| 1. |
- Darabi, H., et al.
(författare)
-
Development of a novel hybrid multi-boosting neural network model for spatial prediction of urban flood
- 2021
-
Ingår i: Geocarto International. - : Taylor and Francis Ltd.. - 1010-6049 .- 1752-0762.
-
Tidskriftsartikel (refereegranskat)abstract
- In this study, a new hybridized machine learning algorithm for urban flood susceptibility mapping, named MultiB-MLPNN, was developed using a multi-boosting technique and MLPNN. The model was tested in Amol City, Iran, a data-scarce city in an ungauged area which is prone to severe flood inundation events and currently lacks flood prevention infrastructure. Performance of the hybridized model was compared with that of a standalone MLPNN model, random forest and boosted regression trees. Area under the curve, efficiency, true skill statistic, Matthews correlation coefficient, misclassification rate, sensitivity and specificity were used to evaluate model performance. In validation, the MultiB-MLPNN model showed the best predictive performance. The hybridized MultiB-MLPNN model is thus useful for generating realistic flood susceptibility maps for data-scarce urban areas. The maps can be used to develop risk-reduction measures to protect urban areas from devastating floods, particularly where available data are insufficient to support physically based hydrological or hydraulic models.
|
|
| 2. |
- Torabi Haghighi, A., et al.
(författare)
-
A power market-based operation support model for sub-daily hydropower regulation practices
- 2019
-
Ingår i: Applied Energy. - : Elsevier Ltd. - 0306-2619 .- 1872-9118. ; 255
-
Tidskriftsartikel (refereegranskat)abstract
- With increasing power production from renewable energy sources, sub-daily variations in energy demand need to be balanced. Today, hydropower is commonly used as balancing power. In this study, we quantified the impact of capacity constraints, in terms of reservoir volume and hydropower capacity, on the potential to comply with instant energy demand. To evaluate the impact, we developed two new metrics, power market impact and system efficiency ratio, which are based on two threshold flow regimes derived from natural flow as lower threshold release and regulated flow (based on hourly energy prices) as upper threshold release. The operation support model comprises 96 different regulation scenarios based on varying combinations of hydropower and reservoir capacities. For each scenario, an hourly water balance was simulated, to obtain the highest complying with upper threshold release based on actual energy demand. We tested the framework on the Kemijoki river with defined thresholds based on the natural flow regime (tributary river Ounasjoki) and the hourly energy price in Finland in 2017, and estimated the impact of regulation on hourly flow regime at the Taivalkoski hydropower station. The annual flow regime impact in 2013, 2014 and 2015 was estimated to be 74%, 84% and 61%, respectively, while the monthly impact varied from 27% to 100%. Our framework for evaluating interactions between the power market and sub-daily regulation practices is a useful novel tool for sustainable river management and can be easily applied to different rivers and regions and evaluated for different timescales.
|
|
