Fully distributed rainfall-runoff modeling using spatial-temporal graph neural network

Recent studies using latest deep learning algorithms such as LSTM (Long Short-Term Memory) have shown great promise in time-series modeling. There are many studies focusing on the watershed-scale rainfall-runoff modeling or streamflow forecasting, often considering a single watershed with limited generalization capabilities. To improve the model performance, several studies explored an integrated approach by decomposing a large watershed into multiple sub-watersheds with semi-distributed structure. In this study, we propose an innovative physics-informed fully-distributed rainfall-runoff model, NRM-Graph (Neural Runoff Model-Graph), using Graph Neural Networks (GNN) to make full use of spatial information including the flow direction and geographic data. Specifically, we applied a time-series model on each grid cell for its runoff production. The output of each grid cell is then aggregated by a GNN as the final runoff at the watershed outlet. The case study shows that our GNN based model successfully represents the spatial information in predictions. NRM-Graph network has shown less over-fitting and a significant improvement on the model performance compared to the baselines with spatial information. Our research further confirms the importance of spatially distributed hydrological information in rainfall-runoff modeling using deep learning, and we encourage researchers to incorporate more domain knowledge in modeling.

Examples on Simulation Model

A new methodology was developed Further real-time determination gate control operations of a river-reservoir system to minimize flooding conditions. The methodology is based upon an optimization-simulation model approach interfacing the genetic algorithm within simulation software for short-term rainfall forecasting, rainfall–runoff modeling (HEC-HMS), and a one-dimensional (1D), two-dimensional (2D), and combined 1D and 2D combined unsteady flow models (HEC-RAS). Both realtime rainfall data from next-generation radar (NEXRAD) and gaging stations, and forecasted rainfall are needed to make gate control decisions (reservoir releases) in real-time so that at timet, rainfall is known and rainfall over the future timeperiod(∆t)totimet+ ∆t can be forecasted. This new model can be used to manage reservoir release schedules (optimal gate operations) before, during, and after a rainfall event. Through real-time observations and optimal gate controls, downstream water surface elevations are controlled to avoid exceedance of threshold flood levels at target locations throughout a riverreservoir system to minimize the damage. In an example application, an actual river reach with a hypothetical upstream flood control reservoir is modeled in real-time to test the optimization-simulation portion of the overall model. Keywords: Simulation – Random numbers- Steps for simulation – Problems.

Runoff modeling in Kolar river basin using hybrid approach of wavelet with artificial neural network

In this paper, Kolar River watershed, Madhya Pradesh is taken as the study area. This study area is located in Narmada River in Central India. The data set consists of monthly rainfall of three meteorological stations, Ichhawar, Brijesh Nagar, and Birpur rainfall stations from 2000 to 2018, runoff data at Birpur and temperature data of Sehore district. In this paper, radial basis function neural network models have been studied for generation of rainfall–runoff modeling along with wavelet input and without wavelet input to the RBF neural network. A total of 15 models was developed in this experiment based on various combinations of inputs and spread constant of RBF model. The evaluation criteria for the best models selected are based on R2, AARE, and MSE. The best predicting model among the networks is model 8, which has input of R(t-1), R(t-2), R(t-3), R(t-4), and Q(t-1). For RBFNN model, maximum value of R2 is 0.9567 and least value of AARE and MSE is observed. Similarly, for WRBFNN model, maximum value of R2 is 0.9889 and least value of AARE and MSE is observed. WRBF performs better than RBF with any data processing techniques which shows model proposed possess better predictive capability.

Rainfall-runoff modeling using Doppler weather radar data for Adyar watershed, India

Precipitation is a significant input for hydrologic models; so, it needs to be quantified precisely. The measurement with rain gauges gives the rainfall at a particular location, whereas the radar obtains instantaneous snapshots of electromagnetic backscatter from rain volumes that are then converted into rainfall via algorithms. It has been proved that the radar measurement of areal rainfall can outperform rain gauge network measurements, especially in remote areas where rain gauges are sparse, and remotely sensed satellite rainfall data are too inaccurate. The research focuses on a technique to improve rainfall-runoff modeling based on radar derived rainfall data for Adyar watershed, Chennai, India. A hydrologic model called ‘Hydrologic Engineering Center-Hydrologic Modeling System (HEC-HMS)’ is used for simulating rainfall-runoff processes. CARTOSAT 30 m DEM is used for watershed delineation using HEC-GeoHMS. The Adyar watershed is within 100 km radius circle from the Doppler Weather Radar station, hence it has been chosen as the study area. The cyclonic storm Jal event from 4-8 November, 2010 period is selected for the study. The data for this period are collected from the Statistical Department, and the Cyclone Detection Radar Centre, Chennai, India. The results show that the runoff is over predicted using calibrated Doppler radar data in comparison with the point rainfall from rain gauge stations.

