Articles | Volume 20, issue 7
Research article 04 Jul 2016
Research article | 04 Jul 2016
Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds
Julie E. Shortridge et al.
No articles found.
Wanshu Nie, Sujay V. Kumar, Kristi R. Arsenault, Christa D. Peters-Lidard, Iliana E. Mladenova, Karim Bergaoui, Abheera Hazra, Benjamin F. Zaitchik, Sarith P. Mahanama, Rachael McDonnell, David M. Mocko, and Mahdi Navari
Hydrol. Earth Syst. Sci. Discuss.,
Preprint under review for HESSShort summary
The Middle East and North Africa region faces significant food/water insecurity and hydrological hazards. Here we investigate the value of assimilating remote sensing datasets into an earth system model to help build an effective drought monitoring system, supporting risk mitigation and management by countries in the region. We highlight incorporating satellite-informed vegetation condition into the model as one of the key processes to be captured for a successful application for the region.
Mahmoud Osman, Benjamin F. Zaitchik, Hamada S. Badr, Jordan I. Christian, Tsegaye Tadesse, Jason A. Otkin, and Martha C. Anderson
Hydrol. Earth Syst. Sci., 25, 565–581,Short summary
Our study of flash droughts' definitions over the United States shows that published definitions yield markedly different inventories of flash drought geography and frequency. Results suggest there are several pathways that can lead to events that are characterized as flash droughts. Lack of consensus across definitions helps to explain apparent contradictions in the literature on trends and indicates the selection of a definition is important for accurate monitoring of different mechanisms.
Yifan Zhou, Benjamin F. Zaitchik, Sujay V. Kumar, Kristi R. Arsenault, Mir A. Matin, Faisal M. Qamer, Ryan A. Zamora, and Kiran Shakya
Hydrol. Earth Syst. Sci., 25, 41–61,Short summary
South and Southeast Asia face significant food insecurity and hydrological hazards. Here we introduce a South and Southeast Asia hydrological monitoring and sub-seasonal to seasonal forecasting system (SAHFS-S2S) to help local governments and decision-makers prepare for extreme hydroclimatic events. The monitoring system captures soil moisture variability well in most regions, and the forecasting system offers skillful prediction of soil moisture variability 2–3 months in advance, on average.
Justin Schulte, Frederick Policelli, and Benjamin Zaitchik
Nonlin. Processes Geophys. Discuss.,
Revised manuscript accepted for NPGShort summary
The skewness of a time series is commonly used to quantify the extent to which positive (negative) deviations from the mean are larger than negative (positive) ones. However, in some cases, traditional skewness may not provide reliable information about time series skewness, motivating the development of a waveform skewness index in this paper. The waveform skewness index is used to show that changes in the relationship strength between climate time series could arise from changes in skewness.
Justin Schulte, Frederick Policielli, and Benjamin Zaitchik
Hydrol. Earth Syst. Sci., 24, 5473–5489,Short summary
Wavelet coherence is now a commonly used method for detecting scale-dependent relationships between time series. In this study, the concept of wavelet coherence is generalized to higher-order wavelet coherence methods that quantify the relationship between higher-order statistical moments associated with two time series. The methods are applied to the El Niño–Southern Oscillation (ENSO) and the Indian monsoon to show that the ENSO–Indian monsoon relationship is impacted by ENSO nonlinearity.
Shraddhanand Shukla, Kristi R. Arsenault, Abheera Hazra, Christa Peters-Lidard, Randal D. Koster, Frank Davenport, Tamuka Magadzire, Chris Funk, Sujay Kumar, Amy McNally, Augusto Getirana, Greg Husak, Ben Zaitchik, Jim Verdin, Faka Dieudonne Nsadisa, and Inbal Becker-Reshef
Nat. Hazards Earth Syst. Sci., 20, 1187–1201,Short summary
The region of southern Africa is prone to climate-driven food insecurity events, as demonstrated by the major drought event in 2015–2016. This study demonstrates that recently developed NASA Hydrological Forecasting and Analysis System-based root-zone soil moisture monitoring and forecasting products are well correlated with interannual regional crop yield, can identify below-normal crop yield events and provide skillful crop yield forecasts, and hence support early warning of food insecurity.
