CAN MACHINE LEARNING IMPROVE THE ACCURACY OF WATER LEVEL FORECASTS FOR INLAND NAVIGATION? CASE STUDY: RHINE RIVER BASIN, GERMANY

2019 ◽  
Author(s):  
YUELING MA ◽  
ELENA MATTA ◽  
DENNIS MEIßNER ◽  
HANNO SCHELLENBERG ◽  
REINHARD HINKELMANN
Keyword(s):  
Machine Learning ◽  
Water Level ◽  
River Basin ◽  
Rhine River ◽  
Inland Navigation

Connecting global- and local-scale flood risk assessment: a case study of the Rhine River basin flood hazard

2016 ◽  
Vol 9 (4) ◽  
pp. 343-354 ◽  
Author(s):  
M. Gusyev ◽  
A. Gädeke ◽  
J. Cullmann ◽  
J. Magome ◽  
A. Sugiura ◽  
...  
Keyword(s):  
Risk Assessment ◽  
River Basin ◽  
Flood Risk ◽  
Flood Hazard ◽  
Local Scale ◽  
Rhine River ◽  
Flood Risk Assessment ◽  
Global And Local

A Machine Learning Framework to Predict Reverse Flow and Water Level: A Case Study of Tonle Sap Lake

2021 ◽  
pp. 127168
Author(s):  
Khosro Morovati ◽  
Pouria Nakhaei ◽  
Fuqiang Tian ◽  
Mahmut Tudaji ◽  
Shiyu Hou
Keyword(s):  
Machine Learning ◽  
Water Level ◽  
Reverse Flow ◽  
Learning Framework ◽  
Tonle Sap Lake ◽  
Tonle Sap

scholarly journals Diversion Canal to Decrease Flooding (Case Study : Kebon Jati-Kalibata Segment, Ciliwung River Basin)

2018 ◽  
Vol 147 ◽  
pp. 03006 ◽  
Author(s):  
Dian Indrawati ◽  
Iwan K. Hadihardaja ◽  
M. Bagus Adityawan ◽  
Syambali F. Pahrizal ◽  
Fajar Taufik
Keyword(s):  
Water Level ◽  
River Basin ◽  
Carrying Capacity ◽  
River Discharge ◽  
Hydraulic Structure ◽  
Steep Slope ◽  
Stilling Basin ◽  
Flood Level ◽  
Heavy Rainfalls

The flood in Jakarta has become a national concern in Indonesia. It is a haunting disaster, with a high probability to happen when heavy rainfalls in Jakarta and/or its upstream area. Based on data that was provided by Public Work Agency of DKI Jakarta, there are 78 vulnerable points of inundation in which, most of them are located in Ciliwung river basin, commonly in the meandering segments. One of the worst flooding occurs in Pancoran, at Kebonjati to Kalibata segment in particular. The river discharge in this segment is much higher as compared to the carrying capacity. In addition, this area has a high density of population and thus, difficult to increase the *river capacity* by enlarging the river dimension. In this research, a closed diversion canal is proposed as a solution. The effectiveness of the solution is evaluated using a numerical model, HEC-RAS 4.1. The diversion canal is designed as two culverts, with 2.0 m in diameter. Nevertheless, hydraulic jump may occur at the outlet of the canal due to the relatively steep slope. Therefore, the canal outlet should be designed accordingly. A Hydraulic structure such as a stilling basin can be employed to reduce the energy. The results show that the diversion canal has a good performance in decreasing water level and flood discharge in the study area. The canal has the capacity of 17,72 m3/sec and succesfully decreases the water level by 4.71 – 5.66 m from flood level for 2 – 100 years returned period.

scholarly journals A machine learning approach to water quality forecasts and sensor network expansion: Case study in the Wabash River Basin, USA

2021 ◽  
Author(s):  
Tyler Balson ◽  
Adam Ward
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Sensor Network ◽  
River Basin ◽  
Synthetic Data ◽  
Support Vector ◽  
Data Set ◽  
Forecast Performance ◽  
Wabash River

Midwestern cities require forecasts of surface nitrate loads to bring additional treatment processes online or activate alternative water supplies. Concurrently, networks of nitrate monitoring stations are being deployed in river basins, co-locating water quality observations with established stream gauges. Here, we construct a synthetic data set of stream discharge and nitrate for the Wabash River Basin - one of the U.S.’s most nutrient polluted basins - using the established Agro-IBIS model. While real-world observations are limited in space and time, particularly for nitrate, the synthetic data set allows for sufficiently long periods to train machine learning models and assess their performance. Using the synthetic data, we established baseline 1-day forecasts for surface water nitrate at 12 cities in the basin using support vector machine regression (SVMR; RMSE 0.48-3.3 mg/L). Next, we used the SVMRs to evaluate the improvement in forecast performance associated with deployment of additional sensors. Synthetic data enable us to quantitatively assess the expected value of an additional nitrate sensor being deployed, which is, of course, not possible if we are limited to the present observational network. We identified the optimal sensor placement to improve forecasts at each city, and the relative value of sensors at all possible locations. Finally, we assessed the co-benefit realized by other cities when a sensor is deployed to optimize a forecast at one city, finding significant positive externalities in all cases. Ultimately, our study explores the potential for AI to make short-term predictions and provide an unbiased assessment of the marginal benefit and co-benefits to an expanded sensor network. While we use water quantity in the Wabash River Basin as a case study, this approach could be readily applied to any problem where the future value of sensors and network design are being evaluated.

Sign in / Sign up

Export Citation Format

Share Document