far future. An uptrend maximum minimum temperatures all observed far-future relative baseline period. Furthermore, predictions near-future decrease total annual streamflow, followed by an 41%

Language: Английский

---

Hydrological response to climate and land use and land cover change in the Teesta River basin

Hydrology Research, Journal Year: 2024, Volume and Issue: 55(11), P. 1123 - 1142

Published: Nov. 1, 2024

ABSTRACT The Teesta basin is shared by Bangladesh and India, holds significant importance in the bilateral relationship, sustains livelihoods of over 30 million people Bangladesh. Employing a cellular-automata model (CA), we accurately estimate LULC for 2020s projected 2050s 2080s. A semi-distributed hydrological model, Soil Water Assessment Tool (SWAT), used to generate flow base period (1995–2014), near future (2035–2064), far (2071–2100). SWAT forced eight general circulation models (GCMs) under two socioeconomic pathways (SSP245 SSP585). CA-Markov prediction indicates changes, especially increased agriculture settlements 76 42%, decreased forest water 13 36%, respectively, which are expected will influence discharge patterns. This results additional increases 4% (–8 5%) SSP245 5% 10%) SSP585 scenarios during wet seasons. In future, monsoon increase 13% (0.4 23%) 52% (–29 151%) SSP585. marginal change winter was shown –6% (–16 4%) reduction –13% (–64 63%)

Language: Английский

---