An assessment of multi-layer perceptron networks for streamflow forecasting in large-scale interconnected hydrosystems

2021 ◽  
Author(s):  
V. A. D. de Faria ◽  
A. R. de Queiroz ◽  
L. M. Lima ◽  
J. W. M. Lima ◽  
B. C. da Silva
Keyword(s):  
Large Scale ◽  
Multi Layer Perceptron ◽  
Streamflow Forecasting

scholarly journals GloFAS – global ensemble streamflow forecasting and flood early warning

2012 ◽  
Vol 9 (11) ◽  
pp. 12293-12332 ◽  
Author(s):  
L. Alfieri ◽  
P. Burek ◽  
E. Dutra ◽  
B. Krzeminski ◽  
D. Muraro ◽  
...  
Keyword(s):  
Early Warning ◽  
Large Scale ◽  
River Basins ◽  
Developed Countries ◽  
Large River ◽  
Streamflow Forecasting ◽  
Forecast Horizon ◽  
Hydrological Simulation ◽  
Streamflow Forecasts ◽  
Awareness System

Abstract. Anticipation and preparedness for large-scale flood events have a key role in mitigating their impact and optimizing the strategic planning of water resources. Although several developed countries have well-established systems for river monitoring and flood early warning, figures of population affected every year by floods in developing countries are unsettling. This paper presents the Global Flood Awareness System, which has been set up to provide an overview on upcoming floods in large world river basins. The Global Flood Awareness System is based on distributed hydrological simulation of numerical ensemble weather predictions with global coverage. Streamflow forecasts are compared statistically to climatological simulations to detect probabilistic exceedance of warning thresholds. In this article, the system setup is described, together with an evaluation of its performance over a two-year test period and a qualitative analysis of a case study for the Pakistan flood, in summer 2010. It is shown that hazardous events in large river basins can be skilfully detected with a forecast horizon of up to 1 month. In addition, results suggest that an accurate simulation of initial model conditions and an improved parameterization of the hydrological model are key components to reproduce accurately the streamflow variability in the many different runoff regimes of the Earth.

scholarly journals Modelling provenance in hydrologic science: a case study on streamflow forecasting

2012 ◽  
Vol 14 (4) ◽  
pp. 944-959 ◽  
Author(s):  
Yanfeng Shu ◽  
Kerry Taylor ◽  
Prasantha Hapuarachchi ◽  
Chris Peters
Keyword(s):  
Semantic Web ◽  
Large Scale ◽  
Streamflow Forecasting ◽  
Provenance Information ◽  
Domain Specific ◽  
Recent Developments ◽  
New Ideas ◽  
Ontological Model ◽  
Domain Independent

The web, and more recently the concept and technology of the Semantic Web, has created a wealth of new ideas and innovative tools for data management, integration and computation in an open framework and at a very large scale. One area of particular interest to the science of hydrology is the capture, representation, inference and presentation of provenance information: information that helps to explain how data were computed and how they should be interpreted. This paper is among the first to bring recent developments in the management of provenance developed for e-science and the Semantic Web to the problems of hydrology. Our main result is a formal ontological model for the representation of provenance information driven by a hydrologic case study. Along the way, we support usability, extensibility and reusability for provenance representation, relying on the concept of modelling both domain-independent and domain-specific aspects of provenance. We evaluate our model with respect to its ability to satisfy identified requirements arising from the case study on streamflow forecasting for the South Esk River catchment in Tasmania, Australia.

scholarly journals Fuzzy Postprocessing to Advance the Quality of Continental Seasonal Hydrological Forecasts for River Basin Management

2020 ◽  
Vol 21 (10) ◽  
pp. 2375-2389
Author(s):  
Hector Macian-Sorribes ◽  
Ilias Pechlivanidis ◽  
Louise Crochemore ◽  
Manuel Pulido-Velazquez
Keyword(s):  
River Basin ◽  
Large Scale ◽  
Hydrological Model ◽  
Hydrological Models ◽  
Streamflow Forecasting ◽  
Seasonal Forecasts ◽  
Quantile Mapping ◽  
River Basin Scale ◽  
Basin Scale ◽  
Streamflow Forecasts

