Deep Learning-based Flood Risk Prediction for Climate Resilience Planning in Malawi

Authors

  • Isaac Kadono Mwalwimba

    Department of Climate Sciences, Ndata School of Climate and Earth Sciences, Malawi University of Science and Technology, Limbe 5196, Malawi

    Centre for Research Consult, P.O. Box 1397, Blantyre, Malawi
  • Bessam Kalonjeka

    Centre for Research Consult, P.O. Box 1397, Blantyre, Malawi
  • Vincent Msadala

    Department of Climate Sciences, Ndata School of Climate and Earth Sciences, Malawi University of Science and Technology, Limbe 5196, Malawi
  • Vincent Katonda

    Department of Climate Sciences, Ndata School of Climate and Earth Sciences, Malawi University of Science and Technology, Limbe 5196, Malawi
  • Chikondi Chisenga

    Department of Earth Sciences, Ndata School of Climate and Earth Sciences, Malawi University of Science and Technology, Limbe 5196, Malawi
  • Cosmo Ngongondo

    Department of Geography, Earth Sciences and Environment, School of Natural and Applied Sciences, University of Malawi, Zomba 280, Malawi
  • Mtafu Manda

    Department of Built Environment, Mzuzu University, Mzuzu 201, Malawi

DOI:

https://doi.org/10.30564/jasr.v8i2.10377
Received: 22 February 2025; Revised: 25 March 2025; Accepted: 2 April 2025; Published Online: 7 April 2025

Abstract

Climate change resilience in Malawi faces an institutional gap because most institutions often fail to prioritize risk data when dealing with climate extremes such as floods. This unfortunate gap forces many Malawians to fend for themselves during times of climate extremes This situation is also heightened by a few studies that utilize Time Series Analysis (TSA) and Deep Learning Models (DLM) to predict climate extremes for decision-making processes. Therefore, this study focused on flood risk prediction and assessment in six selected districts of Malawi: Chikwawa, Blantyre, Phalombe, Zomba, Rumphi, and Karonga. Traditional Time Series Models (ARIMA) and Semantic Convolution Deep Learning Analysis were used for this purpose. Data were retrieved from the database of the US National Aeronautics and Space Administration (NASA). The results revealed frequent and significant precipitation peaks in Blantyre and Chikwawa, particularly during the rainy season, suggesting that the areas are at a higher risk of flooding, with a high probability of infrastructural damage and economic losses. Karonga and Phalombe revealed cyclical trends with prominent spikes in rainfall. In contrast, Rumphi and Zomba exhibit less pronounced trends, though there are still significant fluctuations in rainfall patterns, suggesting an increasing likelihood of flood risk in future climate extremes. This study situates its policy implications by emphasizing that residents, institutions, government, partners, and NGOs need to take a problem-focused approach towards climate resilience planning, including updating flood risk maps, designing flood protection infrastructure, and preparing emergency response plans tailored to the specific needs of each district in Malawi.

Keywords:

Vulnerability Assessment; Floods; Climate Change; Lilongwe City; Karonga; Malawi

References

[1] Moreira, L.L., Brito, M.M., Kobiyama, M., 2021. A systematic review and prospects of flood vulnerability indices. Natural Hazards and Earth System Sciences. 21(5), 1513–1530. DOI: https://doi.org/10.5194/nhess-21-1513-2021

[2] Government of Malawi, 2023. Malawi 2023 Tropical Cyclone Freddy Post-Disaster Needs Assessment. Government of Malawi: Lilongwe, Malawi.

[3] Mwalwimba, I.K., Mtafu, M.Z., Ngongondo, C., 2024a. Measuring vulnerability to assess households’ resilience to flood risks in Karonga District, Malawi. Natural Hazards. 120(7), 6609–6628. DOI: https://doi.org/10.1007/s11069-024-06416-4

[4] Manda, M.Z., Wanda, E., 2017. Understanding the nature and scale of risks in Karonga Town, Malawi. Environment and Urbanization. 29(1), 15–32.

[5] Manda, M., Kamlomo, D., Mphande, D., et al., 2016. Karonga Town: Growth and Risk Profile. Working Paper 9. Mzuzu University Malawi: Mzuzu, Malawi, Mzimba.

[6] Adeloye, A.J., Mwale, F.D., Dulanya, Z., 2015. A metric-based assessment of flood risk and vulnerabilities of rural communities in the Lower Shire Valley, Malawi. Proceedings of the International Association of Hydrological Sciences. 370(370), 139–145.

[7] Mwalwimba, I.K., Mtafu, M.Z., Ngongondo, C., 2024b. Flood Vulnerability Assessment in Rural and Urban Informal Settlements: Case Study of Karonga District and Lilongwe City in Malawi. Natural Hazards. 120(11), 10141–10184. DOI: https://doi.org/10.21203/rs.3.rs-3407776/v1

[8] Birkmann, J., Cardona, O.D., Carreno, M.L., et al., 2013. Framing vulnerability, risk, and societal responses: the move framework. Natural Hazards. 67(2), 193–211. DOI: https://doi.org/10.1007/s11069-013-0558-5

[9] Ngongondo, C., Zhou, Y., Xu, C.Y., 2020. Multivariate framework for the assessment of key forcing to Lake Malawi level variations in non-stationary frequency analysis. Environmental Monitoring and Assessment. 192(9), 593. DOI: https://doi.org/10.1007/s10661-020-08519-4

[10] Sankaranarayanan, S., Prabhakar, M., Satish, S., et al., 2020. Flood prediction based on weather parameters using deep learning. Journal of Water and Climate Change. 11(4), 1766–1783. DOI: https://doi.org/10.2166/wcc.2019.321

[11] Jamshed, A., 2015. Assessing vulnerability and capacity of flood-affected communities in Punjab, Pakistan [Master’s Thesis]. University of Stuttgart: Stuttgart, Germany.

