Plastic debris in aquatic environments has become an increasing concern for wildlife and human health. Rivers and canals serve as major sources of plastic transport to the oceans, yet global estimates of plastic flux remain highly uncertain, partly due to non-uniform and sparse field measurements. This poses a significant challenge for effective mitigation strategies, as the contribution of individual streams can vary by multiple orders of magnitude.

This thesis develops and tests deep-learning models that use images from fixed cameras to detect and classify floating litter based on material types. Following these detections, a conversion into a mass estimate is made based on the size of the litter object. A combination of real-world datasets and syn- thetically generated images was used to train a YOLOv11 architecture for a single-class task and two multi-class setups. The performance and generalization capability was evaluated on in-domain test sets and out-of-domain locations, while mass estimates were validated against physical sampled litter at two locations.

The results indicate robust performance for single-class models, while the introduction of material classes caused a performance decrease of 12% in mAP@50-95, due to the visual ambiguity of heterogeneous plastic types. The integration of synthetic data improved generalization to unseen locations through higher recall, albeit at the cost of higher false positive rates. Field validation showed that mass estimates based on traditional methods, such as human visual counting, can cause an uncertainty of up to an order of magnitude. Object detection models tended to underestimate the total mass due to heavy outliers in the ground-truth and a detection bias towards plastic categories. However, the estimate at the urban site was within 20% of the recovered plastic load. Overall, results indicate that deep learning can provide conservative and reviewable estimates of plastic mass flux from camera data. Detailed material classification is feasible for visually distinct categories, but remains data-limited for more heterogeneous materials. ... Read more

This research explores the feasibility of implementing ceramic microfiltration (CMF) treatment in Maputo, Mozambique, to reclaim wastewater for industrial reuse, addressing the city's pressing water scarcity challenges. As rapid urbanization increases Maputo's reliance on potable water for industrial and agricultural needs, this study evaluates reclaimed wastewater as a sustainable alternative to alleviate demand on the city's limited freshwater resources. Using a CMF pilot plant, the project tested wastewater from the recently upgraded Infulene Wastewater Treatment Plant (WWTP) to assess whether CMF treatment could achieve quality standards suitable for applications such as cooling, concrete production, car washes, agricultural irrigation, and municipal park irrigation. Furthermore, the opportunity of scalability was tested through a water balance, while relevant stakeholders were interviewed and costs estimated to complete the feasibility assessment.

Laboratory results indicated that CMF treatment effectively reduces turbidity, chemical oxygen demand (COD), and biological pollutants like E. coli and coliforms. However, dissolved particles and heavy metals were not removed, limiting its efficacy for high-specification uses. While the treated effluent met quality standards for lower-specification applications, such as local car washes and park irrigation, it did not reach the stricter requirements needed for cooling water or concrete production. This underscores a need for process optimization, particularly through coagulation, to expand CMF's application range.

To assess sustainable water availability, a water balance analysis of the Infulene WWTP considered seasonal flows and local agricultural demands. The findings suggest that although the current water supply is insufficient during dry months, full capacity utilization and improved sewer network connections in the future could support CMF-based water reuse consistently across seasons, with potential scalability for additional users.

Economic analysis compared CMF's capital and operational costs with revenue from reclaimed water sales, showing that while considerable initial investment is required, direct piping could potentially make CMF-treated water competitively priced against potable supplies under the condition of reaching maximum treatment capacity at a scaled up CMF plant. High costs associated with truck-based delivery, however, present a barrier to adoption for potential users. Stakeholder interest was strong across industrial users and developers, though contingent on achieving cost parity with the existing water network.

This study concludes that, while integrating CMF technology into Maputo's water management strategy offers promise, challenges remain in achieving quality standards for certain industrial applications and in lowering costs. Addressing these technical and economic barriers could open avenues for CMF's broader adoption, especially with future assessments that include alternative suppliers and configurations. ... Read more