Training Issues in Classifying Urban Flood Object Detection – A Deep Learning Study

Lambu, Padmavathi; Duvvuru, Rajesh

doi:10.12912/27197050/191861

Artykuł - szczegóły

Tytuł artykułu

Training Issues in Classifying Urban Flood Object Detection – A Deep Learning Study

Autorzy

Lambu Padmavathi , Duvvuru Rajesh

Treść / Zawartość

Pełne teksty:

Pobierz

Identyfikatory

DOI

10.12912/27197050/191861

Warianty tytułu

Języki publikacji

Abstrakty

Climate change has had a significant impact on natural disasters, particularly floods, in recent times. Early warning systems play an important role in river flood prediction. However, cloudbursts trigger urban flash floods, causing significant disruption to humanity, property damage, and loss of life. In particular, the number of deaths from urban floods has increased in recent times, primarily due to a lack of information. Urban floods, in particular, inflict damage on assets such as vehicles, electric poles, and plants. In addition, flash floods in urban areas submerge roads, drainage, etc., leading to drowning and fatalities. Currently, there is a need to develop smart urban flood prediction and monitoring systems that disseminate instant flood information to rescue teams for a quick response. Currently, deep learning technologies play a significant role in object prediction, but their accuracy in predicting urban flood objects is relatively low. In deep learning algorithms, the training of networks, in conjunction with optimizers and epochs, plays a crucial role in achieving higher accuracies in object detection. The current article investigates the best deep learning training networks, optimizers, and epochs to train urban flood data objects that can achieve higher accuracy. This study considers two pre-trained models, XceptionNet and AlexNet, and three optimizers, including SGDM, ADAM, and RMSProp, to train the urban flood dataset, ensuring balance. We evaluate each training network’s performance with the optimizer by tuning epochs and hyper-parameters as constants. Specifically, applying XceptionNet to the SGDM optimizer resulted in an accuracy of 97.47%. The results show that XceptionNet outperforms AlexNet in terms of performance and is recommended for flood object classification. Currently, the study solely focuses on two pre-trained networks and achived 97.47% accuracy; however, it has the potential to evaluate other deep convolutional neural networks, potentially achieving 100% data object training.

Słowa kluczowe

deep learning CNN algorithm flood detection xceptionnet alexnet

Wydawca

Lubelski Oddział Polskiego Towarzystwo Inżynierii Ekologicznej
Lublin University of Technology
WNGB Wydawnictwo Naukowe

Czasopismo

Ecological Engineering & Environmental Technology

Rocznik

2024

Tom

Vol. 25, iss. 10

Strony

236--256

Opis fizyczny

Bibliogr. 48 poz., rys., tab.