[12] Mulumpwa, M., Jere, W., Lazaro, M., et al, 2018. Modelling and forecasting Lake Malawi water level fluctuations using stochastic models. African Journal of Rural Development. 3(3), 831–841.

[13] Atashi, V., Gorji, H.T., Shahabi, S.M., et al., 2022. Water Level Forecasting Using Deep Learning Time-Series Analysis: A Case Study of Red River of the North. Water. 14(12), 1971. DOI: https://doi.org/10.3390/w14121971

[14] Ludin, S.M., 2018. Risk of Deterioration among General Ward Patients: Nurses' Ability in Assessing Early Warning SIGNS. Malaysian Journal of Medical Research. 2(1), 19–29.

[15] Kia, M.B., Pirasteh, S., Pradhan, B., et al., 2012. An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia. Environmental Earth Sciences. 67, 251–264. DOI: https://doi.org/10.1007/s12665-011-1504-z

[16] Fritzsche, K., Schneiderbauer, S., Bubeck, P., et al., 2014. The Vulnerability Sourcebook: Concept and guidelines for standardised vulnerability assessments. Federal Ministry for Economic Cooperation and Development: Bonn, Germany.

[17] Brown, W., 2013. Sovereignty Matters: Africa, Donors and the Aid Relationship. African Affairs. 112(447), 262–282.

[18] Government of Malawi, 2022. Malawi 2022 floods post-disaster needs Assessment report. Government of Malawi: Lilongwe, Malawi.

[19] Government of Malawi, 2019. Malawi 2019 Floods Post Disaster Needs Assessment Report. Government of Malawi: Lilongwe, Malawi.

[20] Government of Malawi, 2018. National Resilience Strategy (2018-2030): Breaking the cycle of food insecurity in Malawi. Department of Disaster Management Affairs (DODMA): Lilongwe, Malawi.

[21] Government of Malawi, 2015. Malawi 2015 floods post-disaster needs Assessment report. March 2015. Government of Malawi: Lilongwe, Malawi.

[22] Wisner, B., 2016. Vulnerability as Concept, Model, Metric and Tool. Oxford Research Encyclopaedia of Natural Hazard Science. DOI: https://doi.org/10.1093/acrefore/9780199389407.013.25

[23] Iloka, N.G., 2017. Perception of Ethnicity, local knowledge, and sustainable livelihoods about DRR. The Case of Nsukka in South-East Nigeria [PhD Thesis]. University of Northumbria: Newcastle, UK.

[24] Salami, R.O., Meding, J.K., Giggins, H., 2017. Urban settlements’ vulnerability to floods in African cities: A conceptual framework. Journal of Disaster Risk. 9(1), 1–9.

[25] Msasa, C.M., Manda, M.A.Z.C., 2025. Physical vulnerability of buildings to flooding in Lilongwe City, Malawi. UCL Open: Environment. 7, e3216. DOI: https://doi.org/10.14324/111.444/ucloe.3216

[26] Elias, Z., Mekonnen, A., Gebre, S., 2025. Evaluating Flood Vulnerability in Bahir Dar City Through an Indicator-Based Method. In: Fanta, S.W., Tenagashaw, M.W., Tigabu, M.T., et al. (eds.). Sustainable Development Research in Manufacturing, Process Engineering, Green Infrastructure, and Water Resources. Green Energy and Technology. Springer: Cham, Switzerland. pp. 377–393. https://doi.org/10.1007/978-3-031-77339-6_23

[27] Blantyre City Disaster Risk Management, 2017.Blantyre City Council : Malawi. Available from: Blantyre City Council (cited 17 February 2025).

[28] Mwale, F.D., Adeloye, A.J., Beevers, L., 2015. Quantifying vulnerability of rural communities to flooding in SSA. International Journal of Disaster Risk Reduction. 12, 172–187.

Downloads

How to Cite

Mwalwimba, I. K., Kalonjeka, B., Msadala, V., Katonda, V., Chisenga, C., Ngongondo, C., & Manda, M. (2025). Deep Learning-based Flood Risk Prediction for Climate Resilience Planning in Malawi. Journal of Atmospheric Science Research, 8(2), 37–50. https://doi.org/10.30564/jasr.v8i2.10377

Issue

Vol. 8 , Iss. 2 (April 2025)

Article Type

Article

License

Copyright © 2025 Isaac Kadono Mwalwimba, Bessam Kalonjeka, Vincent Msadala, Vincent Katonda, Chikondi Chisenga, Cosmo Ngongondo, Mtafu Manda

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC