Route selection for opportunity-sensing and prediction of waterlogging

Abstract

Accurate monitoring of urban waterlogging contributes to the city’s normal operation and the safety of residents’ daily travel. However, due to feedback delays or high costs, existing methods make large-scale, fine-grained waterlogging monitoring impossible. A common method is to forecast the city’s global waterlogging status using its partial waterlogging data. This method has two challenges: first, existing predictive algorithms are either driven by knowledge or data alone; and second, the partial waterlogging data is not collected selectively, resulting in poor predictions. To overcome the aforementioned challenges, this paper proposes a framework for large-scale and fine-grained spatiotemporal waterlogging monitoring based on the opportunistic sensing of limited bus routes. This framework follows the Sparse Crowdsensing and mainly comprises a pair of iterative predictor and selector. The predictor uses the collected waterlogging status and the predicted status of the uncollected area to train the graph convolutional neural network. It combines both knowledge-driven and data-driven approaches and can be used to forecast waterlogging status in all regions for the upcoming term. The selector consists of a two-stage selection procedure that can select valuable bus routes while satisfying budget constraints. The experimental results on real waterlogging and bus routes in Shenzhen show that the proposed framework could easily perform urban waterlogging monitoring with low cost, high accuracy, wide coverage, and fine granularity.

Graphical abstract

Keywords

waterlogging prediction / sparse crowdsensing / active learning / route selection / graph convolutional network

References

[1] Xu H . Analysis of impervious surface and its impact on urban heat environment using the normalized difference impervious surface index (NDISI). Photogrammetric Engineering & Remote Sensing, 2010, 76( 5): 557–565

[2] Dong X, Guo H, Zeng S . Enhancing future resilience in urban drainage system: green versus grey infrastructure. Water Research, 2017, 124: 280–289

[3] Gironás J, Roesner L A, Davis J. Storm water management model applications manual. EPA/600/R-09/077. Washington: U.S. Environmental Protection Agency, 2009

[4] Shi Y Y, Wan D H, Chen L, Zheng J L. Simulation of rainstorm waterlogging and submergence in urban areas based on GIS and SWMM. Water Resources and Power, 2014, 32(6): 57–60, 12

[5] Guo W, Zhu W, Yu Z, Wang J, Guo B . A survey of task allocation: contrastive perspectives from wireless sensor networks and mobile crowdsensing. IEEE Access, 2019, 7: 78406–78420

[6] Chen J, Yang J . Maximizing coverage quality with budget constrained in mobile crowd-sensing network for environmental monitoring applications. Sensors, 2019, 19( 10): 2399

[7] Ludwig T, Reuter C, Pipek V. What you see is what I need: Mobile reporting practices in emergencies. In: Proceedings of the 13th European Conference on Computer Supported Cooperative Work. 2013, 181–206

[8] Wang L, Zhang D, Wang Y, Chen C, Han X, M’hamed A . Sparse mobile crowdsensing: challenges and opportunities. IEEE Communications Magazine, 2016, 54( 7): 161–167

[9] Liu J, Bao Y, Liu Y, Li W. Design of an urban waterlogging monitoring system based on internet of things. In: Proceedings of the 2nd EAI International Conference on Security and Privacy in New Computing Environments. 2019, 333–341

[10] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations. 2016

[11] Wu D, Xiao T, Liao X, Luo J, Wu C, Zhang S, Li Y, Guo Y . When sharing economy meets IoT: towards fine-grained urban air quality monitoring through mobile crowdsensing on bike-share system. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2020, 4( 2): 61

[12] Pirrone N, Aas W, Cinnirella S, Ebinghaus R, Hedgecock I M, Pacyna J, Sprovieri F, Sunderland E M . Toward the next generation of air quality monitoring: mercury. Atmospheric Environment, 2013, 80: 599–611