Twórcy

autor

Lambu Padmavathi

padmavathi.22phd7094@vitap.ac.in

School of Computer Science and Engineering, VIT-AP University, Guntur, India

https://orcid.org/0009-0001-0911-9038

autor

Duvvuru Rajesh

dr.rajeshduvvuru@gmail.com

School of Computer Science and Engineering, VIT-AP University, Guntur, India

https://orcid.org/0000-0002-5053-0590

Bibliografia

1. Agonafir C., Lakhankar T., Khanbilvardi R., Krakauer N., Radell D., Devineni N. 2023. A review of recent advances in urban flood research., Water Security, 19, 100141, https://doi.org/10.1016/j.wasec.2023.100141
2. Ahmed I., Ahmad M., Jeon, G. and Chehri A. 2023. An Internet-of-Things and AI-Powered Framework for Long-Term Flood Risk Evaluation. IEEE Internet of Things Journal. 11(3), 3812–3819. https://doi.org/10.1109/JIOT.2023.3308564
3. Alabbad Y., Demir I. 2022. Comprehensive flood vulnerability analysis in urban communities: Iowa case study, International Journal of Disaster Risk Reduction, 74, 102955. https://doi.org/10.1016/j.ijdrr.2022.102955
4. Angloher G., Banik S., Bartolot D., Benato G., Bento A., Bertolini A., Breier R., Bucci C., Burkhart J., Canonica L. and D’Addabbo A. 2023. Towards an automated data cleaning with deep learning in CRESST. The European Physical Journal Plus, 138(1), 1–11. https://doi.org/10.1140/epjp/s13360-023-03674-2
5. Anil H., Pawan B. 2022. a review on urban flood management techniques for smart city and future research, Springer Charm, International conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI 2022) proceedings, 3, 319–336. https://doi.org/10.1007/978-3-031-18497-0_23
6. Avand M., Moradi H.R., Ramazanzadeh Lasboyee M. 2021. Spatial Prediction of Future Flood Risk: An Approach to the Effects of Climate Change, Geosciences, 11(1), 25. https://doi.org/10.3390/geosciences11010025
7. Baghermanesh S.S., Jabari S., McGrath, H. 2021. Urban flood detection using sentinel1-a images. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 527–530. https://doi.org/10.1109/IGARSS47720.2021.9554283
8. Bagyaraj M., Senapathi V., Chung S.Y., Gopalakrishnan G., Xiao Y., Karthikeyan S., Nadiri A.A., Barzegar R. 2023. A geospatial approach for assessing urban flood risk zones in Chennai, Tamil Nadu, India. Environmental Science and Pollution Research, 30(45), 100562–100575. https://doi.org/10.1007/s11356-023-29132-1
9. Bakhtiari V., Piadeh F., Behzadian K., Kapelan Z. 2023. Dealing with urban floods within a resilience framework regarding disaster stages. Habitat International, 136, 102783. https://doi.org/10.1016/j.scs.2023.104958
10. Bentivoglio R., Isufi E., Jonkman S.N., Taormina R. 2022. Deep learning methods for flood mapping: a review of existing applications and future research directions. Hydrology and earth system sciences, 26(16), 4345–4378, https://doi.org/10.5194/hess-26-4345-2022
11. Braveen M., Anusha K., Jerlin M.A., Seetha R., Sampath N. 2023. IDISense: IoT-based dam water disaster sensing and prevention system. IEEE Sensors Journal, 23(23), 29451–29457. https://doi.org/10.1109/JSEN.2023.3322290
12. Chen J., Li Y., Zhang C., Tian Y., Guo Z. 2023. Urban flooding prediction method based on the combination of LSTM neural network and numerical model. International Journal of Environmental Research and Public Health, 20(2), 1043. https://doi.org/10.3390/ijerph20021043
13. Chen Z., Duan J., Kang L., Qiu G. 2021. Classimbalanced deep learning via a class-balanced ensemble. IEEE transactions on neural networks and learning systems, 33(10), 5626–5640. https://doi.org/10.1109/TNNLS.2021.3071122
14. Deccan Herland. 2023. FIR filed after Bengaluru techie drowns in flooded underpass. (Accessed on 15 January, 2024) (https://www.deccanherald.com/india/karnataka/bengaluru/fir-filed-after-bengalurutechie-drowns-in-flooded-underpass-1220935.html).
15. Esfandiari M., Jabari S., McGrath H., Coleman D. 2020. Flood mapping using random forest and identifying the essential conditioning factors; a case study in Fredericton New Brunswick Canada, ISPRS Annals of Photogrammetry Remote Sensing Spatial Information Sciences, 3(3), 609–615. https://doi.org/10.5194/isprs-annals-V-3-2020-609-2020
16. Faruq A., Arsa H.P., Hussein S.F., Razali C.M., Marto A., Abdullah S.S. 2020. Deep learning-based forecast and warning of floods in Klang River, Malaysia. Ingénierie des Systems d Inf., 25(3), 365– 370, https://doi.org/10.18280/isi.250311
17. Fazel-Rastgar F., Sivakumar V. 2023. A case study of an extreme flooding episode in Charikar, Eastern Afghanistan, Journal of Water and Climate Change, 14(12), 4689–4707, https://doi.org/10.2166/wcc.2023.462
18. Gaffinet B., Hagensieker R., Loi L. and Schumann G. 2023. Supervised machine learning for flood extent detection with optical satellite data, IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 2084–2087, https://doi.org/10.1109/IGARSS52108.2023.10282274
19. Ghasemi P., Karimian N. 2020. A qualitative study of various aspects of the application of IoT in disaster management. 6th International Conference on Web Research (ICWR), 77–83. IEEE. https://doi.org/10.1109/ICWR49608.2020.9122323
20. Goyal H.R., Sharma S. 2023. Flood management system using cloud computing and internet-ofthings, 2023 5th Biennial International Conference on Nascent Technologies in Engineering (ICNTE), Navi Mumbai, India. 1–6, https://doi.org/10.1109/ICNTE56631.2023.10146661
21. Gude V., Corns S., Long S. 2020. Flood prediction and uncertainty estimation using deep learning. Water, 12(3), 884. https://doi.org/10.3390/w12030884
22. Gupta L., Dixit J. 2023. Assessment of urban flood susceptibility and role of urban green space (UGS) on flooding susceptibility using GIS-based probabilistic models. Environmental Monitoring and Assessment, 195(12), 1518, https://doi.org/10.1007/s10661-023-12061-4
23. Harshasimha A.C., Bhatt C.M. 2023. Flood vulnerability mapping using maxent machine learning and Analytical Hierarchy Process (AHP) of Kamrup Metropolitan District, Assam. Environ., Sci. Proc. 2023, 25(1), 73. https://doi.org/10.3390/ECWS-7-14301
24. Hashi A.O., Abdirahman A.A., Elmi M.A., Hashi S.Z., Rodriguez O.E. 2021. A real-time flood detection system based on machine learning algorithms with emphasis on deep learning.International Journal of Engineering Trends and Technology, 69(5), 249–256. https://doi.org/10.14445/22315381/IJETT-V69I5P232
25. Ignatowicz J., Kutt K., Nalepa G.J. 2024. Evaluation and Comparison of Emotionally Evocative Image Augmentation Methods. 28th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2024), Procedia Computer Science, Elsevier. https://arxiv.org/pdf/2406.16187
26. Kalantar B., Ueda N., Saeidi V., Janizadeh S., Shabani F., Ahmadi K., Shabani F. 2021. Deep neural network utilizing remote sensing datasets for flood hazard susceptibility mapping in Brisbane, Australia. Remote Sensing, 13(13), 2638. https://doi.org/10.3390/rs13132638
27. Kumar V., Azamathulla H.M., Sharma K.V., Mehta D.J., Maharaj K.T. 2023. The state of the art in deep learning applications, challenges, and future prospects: A comprehensive review of flood forecasting and management, Sustainability, 15(13), 10543. https://doi.org/10.3390/su151310543
28. Lei X., Chen W., Panahi M., Falah F., Rahmati O., Uuemaa E., Kalantari Z., Ferreira C.S., Rezaie F., Tiefenbacher J.P., Lee S. 2021. Urban flood modeling using deep-learning approaches in Seoul, South Korea. Journal of Hydrology, 601, 126684, https://doi.org/10.1016/j.jhydrol.2021.126684
29. Putranto M.F. and Munir R. 2023. Deep Learning Approach for Heavy Rainfall Prediction Using Himawari-8 And RDCA Data, International Conference on Computer, Control, Informatics and its Applications (IC3INA), Bandung, Indonesia, 424–429. https://doi.org/10.1109/IC3INA60834.2023.10285744
30. Maurya J., Pant H., Dwivedi S., Jaiswal M. 2021, Flood avoidance using IOT. International Journal of Engineering Applied Sciences and Technology, 6(1), 155–158. https://ijeast.com/papers/155- 158,Tesma601,IJEAST.pdf
31. Miau S., Hung W.H. 2020. River flooding forecasting and anomaly detection based on deep learning. IEEE Access, 8, 198384–198402. https://doi:10.1109/ACCESS.2020.3034875
32. Munawar H.S., Ullah F., Qayyum S., Heravi A. 2021. Application of deep learning on uav-based aerial images for flood detection. Smart Cities, 4(3), 1220– 1242, https://doi.org/10.3390/smartcities4030065
