Flood Image Classification using Convolutional Neural Networks
Main Article Content
Abstract
Flood disaster is a natural disaster that leads to loss of lives, properties damage, devastating effects on the economy and environment; therefore, there should be effective predictive measures to curb this problem. Between the years 2002- 2023, flood has caused death of over 200,000 people globally and occurred majorly in resource poor countries and communities. Different machine learning approaches have been developed for the prediction of floods. This study develops a novel model using convolutional neural networks (CNN) for the prediction of floods. Important parameters such as standard deviation and variance were incorporated in the parameters tuned CNN model that performed flood images feature extraction and classification for better predictive performance. The enhanced model was assessed with accuracy and loss measurement and compared with the existing model. The model leverage on the unique features of region of Interest aligns to resolve the issues of misalignments caused by the use of region of Interest pooling engaged in the traditional Faster-RCNN. The techniques and the developed system were implemented using a Python-based integrated development environment called “Anaconda Navigator” on Intel Core i5 with 8G Ram hardware of Window 10 operating system. The developed model achieved optimal accuracy at 200 epochs with 99.80% and corresponding loss of 0.0890. The results confirmed that predictive performance of a model can be improved by incorporating standard deviation and variance on model, coupled with its parameters tunning approach before classification.
Article Details
References
Jin, W. (2020). Research on Machine Learning and Its Algorithms and Development. Physics journal.
Alafif, T., Tehame, A. M., Bajaba, S., Barnawi, A. & Zia, S. (2021). Machine and Deep Learning towards COVID-19 Diagnosis and Treatment: Survey, Challenges, and Future Directions. Int. J. Environ. Res. Public Heal, 8(1): 11- 17.
Sitterson, J., Knightes, C., Parmar, R., Wolfe, K.., Muche, M. & Avant, B. (2017). An Overview of Rainfall-Runoff Model Types. U.S Environ. Prot. Agency.
Bukohwo, M. & OfikwuEne, P. (2018). Flood Prediction in Nigeria Using Artificial Neural Network. Am. J. Eng. Res.,7(9): 15 – 21.
Baalaji, S. V. & Sandhya, S. (2020). Flood Prediction System using Multilayer Perceptron Classifier and Neural Networks. Water , 6245–6254.
Tanim, A. H.., McRae, C. B., Tavakol‐davani, H. & Goharian, E. (2022). Flood Detection in Urban Areas Using Satellite Imagery and Machine Learning. Water (Switzerland), 4(1): 7 - 20, doi: 10.3390/w14071140.
Arora, A., Arabameri, A., Pandey, M., Siddiqui, M. A. Shukla, U. K., Tien, D., Narayan, V. & Bhardwaj, A. (2021). Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for fl ood susceptibility prediction mapping in the Middle Ganga Plain , India. Sci. Total Environ., 5(7): 41-56, doi: 10.1016/j.scitotenv.2020.141565.
Madhuram, M. Kakar, A., Sharma, A. & Chaudhuri, S. (2019). Flood Prediction and warning system using SVM and ELM models . Int. J. Innov. Sci. Res. Technol.,5366–5369, doi: 10.35940/ijrte.D7573.118419.
Kabbas, A.., Alharthi, A. & Munshi, A. (2020) . Artificial Intelligence Applications in Cyber security. Int. J. Comput. Sci. Netw. Secur., 2(20): 14 -26
Julius, A. O., Ayokunle, A. O. & Ibrahim, F. O. (2021). Early Diabetic Risk Prediction using Machine Learning Classification Techniques. Int. J. Innov. Sci. Res. Technol., 9(6): 502–507.
Farhadi, H. & Najafzadeh, M. (2021). Flood risk mapping by remote sensing data and random forest technique,” Water (Switzerland), 21(13): 15 - 28, doi: 10.3390/w13213115.
Mukhamediev, R. (2022). Review of Artificial Intelligence and Machine Learning Technologies: Classification, Restrictions, Opportunities and Challenges. Math. 2022, https//doi.org/10.3390/ math10152552.
Volkmar, G., Fischer, P.M., & Reinecke, S. (2022). Artificial Intelligence and Machine Learning: Exploring drivers, barriers, and future developments in marketing management. J. Bus. Res.
Feizizadeh, B., Gheshlaghi, H. A., & Bui, D. T. (2020). An integrated approach of GIS and hybrid intelligence techniques applied for flood risk modeling. J. Environ. Plan. Manag., 1(1): 1-32, doi: 10.1080/09640568.2020.1775561.
Madhuri, R., Sistla, S. & Raju, K. S. (2021). Application of machine learning algorithms for flood susceptibility assessment and risk management. J. water Clim. Chang., 1–16, doi: 10.2166/wcc.2021.051.
