Data-Enabled Field Experiment Planning, Management, and Research Using Cyberinfrastructure

Demir, İbrahim; Conover, H.; Krajewski, Witold F.; Seo, Bong-Chul; Goska, Radosław; He, Yubin; McEniry, M.; Graves, Sara; Petersen, Walter A.

doi:10.1175/jhm-d-14-0163.1

Cited by 40 publications

(16 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has a narrow shape with a much longer time of concentration than has the Clear Creek Watershed. Both watersheds are vulnerable to flooding and part of the Iowa Watershed Approach project (Demir et al, 2015;Weber et al, 2018) for flood risk reduction. Available data for the case study includes runoff data from the U.S. Geological Survey (2016), 15-min Radar Stage IV precipitation data (Lin, 2011), and monthly ET data from the Iowa Flood Center (Krajewski et al, 2017).…”

Section: Case Studymentioning

confidence: 99%

A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning

Xiang

Yan²,

Demir

2020

Water Resources Research

Self Cite

380

169

View full text Add to dashboard Cite

Rainfall-runoff modeling is a complex nonlinear time series problem. While there is still room for improvement, researchers have been developing physical and machine learning models for decades to predict runoff using rainfall data sets. With the advancement of computational hardware resources and algorithms, deep learning methods such as the long short-term memory (LSTM) model and sequence-to-sequence (seq2seq) modeling have shown a good deal of promise in dealing with time series problems by considering long-term dependencies and multiple outputs. This study presents an application of a prediction model based on LSTM and the seq2seq structure to estimate hourly rainfall-runoff. Focusing on two Midwestern watersheds, namely, Clear Creek and Upper Wapsipinicon River in Iowa, these models were used to predict hourly runoff for a 24-hr period using rainfall observation, rainfall forecast, runoff observation, and empirical monthly evapotranspiration data from all stations in these two watersheds. The models were evaluated using the Nash-Sutcliffe efficiency coefficient, the correlation coefficient, statistical bias, and the normalized root-mean-square error. The results show that the LSTM-seq2seq model outperforms linear regression, Lasso regression, Ridge regression, support vector regression, Gaussian processes regression, and LSTM in all stations from these two watersheds. The LSTM-seq2seq model shows sufficient predictive power and could be used to improve forecast accuracy in short-term flood forecast applications. In addition, the seq2seq method was demonstrated to be an effective method for time series predictions in hydrology. Key Points:• An hourly runoff model was developed using the LSTM sequence-to-sequence learning method for 24-hr predictions on USGS stations • The proposed model shows better performance than traditional data-driven models and is applicable to different watersheds • The advantages and limitations of seq2seq models and how this model structure could work on the rainfall-runoff modeling is presented Supporting Information:• Supporting Information S1 Correspondence to: Z. Xiang, zhongrun-xiang@uiowa.edu Citation: Xiang, Z., Yan, J., & Demir, I. (2020). A rainfall-runoff model with LSTM-based sequence-to-sequence learning. Water Resources Research, 56, e2019WR025326. https://doi.

show abstract

Section: Case Studymentioning

confidence: 99%

A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning

Xiang

Yan²,

Demir

2020

Water Resources Research

Self Cite

380

169

View full text Add to dashboard Cite

show abstract

“…The IWQIS design is based on the vision and technical expertise of the generalized water cyberinfrastructure developed at the Iowa Flood Center (Demir and Krajewski, 2013;Krajewski et al, 2017). IWQIS provides an integrated and scalable workflow environment to support end-to-end cyberinfrastructure for sharing scientific research and observations (Duffy et al, 2012;Gil et al, 2016), as well as scientific visualization, communication of observations, and modeling results that assist watershed management and research Demir et al, , 2015. A wide variety of data are available for immediate public use through IWQIS (IIHR-University of Iowa, 2017, accessed September 2017, http://iwqis.iowawis.…”

