Hybrid machine learning for flood prediction: comparing CHIRPS satellite and ground station data

• Autorzy: Rachmawardani Agustina , Kurniawan Budhy , Wijaya Sastra Kusuma , Sopaheluwakan Ardhasena , Sinambela Marzuki

Identyfikatory

DOI

10.24425/jwld.2025.153520

• Języki publikacji: EN

Abstrakty

EN

Flooding in Jakarta is a multifaceted issue influenced by a combination of geographical, social, economic, and environmental factors. This study focuses on predicting floods by comparing automatic rain gauge (ARG) ground station data and Climate Hazards Group InfraRed Precipitation (CHIRPS) satellite data using the Adaptive Neurofuzzy Inference System (ANFIS) integrated with principal component analysis (PCA). The dataset includes precipitation measurements from both ARG and CHIRPS along with water level data spanning from 2014 to 2020. ARG provides precise local rainfall data, while CHIRPS offers extensive regional precipitation coverage. To enhance data quality, preprocessing techniques such as mean imputation, data normalisation, and the interquartile range (IQR) method were employed. The ANFIS-PCA model, which integrates fuzzy logic and neural network training, was applied using an 80:20 split for training and validation. When trained with ARG ground station data and water level measurements, the ANFIS-PCA model demonstrated superior accuracy, achieving a root mean square error (RMSE) of 0.13, mean absolute error (MAE) of 0.12, and R² of 0.82. In contrast, the ANFIS model without PCA yielded higher errors, with RMSE 6.3, MAE 6.2, and R² 0.74. Training with CHIRPS satellite data resulted in significantly higher errors (RMSE 30.14, MAE 24.05, R² 0.42). These findings underscore the superiority of ground-based measurements for flood prediction, given the reduced precision and higher susceptibility to errors in satellite-derived data. While CHIRPS satellite data offers broader spatial coverage, its limitation in precision and higher susceptibility to errors reduce its effectiveness for accurate flood prediction.

Słowa kluczowe

EN

adaptive neuro-fuzzy inference system; flood prediction; machine learning; rainfall; satellite data; water level

• Wydawca: Wydawnictwo ITP
• Czasopismo: Journal of Water and Land Development
• Rocznik: 2025
• Tom: no. 64
• Strony: 87--99
• Opis fizyczny: Bibliogr. 44 poz., mapy, rys., tab., wykr.

Twórcy

autor

Rachmawardani Agustina

• Universitas Indonesia, Faculty of Mathematics and Natural Sciences, Department of Physics, Building F, Pondok Cina, Beji District, Depok City 16424, Indonesia
• State College of Meteorology, Climatology and Geophysics, Meteorology Street, No 5, Tanah Tinggi Sub-district, Tangerang District, Tangerang City, Banten 15119, Indonesia

• https://orcid.org/0009-0009-3813-8164

autor

Kurniawan Budhy

• Universitas Indonesia, Faculty of Mathematics and Natural Sciences, Department of Physics, Building F, Pondok Cina, Beji District, Depok City 16424, Indonesia

• https://orcid.org/0000-0002-9203-7438

autor

Wijaya Sastra Kusuma

• Universitas Indonesia, Faculty of Mathematics and Natural Sciences, Department of Physics, Building F, Pondok Cina, Beji District, Depok City 16424, Indonesia

• https://orcid.org/0000-0003-0780-9585

autor

Sopaheluwakan Ardhasena

• Indonesia’s Meteorological, Climatological, and Geophysical Agency, Angkasa 1 No 2 street, Kemayoran, Central Jakarta, DKI Jakarta 10720, Indonesia
• World Meteorological Organization (WMO), 7bis, avenue de la Paix, CH-1211 Geneva 2, Switzerland

• https://orcid.org/0000-0002-4532-854X

autor

Sinambela Marzuki

• State College of Meteorology, Climatology and Geophysics, Meteorology Street, No 5, Tanah Tinggi Sub-district, Tangerang District, Tangerang City, Banten 15119, Indonesia