Shirzadi, A., Asadi, S., Shahabi, H., Ronoud, S. & Clague, J.J. (2020). A novel ensemble learning based on Bayesian Belief Network coupled with an extreme learning machine for flash flood susceptibility mapping,” Eng. Appl. Artif. Intell., 6(9): 32 - 49, doi: 10.1016/j.engappai.2020.103971.
Vazhuthi , H. N. & Kumar, A. (2020). Causes and Impacts of Urban Floods in Indian Cities: A Review. Int. J. Emerg. Technol., 4(11): 140–147.
Bansal, N., Mukherjee, M. & Gairola, A. (2022). Evaluating urban flood hazard index (UFHI) of Dehradun city using GIS and multi-criteria decision analysis. Model. Earth Syst. Environ., 8(3): 4051–4064, doi: 10.1007/s40808-021-01348-5.
Svetlana, D., Radovan, D. & Ján, D. (2022). The Economic Impact of Floods and their Importance in Different Regions of the World with Emphasis on Europe. Procedia Econ. Financ., 15(34): 649–655, doi: 10.1016/s2212-5671(15)01681-0.
Olanrewaju, C. C., Chitakira, M., Olanrewaju, O. A. & Louw, E. (2019). Impacts of flood disasters in Nigeria: A critical evaluation of health implications and management. Jamba J. Disaster Risk Stud., 1(11): 1–9, doi: 10.4102/jamba.v11i1.557.
Echendu, A. J. (2020). The impact of flooding on Nigeria’s sustainable development goals (SDGs). Ecosyst. Heal. Sustain., 1(6): 1-9, doi: 10.1080/20964129.2020.1791735.
WHO (2023). Africa-Nigeria Flood, retrieved from. https//www.afro.who.int/news/nigeria-rushes-current-flash-flooding-mitigate-health-hazards, date accessed 03/07/2023., 2023.
Khosravi, K., Shahabi, H., Thai, B., Adamowski, J. & Shirzadi, A. (2018). A comparative assessment of flood susceptibility modeling using Multi- Criteria Decision-Making Analysis and Machine Learning Methods. J. Hydrol., 311–323, doi: 10.1016/j.jhydrol.2019.03.073.
Khosravi, K. (2018). A comparative assessment of decision trees algorithms for fl ash fl ood susceptibility modeling at Haraz watershed , northern Iran. Sci. Total Environ., 744–755, doi: 10.1016/j.scitotenv.2018.01.266.
Hemba, S. & Elekwachi, W. (2020). Effectiveness of Drainage Networks on Floods in Calabar Metropolis, Nigeria. J. Geogr. Meteorol. Environ. 1(3): 106-120.
Chan, S. W., Abid, S. K., Sulaiman, N., Nazir, U. & Azam, K.. (2022). A systematic review of the flood vulnerability using geographic information system, Heliyon, 3(8): 40 - 52, doi: 10.1016/j.heliyon.2022.e09075.
NEMA (2022) . National Emergency Management Agency, retrieved from . https://www.preventionweb.net, date accessed 08/02/2022,
NEMA (2019). National Emergency Management Agency, retrieved from https://www.preventionweb.net, date accessed 08/02/2021.
Nkwunonwo, B., Malcolm, U. C. W. & Brian, A. (2021). Flooding and Flood risk reduction in Nigeria: Cardinal. Journal of Geography & Natural Disasters.
Berkhahn, S., Fuchs, L. & Neuweiler, I. (2019). An ensemble neural network model for real-time prediction of urban floods. J. Hydrol., 5(7): 743–754, doi: 10.1016/j.jhydrol.2019.05.066.
Ighile, E. H., Shirakawa, H. & Tanikawa, H. (2022). A Study on the Application of GIS and Machine Learning to Predict Flood Areas in Nigeria. Sustain., 9(14): 20-32, doi: 10.3390/su14095039.
Jahangir, M. H., Mahsa, S., Reineh, M. & Abolghasemi, M. (2019). Spatial predication of flood zonation mapping in Kan River Basin , Iran , using arti fi cial neural network algorithm. Weather Clim. Extrem., 5( 25): 1002-1015, doi: 10.1016/j.wace.2019.100215.
Michael, E. & Patience, O. (2018). Flood Prediction In Nigeria Using Artificial Neural Network. American Journal of Engineering Research ( AJER ), 15–21
Paul, A. (2017). Flood Prediction Model using Artificial Neural Network Flood Prediction Model using Artificial Neural Network. Water, doi: 10.7753/IJCATR0307.1016.
Costache, R. (2019). Novel hybrid models between bivariate statistics , artificial neural networks and boosting algorithms for flood susceptibility assessment. j.jenvman., 6(25): 62 - 78, doi: 10.1016/j.jenvman.2020.110485.