S. Satti, B. Zaitchik, and S. Siddiqui
Hydrol. Earth Syst. Sci., 19, 2275–2293,
Related subject area
Subject: Water Resources Management | Techniques and Approaches: Mathematical applicationsOptimal water use strategies for mitigating high urban temperaturesPhysical versus economic water footprints in crop production: a spatial and temporal analysis for ChinaAI-based techniques for multi-step streamflow forecasts: Application for multi-objective reservoir operation optimization and performance assessmentDevelopment of a revised method for indicators of hydrologic alteration for analyzing the cumulative impacts of cascading reservoirs on flow regimeChanging global cropping patterns to minimize national blue water scarcityClimate change impacts on the Water Highway project in MoroccoHESS Opinions: How should a future water census address consumptive use? (And where can we substitute withdrawal data while we wait?)Complex relationship between seasonal streamflow forecast skill and value in reservoir operationsWater footprint of crop production for different crop structures in the Hebei southern plain, North ChinaBenchmark levels for the consumptive water footprint of crop production for different environmental conditions: a case study for winter wheat in ChinaTechnical note: Multiple wavelet coherence for untangling scale-specific and localized multivariate relationships in geosciencesThe question of Sudan: a hydro-economic optimization model for the Sudanese Blue NileEvolution of the human–water relationships in the Heihe River basin in the past 2000 yearsA dynamic water accounting framework based on marginal resource opportunity costClimate change and non-stationary flood risk for the upper Truckee River basinDetermining regional limits and sectoral constraints for water useChina's water sustainability in the 21st century: a climate-informed water risk assessment covering multi-sector water demandsRecent evolution of China's virtual water trade: analysis of selected crops and considerations for policyAssessing water reservoirs management and development in Northern VietnamA framework for the quantitative assessment of climate change impacts on water-related activities at the basin scale
Bin Liu, Zhenghui Xie, Shuang Liu, Yujing Zeng, Ruichao Li, Longhuan Wang, Yan Wang, Binghao Jia, Peihua Qin, Si Chen, Jinbo Xie, and ChunXiang Shi
Hydrol. Earth Syst. Sci., 25, 387–400,Short summary
We implemented both urban water use schemes in a model (Weather Research and Forecasting model) and assessed their cooling effects with different amounts of water in different parts of the city (center, suburbs, and rural areas) for both road sprinkling and urban irrigation by model simulation. Then, we developed an optimization scheme to find out the optimal water use strategies for mitigating high urban temperatures.
Xi Yang, La Zhuo, Pengxuan Xie, Hongrong Huang, Bianbian Feng, and Pute Wu
Hydrol. Earth Syst. Sci., 25, 169–191,Short summary
Maximizing economic benefits with higher water productivity or lower water footprint is the core sustainable goal of agricultural water resources management. Here we look at spatial and temporal variations and developments in both production-based (PWF) and economic value-based (EWF) water footprints of crops, by taking a case study for China. A synergy evaluation index is proposed to further quantitatively evaluate the synergies and trade-offs between PWF and EWF.
Yuxue Guo, Yue-Ping Xu, Xinting Yu, Hao Chen, Haiting Gu, and Jingkai Xie
Hydrol. Earth Syst. Sci. Discuss.,
Revised manuscript accepted for HESSShort summary
We developed an AI-based management methodology to assess forecast quality and forecast-informed reservoir operation performance together due to uncertain inﬂow forecasts. Results showed that higher forecast performance could lead to improved reservoir operation, while uncertain forecasts were more valuable than deterministic forecasts. Moreover, the relationship between forecast horizon and reservoir operation was complex and depended on operating configurations and performance measures.
Xingyu Zhou, Xiaorong Huang, Hongbin Zhao, and Kai Ma
Hydrol. Earth Syst. Sci., 24, 4091–4107,Short summary
The main objective of this work is to discuss the cumulative effects on flow regime with the construction of cascade reservoirs. A revised IHA (indicators of hydrologic alteration) method was developed by using a projection pursuit method based on the real-coded accelerated genetic algorithm in this study. Through this method, IHA parameters with a high contribution to hydrological-alteration evaluation could be selected out and given high weight to reduce the redundancy among the IHA metrics.
