| 1. |
- Anwar, Hamid, et al.
(författare)
-
Intercomparison of deep learning models in predicting streamflow patterns: insight from CMIP6
- 2024
-
Ingår i: Scientific Reports. - : Springer Nature. - 2045-2322. ; 14
-
Tidskriftsartikel (refereegranskat)abstract
- This research was carried out to predict daily streamflow for the Swat River Basin, Pakistan through four deep learning (DL) models: Feed Forward Artificial Neural Networks (FFANN), Seasonal Artificial Neural Networks (SANN), Time Lag Artificial Neural Networks (TLANN) and Long Short-Term Memory (LSTM) under two Shared Socioeconomic Pathways (SSPs) 585 and 245. Taylor Diagram, Random Forest, and Gradient Boosting techniques were used to select the best combination of General Circulation Models (GCMs) for Multi-Model Ensemble (MME) computation. MME was computed via the Random Forest technique for Maximum Temperature (Tmax), Minimum Temperature (Tmin), and precipitation for the aforementioned three techniques. The best MME for Tmax, Tmin, and precipitation was rendered by Compromise Programming. The DL models were trained and tested using observed precipitation and temperature as independent variables and discharge as dependent variables. The results of deep learning models were evaluated using statistical performance indicators such as root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R2). The TLANN demonstrated superior performance compared to the other models based on RMSE, MSE, MAE, and R2 during training (65.25 m3/s, 4256.97 m3/s, 46.793 m3/s and 0.7978) and testing (72.06 m3/s, 5192.95 m3/s, 51.363 m3/s and 0.7443) respectively. Subsequently, TLANN was utilized to make predictions based on MME of SSP245 and SSP585 scenarios for future streamflow until the year 2100. These results can be used for planning, management, and policy-making regarding water resources projects in the study area.
|
|
| 2. |
- Mahmood, Saqib, et al.
(författare)
-
Divergent path: isolating land use and climate change impact on river runoff
- 2024
-
Ingår i: Frontiers in Environmental Science. - : Frontiers Media Sa. - 2296-665X. ; 12
-
Tidskriftsartikel (refereegranskat)abstract
- Water resource management requires a thorough examination of how land use and climate change affect streamflow; however, the potential impacts of land-use changes are frequently ignored. Therefore, the principal goal of this study is to isolate the effects of anticipated climate and land-use changes on streamflow at the Indus River, Besham, Pakistan, using the Soil and Water Assessment Tool (SWAT). The multimodal ensemble (MME) of 11 general circulation models (GCMs) under two shared socioeconomic pathways (SSPs) 245 and 585 was computed using the Taylor skill score (TSS) and rating metric (RM). Future land use was predicted using the cellular automata artificial neural network (CA-ANN). The impacts of climate change and land-use change were assessed on streamflow under various SSPs and land-use scenarios. To calibrate and validate the SWAT model, the historical record (1991-2013) was divided into the following two parts: calibration (1991-2006) and validation (2007-2013). The SWAT model performed well in simulating streamflow with NSE, R2, and RSR values during the calibration and validation phases, which are 0.77, 0.79, and 0.48 and 0.76, 0.78, and 0.49, respectively. The results show that climate change (97.47%) has a greater effect on river runoff than land-use change (2.53%). Moreover, the impact of SSP585 (5.84%-19.42%) is higher than that of SSP245 (1.58%-4%). The computed impacts of climate and land-use changes are recommended to be incorporated into water policies to bring sustainability to the water environment.
|
|