AbstractStreamflow forecasting services driven by seasonal meteorological forecasts from dynamic prediction systems deliver valuable information for decision-making in the water sector. Moving beyond the traditional river basin boundaries, large-scale hydrological models enable a coordinated, efficient, and harmonized anticipation and management of water-related risks (droughts, floods). However, the use of forecasts from such models at the river basin scale remains a challenge, depending on how the model reproduces the hydrological features of each particular river basin. Consequently, postprocessing of forecasts is a crucial step to ensure usefulness at the river basin scale. In this paper we present a methodology to postprocess seasonal streamflow forecasts from large-scale hydrological models and advance their quality for local applications. It consists of fuzzy logic systems that bias-adjust seasonal forecasts from a large-scale hydrological model by comparing its modeled streamflows with local observations. The methodology is demonstrated using forecasts from the pan-European hydrological model E-HYPE at the Jucar River basin (Spain). Fuzzy postprocessed forecasts are compared to postprocessed forecasts derived from a quantile mapping approach as a benchmark. Fuzzy postprocessing was able to provide skillful streamflow forecasts for the Jucar River basin, keeping most of the skill of raw E-HYPE forecasts and also outperforming quantile-mapping-based forecasts. The proposed methodology offers an efficient one-to-one mapping between large-scale modeled streamflows and basin-scale observations preserving its temporal dependence structure and can adapt its input set to increase the skill of postprocessed forecasts.

Assessing the utility of climate variability information in streamflow forecasting

2021 ◽  
Author(s):  
Prem Lal Patel ◽  
Priyank Sharma ◽  
Ramesh Teegavarapu
Keyword(s):  
Climate Variability ◽  
Large Scale ◽  
Southern Oscillation ◽  
Input Parameter ◽  
Statistical Error ◽  
Linear Process ◽  
Linear Regression Models ◽  
Streamflow Forecasting ◽  
Streamflow Prediction ◽  
Time Step

<p>The prediction of total and peak streamflows are essential for effective management of water resources systems. A data-driven approach, Model Tree (MT), is applied to predict daily streamflows for a tropical river basin in India. The Tapi River drains a total area of 65,225 km<sup>2</sup>, wherein more than 20 million people are directly or indirectly dependent on it for their water and food requirements. The MT approach executes piece-wise linearization of a non-linear process for the input parameter space and develops linear regression models for each sub-space. The large-scale oceanic-atmospheric oscillations, such as El Niño-Southern Oscillation (ENSO), exert considerable influence on the hydroclimatic conditions across the globe. Based on the Oceanic Niño Index, the warm and cool phases of ENSO are identified as El Niño and La Niña, respectively. It is found that the El Niño and La Niña are associated with drier and wetter than normal conditions respectively across the Tapi basin. Hence, the hypothesis that incorporation of climate variability information would help in enhancing the predictive performance of the model is being tested. A daily-time step model for streamflow prediction is developed considering various hydrometerological inputs observed for the period 1975-2013 to predict streamflows at the catchment outlet. Additionally, two separate models, viz., El Niño- and La Niña-specific models, are developed considering the observed variables corresponding to these phases, and their skill of prediction with respect to the overall model is evaluated. The evaluation of the developed models is further carried out through a suite of statistical error and performance indices, and inferences are drawn.</p>

scholarly journals A relative humidity profile retrieval from Megha-Tropiques observations without explicit thermodynamical constraints

2014 ◽  
Vol 7 (9) ◽  
pp. 8983-9023 ◽  
Author(s):  
R. G. Sivira ◽  
H. Brogniez ◽  
C. Mallet ◽  
Y. Oussar
Keyword(s):  
Relative Humidity ◽  
Large Scale ◽  
Generalized Additive Model ◽  
Additive Model ◽  
Least Square ◽  
Support Vector ◽  
Training Phase ◽  
Multi Layer Perceptron ◽  
Vector Machines

