Masters

AI-powered prediction of the current and future distributions of Mesosphaerum suaveolens (L.) Kuntze, a major invasive plant species in Burkina Faso: implications for maize cultivation

2025-07-17T00:00:00Z

AI-powered prediction of the current and future distributions of Mesosphaerum suaveolens (L.) Kuntze, a major invasive plant species in Burkina Faso: implications for maize cultivation Faleroun, Oladélé Priscille Invasive alien plant species are expanding globally due to climate change and human pressures, posing growing threats to biodiversity, ecosystem services and agricultural systems. One such species, Mesosphaerum suaveolens, is rapidly spreading across West Africa, where it disrupts rain-fed cropping systems including maize, a staple crop critical to food security in Burkina Faso. Despite its ecological and agronomic impacts, there's limited understanding of how climate change may affect its future distribution and potential interaction with maize cultivation zones. This study aimed to (i) determine the current distribution of M. suaveolens in Burkina Faso, (ii) forecast its future spread under different climate scenarios, and (iii) assess the spatial overlap between invasion risk and maize-growing areas. We compiled 3254 presence records of M. suaveolens and 51 environmental predictors. After reducing multicollinearity using a variance inflation factor threshold (VIF < 5), a subset of 9 uncorrelated predictors was retained. Three AI-based algorithms: Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) were implemented in Python 3.10 to model current suitability. Models’ performance were evaluated using AUC and TSS, and only RF and CNN, which outperformed SVM, were used for future projections under eight combinations of general circulation models (MIROC6 and HadGEM3-GC31-LL), scenarios (SSP245 and SSP585), and time horizons (2050 and 2080). Maize suitability was modeled using RF, based on 547 presence records and 11 predictors (VIF-filtered). Current and future maize maps were intersected with M. suaveolens risk maps to assess spatial overlaps and quantify exposure levels. CNN projected a 42 to 46% decline in suitable habitats for M. suaveolens by 2080, while RF predicted minor changes (-2.6% to +0.8%). Currently, high-suitability maize areas cover 107,336 km² (39.77%), increasing to 133,362 km² (HadGEM3-GC31-LL) and 136,881 km² (MIROC6) by 2090 under SSP5-8.5. Currently, 62% of maize zones overlap with high invasion risk (CNN), decreasing to 14-16% by 2090, while RF estimates remain stable at ca. 3-4%. These results highlight the CNN model’s higher sensitivity to climate variability and the more conservative nature of RF projections. The combine use of SDMs and crop modeling in an AI framework offers a robust tool for anticipating invasive spread and informing climate-resilient agricultural planning. This study contributes to ecological forecasting and supports the achievement of SDGs 2, 13 and 15 through evidence-basedland-use strategies. A Thesis submitted to the West African Science Service Center on Climate Change and Adapted Land Use and Université Joseph KI-ZERBO, Burkina Faso in partial fulfillment of the requirements for the Master of Science Degree in Informatics for Climate Change

Flood Risk Analysis for Anticipatory Action in Guinea

2025-07-09T00:00:00Z

Flood Risk Analysis for Anticipatory Action in Guinea Barry, Thierno Hamidou Mariama Like most West African countries, Guinea experiences recurrent flooding that severely affects its infrastructure, economy, and the lives of the population. These phenomena are exacerbated by climate change, and the country's vulnerability is particularly evident in poorly planned urban areas, where people often settle in high risk flood zones. The main objective is to study flood anticipatory actions in Guinea through data driven risk assessments. To better understand these risks, several types of data were combined: We used rainfall data from CHIRPS 1981 to 2024, river flow data 1992 to 2024, information on soil permeability, and risk exposure, vulnerability, and ability to adapt. Four main indicators are used to analyze flood risk: hazard, exposure, vulnerability, and Coping capacity. Hazard was measured using average annual precipitation, the 95th percentile of rainfall, and soil permeability coefficients, allowing for the evaluation of the intensity, frequency of extreme rainfall events and soil characteristics. Exposure was calculated based on the population, agricultural land, and livestock in risk prone areas. Vulnerability was assessed through the Multidimensional Poverty Index (MPI), the presence of thatched or earthen roofs, and the number of vulnerable individuals (children under 4, the elderly, and people with disabilities). Lack of coping capacity was measured through access to essential services such as emergency services, health infrastructure, and communication networks. All data were processed and analyzed using Python and the R package. The results showed that pluvial flood hazards (i.e., floods resulting from heavy rainfall) are concentrated in coastal areas and the southern part of the country, while fluvial flood risks (linked to rivers exceeding their capacity) occur throughout the country. The selection of vulnerability indicators also has a significant impact on the results. The analysis reveals that Kindia is the most affected region while presenting the highest flood risk. A Thesis submitted to the West African Science Service Center on Climate Change and Adapted Land Use and Université Joseph KI-ZERBO, Burkina Faso in partial fulfillment of the requirements for the Master of Science Degree in Informatics for Climate Change

