ML for Flood Forecasting at Scale

01/28/2019
by   Sella Nevo, et al.
14

Effective riverine flood forecasting at scale is hindered by a multitude of factors, most notably the need to rely on human calibration in current methodology, the limited amount of data for a specific location, and the computational difficulty of building continent/global level models that are sufficiently accurate. Machine learning (ML) is primed to be useful in this scenario: learned models often surpass human experts in complex high-dimensional scenarios, and the framework of transfer or multitask learning is an appealing solution for leveraging local signals to achieve improved global performance. We propose to build on these strengths and develop ML systems for timely and accurate riverine flood prediction.

READ FULL TEXT VIEW PDF
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

04/24/2020

Towards A Domain-Customized Automated Machine Learning Framework For Networks and Systems

Clouds gather a vast volume of telemetry from their networked systems wh...
11/29/2020

ML-based Flood Forecasting: Advances in Scale, Accuracy and Reach

Floods are among the most common and deadly natural disasters in the wor...
08/04/2020

Macroeconomic Data Transformations Matter

From a purely predictive standpoint, rotating the predictors' matrix in ...
06/02/2020

Local Interpretability of Calibrated Prediction Models: A Case of Type 2 Diabetes Mellitus Screening Test

Machine Learning (ML) models are often complex and difficult to interpre...
02/17/2020

Simulating Performance of ML Systems with Offline Profiling

We advocate that simulation based on offline profiling is a promising ap...
03/12/2020

Customized Video QoE Estimation with Algorithm-Agnostic Transfer Learning

The development of QoE models by means of Machine Learning (ML) is chall...
09/29/2021

PyHard: a novel tool for generating hardness embeddings to support data-centric analysis

For building successful Machine Learning (ML) systems, it is imperative ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.

References

  • (1) The Centre for Research on the Epidemology of Disasters (CRED) - Natural Disasters 2017. https://cred.be/sites/default/files/adsr_2017.pdf, 2017. [Online; accessed 30-09-2018].
  • (2) United Nations Office for Disaster Risk Reduction (UNISDR) - The Human Cost of Weather Related Disasters. https://www.unisdr.org/2015/docs/climatechange/COP21_WeatherDisastersReport_2015_FINAL.pdf, 2015. [Online; accessed 30-09-2018].
  • (3) United Nations Development Programme (UNDP) - Sustainable Development Goals. https://shop.undp.org/pages/the-sustainable-development-goals, 2015. [Online; accessed 30-09-2018].
  • (4) World Health Organization (WHO) - Global Report on Drowning. http://www.who.int/violence_injury_prevention/global_report_drowning/Final_report_full_web.pdf, 2014. [Online; accessed 30-09-2018].
  • (5) World Bank - Global Assessment Report on Costs and Benefits of Early Warning Systems. https://www.preventionweb.net/english/hyogo/gar/2011/en/bgdocs/Rogers_&_Tsirkunov_2011.pdf, 2011. [Online; accessed 30-09-2018].
  • (6) Yohai Bar-Sinai, Stephan Hoyer, Jason Hickey, and Michael P Brenner. Data-driven discretization: a method for systematic coarse graining of partial differential equations. arXiv preprint arXiv:1808.04930, 2018.
  • (7) Keith Beven. Changing ideas in hydrology—the case of physically-based models. Journal of hydrology, 105(1-2):157–172, 1989.
  • (8) Keith J Beven. Rainfall-runoff modelling: the primer. John Wiley & Sons, 2011.
  • (9) George EP Box, Gwilym M Jenkins, Gregory C Reinsel, and Greta M Ljung. Time series analysis: forecasting and control. John Wiley & Sons, 2015.
  • (10) Douglas P Boyle, Hoshin V Gupta, and Soroosh Sorooshian. Toward improved calibration of hydrologic models: Combining the strengths of manual and automatic methods. Water Resources Research, 36(12):3663–3674, 2000.
  • (11) Marina Campolo, Paolo Andreussi, and Alfredo Soldati.