Hatem Chouchane, Maarten S. Krol, and Arjen Y. Hoekstra
Hydrol. Earth Syst. Sci., 24, 3015–3031,Short summary
Previous studies on water saving through food trade focussed either on comparing water productivities among countries or on analysing food trade in relation to national water endowments. Here, we consider, for the first time, both differences in water productivities and water endowments to analyse national comparative advantages. Our study reveals that blue water scarcity can be reduced to sustainable levels by changing cropping patterns while maintaining current levels of global production.
Nabil El Moçayd, Suchul Kang, and Elfatih A. B. Eltahir
Hydrol. Earth Syst. Sci., 24, 1467–1483,Short summary
The present work addresses the impact of climate change on the Water Highway project in Morocco. This project aims to transfer 860 × 106 m3 yr−1 of water from the north to the south. As the project is very sensitive to the availability of water in the northern regions, we evaluate its feasibility under different future climate change scenarios: under a pessimistic climate scenario, the project is infeasible; however, under an optimistic scenario a rescaled version might be feasible.
Benjamin L. Ruddell
Hydrol. Earth Syst. Sci., 22, 5551–5558,Short summary
We now lack sufficient empirical observations of consumptive use of water by humans and their economy, so it is worth considering what we can do with the withdrawal-based water use data we already possess. Fortunately, a wide range of applied water management and policy questions can be addressed using currently available withdrawal data. This discussion identifies important data collection problems and argues that the withdrawal data we already possess are adequate for some important purposes.
Sean W. D. Turner, James C. Bennett, David E. Robertson, and Stefano Galelli
Hydrol. Earth Syst. Sci., 21, 4841–4859,Short summary
This study investigates the relationship between skill and value of ensemble seasonal streamflow forecasts. Using data from a modern forecasting system, we show that skilled forecasts are more likely to provide benefits for reservoirs operated to maintain a target water level rather than reservoirs operated to satisfy a target demand. We identify the primary causes for this behaviour and provide specific recommendations for assessing the value of forecasts for reservoirs with supply objectives.
Yingmin Chu, Yanjun Shen, and Zaijian Yuan
Hydrol. Earth Syst. Sci., 21, 3061–3069,Short summary
In this study, we analyzed the water footprint (WF) of crop production and found winter wheat, summer maize and vegetables were the top water-consuming crops in the Hebei southern plain (HSP). The total WF, WFblue, WFgreen and WFgrey for 13 years (2000–2012) of crop production were 604.8, 288.5, 141.3 and 175.0 km3, respectively, with an annual downtrend from 2000 to 2012. Finally, we evaluated a reasonable farming structure by analyzing scenarios of the main crops' WF.
La Zhuo, Mesfin M. Mekonnen, and Arjen Y. Hoekstra
Hydrol. Earth Syst. Sci., 20, 4547–4559,Short summary
Benchmarks for the water footprint (WF) of crop production can serve as a reference and be helpful in setting WF reduction targets. The study explores which environmental factors should be distinguished when determining benchmarks for the consumptive (green and blue) WF of crops. Through a case study for winter wheat in China over 1961–2008, we find that when determining benchmark levels for the consumptive WF of a crop, it is most useful to distinguish between different climate zones.
Wei Hu and Bing Cheng Si
Hydrol. Earth Syst. Sci., 20, 3183–3191,Short summary
Bivariate wavelet coherence has been used to explore scale- and location-specific relationships between two variables. In reality, a process occurring on land surface is usually affected by more than two factors. Therefore, this manuscript is to develop a multiple wavelet coherence method. Results showed that new method outperforms other multivariate methods. Matlab codes for a new method are provided. This method can be widely applied in geosciences where a variable is controlled by many factors.
S. Satti, B. Zaitchik, and S. Siddiqui
Hydrol. Earth Syst. Sci., 19, 2275–2293,
Z. Lu, Y. Wei, H. Xiao, S. Zou, J. Xie, J. Ren, and A. Western
Hydrol. Earth Syst. Sci., 19, 2261–2273,Short summary
This paper quantitatively analyzed the evolution of human-water relationships in the Heihe River basin over the past 2000 years by reconstructing the catchment water balance. The results provided the basis for investigating the impacts of human societies on hydrological systems. The evolutionary processes of human-water relationships can be divided into four stages: predevelopment, take-off, acceleration, and rebalancing. And the transition of the human-water relationship had no fixed pattern.
