• Digital Humanities and Cultural Heritage
• Publicationsclose
• Open Access close
• SE close
• Publikationer från KTH close
• Digital Humanities and Cultural Heritage close

Part of book: ISBN 978-1-009-10023-6QC 20221219

Extractivism has been predominant in the Arctic since whaling and sealing campaigns began in the sixteenth century, followed by mining and drilling for oil and gas. In this chapter we present some of the main features of this ‘extractivist history’ of the circumpolar region. We organize this development along a set of themes. First, we explore the extractive frame of mind in Western thought and how it has continued to shape visions of the region. Second, we explore the material and social impacts of historical extractivism. Third, we use the theoretical lens of colonialism and decolonialism to understand the social and political relations, especially with aboriginal populations. Fourth, we examine the, often fraught, recent and contemporary debates around contemporary and future extractivism and its implications for the Arctic. The historical overview serves the purpose of providing a legible pattern from what is also a range of diverse and rich variations. A key finding is that extractivism is a lasting legacy and a path dependency of the region. At the same time resource extraction has many problematic sides that the seeking of new Arctic futures will have to deal with. QC 20221215Chapter in book: ISBN 978-1-009-10023-6

Part of book: ISBN 978-1-009-10023-6QC 20221219

This chapter explores knowledge associated with the humanities that hasbeen developed in practice-oriented research domains of the Swedishgovernment to help solve societal challenges. I study the Swedish NationalDefense Research Establishment [Försvarets forskningsanstalt] (FOA). Theconcept of “borderline humanities” refers to research activities that didnot abide by academic distinctions between the humanities, the socialsciences, and the natural sciences. The study shows how knowledge onhuman culture, history, language, and beliefs developed in a researchenvironment that drew on diverse fields of both research and practice.The chapter brings to the fore shared themes and concepts betweendifferent research fields and draws attention to how this affects the viewof research impact. Part of book: ISBN 978-90-485-5502-4QC 20220815

QC 20221011 ERC StG 716211

This article discusses David Lowenthal's last book, Quest for the Unity of Knowledge, which was published posthumously by Routledge in 2019 (available in print from November 2018). The book is based on a series of lectures that he gave while a visiting fellow with the KTH Royal Institute of Technology’s Environmental Humanities Laboratory in Stockholm in 2012. Aimed at a general academic audience, it is an erudite and passionate overview showing how ingrained bias towards unity or diversity shapes major issues in education, religion, genetics, race relations, heritage governance, and environmental policy. Quest for the Unity of Knowledge explores the Two Cultures debate, initiated by C.P. Snow, concerning the gulf between the sciences and the humanities. It covers areas such as conservation, ecology, history of ideas, museology, landscape, and heritage studies, aligning with Lowenthal's career-long research interests, and serving as well as a meta-comment to the emerging Environmental Humanities. QC 20220412

In the late twentieth century, as the United Nations struggled to come up with a new legal system for the oceans, one woman saw the opportunity to promote radical new ideas of justice and internationalism. Ocean governance expert Elisabeth Mann Borgese (1918–2002) spent decades working with the United Nations Law of the Sea Convention. Throughout this sprawling series of global conferences, she navigated allegiances and enmities, intrigues and setbacks, fighting determinedly to develop a just ocean order. Featuring extensive research and new interviews with Mann Borgese’s colleagues and family, this book explores timeless questions of justice and international collaboration and asks whether the extraordinary drive and vision of a single person can influence the course of international law. QC 20220412

