Isaac Nzayisenga

Mr. Isaac Nzayisenga

College of Geography and Remote Sensing, Hohai University, Nanjing, Jiangsu, China
orcid
Master of Science (Hons) in Cartography and GIS (Machine Lea...

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
12 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
BMBoaz Mwubahimana
Boaz Mwubahimana
JYJianguo Yan
Jianguo Yan
DMDingruibo Miao
Dingruibo Miao
Swalpa Kumar RoySwalpa Kumar Roy
Swalpa Kumar Roy
ZLZhuohong Li
Zhuohong Li
Xiao HuangXiao Huang
Xiao Huang
Autonomous feature extraction from high-resolution (HR) Remote Sensing (RS) imagery presents complex spatial–spectral heterogeneity and diverse land-cover patterns, challenging conventional single-architecture models that lack multiscale feature diversity and cross-domain generalization. Convolutional neural networks (CNNs) effectively capture localized hierarchical structures, whereas transformers model long-range contextual dependencies via self-attention. However, using these architectures independently restricts their complementary potential. This study proposes FWDNNet (Fused Weights Deep Neural Tokenization Networks), a fusion framework introducing a CNN-to-token conversion mechanism that transforms convolutional feature maps from heterogeneous encoders into transformer-compatible token sequences. Beyond standard concatenation, FWDNNet integrates a TensorDot-based fusion module to learn high-order cross-architectural interactions, while a shared decoding pathway maintains multiscale feature hierarchies and computational efficiency. Experiments across three diverse datasets show that FWDNNet achieves 58.2 ms inference latency with minimal cross-domain performance degradation (2.3–4.2% mIoU drop). Compared to conventional fusion strategies, FWDNNet attains 21% faster inference and 1.7–2.7% higher mIoU over baseline methods. See Materials at https://github.com/BoazGithub/FWDNNet for reproducibility.

4 July 2025 in Academia Environmental Sciences and Sustainability
Verified
Journal Article
Open access
PDF file
Tuyizere Ndera MucyoTuyizere Ndera Mucyo
Tuyizere Ndera Mucyo
ENElias Nyandwi
Elias Nyandwi
GRGaspard Rwanyiziri
Gaspard Rwanyiziri
EMEmmanuel Muyombano
Emmanuel Muyombano
NJNdera Jackson
Ndera Jackson
Isaac NzayisengaIsaac Nzayisenga
Isaac Nzayisenga
Forest landscape restoration (FLR) plays a crucial role in enhancing ecological resilience, biodiversity, and livelihoods. The effectiveness of FLR is influenced by regional differences, socio-economic conditions, and the policy–practice gap. This study assesses key factors contributing to the success of FLR and its impact in the Congo–Nile Crest agro-ecological zone (CNC AEZ), a portion of the Congo basin in Rwanda. The research draws on 150 household surveys, 15 key informant interviews, and a review of 21 regulatory frameworks, including international agreements, global strategies, national laws, policies, and institutional frameworks. Findings from the survey indicate that 98% of farmers are aware of FLR initiatives and 90.6% participated in FLR projects, with 83.33% using both native and non-native species. Farmers reported a number of benefits from FLR, including improved climate resilience, income from agriculture and forest products, better infrastructure, and increased knowledge of sustainable practices. However, many farmers felt unsupported due to inconsistent seed availability and a lack of follow-up training. Challenges identified from both survey and regulatory framework analysis include a lack of strong financial mechanisms and monitoring system, limited resources, land use competition, soil erosion, illegal deforestation, market constraints, and low private sector involvement. Agroforestry emerged as a promising approach, enhancing restoration and food security at once. This study emphasizes the need for aligning policy frameworks with socio-economic realities. The findings from farmers, environmental practitioners, and policy documents highlight key recommendations, including community participation, quality seed provision, research, market accessibility, and cross-sectoral collaboration, as essential to FLR success. This study provides critical community-informed evidence to guide FLR policy refinement and implementation in CNC AEZ and other regions with similar socio-ecological contexts.

10 February 2026 in Rwanda Journal of Engineering, Science, Technology and Environment
Verified
Journal Article
Open access
PDF file
MEMuyombano Emmanuel
Muyombano Emmanuel
MFMwizerwa Fidele
Mwizerwa Fidele
Isaac NzayisengaIsaac Nzayisenga
Isaac Nzayisenga
NDNzirorera Jean De Dieu
Nzirorera Jean De Dieu
Informal settlements are residential areas developed outside formal planning and tenure systems, housing nearly one billion people globally and exacerbating urban challenges such as overcrowding and environmental degradation, particularly in developing countries. In Kigali, Rwanda, their growth has contributed to insecurity and limited access to basic services. To address these issues, the government, in collaboration with the World Bank, initiated upgrading programs such as the Agatare project, aiming to improve infrastructure and provide affordable housing. Sustainable urban development also requires attention to environmental concerns, including waste management and drainage. This study evaluates the effectiveness of informal settlement upgrading in Agatare Cell, Nyarugenge Sector, using a mixed-methods approach that combines field observations, questionnaire surveys, semi-structured interviews, and spatial data analysis. Findings indicate that the project generated local employment, enhanced housing quality, contributed to the provision of basic infrastructure and facilities. In addition, it fostered the improvement of the environment and increased public safety through street lighting. It also contributed to the attainment of Kigali’s urban development goals by promoting a secure and clean city. However, challenges were identified. These include the limited financial resources available to property owners to improve their dwellings which can trigger tenure insecurity, inadequate compensation during expropriation, and insufficient community participation. The study recommends the prioritization of tenure security and promoting inclusive community engagement that would strengthen the upgrading initiatives and support sustainable urban resilience.

