{"type":"ScholarlyArticle","title":"Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach","authors":[{"name":"Mohammed Amine Gharsallaoui","slug":"mohammed-amine-gharsallaoui","given":"Mohammed Amine","family":"Gharsallaoui","affiliation":"Washington State University , Pullman , WA , USA"},{"name":"Bhupinderjeet Singh","slug":"bhupinderjeet-singh","given":"Bhupinderjeet","family":"Singh","affiliation":"Washington State University , Pullman , WA , USA"},{"name":"Supriya Savalkar","slug":"supriya-savalkar","given":"Supriya","family":"Savalkar","affiliation":"Washington State University , Pullman , WA , USA"},{"name":"Aryan Deshwal","slug":"aryan-deshwal","given":"Aryan","family":"Deshwal","affiliation":"Washington State University , Pullman , WA , USA"},{"name":"Ananth Kalyanaraman","slug":"ananth-kalyanaraman","given":"Ananth","family":"Kalyanaraman","affiliation":"Washington State University , Pullman , WA , USA"},{"name":"Kirti Rajagopalan","slug":"kirti-rajagopalan","given":"Kirti","family":"Rajagopalan","affiliation":"Washington State University , Pullman , WA , USA"},{"name":"Janardhan Rao Doppa","slug":"janardhan-rao-doppa","given":"Janardhan Rao","family":"Doppa","affiliation":"Washington State University , Pullman , WA , USA"}],"abstract":"Predicting the spatiotemporal variation in streamflow along with uncertainty quantification enables decision-making for sustainable management of scarce water resources. Process-based hydrological models (aka physics-based models) are based on physical laws, but use simplifying assumptions which can lead to poor accuracy. Data-driven approaches offer a powerful alternative, but they require large amount of training data and tend to produce predictions that are inconsistent with physical laws. This paper studies a constrained reasoning and learning (CRL) approach where physical laws represented as logical constraints are integrated as a layer in the deep neural network. To address  small data setting, we develop a theoretically-grounded training approach to improve the generalization accuracy of deep models. For uncertainty quantification, we combine the synergistic strengths of Gaussian processes (GPs) and deep temporal models by passing the learned latent representation as input to a standard distance-based kernel. Experiments on multiple real-world datasets demonstrate the effectiveness of both CRL and GP with deep kernel approaches over strong baseline methods.","doi":"10.24963/ijcai.2024/804","url":"https://ijcai.org/proceedings/2024/804","pdf":"https://ijcai.org/proceedings/2024/0804.pdf","markdown":"https://ijcai.org/proceedings/2024/804.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/804","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI for Good","track":"AI for Good","number":804,"pages":{"first":7269,"last":7277},"keywords":["Multidisciplinary Topics and Applications: General","Machine Learning: General"],"videos":[],"references":[{"position":1,"raw":"[Ahmed et al., 2022a] Kareem Ahmed, Tao Li, Thy Ton, Quan Guo, Kai-Wei Chang, Parisa Kordjamshidi, Vivek Srikumar, Guy Van den Broeck, and Sameer Singh. Py- lon: A pytorch framework for learning with constraints. In NeurIPS 2021 Competitions and Demonstrations Track, pages 319-324. PMLR, 2022.","title":"Pylon: A pytorch framework for learning with constraints","authors":"Ahmed","year":"2022","venue":"NeurIPS 2021 Competitions and Demonstrations Track","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ahmed et al., 2022b] Kareem Ahmed, Stefano Teso, Kai- Wei Chang, Guy Van den Broeck, and Antonio Vergari. Semantic probabilistic layers for neuro-symbolic learning. In Advances in Neural Information Processing Systems 35 (NeurIPS), dec 2022.","title":"Semantic probabilistic layers for neuro-symbolic learning","authors":"Ahmed","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai et al., 2021] Shengze Cai, Zhiping Mao, Zhicheng Wang, Minglang Yin, and George Em Karniadakis. Physics-informed neural networks (PINNs) for fluid me- chanics: A review, 2021.","title":"Physics-informed neural networks (PINNs) for fluid mechanics: A review","authors":"Shengze Cai, Zhiping Mao, Zhicheng Wang, Minglang Yin, George Em Karniadakis","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Choi et al., 2020] Y Choi, Antonio Vergari, and Guy Van den Broeck. Probabilistic circuits: A unifying frame- work for tractable probabilistic models. UCLA. URL: http://starai. cs. ucla. edu/papers/ProbCirc20. pdf, 2020.","title":"Probabilistic circuits: A unifying framework for tractable probabilistic models","authors":"Antonio Choi, Guy Vergari, Van Den