A. Tilmant, G. Marques, and Y. Mohamed
Hydrol. Earth Syst. Sci., 19, 1457–1467,Short summary
As water resources are increasingly used for various purposes, there is a need for a unified framework to describe, quantify and classify water use in a region, be it a catchment, a river basin or a country. This paper presents a novel water accounting framework whereby the contribution of traditional water uses but also storage services are properly considered.
L. E. Condon, S. Gangopadhyay, and T. Pruitt
Hydrol. Earth Syst. Sci., 19, 159–175,
T. K. Lissner, C. A. Sullivan, D. E. Reusser, and J. P. Kropp
Hydrol. Earth Syst. Sci., 18, 4039–4052,
X. Chen, D. Naresh, L. Upmanu, Z. Hao, L. Dong, Q. Ju, J. Wang, and S. Wang
Hydrol. Earth Syst. Sci., 18, 1653–1662,
J. Shi, J. Liu, and L. Pinter
Hydrol. Earth Syst. Sci., 18, 1349–1357,
A. Castelletti, F. Pianosi, X. Quach, and R. Soncini-Sessa
Hydrol. Earth Syst. Sci., 16, 189–199,
D. Anghileri, F. Pianosi, and R. Soncini-Sessa
Hydrol. Earth Syst. Sci., 15, 2025–2038,
Abrahart, R. J. and See, L. M.: Neural network modelling of non-linear hydrological relationships, Hydrol. Earth Syst. Sci., 11, 1563–1579, https://doi.org/10.5194/hess-11-1563-2007, 2007.
Achenef, H., Tilahun, A., and Molla, B.: Tana Sub Basin Initial Scenarios and Indicators Development Report, Tana Sub Basin Organization, Bahir Dar, Ethiopia, 8–9, 2013.
Alemayehu, T., McCartney, M., and Kebede, S.: The water resource implications of planned development in the Lake Tana catchment, Ethiopia, Ecohydrol. Hydrobiol., 10, 211–221, https://doi.org/10.2478/v10104-011-0023-6, 2010.
Antar, M. A., Elassiouti, I., and Allam, M. N.: rainfall–runoff modelling using artificial neural networks technique: a Blue Nile catchment case study, Hydrol. Process., 20, 1201–1216, https://doi.org/10.1002/hyp.5932, 2006.
Aqil, M., Kita, I., Yano, A., and Nishiyama, S.: Neural Networks for Real Time Catchment Flow Modeling and Prediction, Water Resour. Manage., 21, 1781–1796, https://doi.org/10.1007/s11269-006-9127-y, 2007.
Asefa, T., Kemblowski, M., McKee, M., and Khalil, A.: Multi-time scale stream flow predictions: The support vector machines approach, J. Hydrol., 318, 7–16, https://doi.org/10.1016/j.jhydrol.2005.06.001, 2006.
Beven, K. J.: rainfall–runoff Modelling: The Primer, John Wiley & Sons, West Sussex, UK, 83–113 and 307–309, 2011.
Breiman, L.: Bagging predictors, Mach. Learn., 24, 123–140, https://doi.org/10.1007/BF00058655, 1996.
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, 2001.
Chen, F., Mitchell, K., Schaake, J., Xue, Y., Pan, H.-L., Koren, V., Duan, Q. Y., Ek, M., and Betts, A.: Modeling of land surface evaporation by four schemes and comparison with FIFE observations, J. Geophys. Res., 101, 7251–7268, https://doi.org/10.1029/95JD02165, 1996.
Chibanga, R., Berlamont, J., and Vandewalle, J.: Modelling and forecasting of hydrological variables using artificial neural networks: the Kafue River sub-basin, Hydrolog. Sci. J., 48, 363–379, https://doi.org/10.1623/hysj.48.3.363.45282, 2003.
Criss, R. E. and Winston, W. E.: Do Nash values have value? Discussion and alternate proposals, Hydrol. Process., 22, 2723–2725, https://doi.org/10.1002/hyp.7072, 2008.
Dessie, M., Verhoest, N. E. C., Admasu, T., Pauwels, V. R. N., Poesen, J., Adgo, E., Deckers, J., and Nyssen, J.: Effects of the floodplain on river discharge into Lake Tana (Ethiopia), J. Hydrol., 519, 699–710, https://doi.org/10.1016/j.jhydrol.2014.08.007, 2014.
