skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Quantifying Climate and Catchment Control on Hydrological Drought in the Continental United States

Abstract

The evolution of hydrological drought events is a result of complex (nonlinear) interactions between climate and catchment processes. To investigate such nonlinear relationship, we integrated a machine learning modeling framework based on the random forest (RF) algorithms with an interpretation framework to quantify the role of climate and catchment controls on hydrological drought. More particularly, our framework interprets a built RF machine-learning model to identify dominant variables and visualize their functional dependence and interaction effects on hydrological drought characteristics utilizing concepts of minimal depth, interactive depth, and partial dependence. We test our proposed modeling framework based on a set of 652 continental United States catchments with minimal human interference for a period of 1979–2010. Application of this framework indicated presence of three distinct drought regimes, which includes, Regime 1: droughts with longer duration, less frequent and lesser intensity; Regime 2: droughts with moderate duration, moderate frequency, and moderate intensity; and Regime 3: droughts with shorter duration, more frequent, and more intense. RF algorithm was able to accurately model the drought characteristics (intensity, duration, and number of events) for all the three drought regimes as a function of selected variables. It was observed that the type of dominant variables as wellmore » as their nonlinear functional relationship with hydrological droughts characteristics can vary between three selected regimes. Finally, our interpretation framework indicated that catchment characteristics have a significant role in controlling the hydrologic drought for catchments (regime 1), whereas both climate and catchment characteristics control hydrological drought in regimes 2 and 3.« less

Authors:
 [1];  [2]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Clemson Univ., SC (United States)
  2. Clemson Univ., SC (United States)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE; National Science Foundation (NSF)
OSTI Identifier:
1649301
Grant/Contract Number:  
AC05-00OR22725
Resource Type:
Accepted Manuscript
Journal Name:
Water Resources Research
Additional Journal Information:
Journal Volume: 56; Journal Issue: 1; Journal ID: ISSN 0043-1397
Publisher:
American Geophysical Union (AGU)
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES

Citation Formats

Konapala, Goutam, and Mishra, Ashok. Quantifying Climate and Catchment Control on Hydrological Drought in the Continental United States. United States: N. p., 2019. Web. https://doi.org/10.1029/2018wr024620.
Konapala, Goutam, & Mishra, Ashok. Quantifying Climate and Catchment Control on Hydrological Drought in the Continental United States. United States. https://doi.org/10.1029/2018wr024620
Konapala, Goutam, and Mishra, Ashok. Wed . "Quantifying Climate and Catchment Control on Hydrological Drought in the Continental United States". United States. https://doi.org/10.1029/2018wr024620. https://www.osti.gov/servlets/purl/1649301.
@article{osti_1649301,
title = {Quantifying Climate and Catchment Control on Hydrological Drought in the Continental United States},
author = {Konapala, Goutam and Mishra, Ashok},
abstractNote = {The evolution of hydrological drought events is a result of complex (nonlinear) interactions between climate and catchment processes. To investigate such nonlinear relationship, we integrated a machine learning modeling framework based on the random forest (RF) algorithms with an interpretation framework to quantify the role of climate and catchment controls on hydrological drought. More particularly, our framework interprets a built RF machine-learning model to identify dominant variables and visualize their functional dependence and interaction effects on hydrological drought characteristics utilizing concepts of minimal depth, interactive depth, and partial dependence. We test our proposed modeling framework based on a set of 652 continental United States catchments with minimal human interference for a period of 1979–2010. Application of this framework indicated presence of three distinct drought regimes, which includes, Regime 1: droughts with longer duration, less frequent and lesser intensity; Regime 2: droughts with moderate duration, moderate frequency, and moderate intensity; and Regime 3: droughts with shorter duration, more frequent, and more intense. RF algorithm was able to accurately model the drought characteristics (intensity, duration, and number of events) for all the three drought regimes as a function of selected variables. It was observed that the type of dominant variables as well as their nonlinear functional relationship with hydrological droughts characteristics can vary between three selected regimes. Finally, our interpretation framework indicated that catchment characteristics have a significant role in controlling the hydrologic drought for catchments (regime 1), whereas both climate and catchment characteristics control hydrological drought in regimes 2 and 3.},
doi = {10.1029/2018wr024620},
journal = {Water Resources Research},
number = 1,
volume = 56,
place = {United States},
year = {2019},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 2 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

