Abstract
Rainfall is changing in intensity and abundance for much of the world as a result of global climate change. Rwanda has been negatively affected by a changing climate, exacerbated by human impact on land and water resources. In most parts of the country, the rainfall pattern has changed over the last decades resulting in both enhanced flooding and water shortage/scarcity in much of the country, especially in the Capital City of Kigali and peripheries which is the main economic hub of the country with strong links to the East African region. Changes in precipitation have affected agricultural production, hydropower production, and water supplies, and has been a result of increased flash floods in the city. This study developed a new predictive model of rainfall patterns in the City of Kigali (CoK) in the Republic of Rwanda using evolutionary methodologies that apply machine learning techniques of Fuzzy Inference Systems (FIS) trained via Genetic Algorithms, Neuro Network Systems and a comparative Support Vector Machine tool, and assessment downscaled climate change combinations with predicted rainfall patterns. The models were calibrated and validated using measured rainfall data in the City of Kigali from 1991 through 2023. The model results show the developed Geno Fuzzy Inference System (GENOFIS) model performed better than the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Support Vector Machine (SVM) models. The Coefficient of Efficiency (CE), and Root Mean Square Error (RMSE) were used as diagnostic measures for model performance evaluation. Models generated with GENOFIS are therefore recommended for rainfall and related prediction patterns in the City of Kigali for climate change adaptation and resilience policy and planning.
Similar content being viewed by others
Data availability
The gauged rainfall data used in this study will be available upon request from the corresponding author.
References
Aboniyo J et al (2017) 2017 National water resources management authority for a sustainable water use in Rwanda. Sustainable Resour Manage J 2(3):01–15
Altunkaynak A (2019) Predicting water level fluctuations in lake van using hybrid season-neuro approach. J Hydrol Eng 24:4019021
Altunkaynak A, Kartal E (2019) Performance comparison of continuous wavelet-fuzzy and discrete wavelet-fuzzy models for water level predictions at northern and southern boundary of Bosphorus. Ocean Eng 186:106097
Altunkaynak A (2010) A predictive model for well loss using fuzzy logic approach. Hydrol Process 24(17):2400–2404
Altunkaynak A, Nigussie TA (2015) Prediction of daily rainfall by a hybrid wavelet-season-neuro technique. J Hydrol 529:287–301
Altunkaynak A, Şen Z (2007) Fuzzy logic model of lake water level fluctuations in Lake Van. Turkey Theore Appl Climatol 90(3-4):227–233
Atiah, W. A., Bendito, E. G., & Muthoni, F. K. (2023). Evaluating Seasonal Rainfall Forecast Gridded Models over Sub-Saharan Africa
Belohlavek R, Urbanec T (2023) On the concept of fuzzy order I: Remarks and observations. Int J Gen Syst 52(8):948–971
Bibri SE, Krogstie J, Kaboli A, Alahi A (2024) Smarter eco-cities and their leading-edge artificial intelligence of things solutions for environmental sustainability: A comprehensive systematic review. Environ Sci Ecotechnol 19:100330
Bizimana H, Altunkaynak A (2020) Modeling the initiation of sediment motion under a wide range of flow conditions using a Geno-Mamdani Fuzzy Inference System method. Int J Sediment Res 35(5):467–483
Bizimana H, Altunkaynak A (2019) A novel approach for the prediction of the incipient motion of sediments under smooth, transitional and rough flow conditions using Geno-Fuzzy Inference System model. J Hydrol 577:123952
Bridgman HA, Oliver JE (2014) The global climate system: patterns, processes, and teleconnections. Cambridge University Press
Deltares (2021): Inception Report. Stormwater and Wetland Management Model for the delineated flood prone areas in Kigali City
Donigian AS, Love JT (2003) Sediment calibration procedures and guidelines for watershed modeling. Proceedings of the Water Environment Federation 2003(4):728–747
FONERWA (2023): Final Report. Strategic Integrated Water Resources Planning and Management
Gebrechorkos SH, Taye MT, Birhanu B, Solomon D, Demissie T (2023) Future changes in climate and hydroclimate extremes in East Africa. Earth's. Future 11(2):e2022EF003011
Gholami A, Bonakdari H, Ebtehaj I, Akhtari AA, 2017. Design of an adaptive neuro-fuzzy computing technique for predicting flow variables in a 90° sharp bend. J. Hydroinformatics jh2017200. https://doi.org/10.2166/hydro.2017.200
Gustafson DE, Kessel WC, 1979 Fuzzy clustering with a fuzzy covariance matrix. In 1978 IEEE conference on decision and control including the 17th symposium on adaptive processes (pp. 761- 766). IEEE.