Implementation of software for calculating the thermal balance of air conditioning systems in steady state

2025-07-21T00:00:00Z

Implementation of software for calculating the thermal balance of air conditioning systems in steady state Sawadogo, Wendwaogo Armel Régis Burkina Faso, like many developing tropical countries, is facing a growing demand for air conditioning due to rising temperatures linked to climate change, rapid urbanization, and improved living conditions. However, most actors in the building sector still rely on empirical methods for sizing air conditioning systems, which are often unsuitable for the local context and lead to significant errors. This thesis aims to design and validate a simple and accessible software tool for calculating the thermal balance of residential buildings, based on the IEPF method, to provide a scientific solution adapted to Burkina Faso’s climatic zones. Three cities representative of the country’s climatic zones were selected: Dori for the Sahelian zone, Ouagadougou for the Sudano-Sahelian zone, and Bobo for the Sudanian zone. The software was tested on a typical building located in Ouagadougou, under steady-state conditions at peak thermal loads (April month), with precisely defined climatic, material, occupancy, and orientation parameters. The results show excellent agreement between manual calculations performed according to the IEPF method and those provided by the application, with a relative error below 0.2%, confirming the software’s reliability. The tool stands out for its ease of use, user-friendly interface, and the precision of the detailed outputs (sensible and latent loads, required electrical power). However, its validity is limited to simple cases under steady-state conditions and strongly depends on the quality of input data. This work highlights the urgency of replacing empirical practices with validated and contextualized digital tools, to optimize air conditioning system design in tropical climates. A Thesis submitted to the West African Science Service Center on Climate Change and Adapted Land Use and Université Joseph KI-ZERBO, Burkina Faso in partial fulfillment of the requirements for the Master of Science Degree in Informatics for Climate Change

Assessing the Dynamics of Heatwaves over the Sahel Region of West Africa: Characterization and Projections

2025-07-21T00:00:00Z

Assessing the Dynamics of Heatwaves over the Sahel Region of West Africa: Characterization and Projections Oyeribhor, Susan Osaremeh This study investigates the historical trends and future projections of heatwaves over the Sahel region of West Africa, a climate-sensitive and socioeconomically vulnerable area. Utilizing ERA5 reanalysis data (1984–2014) and statistically downscaled outputs from 11 CMIP6 models under SSP2-4.5 and SSP5-8.5 scenarios, the study examines five heatwave metrics (frequency, number, duration, amplitude, and magnitude) across three heatwave definitions (TX90, TN90, EHF). The results confirm that the Sahel is experiencing intensifying heatwave events. Historically, daytime heatwaves (TX90) show higher frequencies (1.0–1.9 events/year), while nighttime heatwaves (TN90) reveal significant positive trends in frequency and duration, especially in the northern zones. The Excess Heat Factor (EHF) underscores the growing intensity and compound impact of heat extremes. Model validation using Taylor diagrams and Mann-Kendall trend tests confirms the robustness of projections despite biases among models. Future projections reveal alarming trends. By 2091, under SSP5-8.5, HWF could exceed 25 days/year, with amplitude values surpassing 50°C in parts of the central Sahel. These findings suggest a severe escalation in heat-related health risks, especially due to rising nighttime temperatures that limit physiological recovery. The study confirms the hypothesis that heatwaves in the Sahel are intensifying and are expected to worsen under future climate scenarios. This research provides vital input for developing region-specific early warning systems and adaptation plans. It highlights the urgency of strengthening climate resilience in the Sahel through enhanced forecasting, infrastructure planning, and health interventions. A Thesis submitted to the West African Science Service Center on Climate Change and Adapted Land Use and Université Joseph KI-ZERBO, Burkina Faso in partial fulfillment of the requirements for the Master of Science Degree in Informatics for Climate Change