Broeck","year":"2020","venue":null,"doi":null,"url":"http://starai.cs.ucla.edu/papers/ProbCirc20.pdf","internal_url":null},{"position":5,"raw":"[Cortes et al., 2010] Corinna Cortes, Yishay Mansour, and Mehryar Mohri. Learning bounds for importance weight- ing. In Advances in neural information processing sys- tems, volume 23, 2010.","title":"Learning bounds for importance weighting","authors":"Corinna Cortes, Yishay Mansour, Mehryar Mohri","year":"2010","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hinton et al., 2012] Geoffrey E Hinton, Nitish Srivas- tava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. Improving neural networks by prevent- ing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580, 2012.","title":"Improving neural networks by preventing co-adaptation of feature detectors","authors":"Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R Salakhutdinov","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hoedt et al., 2021] Pieter-Jan Hoedt, Frederik Kratzert, Daniel Klotz, Christina Halmich, Markus Holzleitner, Grey S Nearing, Sepp Hochreiter, and Günter Klambauer. Mc-lstm: Mass-conserving lstm. In International con- ference on machine learning, pages 4275-4286. PMLR, 2021.","title":"Mc-lstm: Mass-conserving lstm","authors":"Pieter-Jan Hoedt, Frederik Kratzert, Daniel Klotz, Christina Halmich, Markus Holzleitner, S Grey, Sepp Nearing, Günter Hochreiter, Klambauer","year":"2021","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jia et al., 2019] Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan Read, Jacob Zwart, Michael Steinbach, and Vipin Kumar. Physics guided rnns for modeling dynamical sys- tems: A case study in simulating lake temperature profiles. In Proceedings of the 2019 SIAM international conference on data mining, pages 558-566. SIAM, 2019.","title":"Physics guided rnns for modeling dynamical systems: A case study in simulating lake temperature profiles","authors":"Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan Read, Jacob Zwart, Michael Steinbach, Vipin Kumar","year":"2019","venue":"Proceedings of the 2019 SIAM international conference on data mining","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jia et al., 2021] Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan S Read, Jacob A Zwart, Michael Steinbach, and Vipin Kumar. Physics-guided machine learning for scien- tific discovery: An application in simulating lake temper- ature profiles. ACM/IMS Transactions on Data Science, 2(3):1-26, 2021.","title":"Physics-guided machine learning for scientific discovery: An application in simulating lake temperature profiles","authors":"Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan S Read, Jacob A Zwart, Michael Steinbach, Vipin Kumar","year":"2021","venue":"ACM/IMS Transactions on Data Science","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kamruzzaman et al., 2021] Sarker Md Kamruzzaman, Zhou Lu, Eberhart Aaron, and Hitzler Pascal. Neuro- symbolic artificial intelligence: Current trends. arXiv preprint arXiv: 2105.05330, 2021.","title":"Neurosymbolic artificial intelligence: Current trends","authors":"Zhou Sarker Md Kamruzzaman, Eberhart Lu, Hitzler Aaron, Pascal","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Karpatne et al., 2016] Anuj Karpatne, Ankush Khandelwal, Xi Chen, Varun Mithal, James Faghmous, and Vipin Ku- mar. Global monitoring of inland water dynamics: State- of-the-art, challenges, and opportunities. Computational sustainability, pages 121-147, 2016.","title":"Global monitoring of inland water dynamics: Stateof-the-art, challenges, and opportunities","authors":"Anuj Karpatne, Ankush Khandelwal, Xi Chen, Varun Mithal, James Faghmous, Vipin Kumar","year":"2016","venue":"Computational sustainability","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Karpatne et al., 2017a] Anuj Karpatne, Gowtham Atluri, James H Faghmous, Michael Steinbach, Arindam Baner- jee, Auroop Ganguly, Shashi Shekhar, Nagiza Samatova, and Vipin Kumar. Theory-guided data science: A new paradigm for scientific discovery from data. IEEE Trans- actions on knowledge and data engineering, 29(10):2318- 2331, 2017.","title":"Theory-guided data science: A new paradigm for scientific discovery from data","authors":"Karpatne","year":"2017","venue":"IEEE Transactions on knowledge and data engineering","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Karpatne et al., 2017b] Anuj Karpatne, William Watkins, Jordan Read, and Vipin Kumar. Physics-guided neural net- works (pgnn): An application in lake temperature model- ing. arXiv preprint arXiv:1710.11431, 2, 2017.","title":"Physics-guided neural networks (pgnn): An application in lake temperature