• https://orcid.org/0000-0003-3363-4440

Bibliografia

• Ahmadi, N. and Moradinia, S.F. (2024) “An approach for flood flow prediction utilizing new hybrids of ANFIS with several optimization techniques: A case study,” Hydrology Research, 55(5), pp. 560–575. Available at: https://doi.org/10.2166/nh.2024.191.
• Al-Areeq, A.M. et al. (2024) “Implication of novel hybrid machine learning model for flood subsidence susceptibility mapping: A representative case study in Saudi Arabia,” Journal of Hydrology, 630, 130692. Available at: https://doi.org/10.1016/j.jhydrol.2024.130692.
• Amiri, A. et al. (2024) “A novel machine learning tool for current and future flood susceptibility mapping by integrating remote sensing and geographic information systems,” Journal of Hydrology, 632, 130936. Available at: https://doi.org/10.1016/j.jhydrol.2024.130936.
• Ansari, S. et al. (2021) “Parameter tuning of MLP, RBF, and ANFIS models using genetic algorithm in modeling and classification applications,” 2021 International Conference on Information Technology, ICIT 2021, Amman, Jordan 14–15 July 2021. Amman: Al-Zaytoonah University of Jordan, pp. 660–666. Available at: https://doi.org/10.1109/ICIT52682.2021.9491682.
• Antzoulatos, G. et al. (2022) “Flood hazard and risk mapping by applying an explainable machine learning framework using satellite imagery and GIS data,” Sustainability, 14(6), 3251. Available at: https://doi.org/10.3390/su14063251.
• Arora, A. et al. (2021) “Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India,” Science of the Total Environment, 750, 141565. Available at: https://doi.org/10.1016/j.scitotenv.2020.141565.
• Bennett, W.G. et al. (2023) “Modelling compound flooding: A case study from Jakarta, Indonesia. Natural Hazards, 118(1), 277–305. Available at: https://doi.org/10.1007/s11069-023-06001-1.
• Bensaid, R. et al. (2024) “Toward a real-time TCP SYN flood DDoS mitigation using adaptive neuro-fuzzy classifier and SDN assistance in fog computing,” Security and Communication Networks, 2024, 651584. Available at: https://doi.org/10.1155/2024/6651584.
• Buuren van, S. and Groothuis-Oudshoorn, K. (2011) “mice: Multi-variate Imputation by Chained Equations in R,” Journal of Statistical Software, 45(3), pp. 1–67. Available at: https://doi.org/10.18637/jss.v045.i03.
• Cho, I., Park, S. and Kim, J. (2022). “A fire risk assessment method for high-capacity battery packs using interquartile range filter,” Journal of Energy Storage, 50, 104663. Available at: https://doi.org/10.1016/j.est.2022.104663.
• Dong, S. et al. (2021) “A hybrid deep learning model for predictive flood warning and situation awareness using channel network sensors data,” Computer-Aided Civil and Infrastructure Engineering, 36(4), pp. 402–420. Available at: https://doi.org/10.1111/mice.12629.
• Du, H. et al. (2024) “Evaluating the effectiveness of CHIRPS data for hydroclimatic studies,” Theoretical and Applied Climatology, 155(3), pp. 1519–1539. Available at: https://doi.org/10.1007/s00704-023-04721-9.
• Gabr, M.I., Helmy, Y.M. and Elzanfaly, D.S. (2023) “Effect of missing data types and imputation methods on supervised classifiers: An evaluation study,” Big Data and Cognitive Computing, 7(1), 55. Available at: https://doi.org/10.3390/bdcc7010055.
• García-Laencina, P.J., Sancho-Gómez, J.L. and Figueiras-Vidal, A.R. (2010) “Pattern classification with missing data: A review,” Neural Computing and Applications, 19(2), pp. 263–282. Available at: https://doi.org/10.1007/s00521-009-0295-6.
• Günal, A.Y. (2024) “Implementing fuzzy SMRGT, ANN, and ANFIS for flow coefficient estimation in Antalya River Basin,” Journal of Hydrology, 640, 131705. Available at: https://doi.org/10.1016/j.jhydrol.2024.131705.