Abstract. A statistical method trained and optimized to retrieve relative humidity (RH) profiles is presented and evaluated with measurements from radiosoundings. The method makes use of the microwave payload of the Megha-Tropiques plateform, namely the SAPHIR sounder and the MADRAS imager. The approach, based on a Generalized Additive Model (GAM), embeds both the physical and statistical characteritics of the inverse problem in the training phase and no explicit thermodynamical constraint, such as a temperature profile or an integrated water vapor content, is provided to the model at the stage of retrieval. The model is built for cloud-free conditions in order to avoid the cases of scattering of the microwave radiation in the 18.7–183.31 GHz range covered by the payload. Two instrumental configurations are tested: a SAPHIR-MADRAS scheme and a SAPHIR-only scheme, to deal with the stop of data acquisition of MADRAS in January 2013 for technical reasons. A comparison to retrievals based on the Multi-Layer Perceptron (MLP) technique and on the Least Square-Support Vector Machines (LS-SVM) shows equivalent performance over a large realistic set, promising low errors (bias < 2.2%) and scatters (correlation > 0.8) throughout the troposphere (150–900 hPa). A comparison to radiosounding measurements performed during the international field experiment CINDY/DYNAMO/AMIE of winter 2011–2012 confirms these results for the mid-tropospheric layers (correlation between 0.6 and 0.92), with an expected degradation of the quality of the estimates at the surface and top layers. Finally a rapid insight of the large-scale RH field from Megha-Tropiques is discussed and compared to ERA-Interim.

Hybrid model to improve the river streamflow forecasting utilizing multi-layer perceptron-based intelligent water drop optimization algorithm

2020 ◽  
Vol 24 (23) ◽  
pp. 18039-18056 ◽  
Author(s):  
Quoc Bao Pham ◽  
Haitham Abdulmohsin Afan ◽  
Babak Mohammadi ◽  
Ali Najah Ahmed ◽  
Nguyen Thi Thuy Linh ◽  
...  
Keyword(s):  
Hybrid Model ◽  
Optimization Algorithm ◽  
Water Drop ◽  
Multi Layer Perceptron ◽  
Streamflow Forecasting

Short-Term Basin-Scale Streamflow Forecasting Using Large-Scale Coupled Atmospheric–Oceanic Circulation and Local Outgoing Longwave Radiation

2010 ◽  
Vol 11 (2) ◽  
pp. 370-387 ◽  
Author(s):  
Rajib Maity ◽  
S. S. Kashid
Keyword(s):  
Genetic Programming ◽  
Outgoing Longwave Radiation ◽  
Large Scale ◽  
Southern Oscillation ◽  
Longwave Radiation ◽  
Programming Approach ◽  
Complex Relationship ◽  
Streamflow Forecasting ◽  
Short Term ◽  
Basin Scale

Abstract This paper investigates the use of large-scale circulation patterns (El Niño–Southern Oscillation and the equatorial Indian Ocean Oscillation), local outgoing longwave radiation (OLR), and previous streamflow information for short-term (weekly) basin-scale streamflow forecasting. To model the complex relationship between these inputs and basin-scale streamflow, an artificial intelligence approach—genetic programming (GP)—has been employed. Research findings of this study indicate that the use of large-scale atmospheric circulation information and streamflow at previous time steps, along with OLR as a local meteorological input, potentially improves the performance of weekly basin-scale streamflow prediction. The genetic programming approach is found to capture the complex relationship between the weekly streamflow and various inputs. Different input variable combinations were explored to come up with the best one. The observed and predicted streamflows were found to correspond well with each other with a coefficient of determination of 0.653 (correlation coefficient r = 0.808), which may appear attractive for such a complex system.

Sign in / Sign up

Export Citation Format

Share Document