De Vos, N. J. and Rientjes, T. H. M.: Multiobjective training of artificial neural networks for rainfall–runoff modeling, Water Resour. Res., 44, W08434, https://doi.org/10.1029/2007WR006734, 2008.
Ek, M. B., Mitchell, K. E., Lin, Y., Rogers, E., Grunmann, P., Koren, V., Gayno, G., and Tarpley, J. D.: Implementation of Noah land surface model advances in the National Centers for Environmental Prediction operational mesoscale Eta model, J. Geophys. Res., 108, 8851, https://doi.org/10.1029/2002JD003296, 2003.
Elshorbagy, A., Corzo, G., Srinivasulu, S., and Solomatine, D. P.: Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology – Part 1: Concepts and methodology, Hydrol. Earth Syst. Sci., 14, 1931–1941, https://doi.org/10.5194/hess-14-1931-2010, 2010a.
Elshorbagy, A., Corzo, G., Srinivasulu, S., and Solomatine, D. P.: Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology – Part 2: Application, Hydrol. Earth Syst. Sci., 14, 1943–1961, https://doi.org/10.5194/hess-14-1943-2010, 2010b.
Friedman, J. H.: Multivariate adaptive regression splines, Ann. Stat., 19, 1–67, 1991.
Galelli, S. and Castelletti, A.: Assessing the predictive capability of randomized tree-based ensembles in streamflow modelling, Hydrol. Earth Syst. Sci., 17, 2669–2684, https://doi.org/10.5194/hess-17-2669-2013, 2013a.
Galelli, S. and Castelletti, A.: Tree-based iterative input variable selection for hydrological modeling, Water Resour. Res., 49, 4295–4310, https://doi.org/10.1002/wrcr.20339, 2013b.
Garede, N. M. and Minale, A. S.: Land Use/Cover Dynamics in Ribb Watershed, North Western Ethiopia, J. Nat. Sci. Res., 4, 9–16, 2014.
Gaume, E. and Gosset, R.: Over-parameterisation, a major obstacle to the use of artificial neural networks in hydrology?, Hydrol. Earth Syst. Sci., 7, 693–706, https://doi.org/10.5194/hess-7-693-2003, 2003.
Gebrehiwot, S. G., Taye, A., and Bishop, K.: Forest Cover and Stream Flow in a Headwater of the Blue Nile: Complementing Observational Data Analysis with Community Perception, Ambio, 39, 284–294, https://doi.org/10.1007/s13280-010-0047-y, 2010.
Gleick, P. H.: Methods for evaluating the regional hydrologic impacts of global climatic changes, J. Hydrol., 88, 97–116, https://doi.org/10.1016/0022-1694(86)90199-X, 1986.
Han, D., Kwong, T., and Li, S.: Uncertainties in real-time flood forecasting with neural networks, Hydrol. Process., 21, 223–228, https://doi.org/10.1002/hyp.6184, 2007.
Harris, I., Jones, P. D., Osborn, T. J., and Lister, D. H.: Updated high-resolution grids of monthly climatic observations – the CRU TS3.10 Dataset, Int. J. Climatol., 34, 623–642, https://doi.org/10.1002/joc.3711, 2014.
Hastie, T. and Tibshirani, R.: Generalized Additive Models, Stat. Sci., 1, 297–310, 1986.
Hastie, T. and Tibshirani, R.: Generalized additive models, Chapman and Hall, London, 9–35, 1990.
Hastie, T., Tibshirani, R., and Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd Edn., Springer, New York, 389–414, 2009.
Iorgulescu, I. and Beven, K. J.: Nonparametric direct mapping of rainfall–runoff relationships: An alternative approach to data analysis and modeling?, Water Resour. Res., 40, W08403, https://doi.org/10.1029/2004WR003094, 2004.
Jain, A., Sudheer, K. P., and Srinivasulu, S.: Identification of physical processes inherent in artificial neural network rainfall runoff models, Hydrol. Process., 18, 571–581, https://doi.org/10.1002/hyp.5502, 2004.
Kuhn, M.: caret: Classification and regression training, available at: http://CRAN.R-project.org/package=caret, last access: 6 September 2015.