• Hassan, W.I., Joseph, I. and Abubakar, S. (2024) “Assessment of effect of flooding and flood risk reduction strategies in urban centres,” Journal of Built Environment and Geological Research, 04(4), pp. 286–299. Available at: https://africanscholarpub.com/ajbegr/article/view/231/238 (Accessed: June 03, 2024).
• Helmi, A.M. et al. (2024) “Comparing remote sensing and geostatistical techniques in filling gaps in rain gauge records and generating multi-return period isohyetal maps in arid regions – Case study: Kingdom of Saudi Arabia,” Water, 16(7), 925. Available at: https://doi.org/10.3390/w16070925.
• Indriastuti, D. (2016) “Analysis of runoff due to the change in land use at the watershed of Upstream Ciliwung,” Journal of the Civil Engineering Forum, 2(1), 131. Available at: https://doi.org/10.22146/jcef.26576.
• Islam, A.R.M.T. et al. (2023) “Improvement of flood susceptibility mapping by introducing hybrid ensemble learning algorithms and high-resolution satellite imageries,” Natural Hazards, 119(1), pp. 1–37. Available at: https://doi.org/10.1007/s11069-023-06106-7.
• Jang, J.-R.R. (1993) “ANFIS: Adaptive-network-based fuzzy inference system,” IEEE Transactions on Systems, Man, and Cybernetics, 23(3), pp. 665–685. Available at: https://doi.org/10.1109/21.256541.
• Karamizadeh, S. et al. (2013) “An overview of Principal Component Analysis,” Journal of Signal and Information Processing, 04(3B), pp. 173–175. Available at: https://doi.org/10.4236/jsip.2013.43b031.
• Llovo, I.F., Mosqueira, J. and Vidal, F. (2018) “Analysis of the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) in Assessing Rounding Model Analysis of the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) in Assessing Rounding Model,” OP Conference Series: Materials Science and Engineering. Available at: https://doi.org/10.1088/1757-899X/324/1/012049.
• Ly H.-B. et al. (2019) “Improvement of ANFIS model for prediction of compressive strength of manufactured sand concrete,” Applied Sciences, 9(18), 3841. Available at: https://doi.org/10.3390/app9183841.
• Maharana, K., Mondal, S. and Nemade, B. (2022) “A review: Data pre-processing and data augmentation techniques,” Global Transitions Proceedings, 3(1), pp. 91–99. Available at: https://doi.org/10.1016/j.gltp.2022.04.020.
• Navale, V. and Mhaske, S. (2023) “Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) model for forecasting groundwater level in the Pravara River Basin, India,” Modeling Earth Systems and Environment, 9(2), pp. 2663–2676. Available at: https://doi.org/10.1007/s40808-022-01639-5.
• Pishnamazi, M. et al. (2020) “ANFIS grid partition framework with difference between two sigmoidal membership functions structure for validation of nanofluid flow,” Scientific Reports, 10, 15395. Available at: https://doi.org/10.1038/s41598-020-72182-5.
• Priyambodoho, B.A. et al. (2021) “Flood inundation simulations based on GSMaP satellite rainfall data in Jakarta, Indonesia,” Progress in Earth and Planetary Science, 8, 34. Available at: https://doi.org/10.1186/s40645-021-00425-8.
• Rachmawardani, A. et al. (2022) “State of the art of remote sensing in flood early warning system: review article,” Social, Humanities, and Educational Studies (SHES): Conference Series, 5(4), 108. Available at: https://doi.org/10.20961/shes.v5i4.68977.
• Rashidi Shikhteymour, S. et al. (2023) “A novel approach for assessing flood risk with machine learning and multi-criteria decision-making methods,” Applied Geography, 158, 103035. Available at: https://doi.org/10.1016/j.apgeog.2023.103035.