Liu, J. (2021). Assessment of Flood Susceptibility Using Support Vector Machine in the Belt and Road Region. Nat. Hazards Earth Syst. Sci. Discuss., 1–37.
Pham, B. T. (2019). A comparison of Support Vector Machines and Bayesian algorithms for landslide susceptibility modelling. Geocarto Int., 13(34): 1385–1407, doi: 10.1080/10106049.2018.1489422.
Nguyen, V., Yariyan, P., Amiri,b M. Tran, A. D. & Pham, T. D. (2020). A New Modeling Approach for Spatial Prediction of Flash Flood with Biogeography Optimized CHAID Tree Ensemble and Remote Sensing Data. J. Hydrol.
Nguyen, H. & Bae, D. (2019). An approach for improving the capability of a coupled meteorological and hydrological model for rainfall and flood forecasts. J. Hydrol., 5(7): 124-134, doi: 10.1016/j.jhydrol.2019.124014.
Bui, D. T. (2019). A novel hybrid approach based on a swarm intelligence optimized extreme learning machine for flash flood susceptibility mapping,. Catena, 7(9): 184–196, 2019, doi: 10.1016/j.catena.2019.04.009.
Talukdar, S., Ghose, B., Roquia, S. & Susanta, S. (2020). Flood susceptibility modeling in Teesta River basin , Bangladesh using novel ensembles of bagging algorithms. Stoch. Environ. Res. Risk Assess., 12(34): 2277–2300, doi: 10.1007/s00477-020-01862-5.
Pham, B. T. (2021). Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques. Geosci. Front., 3(12): 101-120, doi: 10.1016/j.gsf.2020.11.003.
Nawi, N. M., Makhtar, M., Salikon, M. Z. & Afip, Z. A. (2020). A comparative analysis of classification techniques on predicting flood risk, 3(18): 1342–1350, doi: 10.11591/ijeecs.v18.i3.pp1342-1350.
Razali, N., Ismail, S. & Mustapha, A. (2020). Machine learning approach for flood risks prediction. ijai.,1(9): 73–80, doi: 10.11591/ijai.v9.i1.pp73-80.
Baharom, A. S., Idris, Z., Isa, S. S., Nazir, M. & Khan, A. (2020). Prediction of Flood Detection System: Fuzzy Logic Approach.. Int. J. Enhanc. Res. Sci. Technol. Eng, ISSN 2319 – 74635.
Nazir, M., Baharom, A. S., Idris, Z., Isa, S. S. & Khan, A. (2021). Prediction of Flood using Decision Tree. Int. J. Enhanc. Res. Sci. Technol. Eng. ISSN 2319 – 74635.
Khan, A., Baharom, A. S., Idris, Z., Isa, S. S. & Nazir, M. (2022). Prediction of Flood Prediction Using Decision Tree. Int. J. Enhanc. Res. Sci. Technol. Eng. ISSN 2319 – 74635.
Campolo, M. , Soldati, A. & Andreussi, P. (2022). Artificial neural network approach to flood forecasting in the River Arno. Hydrol. Sci. J., 3(48): 381–398, doi: 10.1623/hysj.48.3.381.45286.
Khan, P.D. & Nazir, S. C. (2018). Flood Modeling and Prediction Using Artificial Neural Network. IEEE Int. Conf. Internet Things Intell. Syst. ISSN 2371-2394.
Ayodele, O. & Adegbenjo, A. (2020). Development of a Flood Forecasting System using Neuro-Fussy Techniques Int. J. Enhanc. Res. Sci. Technol.
Elsafi, S. H. (2019). Artificial Neural Networks ( ANNs ) for flood forecasting at Dongola Station in the River Nile , Sudan. ALEXANDRIA Eng. J., doi: 10.1016/j.aej.2014.06.010.
Dhananjali G. (2019). Flood Forecasting Using Artificial Neural Network for Kalu Ganga. Copernicus Publ. behalf Eur. Geosci. Union.
Kumar, B., Soumya, P., Tushar, D., Nath, K. & Ranjan, M. (2018). An Application of Data Mining Techniques for Flood Forecasting : Application in Rivers Daya and Bhargavi , India. J. Inst. Eng. Ser. B, doi: 10.1007/s40031-018-0333-9.
Vinothini, A., Kruthiga, L. & Monisha, U. (2020). Prediction of Flash Flood using Rainfall by MLP Classifier. Int. J. Recent Technol. Eng. 1(1): 425–429, doi: 10.35940/ijrte.F9880.059120.
Tehrany, M. S., Pradhan, B., Mansor, S. & Ahmad, N. (2015). Flood susceptibility assessment using GIS-based support vector machine model with different kernel type. Catena, 12(5): 91–101, doi: 10.1016/j.catena.2014.10.017.