    River flood forecasting with a neural network model.

    Water resources research, 35(4):1191–1197, 1999.
  • (12) XY Chen, Kwok-Wing Chau, and AO Busari. A comparative study of population-based optimization algorithms for downstream river flow forecasting by a hybrid neural network model.

    Engineering Applications of Artificial Intelligence

    , 46:258–268, 2015.
  • (13) CW Dawson and RL Wilby. Hydrological modelling using artificial neural networks. Progress in physical Geography, 25(1):80–108, 2001.
  • (14) Shannon Doocy, Amy Daniels, Catherine Packer, Anna Dick, and Thomas D Kirsch. The human impact of earthquakes: a historical review of events 1980-2009 and systematic literature review. PLoS currents, 5, 2013.
  • (15) K Eckhardt and JG Arnold. Automatic calibration of a distributed catchment model. Journal of hydrology, 251(1-2):103–109, 2001.
  • (16) Yotam Gigi, Gal Elidan, Avinatan Hassidim, Yossi Matias, Zach Moshe, Sella Nevo, Guy Shalev, and Ami Wiesel. Towards global remote discharge estimation: Using the few to estimate the many. In Proceedings of the NeurIPS AI for Social Good Workshop, 2018.
  • (17) Hoshin Vijai Gupta, Soroosh Sorooshian, and Patrice Ogou Yapo. Status of automatic calibration for hydrologic models: Comparison with multilevel expert calibration. Journal of Hydrologic Engineering, 4(2):135–143, 1999.
  • (18) Kuo-lin Hsu, Hoshin V Gupta, Xiaogang Gao, Soroosh Sorooshian, and Bisher Imam. Self-organizing linear output map (solo): An artificial neural network suitable for hydrologic modeling and analysis. Water Resources Research, 38(12):38–1, 2002.
  • (19) Kuo-lin Hsu, Hoshin Vijai Gupta, and Soroosh Sorooshian. Artificial neural network modeling of the rainfall-runoff process. Water resources research, 31(10):2517–2530, 1995.
  • (20) Ashu Jain and Avadhnam Madhav Kumar. Hybrid neural network models for hydrologic time series forecasting. Applied Soft Computing, 7(2):585–592, 2007.
  • (21) Sebastiaan N Jonkman. Global perspectives on loss of human life caused by floods. Natural hazards, 34(2):151–175, 2005.
  • (22) SN Jonkman. Loss of life caused by floods: an overview of mortality statistics for worldwide floods. DC1-233-6, 2003.
  • (23) Thomas Loster. Flood trends and global change. In Proceedings IIASA Conf on Global Change and Catastrophe Management: Flood Risks in Europe, 1999.
  • (24) Henrik Madsen, Geoffrey Wilson, and Hans Christian Ammentorp. Comparison of different automated strategies for calibration of rainfall-runoff models. Journal of Hydrology, 261(1-4):48–59, 2002.
  • (25) Yossi Matias. Keeping people safe with AI-enabled flood forecasting, Google Blog, The Keyword. https://www.blog.google/products/search/helping-keep-people-safe-ai-enabled-flood-forecasting/, 2018. [Online; accessed 30-09-2018].
  • (26) Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 2010.
  • (27) Paul J Pilon et al. Guidelines for reducing flood losses. In Guidelines for reducing flood losses. Naciones Unidas, 1998.
  • (28) Durga L Shrestha and Dimitri P Solomatine. Machine learning approaches for estimation of prediction interval for the model output. Neural Networks, 19(2):225–235, 2006.
  • (29) David Strömberg. Natural disasters, economic development, and humanitarian aid. Journal of Economic perspectives, 21(3):199–222, 2007.
  • (30) A Sezin Tokar and Peggy A Johnson. Rainfall-runoff modeling using artificial neural networks. Journal of Hydrologic Engineering, 4(3):232–239, 1999.
  • (31) Weiming Wu. Computational river dynamics. CRC Press, 2007.