Online urban-waterlogging monitoring based on a recurrent  neural network for classification of microblogging text

Liu, Hui; Hao, Ya; Zhang, Wenhao; Zhang, Hanyue; Gao, Fei; Tong, Jing

doi:10.5194/nhess-21-1179-2021

Cited by 14 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although only limited water depth data were obtained due to high labor requirements and costs of measurement, this provided a new method to estimate urban flood water depth in the context of citizen science. Citizens sharing their local situation in real time is becoming a rich source of data in the era of smart phones and the Internet 69 . Measurement points and photos of flooding are shown in Fig.…”

Section: Discussionmentioning

confidence: 99%

Flood impacts on urban road connectivity in southern China

Zhou

Zheng

Liu

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Effective measures to improve road accessibility during storms are required as traffic congestion caused by storm floods increasingly constrains the efficiency of urban commuting. However, flood impacts on urban road connectivity are not yet well assessed due to inaccurate simulation of flood processes in urban areas where high-resolution data for drainage networks and gauged hydrological data are insufficient. Thus, this study assesses flood impacts on road network connectivity in an urban area of southern China through joint modeling of 1-D hydrodynamic processes in drainage networks and 2-D flood inundation processes on roads using MIKE Urban and MIKE 21. High-resolution DEM images of 5 m and a drainage network of 5635 pipelines were used for urban hydrological simulation. Flood depths were gauged for model calibration and validation by recruited volunteers in the context of citizen science. The results show that road network connectivity decreases as rainfall increases. More than 40% of road connectivity is lost in the study area when a 1-in-100-year return period rainfall occurs. The study results can help to inform more adaptive strategies for local flood control. The study methods are also applicable to improving urban hydrological modeling in broader regions.

show abstract

Section: Discussionmentioning

confidence: 99%

Flood impacts on urban road connectivity in southern China

Zhou

Zheng

Liu

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Based on the superiority of neural network algorithms in the field of natural language processing, Alina utilized a classification tool based on deep neural networks to automatically extract diagnostic and disease information at the time of surgery from electronic pathology reports monitored by the National Cancer Institute (NCI) and the Surveillance, Epidemiology, and End Results (SEER) population cancer registries, benefiting the cancer registries [3]. Liu trained a recursive neural network model to classify microblog posts related to urban flooding, establishing an online monitoring system for urban inundation triggered by flooding disasters [4]. Yang utilized artificial intelligence technology to improve the speed of encoding classroom dialogues, achieving automated classroom dialogue classification and instant feedback.…”

Section: Introductionmentioning

confidence: 99%

Design of an Automatic Classification System for Educational Reform Documents Based on Naive Bayes Algorithm

Zhang,

Ma,

Ren

et al. 2024

Mathematics

View full text Add to dashboard Cite

With the continuous deepening of educational reform, a large number of educational policies, programs, and research reports have emerged, bringing a heavy burden of information processing and management to educators. Traditional manual classification and archiving methods are inefficient and susceptible to subjective factors. Therefore, an automated method is needed to quickly and accurately classify and archive documents into their respective categories. Based on this, this paper proposes a design of an automatic document classification system for educational reform based on the Naive Bayes algorithm to address the challenges of document management in the education field. Firstly, the relevant literature and document data in the field of educational reform are collected and organized to establish an annotated dataset for model detection. Secondly, the raw data are preprocessed by cleaning and transforming the original text data to make them more suitable for input into machine learning algorithms. Thirdly, various algorithms are trained and selected to determine the best algorithm for classifying educational reform documents. Finally, based on the determined algorithm, a corresponding classification software is designed to automatically classify and archive educational reform documents for analysis. Through experimental evaluation and result analysis, this research demonstrates the effectiveness and accuracy of the education reform document automatic classification system based on the Naive Bayes algorithm. This method can efficiently classify a large number of documents into their respective categories quickly and accurately, thereby improving the efficiency of educators and their information management capabilities. In the future, further exploration of feature extraction methods and machine learning algorithms can be conducted to optimize the classification performance and apply this method to practical management and decision-making in the education field.