modeling","authors":"Karpatne","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kratzert et al., 2019] Frederik Kratzert, Daniel Klotz, Mathew Herrnegger, Alden K Sampson, Sepp Hochreiter, and Grey S Nearing. Toward improved predictions in un- gauged basins: Exploiting the power of machine learning. Water Resources Research, 55(12):11344-11354, 2019.","title":"Toward improved predictions in ungauged basins: Exploiting the power of machine learning","authors":"Frederik Kratzert, Daniel Klotz, Mathew Herrnegger, Alden K Sampson, Sepp Hochreiter, Grey, Nearing","year":"2019","venue":"Water Resources Research","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liang et al., 1994] Xu Liang, Dennis P Lettenmaier, Eric F Wood, and Stephen J Burges. A simple hydrologically based model of land surface water and energy fluxes for general circulation models. Journal of Geophysical Re- search: Atmospheres, 99(D7):14415-14428, 1994.","title":"A simple hydrologically based model of land surface water and energy fluxes for general circulation models","authors":"Xu Liang, Dennis P Lettenmaier, Eric F Wood, Stephen J Burges","year":"1994","venue":"Journal of Geophysical Research: Atmospheres","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2023] Siyan Liu, Dan Lu, Scott L Painter, Na- talie A Griffiths, and Eric M Pierce. Uncertainty quan- tification of machine learning models to improve stream- flow prediction under changing climate and environmental conditions. Frontiers in Water, 5:1150126, 2023.","title":"Uncertainty quantification of machine learning models to improve streamflow prediction under changing climate and environmental conditions","authors":"Siyan Liu, Dan Lu, Scott L Painter, Natalie A Griffiths, Eric M Pierce","year":"2023","venue":"Frontiers in Water","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Malek et al., 2017] Keyvan Malek, Claudio Stöckle, Kiran Chinnayakanahalli, Roger Nelson, Mingliang Liu, Kirti Rajagopalan, Muhammad Barik, and Jennifer C Adam. Vic-cropsyst-v2: A regional-scale modeling platform to simulate the nexus of climate, hydrology, cropping sys- tems, and human decisions. Geoscientific Model Develop- ment, 10(8):3059-3084, 2017.","title":"Vic-cropsyst-v2: A regional-scale modeling platform to simulate the nexus of climate, hydrology, cropping systems, and human decisions","authors":"Keyvan Malek, Claudio Stöckle, Kiran Chinnayakanahalli, Roger Nelson, Mingliang Liu, Kirti Rajagopalan, Muhammad Barik, Jennifer C Adam","year":"2017","venue":"Geoscientific Model Development","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[McLain et al., 2015] Kelly McLain, Jaclyn Hancock, and Margaret Drennan. 2015 drought and agriculture, 2015. Accessed: June 26, 2024.","title":"drought and agriculture","authors":"Kelly Mclain, Jaclyn Hancock, Margaret Drennan","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Muralidhar et al., 2020] Nikhil Muralidhar, Jie Bu, Ze Cao, Long He, Naren Ramakrishnan, Danesh Tafti, and Anuj Karpatne. Phynet: Physics guided neural networks for par- ticle drag force prediction in assembly. In Proceedings of the 2020 SIAM International Conference on Data Mining, pages 559-567. SIAM, 2020.","title":"Phynet: Physics guided neural networks for particle drag force prediction in assembly","authors":"Nikhil Muralidhar, Jie Bu, Ze Cao, Long He, Naren Ramakrishnan, Danesh Tafti, Anuj Karpatne","year":"2020","venue":"Proceedings of the 2020 SIAM International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Nash and Sutcliffe, 1970] J Eamonn Nash and Jonh V Sut- cliffe. River flow forecasting through conceptual models part i-a discussion of principles. Journal of hydrology, 10(3):282-290, 1970.","title":"River flow forecasting through conceptual models part i-a discussion of principles","authors":"Sutcliffe ; Jonh V Nash, Sutcliffe","year":"1970","venue":"Journal of hydrology","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Nossent and Bauwens, 2012] Jiri Nossent and Willy Bauwens. Application of a normalized nash-sutcliffe efficiency to improve the accuracy of the sobol'sensitivity analysis of a hydrological model. In EGU general assembly conference abstracts, page 237, 2012.","title":"Application of a normalized nash-sutcliffe efficiency to improve the accuracy of the sobol'sensitivity analysis of a hydrological model","authors":"Bauwens Nossent, Jiri Nossent, Willy Bauwens","year":"2012","venue":"EGU general assembly conference abstracts","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Peters-Lidard et al., 2017] Christa D Peters-Lidard, Martyn Clark, Luis Samaniego, Niko EC Verhoest, Tim Van Em- merik, Remko