• Rural Digital Europe
• Research data close
• Other research products close
• ZA close

Data accompanying the paper: L.M. Vermeulen, B. Verbist, K. Van Meerbeek, J. Slingsby, P.N. Bernardino, B. Somers. 2024. Wetness severity increases abrupt shifts in ecosystem functioning in arid savannas.

Digital Transformation, Media and Social Inequalities Bucharest, Romania, 25-26 January 2024 Call for papers Recent technological developments and transformations in media and communication require a global reflection on their effects and outcomes on society, democracy and business. The platformisation process with its institutional dimensions: data infrastructures, markets and governance (Poell, Nieborg & van Dijck, 2019) led to new business models and relationships between social, market and political actors. Journalism as an institution has been under question for over a decade or even two (Deuze, 2020) as the news industry is declining. Journalism as a profession strives to retain or regain the people’s trust. With its recent advances artificial intelligence is seen as a threat or a chance for humanity. The AI’s impact on the media and communication sector is open for debate. Is it a threat or an asset for professional practice? At the same time, the hybridisation of communication professions – roughly defined as a mixture of journalistic and public relations and advertising&marketing practices in the digital context – adds new challenges in maintaining a fair and democratic public sphere and ensuring equal access to quality information. Our focus is to foster an open academic debate on broad themes related to the outcomes of digital transformation in contemporary media and communication. We encourage contributions that adhere to the critical sociology perspective.

The models weights shared here corresponds to the research detailed in the article Kleebauer, M.; Marz, C.; Reudenbach, C.; Braun, M. Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning. Remote Sens. 2023, 15, 5687. The following abstract briefly describes the article: In the realm of solar photovoltaic system image segmentation, existing deep learning networks focus almost exclusively on single image sources both in terms of sensors used and image resolution. This often prevents the wide deployment of such networks. Our research introduces a novel approach to train a network on a diverse range of image data, spanning UAV, aerial, and satellite imagery at both native and aggregated resolutions of 0.1 m, 0.2 m, 0.3 m, 0.8 m, 1.6 m, and 3.2 m. Using extensive hyperparameter tuning, we first determined the best possible parameter combinations for the network based on the DeepLabV3 ResNet101 architecture. We then trained a model using the wide range of different image sources. The final network offers several advantages. It outperforms networks trained with single image sources in multiple test applications as measured by the F1-Score (95.27%) and IoU (91.04%). The network is also able to work with a variety of target imagery due to the fact that a diverse range of image data was used to train it. The model is made freely available for further applications. The model is a DeepLabV3 ResNet101 model with approx. 61 million model parameters and 258.7 GFLOPS. Trained with Python 3.10, Torch 1.14.0, and Torchvision 0.15.0, the configurations of the final model are summarized below. BCE loss was used as the loss function, Adam as the optimizer, 0.0001 as the learning rate, a batch size of 8, 100 epochs, and a stride of 2. The ASSP segmentation head was set to 2048 input channels and 12, 24, and 36 dilation rates. A test application can be found on Google Colab. Further details on the model, training and validation can be found in the Article and on Github. 

Presentation materials from a LIASA (Library and Information Association of South Africa) - HELIG (Higher Education Libraries Interest Group) webinar on digital transformation in the academic library profession, Friday, 6 May, 13h00 - 14h00. The effect of technology on libraries has enabled them to transform and adapt to the e-space, thereby undergoing digital transformation. The Covid-19 pandemic expedited this and necessitated more library materials moving to electronic formats to remain accessible and (re-)usable. Digitisation improves access to information and availability in support of virtual offerings. It is indeed fundamental that digital library resources are appropriately preserved in times of risk, such as the recent fire at UCT and floods in KZN.

Presentation slides for an invited talk at the monthly meeting of the UNISA Library and Information Services Data Champions. Topic: the UCT Data Stewards and Champions community of practice, convened by Digital Library Services. 13th August 2021, 14:30 - 15:30 on MS Teams.

This video focuses on the theme of agriculture. We show that as the popuplation increases the demand fr food also increases, providing a big opportunity for investment. We also highlight that the smallholder frming households, estimated to be 450 million comprise of a large ortion that lives on less than $2 a day. whe show that this is an opportunity for private investment to improve livelihoods. This is video 8/11 in week 1 of the Innovative Finance: Hacking Finance to change the World course.

Presentation given on World Digital Preservation Day 2019, 7th Nov 2019, 13:00 - 14:00, in the Kirby Collection room at the South African College of Music, University of Cape Town.A brief overview to share some of our experiences, activities and challenges around digital preservation at the University of Cape Town. Presently, expertise in digital preservation is growing only slowly in South Africa: relevant training opportunities remain rare because many institutions have yet to recognise the fundamental issues, and get started with sustainably resourcing solutions. While some of our needs may be about driving appropriately funded and structured projects forward, even more important to our capacity-building efforts will be to convene a local digital preservation community of practise that is vitally connected to global exchange of ways of knowing and describing the world.

Screencasts of 6 participants navigating and exploring a digital museum. Participants engaged with a digital platform before interviews took place. Research for a dissertation submitted in partial fulfillment of an MPhil specialising in Digital Curation at the University of Cape Town. Title of the dissertation: Perceptions and experiences of selected participants engaging with a digitally curated environmental Outsider Art collection.

Transcripts of interviews with six voluntary participants for the dissertation submitted in partial fulfillment of an MPhil specialising in Digital Curation at the University of Cape Town. Title of the dissertation: Perceptions and experiences of selected participants engaging with a digitally curated environmental Outsider Art collection.

Interviews with six voluntary participants for the dissertation submitted in partial fulfillment of an MPhil specialising in Digital Curation at the University of Cape Town. Title of the dissertation: Perceptions and experiences of selected participants engaging with a digitally curated environmental Outsider Art collection. The participants signed consent forms, but their identities are confidential.