33. Patil S., Sawant S., Joshi A. 2023. Flood detection using remote sensing and deep learning approaches, 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, 1–6, https://doi.org/10.1109/ICCCNT56998.2023.10306978
34. Prathyusha K., Raju A.J., Rao P.J. 2024. Novel Malaria Risk Prediction and Mapping of Integrated Tribal Development Agency, Paderu Region, India, Using SAMRR. Journal of the Indian Society of Remote Sensing, 52(1),167–187. https://doi.org/10.1007/s12524-023-01796-9
35. Ramachandraiah C. 2011. Coping with urban flooding: a study of the 2009 Kurnool floods, India. Environment and Urbanization, 23(2), 431–46. https://doi/10.1177/0956247811418733
36. Rao G.N., Rao P.J., Duvvuru R., Beulah K., Lydia E.L., Rathnala P., Balakrishna B., Motru V.R. 2024. Neural fuzzy system design in forest fire detection. Microsystem Technologies, 30(4), 455–467. https://doi.org/10.1007/s00542-023-05496-9
37. Rauschmayr N., Kama S., Kim M., Choi M., Kenthapadi K. 2022. Profiling deep learning workloads at scale using amazon sagemaker. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 3801–3809. https://doi.org/10.1145/3534678.3539036
38. Roy P., Pal S.C., Chakrabortty R., Chowdhuri I., Malik S., Das B. 2020. Threats of climate and land use change on future flood susceptibility. Journal of Cleaner Production, 272, 122757, https://doi.org/10.1016/j.jclepro.2020.122757
39. Samikwa E., Voigt T., Eriksson J. 2020. Flood Prediction Using IoT and Artificial Neural Networks with Edge Computing, 2020 International Conferences on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom), IEEE Smart Data(SmartData), 234–240, https://doi.org/10.1109/iThings-GreenCom-CPSComSmartData-Cybermatics50389.2020.00053
40. Sankaranarayanan S., Prabhakar M., Satish S., Jain P., Ramprasad A., Krishnan A. 2020. Flood prediction based on weather parameters using deep learning. Journal of Water and Climate Change, 11(4), 1766–1783. https://doi.org/10.2166/wcc.2019.321
41. Seidel D., Wurster S., Jenks J.D., Sati H., Gangneux J.P., Egger M., Alastruey-Izquierdo A., Ford N.P., Chowdhary A., Sprute R., Cornely O. 2024. Impact of climate change and natural disasters on fungal infections. The Lancet Microbe. 5(6), e594-e605. https://doi.org/10.1016/S2666-5247(24)00039-9
42. Sharma V.K., Azad R.K., Chowdary V.M., Jha C.S. 2022. Delineation of Frequently Flooded Areas Using Remote Sensing: A Case Study in Part of Indo-Gangetic Basin, Geospatial Technologies for Land and Water Resources Management, Springer, Cham, 103, 505–530. https://doi.org/10.1007/978-3-030-90479-1_27
43. Shreekumar S., Madhu D., Akella A.K. 2021. Urban Flood Susceptibility Mapping of Kochi Taluk Using Remote Sensing and GIS. Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT), Erode, India, 1–6. https://doi.org/10.1109/ICECCT52121.2021.9616790
44. The News Minute. 2015. Body of six-year-old washed away in Vizag drain, found 50 km off coast (Accessed on 21September, 2024) (https://www.thenewsminute.com/andhra-pradesh/body-six-year-old-washed-awayvizag-drain-found-50-km-coast-34811)
45. The News Minute. 2021. Andhra flash floods: 30 passengers travelling in RTC buses washed away, 12 dead. (Accessed on 24 December, 2023) (https://www.thenewsminute.com/andhra-pradesh/andhraflash-floods-30-passengers-travelling-rtc-buseswashed-away-12-dead-157835).
46. Vanama V.S., Shitole S., Rao Y.S. 2020. Urban Flood Mapping with C-band RISAT-1 SAR Images: 2016 Flood Event of Bangalore City, India, 2020 International Conference on Convergence to Digital World - Quo Vadis (ICCDW), Mumbai, India, 1–4, https://doi.org/10.1109/ICCDW45521.2020.9318710
47. Qi W., Ma C., Xu H., Chen, Z., Zhao K., Han H. 2021. A review on applications of urban flood models in flood mitigation strategies, Natural Hazards, 108, 31–62. https://doi.org/10.1007/s11069-021-04715-8
48. Yin Y. 2023. Research on natural disaster target change detection method based on deep learning, IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA), Shenyang, China, 946–950. https://doi.org/10.1109/ICPECA56706.2023.10076044

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-10611ef4-7b3d-4a2a-9b5b-2195739c9af6