show abstract

“…The average duration of flash flooding events in the United States has been 3.5 h during the last two decades (Ahmadalipour and Moradkhani, 2019), limiting the applicability of aerial imagery to obtain sufficiently frequent flash flooding observations. To fill this data gap, there is increasing interest in the application of newer "crowdsourced" data into flood modeling, monitoring, and impact assessment (Molinari et al, 2018;Gaitan et al, 2016;See, 2019;Assumpcao et al, 2018;Praharaj et al, 2021a;Helmrich et al, 2021;Zhu et al, 2022;Liu et al, 2021;Schnebele et al, 2014). Previous crowdsourced flood data studies have involved engaging citizens in collecting four types of data: streamflow or rain gauge readings, videos, text messages, and image postings (Li and Willems, 2020;Assumpcao et al, 2018;Zhu et al, 2022;Liu et al, 2021;Schnebele et al, 2014;Le Coz et al, 2016;Smith et al, 2017;Cervone et al, 2015;Wang et al, 2018;Pereira et al, 2020;Moy De Vitry et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…To fill this data gap, there is increasing interest in the application of newer "crowdsourced" data into flood modeling, monitoring, and impact assessment (Molinari et al, 2018;Gaitan et al, 2016;See, 2019;Assumpcao et al, 2018;Praharaj et al, 2021a;Helmrich et al, 2021;Zhu et al, 2022;Liu et al, 2021;Schnebele et al, 2014). Previous crowdsourced flood data studies have involved engaging citizens in collecting four types of data: streamflow or rain gauge readings, videos, text messages, and image postings (Li and Willems, 2020;Assumpcao et al, 2018;Zhu et al, 2022;Liu et al, 2021;Schnebele et al, 2014;Le Coz et al, 2016;Smith et al, 2017;Cervone et al, 2015;Wang et al, 2018;Pereira et al, 2020;Moy De Vitry et al, 2019). Also, Zhu et al (2022) and Liu et al (2021) applied artificial intelligence techniques to extract flooding waterlogging from microblog information shared in crowdsourcing apps.…”

Section: Introductionmentioning

confidence: 99%

“…Previous crowdsourced flood data studies have involved engaging citizens in collecting four types of data: streamflow or rain gauge readings, videos, text messages, and image postings (Li and Willems, 2020;Assumpcao et al, 2018;Zhu et al, 2022;Liu et al, 2021;Schnebele et al, 2014;Le Coz et al, 2016;Smith et al, 2017;Cervone et al, 2015;Wang et al, 2018;Pereira et al, 2020;Moy De Vitry et al, 2019). Also, Zhu et al (2022) and Liu et al (2021) applied artificial intelligence techniques to extract flooding waterlogging from microblog information shared in crowdsourcing apps. A big challenge in using crowdsourced data is identifying the accurate location and flood extent from posted pictures, videos, and texts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating the likelihood of roadway pluvial flood based on crowdsourced traffic data and depression-based DEM analysis

Safaei-moghadam

Tarboton

Minsker

2023

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Water ponding and pluvial flash flooding (PFF) on roadways can pose a significant risk to drivers. Furthermore, climate change, growing urbanization, increasing imperviousness, and aging stormwater infrastructure have increased the frequency of these events. Using physics-based models to predict pluvial flooding at the road segment scale requires notable terrain simplifications and detailed information that is often not available at fine scales (e.g., blockage of stormwater inlets). This brings uncertainty into the results, especially in highly urbanized areas where micro-topographic features typically govern the actual flow dynamics. This study evaluates the potential for flood observations collected from Waze – a community-based navigation app – to estimate the likelihood of PFF at the road segment scale. We investigated the correlation of the Waze flood reports with well-known flood observations and maps, including the National Flood Hazard Layer (NFHL), high watermarks, and low water crossings data inventories. In addition, highly localized surface depressions and their catchments are derived from a 1 m resolution bare-earth digital elevation model (BE-DEM) to investigate the spatial association of Waze flood reports. This analysis showed that the highest correlation of Waze flood reports exists with local surface depressions rather than river flooding, indicating that they are potentially useful indicators of PFF. Accordingly, two data-driven models, empirical Bayes (EB) and random forest (RF) regression, were developed to predict the frequency of flooding, a proxy for flood susceptibility, for three classes of historical storm events (light, moderate, and severe) in every road segment with surface depressions. Applying the models to Waze data from 150 storms in the city of Dallas showed that depression catchment drainage area and imperviousness are the most important predictive features. The EB model performed with reasonable precision in estimating the number of PFF events out of 92 light, 41 moderate, and 17 severe storms with 0.84, 0.85, and 1.09 mean absolute errors, respectively. This study shows that Waze data provide useful information for highly localized PFF prediction. The superior performance of EB compared to the RF model shows that the historical observations included in the EB approach are important for more accurate PFF prediction.

show abstract

Online urban-waterlogging monitoring based on a recurrent neural network for classification of microblogging text

Cited by 14 publications

References 24 publications

Flood impacts on urban road connectivity in southern China

Flood impacts on urban road connectivity in southern China

Design of an Automatic Classification System for Educational Reform Documents Based on Naive Bayes Algorithm

Estimating the likelihood of roadway pluvial flood based on crowdsourced traffic data and depression-based DEM analysis

Contact Info

Product

Resources

About