Habonimana HV et al (2015) Integrated flood modeling for flood hazard assessment in CoK. Rwanda, GeoTechRwanda
Habumugisha V, Mukashyaka MM (2023) Flood Management in Rwanda: An Analysis of Policy Implementation Perspective. African J Climate Change Res Sustain 2(1):117–131
Henninger, S. (2013a). Relief, nocturnal cold-air flow and air quality in Kigali, Rwanda. In EGU General Assembly Conference Abstracts (pp. EGU2013-28)
Henninger SM (2013b) When air quality becomes deleterious—a case study for, Kigali, Rwanda
Huang S, Cai N, Pacheco PP, Narrandes S, Wang Y, Xu W (2018) Applications of support vector machine (SVM) learning in cancer genomics. Cancer Geno Proteom 15(1):41–51
Jakkula V (2006) Tutorial on support vector machine (svm). Washington State University, School of EECS, p 37
Icyimpaye G, Abdelbaki C (2022) GIS-Based Hydrological and Hydraulic Models to Forecast River Flood Risks and Proposition of Management Measures. In: Spatial Modelling of Flood Risk and Flood Hazards: Societal Implications. Springer International Publishing, Cham, pp 143–159
IFRC, “Dref Operation- Rwanda, Floods and Landslides,” 2023
Iradukunda P, Mwanaumo EM, Kabika J (2023). Hydroclimatic trend analysis and projection in Africa tropical urban regions: Cases of Lusaka, Zambia and Kigali, Rwanda Urban Climate, 52, 101680
Jang JS (1992) Neuro-fuzzy modeling: architectures, analyses, and applications. University of California, Berkeley
Jang JS (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst, man, Cybern 23(3):665–685
Jonah K, Wen W, Shahid S, Ali M A, Bilal M, Habtemicheal BA, ... & Tiwari P. (2021)Spatiotemporal variability of rainfall trends and influencing factors in Rwanda. J Atmospheric Solar-Terrestrial Phy, 219, 105631
Jovanovic BB, Reljin IS, Reljin BD (2004) Modified ANFIS architecture-improving efficiency of ANFIS technique. In: In 7th Seminar on Neural Network Applications in Electrical Engineering, 2004. NEUREL 2004. IEEE, pp 215–220
Karamage F, Zhang C, Fang X, Liu T, Ndayisaba F, Nahayo L et al (2017) Modeling rainfall-runoff response to land use and land cover change in Rwanda (1990–2016). Water 9(2):147
Karamage F et al (2016) The need for awareness of drinking water loss reduction for sustainable water resource management in Rwanda. J Geosci Environ Prot 4:74–87
Lake RW, Shaeri S, Senevirathna STMLD (2023) Review of the limitations and potential empirical improvements of the parametric group method of data handling for rainfall modelling. Environ Sci Pollut Res 30(44):98907–98921
Loh J, Wackernagel M (2004) Living Planet Rep:2004
Laknath DPC, Josiah NR, Sirisena TAJG (2015) Analysis of Long-term Trends of Climatological Parameters in Kigali, Rwanda
Mindje R, Li L, Kayumba PM, Mupenzi C, Mindje M, Hao J (2023) Exploring a form of pixel-based information value model for flood probability assessment and geo-visualization over an East African basin: a case of Nyabarongo in Rwanda. Environ Earth Sci 82(17):402
Ministry of Infrastructure (MININFRA), Rwanda. Forward-looking joint sector report (FLSP) Water and Sanitation sector 2016/2017. Kigali, Rwanda; 2016. Available from: http://www.mininfra.gov.rw, [Accessed on 08/11/ 2017]
Moriasi DN, Arnold JG, Van Liew MW, Bingner RL, Harmel RD, Veith TL (2007) Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans ASABE 50(3):885–900
Moosavi V, Vafakhah M, Shirmohammadi B, Behnia N (2013) A wavelet-ANFIS hybrid model for groundwater level forecasting for different prediction periods. Water Resour Manag 27(5):1301–1321
Mugiraneza T, Ban Y, Haas J (2019) Urban land cover dynamics and their impact on ecosystem services in Kigali, Rwanda using multi-temporal Landsat data. Remote Sens Appli: Soc Environ 13:234–246
Munyaneza O, Nzeyimana YK, Wali UG (2013) Hydraulic structures design for flood control in the Nyabugogo wetland, Rwanda
Nafi A, Brans J (2019) Cost–benefit prediction of asset management actions on water distribution networks. Water 11(8):1542
Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I—A discussion of principles. J Hydrol 10(3):282–290
National Policy for Water Resources Management (NPWRM), Rwanda, 2011
National Water Resources Masterplan (NWRMP), Rwanda, 2013
Nazarenko LS, Tausnev N, Russell GL, Rind D, Miller RL, Schmidt GA et al (2022) Future climate change under SSP emission scenarios with GISS-E2. 1. J Adv Model Earth Syst 14(7):e2021MS002871
Nduwayezu G, Manirakiza V, Mugabe L, Malonza JM (2021) Urban Growth and Land Use/Land Cover Changes in the Post-Genocide Period, Kigali, Rwanda. Environ Urban ASIA 12(1_suppl):S127–S146