Li, Q., Li, Z., Chen, L. & Yao, C. (2021). Regionalization of coaxial correlation diagrams for the semi-humid and semi-arid catchments in Northern China. IAHS-AISH Proc. Reports, 8(36): 317–322, doi: 10.5194/piahs-368-317
Huang, P.N. (2019). Application and comparison of coaxial correlation diagram and hydrological model for reconstructing flood series under human disturbance. J. Mt. Sci. 13(7): 123 - 132
Goodarzi, L., Banihabib, M. E., Roozbahani, A. & Dietrich, J. (2019). Bayesian network model for flood forecasting based on atmospheric ensemble forecasts. Nat. Hazards Earth Syst. Sci., 11(19): 2513–2524, doi: 10.5194/nhess-19-2513-2019.
Muhammed, I. (2020). Flood Mapping and Simulation using Sentinel 2 and SRTM Data. FUTY J. Environ, 1(14): 139–148
Wijayarathne, D. B. & Coulibaly, P. (2020). Identification of hydrological models for operational flood forecasting in St. John’s, Newfoundland, Canada. J. Hydrol. Reg. Stud., 2(7): 100-123, doi: 10.1016/j.ejrh.2019.100646.
Rao, J. H., Patle, D. & Sharma, S. K. (2020). Remote Sensing and GIS Technique for Mapping Land Use / Land Cover of Kiknari Watershed. Ind. J. Pure App. Biosci., 8(2): 455–463.
Tarpanelli, A., Mondini, A. C. & Camici, S. (2022). Effectiveness of Sentinel-1 and Sentinel-2 for flood detection assessment in Europe,” Nat. Hazards Earth Syst. Sci., 8(22), 2473–2489, doi: 10.5194/nhess-22-2473-2022.
Khoirunisa, N. & Ku, C. (2021). A GIS-Based Artificial Neural Network Model for Flood Susceptibility Assessment. Int. J. Environ. Res. Public Heal.
Pally, R. J. & Samadi, S. (2022). Application of image processing and convolutional neural networks for flood image classification and semantic segmentation. Environ. Model. Softw., 8(14): 1352–1362.
Islam, M. A., Rashid, S. I., Hossain, N. U. I., Fleming, R. & Sokolov, A. (2023). An integrated convolutional neural network and sorting algorithm for image classification for efficient flood disaster management. Decis. Anal. J., 2(7): 1002 - 1025, doi: 10.1016/j.dajour.2023.100225.
Sarp, S., Kuzlu, M., Cetin, M., Sazara, C. & Güler, O. (2020). Detecting Floodwater on Roadways from Image Data Using Mask-R-CNN. 2020 Int. Conf. Innov. Intell. Syst. Appl.
Zhen, L. & Sun, X. (2021). The Research of Convolutional Neural Network Based on Integrated Classification in Question Classification.. Hindawi Sci. Program., doi: 10.1155/2021/4176059.
Bezdan , T. & Džakula, N. B. (2019). Convolutional Neural Network Layers and Architectures. Int. Sci. Conf. Inf. Technol. Data Relat. Res., 445–451, doi: 10.15308/sinteza-2019-445-451.
Khedgaonkar, R., Singh, K. & Raghuwanshi, M. (2021). Local plastic surgery-based face recognition using convolutional neural networks. Demystifying Big Data, Mach. Learn. Deep Learn. Healthc. Anal., 215–246.
Adetunji, O. J., Adeyanju, I. A. & Esan, A. O. (2023). Flood Areas Prediction in Nigeria using Artificial Neural Network. 2023 Int. Conf. Sci. Eng. Bus. Sustain. Dev. Goals, 1–6, doi: 10.1109/SEB-SDG57117.2023.10124629.
Olaniyan, O. M, Olusesi, A. T., Omodunbi ,B. A., Wahab, W. B., Adetunji, O. J. & Olukoya, B. M. (2023). A Data Security Model for Mobile Ad Hoc Network Using Linear Function Mayfly Advanced Encryption Standard. Int J Emerg Technol Adv Eng.;13(3):101–120
Olusesi, A. T., Olaniyan, O. M., Omodunbi, B. A., Wahab, W. B., Adetunji, O. J. & Olukoya, B. M. (2023). Energy Management Model for Mobile Ad hoc Network using Adaptive Information Weight Bat Algorithm. e-Prime - Adv Electr Eng Electron, https://doi.org/10.1016/j.prime.2023.100255.
Ibitoye, O. T., Osaloni, O. O., Amudipe, S. O. & Adetunji, O. J. (2023). An Adaptive Neural Network Model for Clinical Face Mask Detection. WSEAS Transactions on Biology and Biomedicine, 1(20): 240-246