کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6410109 | 1629917 | 2016 | 61 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
A nonlinear spatio-temporal lumping of radar rainfall for modeling multi-step-ahead inflow forecasts by data-driven techniques
ترجمه فارسی عنوان
بارگیری فضایی و زمان غیر خطی بارش باران رادار برای مدل سازی پیش بینی ورودی چند مرحله ای با تکنیک های هدایت داده
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
علوم زمین و سیارات
فرآیندهای سطح زمین
چکیده انگلیسی
Accurate multi-step-ahead inflow forecasting during typhoon periods is extremely crucial for real-time reservoir flood control. We propose a spatio-temporal lumping of radar rainfall for modeling inflow forecasts to mitigate time-lag problems and improve forecasting accuracy. Spatial aggregation of radar cells is made based on the sub-catchment partitioning obtained from the Self-Organizing Map (SOM), and then flood forecasting is made by the Adaptive Neuro Fuzzy Inference System (ANFIS) models coupled with a 2-staged Gamma Test (2-GT) procedure that identifies the optimal non-trivial rainfall inputs. The Shihmen Reservoir in northern Taiwan is used as a case study. The results show that the proposed methods can, in general, precisely make 1- to 4-hour-ahead forecasts and the lag time between predicted and observed flood peaks could be mitigated. The constructed ANFIS models with only two fuzzy if-then rules can effectively categorize inputs into two levels (i.e. high and low) and provide an insightful view (perspective) of the rainfall-runoff process, which demonstrate their capability in modeling the complex rainfall-runoff process. In addition, the confidence level of forecasts with acceptable error can reach as high as 97% at horizon t+1 and 77% at horizon t+4, respectively, which evidently promotes model reliability and leads to better decisions on real-time reservoir operation during typhoon events.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Hydrology - Volume 535, April 2016, Pages 256-269
Journal: Journal of Hydrology - Volume 535, April 2016, Pages 256-269
نویسندگان
Fi-John Chang, Meng-Jung Tsai,