Urban Water Flow and Water Level Prediction Based on Deep Learning

Assem, Haytham; Ghariba, Salem; Makrai, Gabor; Johnston, Paul; Gill, Laurence; Pilla, Francesco

doi:10.1007/978-3-319-71273-4_26

Cited by 47 publications

(19 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the rapid growth in the amount of annotated data and the uniqueness of CNN structures, remote sensing and hydrology communities have exploited CNN techniques for many applications. These include land cover and land use classification (Castelluccio et al 2015;Chen et al 2014;Luus et al 2015;Makantasis et al 2015;Rezaee et al 2018; Sevo and Avramović 2016), image segmentation (Basaeed et al 2016;Längkvist et al 2016), object localization (Long et al 2017;Salberg 2015), extreme event detection (Liu et al 2016), urban water flow and water level prediction (Assem et al 2017), tropical cyclone intensity estimation (Pradhan et al 2018), and extreme precipitation prediction (Zhuang and Ding 2016). The CNN structure can also be utilized to address the drawback of PERSIANN-SDAE to efficiently utilize neighborhood pixel information for rain-rate estimation (Shen 2018).…”

Section: Introductionmentioning

confidence: 99%

PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks

Sadeghi

Asanjan

Faridzad

et al. 2019

Journal of Hydrometeorology

127

View full text Add to dashboard Cite

Accurate and timely precipitation estimates are critical for monitoring and forecasting natural disasters such as floods. Despite having high-resolution satellite information, precipitation estimation from remotely sensed data still suffers from methodological limitations. State-of-the-art deep learning algorithms, renowned for their skill in learning accurate patterns within large and complex datasets, appear well suited to the task of precipitation estimation, given the ample amount of high-resolution satellite data. In this study, the effectiveness of applying convolutional neural networks (CNNs) together with the infrared (IR) and water vapor (WV) channels from geostationary satellites for estimating precipitation rate is explored. The proposed model performances are evaluated during summer 2012 and 2013 over central CONUS at the spatial resolution of 0.08° and at an hourly time scale. Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)–Cloud Classification System (CCS), which is an operational satellite-based product, and PERSIANN–Stacked Denoising Autoencoder (PERSIANN-SDAE) are employed as baseline models. Results demonstrate that the proposed model (PERSIANN-CNN) provides more accurate rainfall estimates compared to the baseline models at various temporal and spatial scales. Specifically, PERSIANN-CNN outperforms PERSIANN-CCS (and PERSIANN-SDAE) by 54% (and 23%) in the critical success index (CSI), demonstrating the detection skills of the model. Furthermore, the root-mean-square error (RMSE) of the rainfall estimates with respect to the National Centers for Environmental Prediction (NCEP) Stage IV gauge–radar data, for PERSIANN-CNN was lower than that of PERSIANN-CCS (PERSIANN-SDAE) by 37% (14%), showing the estimation accuracy of the proposed model.

show abstract

Section: Introductionmentioning

confidence: 99%

PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks

Sadeghi

Asanjan

Faridzad

et al. 2019

Journal of Hydrometeorology

127

View full text Add to dashboard Cite

show abstract

“…Time series DL rainfall-runoff models that are confined to certain geographic regions have been created (Kratzert et al, 2018). There are also DL studies, based on smaller datasets, to help predict water flows in the urban environment (Assem et al, 2017) and in the water infrastructure (Zhang et al, 2018). In addition to utilizing big data, DL was able to create valuable, big datasets that could not have otherwise been possible.…”

Section: Rapid Adoptionmentioning

confidence: 99%

HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community

Shen

Laloy

Elshorbagy

et al. 2018

Hydrol. Earth Syst. Sci.

211

149

View full text Add to dashboard Cite

Abstract. Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming industry applications and generating new and improved capabilities for scientific discovery and model building. The adoption of DL in hydrology has so far been gradual, but the field is now ripe for breakthroughs. This paper suggests that DL-based methods can open up a complementary avenue toward knowledge discovery in hydrologic sciences. In the new avenue, machine-learning algorithms present competing hypotheses that are consistent with data. Interrogative methods are then invoked to interpret DL models for scientists to further evaluate. However, hydrology presents many challenges for DL methods, such as data limitations, heterogeneity and co-evolution, and the general inexperience of the hydrologic field with DL. The roadmap toward DL-powered scientific advances will require the coordinated effort from a large community involving scientists and citizens. Integrating process-based models with DL models will help alleviate data limitations. The sharing of data and baseline models will improve the efficiency of the community as a whole. Open competitions could serve as the organizing events to greatly propel growth and nurture data science education in hydrology, which demands a grassroots collaboration. The area of hydrologic DL presents numerous research opportunities that could, in turn, stimulate advances in machine learning as well.

show abstract

“…The development of CNNs was largely driven by image classification applications (Krizhevsky et al, 2012). In the geosciences, CNNs have gained popularity only relatively recently with applications including long-term El-Nino forecasting (Ham et al, 2019), precipitation downscaling (Vandal et al, 2017), and urban water flow forecasting (Assem et al, 2017). Importantly, CNNs have been combined with LSTMs to encode both spatial and temporal information.…”

Section: Introductionmentioning

confidence: 99%

Evaluation and interpretation of convolutional-recurrent networks for regional hydrological modelling

Anderson

Radić

2021

Preprint

View full text Add to dashboard Cite

Abstract. Deep learning has emerged as a useful tool across geoscience disciplines; however, there remain outstanding questions regarding the suitability of unexplored model architectures and how to interpret model learning for regional scale hydrological modelling. Here we use a convolutional-recurrent network, a deep learning approach for learning both spatial and temporal patterns, to predict streamflow at 226 stream gauges across the region of southwestern Canada. The model is forced by gridded climate reanalysis data and trained to predict observed daily streamflow between 1979 and 2015. To interpret the model learning of both spatial and temporal patterns, we introduce two experiments with evaluation metrics to track the model's response to perturbations in the input data. The model performs well in simulating the daily streamflow over the testing period, with a median Nash-Sutcliffe Efficiency (NSE) of 0.68 and 35 % of stations having NSE > 0.8. When predicting streamflow, the model is most sensitive to perturbations in the input data prescribed near and within the basins being predicted, demonstrating that the model is automatically learning to focus on physically realistic areas. When uniformly perturbing input temperature timeseries to obtain relatively warmer and colder input data, the modelled freshet timing and intensity changes in accordance with the transition timing from below- to above-freezing temperatures. The results demonstrate the suitability of a convolutional-recurrent network architecture for spatiotemporal hydrological modelling, making progress towards interpretable deep learning hydrological models.

show abstract

Urban Water Flow and Water Level Prediction Based on Deep Learning

Cited by 47 publications

References 14 publications

PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks

PERSIANN-CNN: Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Convolutional Neural Networks

HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community

Evaluation and interpretation of convolutional-recurrent networks for regional hydrological modelling

Contact Info

Product

Resources

About