[13] Sîrbu A, Becker M, Caminiti S, De Baets B, Elen B, Francis L, Gravino P, Hotho A, Ingarra S, Loreto V, Molino A, Mueller J, Peters J, Ricchiuti F, Saracino F, Servedio V D P, Stumme G, Theunis J, Tria F, Van den Bossche J . Participatory patterns in an international air quality monitoring initiative. PLoS One, 2015, 10( 8): e0136763

[14] Zheng H, Chang W, Wu J . Traffic flow monitoring systems in smart cities: coverage and distinguishability among vehicles. Journal of Parallel and Distributed Computing, 2019, 127: 224–237

[15] Atkinson I M, Adam T B W, Dixon M J. Traffic flow monitoring: 6650948. 2003-11-18

[16] Hao G, Sha Y, Li C, Xia J, Zhang N, Ding F, Yin Y, Ding F. Toward a highway traffic flow monitoring system based on mobile phone signaling data. In: Proceedings of 2020 International Wireless Communications and Mobile Computing (IWCMC). 2020, 235–239

[17] Nguyen T D. Energy efficient wireless sensor network and low power consumption station design for an urban water level monitoring system. In: Proceedings of the 2016 3rd National Foundation for Science and Technology Development Conference on Information and Computer Science (NICS). 2016, 252–256

[18] Liu Y, Du M, Jing C, Cai G. Design and implementation of monitoring and early warning system for urban roads waterlogging. In: Proceedings of the 8th IFIP WG 5.14 International Conference on Computer and Computing Technologies in Agriculture. 2014, 610–615

[19] Chen L, Fan X, Wang L, Zhang D, Yu Z, Li J, Nguyen T M T, Pan G, Wang C . RADAR: road obstacle identification for disaster response leveraging cross-domain urban data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 1( 4): 130

[20] Yang B, Zhao R . Urban storm flood simulation and analysis based on storm water management model. Water Resources Informatization, 2017, ( 5): 56–62

[21] Wang H J, Xu Y Q, Tan Y Z, Jiang C, Li W . City hydrops forewarning model structure based on city area meshing. Machine Building & Automation, 2014, ( 2): 117–120,125

[22] Wang Y, Li J, Zhang H. Study on city rainstorm waterlogging warning system based on historical data. In: Proceedings of the 13th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). 2016, 171–174

[23] Xie K, Li X, Wang X, Xie G, Wen J, Zhang D. Active sparse mobile crowd sensing based on matrix completion. In: Proceedings of 2019 International Conference on Management of Data. 2019, 195–210

[24] Wang E, Zhang M, Cheng X, Yang Y, Liu W, Yu H, Wang L, Zhang J . Deep learning-enabled sparse industrial crowdsensing and prediction. IEEE Transactions on Industrial Informatics, 2021, 17( 9): 6170–6181

[25] Feng Y, Wang J, Wang Y, Chu X . Towards sustainable compressive population health: a GAN-based year-by-year imputation method. ACM Transactions on Computing for Healthcare, 2023, 4( 1): 8

[26] Huang F, Zheng W, Guo W, Yu Z . Estimating missing data for sparsely sensed time series with exogenous variables using bidirectional-feedback echo state networks. CCF Transactions on Pervasive Computing and Interaction, 2023, 5: 45–63

[27] Liu W, Yang Y, Wang E, Wu J . User recruitment for enhancing data inference accuracy in sparse mobile crowdsensing. IEEE Internet of Things Journal, 2020, 7( 3): 1802–1814

[28] Xiao Y, Simoens P, Pillai P, Ha K, Satyanarayanan M. Lowering the barriers to large-scale mobile crowdsensing. In: Proceedings of the 14th Workshop on Mobile Computing Systems and Applications. 2013, 9

[29] Sun S, Hussain Z, Shawe-Taylor J . Manifold-preserving graph reduction for sparse semi-supervised learning. Neurocomputing, 2014, 124: 13–21

[30] Fu Y, Zhu X, Li B . A survey on instance selection for active learning. Knowledge and Information Systems, 2013, 35( 2): 249–283

RIGHTS & PERMISSIONS

Higher Education Press