Section: Network Descriptionmentioning

confidence: 99%

Iowa Statewide Stream Nitrate Load Calculated Using In Situ Sensor Network

Jones

Davis

Drake

et al. 2017

J American Water Resour Assoc

Self Cite

View full text Add to dashboard Cite

Various techniques exist to estimate stream nitrate loads when measured concentration data are sparse. The inherent uncertainty associated with load estimation, however, makes tracking progress toward water quality goals more difficult. We used high‐frequency, in situ nitrate sensors strategically deployed across the agricultural state of Iowa to evaluate 2016 stream concentrations at 60 sites and loads at 35 sites. The generated data, collected at an average of 225 days per site, show daily average nitrate‐N yields ranging from 12 to 198 g/ha, with annual yields as high as 53 kg/ha from the intensely drained Des Moines Lobe. Thirteen of the sites that capture water from 82.5% of Iowa's area show statewide nitrate‐N loading in 2016 totaled 477 million kg, or 41% of the load delivered to the Mississippi–Atchafalaya River Basin (MARB). Considering the substantial private and public investment being made to reduce nitrate loading in many states within the MARB, networks of continuous, in situ measurement devices as described here can inform efforts to track year‐to‐year changes in nitrate load related to weather and conservation implementation. Nitrate and other data from the sensor network described in this study are made publicly available in real time through the Iowa Water Quality Information System.

show abstract

“…They gather soils supported by basaltic rock (16a), scoria and tuffs , and (c) (1 : 100 000 soil map, source: INRA). Icons for X-band radars from the IFLOODS project website (http://ifis.iowafloodcenter.org/ifis/more/ifloods/) (Demir et al, 2015).…”

Section: Catchment Descriptionmentioning

confidence: 99%

A high space–time resolution dataset linking meteorological forcing and hydro-sedimentary response in a mesoscale Mediterranean catchment (Auzon) of the Ardèche region, France

Nord

Boudevillain

Berne

et al. 2017

Earth Syst. Sci. Data

View full text Add to dashboard Cite

Abstract.A comprehensive hydrometeorological dataset is presented spanning the period 1 January 2011-31 December 2014 to improve the understanding of the hydrological processes leading to flash floods and the relation between rainfall, runoff, erosion and sediment transport in a mesoscale catchment (Auzon, 116 km 2 ) of the Mediterranean region. Badlands are present in the Auzon catchment and well connected to high-gradient channels of bedrock rivers which promotes the transfer of suspended solids downstream. The number of observed variables, the various sensors involved (both in situ and remote) and the space-time resolution (∼ km 2 , ∼ min) of this comprehensive dataset make it a unique contribution to research communities focused on hydrometeorology, surface hydrology and erosion. Given that rainfall is highly variable in space and time in this region, the observation system enables assessment of the hydrological response to rainfall fields. Indeed, (i) rainfall data are provided by rain gauges (both a research network of 21 rain gauges with a 5 min time step and an operational network of 10 rain gauges with a 5 min or 1 h time step), S-band Doppler dual-polarization radars (1 km 2 , 5 min resolution), disdrometers (16 sensors working at 30 s or 1 min time step) and Micro Rain Radars (5 sensors, 100 m height resolution). Additionally, during the special observation period (SOP-1) of the HyMeX (Hydrological Cycle in the Mediterranean Experiment) project, two X-band radars provided precipitation measurements atPublished by Copernicus Publications. 222G. Nord et al.: High-resolution hydrometeorological data in a mesoscale Mediterranean catchment very fine spatial and temporal scales (1 ha, 5 min). (ii) Other meteorological data are taken from the operational surface weather observation stations of Météo-France (including 2 m air temperature, atmospheric pressure, 2 m relative humidity, 10 m wind speed and direction, global radiation) at the hourly time resolution (six stations in the region of interest). (iii) The monitoring of surface hydrology and suspended sediment is multi-scale and based on nested catchments. Three hydrometric stations estimate water discharge at a 2-10 min time resolution. Two of these stations also measure additional physico-chemical variables (turbidity, temperature, conductivity) and water samples are collected automatically during floods, allowing further geochemical characterization of water and suspended solids. Two experimental plots monitor overland flow and erosion at 1 min time resolution on a hillslope with vineyard. A network of 11 sensors installed in the intermittent hydrographic network continuously measures water level and water temperature in headwater subcatchments (from 0.17 to 116 km 2 ) at a time resolution of 2-5 min. A network of soil moisture sensors enables the continuous measurement of soil volumetric water content at 20 min time resolution at 9 sites. Additionally, concomitant observations (soil moisture measurements and stream gauging) were performed during floo...

show abstract

Data-Enabled Field Experiment Planning, Management, and Research Using Cyberinfrastructure

Cited by 40 publications

References 25 publications

A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning

A Rainfall‐Runoff Model With LSTM‐Based Sequence‐to‐Sequence Learning

Iowa Statewide Stream Nitrate Load Calculated Using In Situ Sensor Network

A high space–time resolution dataset linking meteorological forcing and hydro-sedimentary response in a mesoscale Mediterranean catchment (Auzon) of the Ardèche region, France

Contact Info

Product

Resources

About