Niyonsenga D (2012). Assessing public transport supply for Kigali, Rwanda (Master's thesis, University of Twente)
Ntirenganya F, 2018 Analysis of Rainfall Variability in Rwanda for Smallscale farmers Coping Strategies to Climate Variability. East African Journal of Science and Technology, Vol.8 Issue1, (P.75-96)
Özger M (2009) Comparison of fuzzy inference systems for streamflow prediction. Hydrol Sci J 54(2):261–273
Rema (2010). Rwanda Environmental Education for Sustainable Development Strategy: A Strategy and Action Plan for 2010–2015. Kigali, Rwanda; Rema 2011. Guidelines for Mainstreaming Climate Change Adaptation and Mitigation in the Environment and Natural Resources Sectors. Kigali
Rukundo E, Doğan A (2016) Assessment of Climate and Land Use Change Projections and their Impacts on Flooding. Pol J Environ Stud 25(6)
Rwanda Natural Resources Authority. (2013). National Water Resources Masterplan
Saidi L, Ali JB, Fnaiech F (2015) Application of higher order spectral features and support vector machines for bearing faults classification. ISA Trans 54:193–206
Schwing FB, Murphree T, Dewitt L, Green PM (2002) The evolution of oceanic and atmospheric anomalies in the northeast Pacific during the El Niño and La Niña events of 1995–2001. Prog Oceanogr 54(1-4):459–491
Sern CC, Nasir AFA, Majeed APA, Zakaria MA, Razman MAM, Azmi A (2020) Comparison of Support Vector Machine and Friis Equation For Identification of Pallet-Level Tagging Using RFID Signal. In: In 2020 IEEE 10th Symposium on Computer Applications & Industrial Electronics (ISCAIE). IEEE, pp 215–219
Solomatine DP, Shrestha DL (2009) A novel method to estimate model uncertainty using machine learning techniques. Water Resour Res 45(12)
Sugeno M, Kang GT (1988) Structure identification of fuzzy model. Fuzzy Sets Syst 28(1):15–33
Takagi T, Sugeno M (1985) Fuzzy identification of systems and its applications to modeling and control. IEEE Trans Syst Man Cybern SMC-15(1):116–132
Theobald B, 2018 Water Demand Management as a Solution to Water Resources Challenges in Rwanda
Theobald B et al (2018) Water Demand Management as a Solution to Water Resources Challenges in Rwanda. Ijsrm Human 9(1):51–70
Thrasher B, Wang W, Michaelis A, Melton F, Lee T, Nemani R (2022) NASA global daily downscaled projections, CMIP6. Scientific Data 9(1):262
Tsinda A, Kind C, Hess JS, Mugisha R, Bizoza AR (2019) Estimating damage costs of flooding on small-and medium-sized enterprises in Kigali, Rwanda. Jàmbá: J Disaster Risk Stud 11(1):1–11
Twizeyimana (2023) Field data collection Technical report of 2 days from 05th to 06th May 2023
UNDP, ‘Turning Vision 2020 into Reality: From Recovery to Sustainable Human Development. National Human Development Report’, Kigali, 2007
USAID (2014) Planning for Resilience in East Africa through Policy. Adaptation, Research, And Economic Development
Uwera C (2013) Water Demand and Financing in Rwanda: An Empirical Analysis. University of Gothenburg
Funding
This research has received funding from the Islamic Development Bank under the postdoctoral fellowship number: IsDB Scholarship: 2020-279583 taken at Istanbul Technical University, Istanbul, Turkey under the supervision of Professor Abdusselam Altunkaynak.
Author information
Authors and Affiliations
Contributions
All authors appearing in the manuscript contributed to the research conceptualization, data collection interpretation, and design of the methodologies. Modeling-based materials, and model preparation, data review, calibration, and analysis were performed by Hussein Bizimana, Abdusselam Altunkaynak, and Mathieu Mbati Mugunga. The first draft of the manuscript was written by Hussein Bizimana, Robert Kalin, and Emmanuel Rukundo, and the second draft was updated by Osman Sönmez, Gamze Tuncer, and Abdulkadir Baycan who also improved the climate change modeling and interpretation. Furthermore, all authors commented on all versions of the manuscript, and read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflicts of interest/Competing interests
The authors declare that there is no conflict of interest regarding publishing this article.
Additional information
Communicated by: H. Babaie
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bizimana, H., Altunkaynak, A., Kalin, R. et al. Assessment of rainfall and climate change patterns via machine learning tools and impact on forecasting in the City of Kigali. Earth Sci Inform 17, 1229–1243 (2024). https://doi.org/10.1007/s12145-024-01231-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-024-01231-8