A Survey of Methods for Explaining Black Box Models
journal, January 2019

  • Guidotti, Riccardo; Monreale, Anna; Ruggieri, Salvatore
  • ACM Computing Surveys, Vol. 51, Issue 5
  • DOI: 10.1145/3236009

High-Quality Spatial Climate data sets for the United States and Beyond
journal, January 2000


Catchment classification: hydrological analysis of catchment behavior through process-based modeling along a climate gradient
journal, January 2011

  • Carrillo, G.; Troch, P. A.; Sivapalan, M.
  • Hydrology and Earth System Sciences, Vol. 15, Issue 11
  • DOI: 10.5194/hess-15-3411-2011

Rainfall Variability, Carbon Cycling, and Plant Species Diversity in a Mesic Grassland
journal, December 2002


A process-based typology of hydrological drought
journal, January 2012


Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - Part 2: Application
journal, January 2010

  • Elshorbagy, A.; Corzo, G.; Srinivasulu, S.
  • Hydrology and Earth System Sciences, Vol. 14, Issue 10
  • DOI: 10.5194/hess-14-1943-2010

Support vector machine applications in the field of hydrology: A review
journal, June 2014


Metamodeling for Groundwater Age Forecasting in the Lake Michigan Basin
journal, July 2018

  • Fienen, Michael N.; Nolan, B. Thomas; Kauffman, Leon J.
  • Water Resources Research, Vol. 54, Issue 7
  • DOI: 10.1029/2017WR022387

Differential sensitivity to regional-scale drought in six central US grasslands
journal, February 2015


Hydrological Drought in the Anthropocene: Impacts of Local Water Extraction and Reservoir Regulation in the U.S.: Hydrological Drought in the Anthropocene
journal, November 2017

  • Wan, Wenhua; Zhao, Jianshi; Li, Hong-Yi
  • Journal of Geophysical Research: Atmospheres, Vol. 122, Issue 21
  • DOI: 10.1002/2017JD026899

High-Dimensional Variable Selection for Survival Data
journal, March 2010

  • Ishwaran, Hemant; Kogalur, Udaya B.; Gorodeski, Eiran Z.
  • Journal of the American Statistical Association, Vol. 105, Issue 489
  • DOI: 10.1198/jasa.2009.tm08622

A Ranking of Hydrological Signatures Based on Their Predictability in Space
journal, November 2018

  • Addor, N.; Nearing, G.; Prieto, C.
  • Water Resources Research, Vol. 54, Issue 11
  • DOI: 10.1029/2018WR022606

A fuzzy extension of the silhouette width criterion for cluster analysis
journal, November 2006


Regionalization of constraints on expected watershed response behavior for improved predictions in ungauged basins
journal, August 2007


Spatiotemporal characteristics of drought in Serbia
journal, March 2014


Modeling Depth of the Redox Interface at High Resolution at National Scale Using Random Forest and Residual Gaussian Simulation
journal, February 2019

  • Koch, Julian; Stisen, Simon; Refsgaard, Jens C.
  • Water Resources Research, Vol. 55, Issue 2
  • DOI: 10.1029/2018WR023939

Coupled modelling of glacier and streamflow response to future climate scenarios: MODELLING OF GLACIER AND STREAMFLOW
journal, February 2008

  • Stahl, K.; Moore, R. D.; Shea, J. M.
  • Water Resources Research, Vol. 44, Issue 2
  • DOI: 10.1029/2007WR005956

Regionalized drought flow hydrographs from a mature glaciated plateau
journal, June 1977


Topography as a driver of local terrestrial vascular plant diversity patterns
journal, May 2013


Development and evaluation of Soil Moisture Deficit Index (SMDI) and Evapotranspiration Deficit Index (ETDI) for agricultural drought monitoring
journal, November 2005


Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics: Random forests in bioinformatics
journal, October 2012

  • Boulesteix, Anne-Laure; Janitza, Silke; Kruppa, Jochen
  • Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, Vol. 2, Issue 6
  • DOI: 10.1002/widm.1072

Future dryness in the southwest US and the hydrology of the early 21st century drought
journal, December 2010

  • Cayan, D. R.; Das, T.; Pierce, D. W.
  • Proceedings of the National Academy of Sciences, Vol. 107, Issue 50
  • DOI: 10.1073/pnas.0912391107

A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists
journal, November 2018


Hydrologic Drought Atlas for Texas
journal, July 2015


Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds
journal, January 2016

  • Shortridge, Julie E.; Guikema, Seth D.; Zaitchik, Benjamin F.
  • Hydrology and Earth System Sciences, Vol. 20, Issue 7
  • DOI: 10.5194/hess-20-2611-2016

Low-complexity fuzzy relational clustering algorithms for Web mining
journal, January 2001

  • Krishnapuram, R.; Joshi, A.; Nasraoui, O.
  • IEEE Transactions on Fuzzy Systems, Vol. 9, Issue 4
  • DOI: 10.1109/91.940971

Global patterns of drought recovery
journal, August 2017

  • Schwalm, Christopher R.; Anderegg, William R. L.; Michalak, Anna M.
  • Nature, Vol. 548, Issue 7666
  • DOI: 10.1038/nature23021

Climate Change and Drought: a Perspective on Drought Indices
journal, April 2018

  • Mukherjee, Sourav; Mishra, Ashok; Trenberth, Kevin E.
  • Current Climate Change Reports, Vol. 4, Issue 2
  • DOI: 10.1007/s40641-018-0098-x

Multiple additive regression trees with application in epidemiology
journal, January 2003

  • Friedman, Jerome H.; Meulman, Jacqueline J.
  • Statistics in Medicine, Vol. 22, Issue 9
  • DOI: 10.1002/sim.1501

How climate seasonality modifies drought duration and deficit
journal, April 2014

  • Van Loon, A. F.; Tijdeman, E.; Wanders, N.
  • Journal of Geophysical Research: Atmospheres, Vol. 119, Issue 8
  • DOI: 10.1002/2013JD020383

Understanding the Role of Climate Characteristics in Drought Propagation: CLIMATE INFLUENCE ON DROUGHT PROPAGATION
journal, November 2017

  • Apurv, Tushar; Sivapalan, Murugesu; Cai, Ximing
  • Water Resources Research, Vol. 53, Issue 11
  • DOI: 10.1002/2017WR021445

Three-parameter-based streamflow elasticity model: application to MOPEX basins in the USA at annual and seasonal scales
journal, January 2016


Random Forests for Classification in Ecology
journal, November 2007

  • Cutler, D. Richard; Edwards, Thomas C.; Beard, Karen H.
  • Ecology, Vol. 88, Issue 11
  • DOI: 10.1890/07-0539.1

Droughts and anti-droughts: the low flow hydrology of Australian rivers
journal, July 2003


Hydrological drought severity explained by climate and catchment characteristics
journal, July 2015


The influence of multiyear drought on the annual rainfall‐runoff relationship: An A ustralian perspective
journal, April 2015

  • Saft, Margarita; Western, Andrew W.; Zhang, Lu
  • Water Resources Research, Vol. 51, Issue 4
  • DOI: 10.1002/2014WR015348

Accurate Computation of a Streamflow Drought Index
journal, February 2012


Exploring the link between meteorological drought and streamflow: Effects of climate-catchment interaction
journal, March 2014

  • Haslinger, Klaus; Koffler, Daniel; Schöner, Wolfgang
  • Water Resources Research, Vol. 50, Issue 3
  • DOI: 10.1002/2013WR015051

Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables
journal, January 2018

  • Hengl, Tomislav; Nussbaum, Madlene; Wright, Marvin N.
  • PeerJ, Vol. 6
  • DOI: 10.7717/peerj.5518

