Browsing by Author "Ikoha, Peters Anselemo"

Now showing 1 - 4 of 4

Adoption of Machine Learning Technologies in Mitigation of Climate Change Risks in North Rift, Kenya
(International Journal of Applied Science and Engineering Review, 2025-07-07) Siunduh, Eric Sifuna; Ikoha, Peters Anselemo; Konje, Martha Muthoni
This study examines the implementation and effectiveness of Machine Learning (ML) technologies in addressing climate change risks within Kenya's North Rift region. The research investigates how ML applications are being utilized to enhance climate resilience, improve agricultural practices, and support decision-making processes in climate risk management. Through a mixed-methods approach combining quantitative data analysis and qualitative stakeholder interviews, this study evaluates the current state of ML adoption, identifies key challenges, and assesses the impact on local communities. Findings indicate that while ML adoption is still in its early stages, there is significant potential for these technologies to improve climate risk prediction, optimize resource allocation, and enhance adaptation strategies. The study reveals that successful implementation requires addressing infrastructure limitations, building local capacity, and ensuring community engagement. This research contributes to the growing body of knowledge on technological solutions for climate change adaptation in developing regions and provides practical recommendations for policymakers and practitioners.
Assessing the Long-Term Changes in Selected Meteorological Parameters over the North-Rift, Kenya: A Regional Climatology Perspective
(Hydrology, 2024-12-03) Makokha, John Wanjala; Masayi, Nelly Nambande; Barasa, Peter; Ikoha, Peters Anselemo; Konje, Martha Muthoni; Mutonyi, Jonathan; Okello, Victor Samuel; Wechuli, Alice Nambiro; Majengo, Collins Otieno; Khamala, Geoffrey Wanjala
Understanding long-term trends in climatic variables is essential for assessing climate change impacts on regional ecosystems and human livelihoods. A regional analysis of climatic variables over some domains is inevitable due to their geographical location and importance to the agricultural sector. Due to the aforementioned demands, the current study analyzes, trends in precipitation (from Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS)), and minimum and maximum temperatures (from TerraClimate) over the North-Rift region of Kenya for over thirty (30) years using satellite data. The seasonal decomposition analysis was performed for each variable to explore the trends and residual components. The findings by the current study indicate that most counties, have experienced enhance precipitation which corresponds to a declining diurnal temperature from 2019 onwards. The seasonality component reveals repeated patterns or variations occurring at steady intervals within each region's data, hence suggesting a distinct regional seasonal trend in the selected meteorological parameters over time. Basically, all counties have reported a relatively constant variability in both maximum and minimum temperatures during the study period except from 2017 onwards where significant variability in the two properties is recorded. In conclusion, the foregoing results that the selected climatic variables exhibit significant spatiotemporal and interannual variability
Learners’ self-directed learning readiness factors towards online learning in Universities: An exploratory factor analysis
(Alupe University Multidisciplinary Research Journal, 2025-04-28) Asenahabi, Bostley Muyembe; Ikoha, Peters Anselemo; Wechuli, Alice Nambiro
Self-directed learning is an essential skill to be possessed by learners for them to comfortably study online besides harnessing their scientific reasoning, critical appraisal, information literacy, and life-long learning. The purpose of this study was to explore factors attributed to self-directed learning readiness towards online learning among university learners. The study adopted the design science world view, quantitative research design and survey research method. This study used a sample size of 398 learners who were randomly selected to take part in the study. Proportional allocation method was used to get the exact number of learners per university who were randomly selected. Quality was ensured through both validity and reliability tests. Exploratory Factor Analysis was used to extract principal components and indicators mapping onto them. Based on the indicators’ themes that were converging on the constructs, the constructs were named: Self-Management with 13 indicators; Self- Control with 11 indicators and Urge to Learn with 6 indicators. This study will be beneficial to policy makers in universities for assessing the state of self-directed learning readiness of learners towards online learning.
Modelling AI Technologies towards Prediction of Disasters Related to Climate Change: Case Study of North Rift, Kenya
(International Journal of Applied Science and Engineering Review, 2025-08-07) Siunduh, Eric Sifuna; Ikoha, Peters Anselemo; Konje, Martha Muthoni
The study explores the application of artificial intelligence (AI) technologies for predicting climate change-induced disasters in Kenya's North Rift region. The North Rift, characterized by diverse topography including highlands, valleys, and arid plains, has experienced increasing frequency and severity of climate-related disasters such as floods, droughts, and landslides over the past decade. These events have significantly impacted agricultural productivity, water resources, infrastructure, and community livelihoods. The study employs machine learning algorithms, including random forests, convolutional neural networks, and long short-term memory (LSTM) networks, to analyze historical meteorological data, satellite imagery, and ground-based observations. This multi-modal approach enables the integration of traditional climate indicators with novel predictive features derived from remote sensing. The research leverages data from Kenya Meteorological Department stations, climate analysis products, and Earth observation satellites to develop regionally calibrated prediction models. Preliminary findings demonstrate that AI-based systems outperform conventional statistical methods in predicting the onset, intensity, and spatial distribution of climate disasters in the region. Notably, the LSTM models achieved 78% accuracy in forecasting drought conditions three months in advance, while CNN-based image analysis shows promising results in identifying flood-prone areas with 82% precision. The research addresses challenges related to data availability and quality through novel data fusion techniques and transfer learning approaches that adapt global climate models to local contexts. The study further examines the integration of AI predictions into existing early warning systems and disaster management frameworks. Stakeholder interviews with local government officials, community representatives, and disaster management agencies reveal both opportunities and barriers for effective implementation. Key recommendations include capacity building for local meteorological services, development of user friendly prediction interfaces, and community-based participatory approaches for validation and refinement of AI outputs. This research contributes to the growing field of climate AI and demonstrates the potential of machine learning in enhancing disaster preparedness and resilience in vulnerable regions. The findings provide a foundation for developing scalable AI-based early warning systems that can be adapted to similar ecological contexts across East Africa