Background: A pre-conference workshop that investigated the experiences and needs of PhD candidates and early career researchers in disability studies in Africa was held as part of the proceedings of the African Network for Evidence to Action in Disability (AfriNEAD) 7th Conference in November 2023. Objectives: To determine how the existing structures in AfriINEAD can be leveraged to support emerging African disability researchers. This article documents this event and summarises the key findings from the discussions that took place. Method: The workshop included presentations from leading scholars in health professions education, panel discussions with PhD candidates and early career researchers, and small group discussions on what is needed to support emerging researchers. Results: Disability studies was positioned by participants as not only an academic exercise but also a deeply personal pursuit, requiring introspection and conscientisation, with which they felt they needed support. There are also specific ethical concerns related to doing research work with persons with disabilities, which need to be prioritised in postgraduate education in disability studies. The needs identified by participants are summarised as: (1) mentorship, (2) networking, and (3) funding. Conclusion: We suggest that the development of African disability scholars and scholarship requires an African ethical approach, which prioritises humanity, community and reciprocity. Contribution: African disability studies scholars are well-placed to disrupt ableism in academic, medical and social spheres, as well as hierarchies within academia, which limit development, mutual growth and respect.

Uncrewed Aerial Vehicles (UAVs) have emerged as a promising tool for complementing terrestrial surveys, offering unique advantages for forest health monitoring (FHM). UAVs have the potential to improve or even replace core tasks such as crown condition assessment, bridging the gap between ground-based surveys and traditional remote sensing platforms. However, present approaches have not yet fully exploited the very high temporal resolution and flexible and convenient utilization that UAVs offer even under cloudy skies. In this paper, we provide a standardized data pipeline to semi-automatically generate reference data and for monitoring forest health by merging ground-based and UAV-based data related to species-specific forest health. Furthermore, we investigated the potential of Convolutional Neural Networks (CNNs) to classify the main tree species and their crown conditions based on the reference data. Therefore, we acquired high resolution multispectral drone imagery of 235 different ICP large scale forest monitoring plots (Level-I plots) distributed across Bavaria for three consecutive years (2020–2022). Using this highly heterogeneous time-series dataset, encompassing diverse weather and lighting conditions, forest stand characteristics, and spatial distribution of study areas, we successfully classified five tree species, three genus level classes and dead trees, including the health status of the main tree species occurring in Germany. This way we managed to classify 14 distinct classes with an average macro F1-score of 0.61 using the EfficientNet CNN architecture. The highest class-specific F1-score apart from the class of dead trees (0.97) was achieved by the class of Picea abies healthy (0.80). If participating countries of the ICP Forests program adopt our approach to harmonize terrestrial and UAV-based monitoring, many ground-based tasks could be reduced or replaced, leading to significant time and cost savings. We provide standardized and open-source monitoring and analysis strategies that can be potentially extended throughout Europe. Our findings demonstrate that UAV monitoring and deep learning can modernize forest management for efficiency and sustainability. We recommend integrating drones with ground surveys in forest monitoring systems to take advantage of their benefits.

Accurately and automatically estimating vineyard yield is a significant challenge. This study focuses on grape bunch counting in commercial vineyards using advanced deep learning techniques and object detection algorithms. The aim is to overcome the limitations of conventional yield estimation techniques, which are labour intensive, costly, and often inaccurate due to the spatial and temporal variability of the vineyard. This research proposes a non-invasive methodology for identifying grape bunches under different occlusion conditions using RGB cameras and deep learning models. The methodology is based on the collection of RGB images captured under field conditions, coupled with the implementation of the YOLOv4 architecture for data processing and analysis. Statistical indicators were used to evaluate the performance of the developed models. The comprehensive model produced a favourable outcome during validation, with an error rate of 1.12 bunches (R2 = 0.83). In the test dataset, the model achieved an error rate of 1.12 (R2 = 0.81). The results highlight the potential of emerging technologies to significantly improve vineyard yield estimation. This approach has the potential to assist vineyard management practices, enabling more informed and efficient decisions that could increase both the quantity and quality of grape production intended for winemaking.

Carbon stocks and flows in forest ecosystems play an important role in the context of climate change mitigation. Different aspects of the forest carbon balance, however, are often treated independently, leading to a fragmented, disciplinary knowledge. With the R-package care4cmodel we want to support a consolidated view of forest growth and forest operations with respect to carbon flows. The software is, in essence, a pragmatic simulation tool that allows juxtaposing the CO2 uptake due to wood increment and the CO2 emissions due to forest operations for given silvicultural concepts in an arbitrary area, over time. At the core, the approach is a dynamic forest area model where forest development stages are represented in a cyclical sequence, which can be broken by disturbances. The model scales up growth and yield information given per forest development stage and unit area to the dynamically simulated development stage areas. This allows to quantify the total forest area's CO2 uptake, and to estimate the CO2 emissions caused by forest operations. The forest operations in our implementation include the maintenance of the forest road network, felling trees, debranching and bucking the stems, and extracting the timber to a landing at a forest road. The transport from there to the industry is beyond the system boundary. For the CO2 uptake of the forest system, the current model version focuses on the wood increment only. We use a practical example to demonstrate the basic features of the model and its plausible behaviour. Beyond the current focus of the model, we see a broad field of applications as a generic meta model, especially in the context of ecosystem service provision.

An improved solution methodology is proposed in this paper for the urban transit routing problem (UTRP). This methodology includes a procedure for the generation of improved initial solutions as well as improved metaheuristic search approaches, involving the use of hyperheuristics to manage search operators in both trajectory-based and population-based metaheuristics. The UTRP variant considered in this paper is that of deciding upon efficient bus transit routes. The design criteria embedded in our UTRP model are the simultaneous minimisation of the expected average passenger travel time and minimisation of the system operator's cost (measuring the latter as the sum total of all route lengths in the system). The model takes as input an origin–destination demand matrix for a pre-specified set of bus stops, along with an underlying road network structure, and returns as output a set of bus route trade-off solutions. The decision maker can then select one of these route sets subjectively, based on the desired degree of trade-off between the aforementioned transit system design criteria. This bi-objective minimisation problem is solved approximately in three distinct stages — a solution initialisation stage, an intermediate analysis stage, and an iterative metaheuristic search stage during which high-quality trade-off solutions are sought. A novel procedure is introduced for the solution initialisation stage, aimed at effectively generating high-quality initial feasible solutions. Two metaheuristics are implemented to solve instances of the problem, namely a dominance-based multi-objective simulated annealing algorithm and an improved non-dominated sorting genetic algorithm, each equipped with a hyperheuristic capable of managing the perturbation operators employed. Various novel operators are proposed for these metaheuristics, of which the most noteworthy take into account the demand of passengers.