Uijlenhoet, Kevin Achieng, Trenton E Franz, and Ross Woods. Scaling, similarity, and the fourth paradigm for hydrology. Hydrology and earth system sci- ences, 21(7):3701-3713, 2017.","title":"Scaling, similarity, and the fourth paradigm for hydrology","authors":"Christa D Peters-Lidard, Martyn Clark, Luis Samaniego, E C Niko, Tim Verhoest, Remko Van Emmerik, Kevin Uijlenhoet, Trenton E Achieng, Ross Franz, Woods","year":"2017","venue":"Hydrology and earth system sciences","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Rajagopalan et al., 2018] K Rajagopalan, KJ Chin- nayakanahalli, CO Stockle, RL Nelson, CE Kruger, MP Brady, K Malek, ST Dinesh, ME Barber, AF Hamlet, et al. Impacts of near-term climate change on irrigation demands and crop yields in the columbia river basin. Water Resources Research, 54(3):2152-2182, 2018.","title":"Impacts of near-term climate change on irrigation demands and crop yields in the columbia river basin","authors":"Rajagopalan, Chinnayakanahalli, Co Stockle, C E Nelson, Kruger, K Brady, Malek, St Dinesh, Barber, Hamlet","year":"2018","venue":"Water Resources Research","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Seo et al., 2016] Youngjoo Seo, Michaël Defferrard, Pierre Vandergheynst, and Xavier Bresson. Structured sequence modeling with graph convolutional recurrent networks, 2016.","title":"Structured sequence modeling with graph convolutional recurrent networks","authors":"Seo","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sit et al., 2021] Muhammed Sit, Bekir Demiray, and Ibrahim Demir. Short-term hourly streamflow prediction with graph convolutional gru networks. arXiv preprint arXiv:2107.07039, 2021.","title":"Short-term hourly streamflow prediction with graph convolutional gru networks","authors":"Muhammed Sit, Bekir Demiray, Ibrahim Demir","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Stöckle et al., 2003] Claudio O Stöckle, Marcello Do- natelli, and Roger Nelson. Cropsyst, a cropping systems simulation model. European journal of agronomy, 18(3- 4):289-307, 2003.","title":"Cropsyst, a cropping systems simulation model","authors":"Marcello Claudio O Stöckle, Roger Donatelli, Nelson","year":"2003","venue":"European journal of agronomy","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Valentin Jospin et al., 2020] Laurent Valentin Jospin, Wray Buntine, Farid Boussaid, Hamid Laga, and Mohammed Bennamoun. Hands-on bayesian neural networks-a tuto- rial for deep learning users. arXiv e-prints, pages arXiv- 2007, 2020.","title":"Hands-on bayesian neural networks-a tutorial for deep learning users","authors":"Laurent Valentin Jospin, Wray Buntine, Farid Boussaid, Hamid Laga, Mohammed Bennamoun","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vergari et al., 2020] Antonio Vergari, Y Choi, Robert Pe- harz, and Guy Van den Broeck. Probabilistic circuits: Rep- resentations, inference, learning and applications. AAAI Tutorial, 2020.","title":"Probabilistic circuits: Representations, inference, learning and applications","authors":"Antonio Vergari, Robert Choi, Guy Peharz, Van Den Broeck","year":"2020","venue":"AAAI Tutorial","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Williams and Rasmussen, 2006] Christopher KI Williams and Carl Edward Rasmussen. Gaussian processes for ma- chine learning, volume 2. MIT press Cambridge, MA, 2006.","title":"Gaussian processes for machine learning","authors":"K I Christopher, Carl Edward Williams, Rasmussen","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wilson et al., 2016] Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, and Eric P Xing. Deep kernel learn- ing. In Artificial intelligence and statistics, pages 370- 378. PMLR, 2016.","title":"Deep kernel learning","authors":"Andrew Gordon Wilson, Zhiting Hu, Ruslan Salakhutdinov, Eric P Xing","year":"2016","venue":"Artificial intelligence and statistics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Xiang and Demir, 2022] Zhongrun Xiang and Ibrahim Demir. Fully distributed rainfall-runoff modeling using spatial-temporal graph neural network. 2022.","title":"Zhongrun Xiang and Ibrahim Demir. Fully distributed rainfall-runoff modeling using spatial-temporal graph neural network","authors":"Demir Xiang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Xu et al., 2021] Da Xu, Yuting Ye, and Chuanwei Ruan. Understanding the role of importance weighting for deep learning. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021.","title":"Understanding the role of importance weighting for deep learning","authors":"Da Xu, Yuting Ye, Chuanwei Ruan","year":"2021","venue":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}