Kuhn, M., Weston, S., Keefer, C., and Coulter, N.: Cubist: Rule- and instance-based regression modeling, available at: http://CRAN.R-project.org/package=Cubist (last access: 6 September 2015), 2014.
Legates, D. R. and McCabe Jr., G. J.: Evaluating the use of "goodness-of-fit" measures in hydrologic and hydroclimatic model validation, Water Resour. Res., 35, 233–241, 1999.
Liaw, A. and Wiener, M.: Classification and regression by randomForest, R News, 2, 18–22, 2002.
Lin, J.-Y., Cheng, C.-T., and Chau, K.-W.: Using support vector machines for long-term discharge prediction, Hydrolog. Sci. J., 51, 599–612, https://doi.org/10.1623/hysj.51.4.599, 2006.
Liston, G. E. and Elder, K.: A Meteorological Distribution System for High-Resolution Terrestrial Modeling (MicroMet), J. Hydrometeorol., 7, 217–234, https://doi.org/10.1175/JHM486.1, 2006.
Machado, F., Mine, M., Kaviski, E., and Fill, H.: Monthly rainfall–runoff modelling using artificial neural networks, Hydrolog. Sci. J., 56, 349–361, https://doi.org/10.1080/02626667.2011.559949, 2011.
Maier, H. R., Jain, A., Dandy, G. C., and Sudheer, K. P.: Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions, Environ. Model. Softw., 25, 891–909, https://doi.org/10.1016/j.envsoft.2010.02.003, 2010.
Mathevet, T., Michel, C., Andreassian, V., and Perrin, C.: A bounded version of the Nash-sutcliffe criterion for better model assessment on large sets of basins, in IAHS-AISH publication, International Association of Hydrological Sciences, 211–219, available at: http://cat.inist.fr/?aModele=afficheN&cpsidt=18790113 (last access: 10 February 2016), 2006.
Mekonnen, M. A., Wörman, A., Dargahi, B., and Gebeyehu, A.: Hydrological modelling of Ethiopian catchments using limited data, Hydrol. Process., 23, 3401–3408, https://doi.org/10.1002/hyp.7470, 2009.
Milborrow, S.: earth: Multivariate Adaptive Regression Splines, available at: http://CRAN.R-project.org/package=earth, last access: 6 September 2015.
Montgomery, D. C., Peck, E. A., and Vining, G. G.: Introduction to Linear Regression Analysis, John Wiley & Sons, Hoboken, New Jersey, 84–95, 2012.
Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., and Veith, T. L.: Model evaluation guidelines for systematic quantification of accuracy in watershed simulations, T. ASABE, 50, 885–900, 2007.
Nash, J. E. and Sutcliffe, J. V.: River flow forecasting through conceptual models part I – A discussion of principles, J. Hydrol., 10, 282–290, https://doi.org/10.1016/0022-1694(70)90255-6, 1970.
Pushpalatha, R., Perrin, C., Moine, N. L., and Andréassian, V.: A review of efficiency criteria suitable for evaluating low-flow simulations, J. Hydrol., 420–421, 171–182, https://doi.org/10.1016/j.jhydrol.2011.11.055, 2012.
Quinlan, J. R.: Learning with Continuous Classes, in: Proceedings of the 5th Australian Joint Conference on Artificial Intelligence, World Scientific, Singapore, 343–348, 1992.
R Development Core Team: R: A language and environment for statistical computing, R Foundation for Statistical Computing, Vienna, Austria, available at: http://www.R-project.org (last access: 6 September 2015), 2014.
Rientjes, T. H. M., Haile, A. T., Kebede, E., Mannaerts, C. M. M., Habib, E., and Steenhuis, T. S.: Changes in land cover, rainfall and stream flow in Upper Gilgel Abbay catchment, Blue Nile basin – Ethiopia, Hydrol. Earth Syst. Sci., 15, 1979–1989, https://doi.org/10.5194/hess-15-1979-2011, 2011.
Ripley, B. D.: Pattern Recognition and Neural Networks, Cambridge University Press, Cambridge, UK, 143–173, 1996.
Schaefli, B. and Gupta, H. V.: Do Nash values have value?, Hydrol. Process., 21, 2075–2080, https://doi.org/10.1002/hyp.6825, 2007.