• Rudra, R.R. and Sarkar, S.K. (2023) “Artificial neural network for flood susceptibility mapping in Bangladesh,” Heliyon, 9(6), e16459. Available at: https://doi.org/10.1016/j.heliyon.2023.e16459.
• Sahoo, A., Samantaray, S. and Paul, S. (2021) “Efficacy of ANFIS-GOA technique in flood prediction: A case study of Mahanadi River basin in India,” H2Open Journal, 4(1), pp. 137–156. Available at: https://doi.org/10.2166/H2OJ.2021.090.
• Samantaray, S. et al. (2023) “Flood discharge prediction using improved ANFIS model combined with hybrid particle swarm optimisation and slime mould algorithm,” Environmental Science and Pollution Research, 30, pp. 83845–83872. Available at: https://doi.org/10.1007/s11356-023-27844-y.
• Santos, L.B.L. et al. (2023) “A neural network-based hydrological model for very high-resolution forecasting using weather radar data,” Eng, 4(3), pp. 1787–1796. Available at: https://doi.org/10.3390/eng4030101.
• Saridewi, T.R. and Fauzi, A. (2019) “A market-based mechanism as an alternative solution for watershed management: a case study of the Ciliwung Watershed, Indonesia,” International Journal of Global Environmental Issues, 18(2), 171. Available at: https://doi.org/10.1504/ijgenvi.2019.10023932.
• Sarkar, S.C. et al. (2021) “Application of soft computing for time series water-level prediction in Jamuna River,” International Journal of Systematic Innovation, 6(6), pp. 13–21. Available at: https://doi.org/10.6977/IJoSI.202112_6(6).0003.
• Shabbir, J. and Ahmed, A. (2022) “Computation estimation of interquartile range in stratified sampling under non-linear cost function,” Communications in Statistics – Simulation and Computation, 51(4), pp. 1891–1898. Available at: https://doi.org/10.1080/03610918.2019.1689267.
• Shahid, M. et al. (2021) “Assessing the potential and hydrological usefulness of the CHIRPS precipitation dataset over a complex topography in Pakistan,” Hydrological Sciences Journal, 66(11), pp. 1664–1684. Available at: https://doi.org/10.1080/02626667.2021.1957476.
• Singh, D. and Singh, B. (2020) “Investigating the impact of data normalization on classification performance,” Applied Soft Computing, 97(B), 105524. Available at: https://doi.org/10.1016/j.asoc.2019.105524.
• Srilakshmi, K. et al. (2024) “Optimization of ANFIS controller for solar/battery sources fed UPQC using an hybrid algorithm,” Electrical Engineering, 106(4), pp. 3743–3770. Available at: https://doi.org/10.1007/s00202-023-02185-8.
• Sulugodu, B. and Deka, P.C. (2019) “Evaluating the performance of CHIRPS satellite rainfall data for streamflow forecasting,” Water Resources Management, 33(11), pp. 3913–3927. Available at: https://doi.org/10.1007/s11269-019-02340-6.
• Szeląg, B. et al. (2024) “Tool for fast assessment of stormwater flood volumes for urban catchment: A machine learning approach,” Journal of Environmental Management, 355, 120214. Available at: https://doi.org/10.1016/j.jenvman.2024.120214.
• Wang, M. et al. (2021) “Sourcing CHIRPS precipitation data for streamflow forecasting using intrinsic time-scale decomposition based machine learning models,” Hydrological Sciences Journal, 66(9), pp. 1437–1456. Available at: https://doi.org/10.1080/02626667.2021.1928138.
• Youssef, A.M. et al. (2023) “Flood vulnerability mapping and urban sprawl suitability using FR, LR, and SVM models,” Environmental Science and Pollution Research, 30(6), pp. 16081–16105. Available at: https://doi.org/10.1007/s11356-022-23140-3.
• Zein, M.R., Anggraheni, E. and Yahya, D.M. (2023) “Impact analysis of land use changes on inundation map in The Ciliwung River Watershed,” CSID Journal of Infrastructure Development, 6(2), 3. Available at: https://doi.org/10.7454/jid.v6.i2.1117.