Ogonna Kizzito Agbahiwe

Ogonna Kizzito Agbahiwe

Auto-generated profile, based on publicly available information

Ogonna Kizzito Agbahiwe

Chukwuemeka Odumegwu Ojukwu University

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 September 2025 in Journal of Engineering Research and Reports
Verified
Journal Article
Closed access
TAToheeb Abbey Animashaun
Toheeb Abbey Animashaun
OSOmolayo Sunday
Omolayo Sunday
EOEmmanuel Ogunleye
Emmanuel Ogunleye
OAOgonna Kizzito Agbahiwe
Ogonna Kizzito Agbahiwe
OAOladele Nicholas Afolayan
Oladele Nicholas Afolayan
EIEbuka Stephen Ifionu
Ebuka Stephen Ifionu
Combining the Artificial Intelligence (AI) together with Digital Twin (DT) technologies is redefining Structural Health Monitoring (SHM) to shift maintenance of the infrastructure to proactive across aspects. The design of a digital twin framework that incorporates a cadre of machine learning and neural-network-based tools into a predictive maintenance approach that can continuously sense, learn, and respond through closed-loop feedback. The framework is based on sensor networks using the IoT, sophisticated models of AI, and immersive visualizations and can provide real-time knowledge about the structural state. Field applications within civil infrastructure, aerospace and renewable energy have proven it to be effective at predicting remaining useful life and limit downtime, improve safety and minimize costs of operations. The results indicate the potential of AI-powered digital twins to establish self-sustaining SHM systems and lead to more resistant and intelligent infrastructure.

4 March 2026 in Computational Intelligence in Modern Power Systems
Verified
Journal Article
Open access
SISamson Micheal Idoghor
Samson Micheal Idoghor
OAOgonna Kizzito Agbahiwe
Ogonna Kizzito Agbahiwe
LELinda Egbubine
Linda Egbubine
PAPeter Akinlotan
Peter Akinlotan
JOJonathan Kuffour Owusu
Jonathan Kuffour Owusu
UOUgochukwu Udonna Okonkwo
Ugochukwu Udonna Okonkwo
Flooding is a major and persistent risk to cities and riverine communities worldwide. We conducted a systematic review to assess how remote sensing is being applied in flood control and stormwater management in operational contexts. Following PRISMA 2020 guidelines, we screened studies published between 2000 and 2024 and identified 20 empirically rigorous articles that reported quantitative validation metrics using satellite, airborne, or UAV-based data. Across these studies, synthetic aperture radar (SAR), particularly Sentinel-1, emerged as the most reliable platform for all-weather flood extent mapping, with typical accuracies above 85%. Optical sensors such as Landsat and Sentinel-2 performed well under cloud-free conditions and were especially useful for surface water detection, vegetation dynamics, and monitoring green stormwater infrastructure through indices such as NDVI. LiDAR provided the most precise topographic information, generating centimeter-level digital elevation models that significantly improved urban flood modeling. UAV platforms offered ultra-high spatial resolution (< 10 cm), supporting localized damage assessment, infrastructure inspection, and post-event validation. We found that machine learning approaches, including convolutional neural networks and vision transformers, consistently outperformed traditional threshold-based methods, often achieving F1-scores above 0.90. However, challenges remain, particularly limited validation data, weak uncertainty quantification, scale mismatches, and difficulties with operational integration. Overall, our review shows that remote sensing has become a practical and indispensable tool for flood and stormwater management when sensor platforms are strategically combined.