20 January 2025 in East African Journal of Agriculture and Biotechnology
Verified
Journal Article
Open access
PDF file
FMFlorien Misago
Florien Misago
Isaac NzayisengaIsaac Nzayisenga
Isaac Nzayisenga
HNHenri Jacques Ngirinshuti
Henri Jacques Ngirinshuti
LILeon De Pere Irakoze
Leon De Pere Irakoze
RMRichard Mind’jE
Richard Mind’jE
This study evaluates the potential of rooftop and wall-based urban agriculture to enhance food security in the Gasabo District of Kigali, Rwanda. It combines GIS and remote sensing techniques to map suitable urban farming spaces and uses a stratified sampling technique to select 400 household heads for assessment using the Household Food Insecurity Access Scale (HFIAS). The findings show that 41.5% of the households experience moderate to severe food insecurity, and approximately 32% of rooftops and walls are structurally appropriate for urban agriculture. While 57.8% of households express willingness to adopt rooftop or wall gardening, 67.4% cite structural and financial constraints. A strong positive correlation (r = 0.68, p < 0.01) was observed between urban agriculture adoption and improved food security. The study recommends prioritising high-suitability sectors such as Kinyinya and Ndera for pilot projects and promoting lightweight hydroponic and vertical farming systems tailored to urban structures. These findings support the integration of urban agriculture into Kigali’s urban planning to enhance food resilience and sustainability

16 April 2026 in Land
Verified
Journal Article
Open access
PDF file
Ngoga Iradukunda FredNgoga Iradukunda Fred
Ngoga Iradukunda Fred
AKAlishir Kurban
Alishir Kurban
AEAnwar Eziz
Anwar Eziz
TAToqeer Ahmed
Toqeer Ahmed
HEHAKORIMANA EGIDE
HAKORIMANA EGIDE
Hossein AzadiHossein Azadi
Hossein Azadi
Urbanisation reshapes Land Cover and Land Use (LCLU) by driving deforestation, wetland loss, and the conversion of natural and agricultural areas into built environments. However, integrated analyses of LCLU change in response to climate variability in topographically complex, rapidly urbanising African cities remain limited. Therefore, this study examined 2000–2024 LCLU changes in hilly Gasabo District (Kigali, Rwanda) using 30 m Landsat imagery and a Random Trees classifier (92.7% accuracy, 70/30 train-test split), with 2032 projections via a population-driven hybrid trend model. Population estimates/projections 320,516 in 2002 to 967,512 in 2024, 1.41 million by 2032, were derived from Rwanda’s census data and exponential growth modelling (calibrated to 5.05% annual growth). Rapid population growth has driven a 539% expansion of Built-up Areas, accompanied by notable declines in cropland and Forest. Local climate trends (Meteo Rwanda stations) aligned with global datasets (ERA5-Land and CHIRPS): rainfall fluctuation and temperature rose, with strong correlations between population-driven Built-up Areas expansion. From 2024 to 2032, LCLU projections indicate that Built-up Areas will continue to expand by 29.5%. Cropland was forecast to decline to 15.9%, while Forest loss slowed to 5.7%. MLR analysis revealed strong correlations between population-driven expansion of Built-up Areas, cropland/forest loss, warming, and rainfall fluctuations in Gasabo. An ARDL model was applied to address multicollinearity among LCLU predictors, which limited the interpretation of individual coefficients, and confirmed the core MLR correlation trends, with statistically significant (p < 0.05) coefficients. The results highlight the need for data-driven spatial planning in Gasabo (stricter zoning, high-rise buildings, targeted reforestation, climate-resilient green infrastructure) to mitigate population and urbanisation-driven environmental degradation.

2 September 2026 in npj Clean Air
Verified
Journal Article
Open access
PDF file
TEThompson Faraday Ediagbonya
Thompson Faraday Ediagbonya
MAMarian Onyemaechi Ashikodi
Marian Onyemaechi Ashikodi
OAOchuko Vincent Akpojivi
Ochuko Vincent Akpojivi
FOFriday Elumah Oziegbe
Friday Elumah Oziegbe
AMAline Françoise Mbabazi
Aline Françoise Mbabazi
Isaac NzayisengaIsaac Nzayisenga
Isaac Nzayisenga
Black carbon (BC) is a major urban pollutant affecting climate and health. This review examines studies published between 2018 and 2026 on BC sources, mixing state, and impacts. Traffic emissions dominate developed cities, while biomass and residential combustion are major sources in developing regions. Particle mixing influences radiative forcing and respiratory deposition. Standardized measurements and integrated climate-health assessments are needed.