Catchment classification by runoff behaviour with self-organizing maps (SOM)
journal, January 2011

  • Ley, R.; Casper, M. C.; Hellebrand, H.
  • Hydrology and Earth System Sciences, Vol. 15, Issue 9
  • DOI: 10.5194/hess-15-2947-2011

Drought modeling – A review
journal, June 2011


Drought frequency analysis using cluster analysis and bivariate probability distribution
journal, February 2012


Testing the daily PRISM air temperature model on semiarid mountain slopes: Testing PRISM Temperature in Mountains
journal, June 2017

  • Strachan, Scotty; Daly, Christopher
  • Journal of Geophysical Research: Atmospheres, Vol. 122, Issue 11
  • DOI: 10.1002/2016JD025920

"Why Should I Trust You?": Explaining the Predictions of Any Classifier
conference, January 2016

  • Ribeiro, Marco Tulio; Singh, Sameer; Guestrin, Carlos
  • Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16
  • DOI: 10.1145/2939672.2939778

Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction
journal, March 2006


Streamflow sensitivity to drought scenarios in catchments with different geology: STREAMFLOW SENSITIVITY TO DROUGHT
journal, September 2014

  • Stoelzle, Michael; Stahl, Kerstin; Morhard, Andreas
  • Geophysical Research Letters, Vol. 41, Issue 17
  • DOI: 10.1002/2014GL061344

Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology - Part 1: Concepts and methodology
journal, January 2010

  • Elshorbagy, A.; Corzo, G.; Srinivasulu, S.
  • Hydrology and Earth System Sciences, Vol. 14, Issue 10
  • DOI: 10.5194/hess-14-1931-2010

Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data
journal, October 2017

  • Karpatne, Anuj; Atluri, Gowtham; Faghmous, James H.
  • IEEE Transactions on Knowledge and Data Engineering, Vol. 29, Issue 10
  • DOI: 10.1109/TKDE.2017.2720168

Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation
journal, January 2015

  • Goldstein, Alex; Kapelner, Adam; Bleich, Justin
  • Journal of Computational and Graphical Statistics, Vol. 24, Issue 1
  • DOI: 10.1080/10618600.2014.907095

Trends in extreme learning machines: A review
journal, January 2015


A framework for hydrologic classification with a review of methodologies and applications in ecohydrology: A FRAMEWORK FOR HYDROLOGIC CLASSIFICATION
journal, August 2011

  • Olden, Julian D.; Kennard, Mark J.; Pusey, Bradley J.
  • Ecohydrology, Vol. 5, Issue 4
  • DOI: 10.1002/eco.251

Hypsometric (Area-Altitude) Analysis of Erosional Topography
journal, January 1952


Role of subsurface flow in generating surface runoff: 1. Base flow contributions to channel flow
journal, June 1972


Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review
journal, June 2014


An introduction to recursive partitioning: Rationale, application, and characteristics of classification and regression trees, bagging, and random forests.
journal, December 2009

  • Strobl, Carolin; Malley, James; Tutz, Gerhard
  • Psychological Methods, Vol. 14, Issue 4
  • DOI: 10.1037/a0016973

A review of drought concepts
journal, September 2010


Hydrological drought across the world: impact of climate and physical catchment structure
journal, January 2013

  • Van Lanen, H. A. J.; Wanders, N.; Tallaksen, L. M.
  • Hydrology and Earth System Sciences, Vol. 17, Issue 5
  • DOI: 10.5194/hess-17-1715-2013

Sensitivity of drought resilience-vulnerability- exposure to hydrologic ratios in contiguous United States
journal, September 2018


A validity measure for fuzzy clustering
journal, January 1991

  • Xie, X. L.; Beni, G.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, Issue 8
  • DOI: 10.1109/34.85677

Clustering Hydrological Homogeneous Regions and Neural Network Based Index Flood Estimation for Ungauged Catchments: an Example of the Chindwin River in Myanmar
journal, October 2014

