Futuristic Streamflow Prediction Based on CMIP6 Scenarios Using Machine Learning Models

Ullah, Basir; Fawad, Muhammad; Khan, Afed Ullah; Mohamand, Sikander Khan; Khan, Mehran; Iqbal, Muhammad Junaid; Khan, Jehanzeb

doi:10.1007/s11269-023-03645-3

Cited by 10 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In each iteration, AdaBoost focuses on the samples that were misclassified in the previous round, increasing their weight to pay more attention to difficult-to-classify samples. Through continuous iteration, AdaBoost can gradually improve the performance and generalisation ability of the model [33,34].…”

Section: Research Methodology 231 Ensemble Learning Methodology Adaboostmentioning

confidence: 99%

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

Dong,

Gong,

Wang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

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

show abstract

Section: Research Methodology 231 Ensemble Learning Methodology Adaboostmentioning

confidence: 99%

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

Dong,

Gong,

Wang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…These discrepancies or biases can arise from model inaccuracies in representing physical processes, errors in the input data, or inadequate model resolution. The goal of bias correction is to make model outputs more closely reflect the observed climate events (Ullah et al, 2023).…”

Section: Bias Correctionmentioning

confidence: 99%

“…Linear scaling is often used for temperature projections because it can effectively adjust for systematic biases in mean temperature. However, caution is needed when applying it to precipitation, as it does not account for changes in precipitation intensity distribution, which can be critical for understanding extreme events (Ullah et al, 2023).…”

Section: Linear Scalingmentioning

confidence: 99%

See 1 more Smart Citation

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

Kartal

2024

Hydrological Processes

View full text Add to dashboard Cite

Water is essential for humans as well as for 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 the most practical methods to evaluate climate change. Based on this, this research evaluated the capability of GCMs from the Coupled Model Intercomparison Project 6 (CMIP6) to reproduce the historical flow of climate prediction centre data for the Konya Closed basin and to project the climate of the basin using the selected GCMs. Global climate models based on the CMIP6 under the scenario of common socioeconomic pathways (SSP245 and SSP 585) were used to analyse the climate change effect on streamflow of the study area by Bias Correction of GCM Models using Long Short‐Term Memory (LSTM), Bidirectional LSTM (BiLSTM), AdaBoost, Gradient Boosting, Regression Tree, and Random Forest methods. The coefficient of determination (R2), mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) were used to assess the performance of the methods. Findings show that the Random Forest Model consistently outperformed other models in both the testing and training phases. A significant downward in the volume of water flowing through the region's rivers and streams in the next decades. It is critical to enhance climate‐resilient water infrastructure financing, establish an early warning system for drought, introduce best management practices, implement integrated water resource management, public awareness, and support water research to alleviate the negative consequences of drought and increase resilience against the effects of climate change on Turkey's water resources.

show abstract

“…Global studies, exemplified by (Gaur & Singh, 2023;Mohseni et al, 2023), highlight the significant influence of LULC changes on basin flow patterns, while (Jiménez-Navarro et al, 2021;Mohammed et al, 2018;Mohammed, Saiful Islam, et al, 2017;Mohseni et al, 2023;Mollel et al, 2023;Sun et al, 2022;Ullah et al, 2023;Yalcin, 2023) explore the impact of climate change on flow across diverse basins. Recent research combining climate change and LULC effects reveals a notable impact on river basin flow, predicting decreased dry period flow and increased wet season flow (Bal et al, 2021;Fields et al, 2021;Mohseni et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Impact of Climate Change and Land Use Land Cover Change on Stream Flow of the Teesta River Basin under CMIP6 Climate Scenarios

Rahman,

Islam

2024

Preprint

View full text Add to dashboard Cite

The Teesta basin, shared by Bangladesh and India, undergoes profound changes due to land use and land cover (LULC) dynamics combined with climate change, significantly impacting its water balance. This study intends to analyse the combined effects of future LULC changes and climate change on the stream flow of the Teesta River. Employing a cellular-automata model, we accurately predicted LULC for 2020 and projected scenarios for 2050 and 2080. A semi-distributed hydrological model, Soil Water Assessment Tool (SWAT) is used to generate flow for the base period (1995-2014), the near future (2035-2064), and the far future (2071-2100). SWAT model is forced by 8 General Circulation Models (GCMs) under two Socioeconomic Pathways (SSP245 and SSP585). Satellite image analysis showed notable LULC changes, with substantial increases in agricultural (0.49%), water bodies (4.24%) and settlement areas (1.67%), while a decrease in forest (1.45%) and sand bar (5.49%) decreased from 2000 to 2010. During 2010 and 2020, increases in agricultural (2.77%), water bodies (7.7%) and settlement areas (8.59%), while decreases in forest (1.36%) and sand bar (0.18%) were found. The CA-Markov prediction indicates significant future increases in settlements and agricultural land by 2050 and 2080, coupled with reductions in forest, water, and snow cover. The calibrated and validated SWAT model effectively simulated discharge, yielding satisfactory results. Projected changes in discharge during the monsoon and winter periods were examined under different scenarios. Monsoon discharge is predicted to increase by 26% to 38% in the near future and 30% to 45% in the far future. Conversely, the winter/dry period may experience a decrease of 46% to 49% in the near future and 38% in the far future for SSP245 and SSP585 scenarios, respectively. Considering LULC changes to account, additional discharge increases during the monsoon are projected, with slight increases in the dry period during the near future and decreases during the far future. This study anticipates an increasing trend in peak flow during the monsoon and a declining trend in mean flow during winter without further upstream water control. Understanding and managing the combined effects of LULC changes and climate change on the hydrological dynamics of the basin is of utmost importance for sustainable water resource management in the region.

show abstract

Futuristic Streamflow Prediction Based on CMIP6 Scenarios Using Machine Learning Models

Cited by 10 publications

References 25 publications

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

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

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

Impact of Climate Change and Land Use Land Cover Change on Stream Flow of the Teesta River Basin under CMIP6 Climate Scenarios

Contact Info

Product

Resources

About