See, L., Solomatine, D., Abrahart, R., and Toth, E.: Hydroinformatics: computational intelligence and technological developments in water science applications – Editorial, Hydrolog. Sci. J., 52, 391–396, https://doi.org/10.1623/hysj.52.3.391, 2007.
Setegn, S. G., Srinivasan, R., Melesse, A. M., and Dargahi, B.: SWAT model application and prediction uncertainty analysis in the Lake Tana Basin, Ethiopia, Hydrol. Process., 24, 357–367, https://doi.org/10.1002/hyp.7457, 2009.
Setegn, S. G., Rayner, D., Melesse, A. M., Dargahi, B., and Srinivasan, R.: Impact of climate change on the hydroclimatology of Lake Tana Basin, Ethiopia, Water Resour. Res., 47, W04511, https://doi.org/10.1029/2010WR009248, 2011.
Sheffield, J., Goteti, G., and Wood, E. F.: Development of a 50-Year High-Resolution Global Dataset of Meteorological Forcings for Land Surface Modeling, J. Climate, 19, 3088–3111, https://doi.org/10.1175/JCLI3790.1, 2006.
Shortridge, J. E., Falconi, S. M., Zaitchik, B. F., and Guikema, S. D.: Climate, agriculture, and hunger: statistical prediction of undernourishment using nonlinear regression and data-mining techniques, J. Appl. Stat., 42, 2367–2390, https://doi.org/10.1080/02664763.2015.1032216, 2015.
Solomatine, D. P. and Ostfeld, A.: Data-driven modelling: some past experiences and new approaches, J. Hydroinform., 10, 3–22, https://doi.org/10.2166/hydro.2008.015, 2008.
Sorooshian, S. and Dracup, J. A.: Stochastic parameter estimation procedures for hydrologie rainfall–runoff models: Correlated and heteroscedastic error cases, Water Resour. Res., 16, 430–442, https://doi.org/10.1029/WR016i002p00430, 1980.
Steenhuis, T. S., Collick, A. S., Easton, Z. M., Leggesse, E. S., Bayabil, H. K., White, E. D., Awulachew, S. B., Adgo, E., and Ahmed, A. A.: Predicting discharge and sediment for the Abay (Blue Nile) with a simple model, Hydrol. Process., 23, 3728–3737, https://doi.org/10.1002/hyp.7513, 2009.
Sudheer, K. P. and Jain, A.: Explaining the internal behaviour of artificial neural network river flow models, Hydrol. Process., 18, 833–844, https://doi.org/10.1002/hyp.5517, 2004.
Van Griensven, A., Ndomba, P., Yalew, S., and Kilonzo, F.: Critical review of SWAT applications in the upper Nile basin countries, Hydrol. Earth Syst. Sci., 16, 3371–3381, https://doi.org/10.5194/hess-16-3371-2012, 2012.
Venables, W. N. and Ripley, B. D.: Modern Applied Statistics with S-PLUS, Springer Science & Business Media, New York, 211–250, 2013.
Wilby, R. L.: Uncertainty in water resource model parameters used for climate change impact assessment, Hydrol. Process., 19, 3201–3219, https://doi.org/10.1002/hyp.5819, 2005.
Wilby, R. L., Abrahart, R. J., and Dawson, C. W.: Detection of conceptual model rainfall–runoff processes inside an artificial neural network, Hydrolog. Sci. J., 48, 163–181, https://doi.org/10.1623/hysj.126.96.36.199699, 2003.
Wood, S. N.: Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models, J. Roy. Stat. Soc. B, 73, 3–36, https://doi.org/10.1111/j.1467-9868.2010.00749.x, 2011.
Wood, S. N.: On p-values for smooth components of an extended generalized additive model, Biometrika, 100, 221–228 https://doi.org/10.1093/biomet/ass048, 2012.
This paper compares six methods for data-driven rainfall–runoff simulation in terms of predictive accuracy, error structure, interpretability, and uncertainty. We demonstrate that autocorrelation in model errors can result in biased estimates of important values and show how certain model structures can be more easily interpreted to yield insights on physical watershed function. Finally, we explore how model structure can impact uncertainty in climate change sensitivity estimates.
This paper compares six methods for data-driven rainfall–runoff simulation in terms of...