  • Latt, Zaw Zaw; Wittenberg, Hartmut; Urban, Brigitte
  • Water Resources Management, Vol. 29, Issue 3
  • DOI: 10.1007/s11269-014-0851-4

Spatial and temporal analysis of droughts in the Iberian Peninsula (1910–2000)
journal, February 2006

  • Vicente-Serrano, Sergio M.
  • Hydrological Sciences Journal, Vol. 51, Issue 1
  • DOI: 10.1623/hysj.51.1.83

Space–time modelling of catchment scale drought characteristics
journal, September 2009


Climate change impact on meteorological, agricultural, and hydrological drought in central Illinois: CLIMATE CHANGE IMPACT ON DROUGHT
journal, September 2011

  • Wang, Dingbao; Hejazi, Mohamad; Cai, Ximing
  • Water Resources Research, Vol. 47, Issue 9
  • DOI: 10.1029/2010WR009845

Hydrological drought across the world: impact of climate and physical catchment structure
journal, January 2012

  • Van Lanen, H. A. J.; Wanders, N.; Tallaksen, L. M.
  • Hydrology and Earth System Sciences Discussions, Vol. 9, Issue 10
  • DOI: 10.5194/hessd-9-12145-2012

An empirical comparison of supervised learning algorithms
conference, January 2006

  • Caruana, Rich; Niculescu-Mizil, Alexandru
  • Proceedings of the 23rd international conference on Machine learning - ICML '06
  • DOI: 10.1145/1143844.1143865

Use of a standardized runoff index for characterizing hydrologic drought
journal, January 2008

  • Shukla, Shraddhanand; Wood, Andrew W.
  • Geophysical Research Letters, Vol. 35, Issue 2
  • DOI: 10.1029/2007GL032487

B-type natriuretic peptide concentrations in contemporary Eisenmenger syndrome patients: predictive value and response to disease targeting therapy
journal, March 2012


Little change in global drought over the past 60 years
journal, November 2012

  • Sheffield, Justin; Wood, Eric F.; Roderick, Michael L.
  • Nature, Vol. 491, Issue 7424
  • DOI: 10.1038/nature11575

Influence of Summer Drought on Spatial Patterns of Resource Availability and Detritus Processing in Mediterranean Stream Sub-Basins (Sardinia, Italy)
journal, November 2004

  • Pinna, Maurizio; Fonnesu, Alessio; Sangiorgio, Franca
  • International Review of Hydrobiology, Vol. 89, Issue 5-6
  • DOI: 10.1002/iroh.200410765

Regionalization and spatial changing properties of droughts across the Pearl River basin, China
journal, November 2012


Slope, aspect and climate: Spatially explicit and implicit models of topographic microclimate in chalk grassland
journal, August 2008


Random Forests
journal, January 2001


Application of soft computing based hybrid models in hydrological variables modeling: a comprehensive review
journal, February 2016

  • Fahimi, Farzad; Yaseen, Zaher Mundher; El-shafie, Ahmed
  • Theoretical and Applied Climatology, Vol. 128, Issue 3-4
  • DOI: 10.1007/s00704-016-1735-8

Random survival forests for high-dimensional data
journal, January 2011

  • Ishwaran, Hemant; Kogalur, Udaya B.; Chen, Xi
  • Statistical Analysis and Data Mining, Vol. 4, Issue 1
  • DOI: 10.1002/sam.10103

Predicting shifts in rainfall-runoff partitioning during multiyear drought: Roles of dry period and catchment characteristics: RUNOFF SHIFTS DURING DECADAL DROUGHT
journal, December 2016

  • Saft, Margarita; Peel, Murray C.; Western, Andrew W.
  • Water Resources Research, Vol. 52, Issue 12
  • DOI: 10.1002/2016WR019525

Catchment classification: empirical analysis of hydrologic similarity based on catchment function in the eastern USA
journal, January 2011

  • Sawicz, K.; Wagener, T.; Sivapalan, M.
  • Hydrology and Earth System Sciences, Vol. 15, Issue 9
  • DOI: 10.5194/hess-15-2895-2011