ANALISIS KETERSEDIAAN AIR PADA DAS INDRAGIRI HILIR MENGGUNAKAN MODEL IHACRES

The imbalance that occurs between the availability of water and the water needs needed in Indragiri Hilir requires a conseptual review and evaluation. The all-time distribution of water availability is greatly influenced by the distribution of rain throughout the year. Conceptual analysis of water discharge with the help of IHACRES software can help analyze DAS indragiri Hilir discharge. Rainfall-runoff modeling is used to predict the value against the runoff, using the IHACRES model. The IHACRES model produces nonlinear loss module parameters and linear unit hydrograph modules. AWLR will be used, namely Bt. Kuantan Rengat station, Rain Data which will be used from Tembilahan station and climatology used from Air Molek station. Determination of success in the model used the equations R2 and R to calculate the deviation that occurs. The calibration, verification and simulation phases begin in 2010-2015. The results of conceptual analysis of water discharge in Indragiri Hilir watershed, mainstay discharge results for irrigation purposes with a probability of 80% maximum discharge occurred in February by 4.33 m3 / s and minimum discharge occurred in April by 0.34 m3/s. Overall availability of water on site is available throughout the year. but it cannot be used for hydropower needs because the available discharge may be affected by tidal factors. Ketidakseimbangan yang terjadi antara ketersediaan air dan kebutuhan air yang diperlukan di Indragiri Hilir memerlukan peninjauan dan evaluasi yang konseptual. Distribusi ketersedian air sepanjang waktu sangat dipengaruhi oleh distribusi hujan sepanjang tahun . Analisis konseptual debit air dengan bantuan software IHACRES dapat membantu menganalisis debit DAS indragiri hilir. Pemodelan rainfall-runoff digunakan untuk memprediksi nilai terhadap runoff salah satunya yaitu menggunakan model IHACRES. Model IHACRES menghasilkan parameter nonlinier loss module dan linier unit hydrograph module. AWLR akan digunakan yaitu stasiun Bt. Kuantan Rengat, Data Hujan yang akan digunakan yaitu dari stasiun Tembilahan dan klimatologi yang digunakan dari stasiun Air Molek. Penentuan keberhasilan pada model digunakan persamaan R2 dan R untuk menghitung simpangan yang terjadi. Tahap kalibrasi, verifikasi dan simulasi dimulai tahun 2010-2015. Hasil analisis konseptual debit air pada DAS Indragiri Hilir, hasil debit andalan untuk keperluan irigasi dengan probabilitas 80% debit maksimum terjadi pada bulan Februari sebesar 4,33 m3/s dan debit minimum terjadi pada bulan April sebesar 0,34 m3/s. Secara keseluruhan ketersediaan air di lokasi tersedia sepanjang tahun. tetapi tidak bisa digunakan untuk kebutuhan PLTA karena debit yang tersedia mungkin dipengaruhi faktor pasang surut

A Polynomial Method Approximating S-Curve with Limited Availability of Reliable Rainfall Data

A methodology named the step response separation (SRS) method for deriving S-curves solely from the data for basin runoff and the associated instantaneous unit hydrograph (IUH) is presented. The SRS method extends the root selection (RS) method to generate a clearly separated S-curve from runoff incorporated in mathematical procedure utilizing the step response function. Significant improvements in performance are observed in separating the S-curve with rainfall. A procedure to evaluate the hydrologic stability provides ways to minimize the oscillation of the S-curve associated with the determination of infiltration and baseflow. The applicability of the SRS method to runoff reproduction is examined by comparison with observed basin runoff based on the RS method. The SRS method applied to storm events for the Nenagh basin resulted in acceptable S-curves and showed its general applicability to optimization for rainfall-runoff modeling.