The use of Deep Learning methods for Document Understanding has been embraced by the research community in recent years. A requirement for Deep Learning methods and especially Transformer Networks, is access to large datasets. The objective of this thesis was to evaluate a state-of-the-art model for Document Layout Analysis on a public and custom dataset. Additionally, the objective was to build a pipeline for building a dataset specifically for Visually Rich Documents. The research methodology consisted of a literature study to find the state-of-the-art model for Document Layout Analysis and a relevant dataset used to evaluate the chosen model. The literature study also included research on how existing datasets in the domain were collected and processed. Finally, an evaluation framework was created. The evaluation showed that the chosen multi-modal transformer network, LayoutLMv2, performed well on the Docbank dataset. The custom build dataset was limited by class imbalance, although good performance for the larger classes. The annotator tool and its auto-tagging feature performed well and the proposed pipelined showed great promise for creating datasets with Visually Rich Documents. In conclusion, this thesis project answers the research questions and suggests two main opportunities. The first is to encourage others to build datasets with Visually Rich Documents using a similar pipeline to the one presented in this paper. The second is to evaluate the possibility of creating the visual token information for LayoutLMv2 as part of the transformer network rather than using a separate CNN. Användningen av Deep Learning-metoder för dokumentförståelse har anammats av forskarvärlden de senaste åren. Ett krav för Deep Learning-metoder och speciellt Transformer Networks är tillgång till stora datamängder. Syftet med denna avhandling var att utvärdera en state-of-the-art modell för analys av dokumentlayout på en offentligt tillgängligt dataset. Dessutom var målet att bygga en pipeline för att bygga en dataset specifikt för Visuallt Rika Dokument. Forskningsmetodiken bestod av en litteraturstudie för att hitta modellen för Document Layout Analys och ett relevant dataset som användes för att utvärdera den valda modellen. Litteraturstudien omfattade också forskning om hur befintliga dataset i domänen samlades in och bearbetades. Slutligen skapades en utvärderingsram. Utvärderingen visade att det valda multimodala transformatornätverket, LayoutLMv2, fungerade bra på Docbank-datasetet. Den skapade datasetet begränsades av klassobalans även om bra prestanda för de större klasserna erhölls. Annotatorverktyget och dess autotaggningsfunktion fungerade bra och den föreslagna pipelinen visade sig vara mycket lovande för att skapa dataset med VVisuallt Rika Dokument.svis besvarar detta examensarbete forskningsfrågorna och föreslår två huvudsakliga möjligheter. Den första är att uppmuntra andra att bygga datauppsättningar med Visuallt Rika Dokument med en liknande pipeline som den som presenteras i denna uppsats. Det andra är att utvärdera möjligheten att skapa den visuella tokeninformationen för LayoutLMv2 som en del av transformatornätverket snarare än att använda en separat CNN.

Podcasts are an exponentially growing audio medium where useful and relevant content should be served, which requires new methods of information sorting. This thesis is the first to look into the state-of-art problem of segmenting podcasts into chapters (structurally and topically coherent sections). Podcast segmentation is a more difficult problem than segmenting structured text due to spontaneous speech and transcription errors from automatic speech recognition systems. This thesis used author-provided timestamps from podcast descriptions as labels to perform supervised learning. Binary classification is performed on sentences from podcast transcripts. A general framework is delivered for creating a dataset with 21 436 podcast episodes, training a supervised model, and for evaluation. The framework managed to address technical challenges such as a high data imbalance (there are few chapter transitions per episode), and finding an appropriate context size (how many sentences are shown to the model during inference). The proposed model outperformed a baseline model in quantitative metrics and in a human evaluation with 100 transitions. The solution provided in this thesis can be used to chapterize podcasts, which has many downstream applications, such as segment sorting, summarization, and information retrieval. Podcasts är ett exponentiellt växande ljudmedium där användbart och relevant innehåll är viktigt, vilket kräver nya metoder för sortering av information. Detta examensarbete är det första projektet som antar utmaningen att segmentera podcasts in i kapitel (strukturellt och tematiskt sammanhängande avsnitt). Podcastsegmentering är ett svårare problem än att segmentera strukturerad text på grund av spontant tal och fel i transkriberingssystem. Detta projekt använde kapiteltider från podcastbeskrivningar som signaler för att kunna göra supervised learning. Binär klassificering görs på meningar från podcast-transkript. Denna uppsats levererar ett ramverk för att skapa ett dataset med 21 436 podcasts, träna en supervised maskininlärningsmodell samt för utvärdering. Ramverket lyckades lösa tekniska utmaningar såsom obalanserad data (det är få kapitelövergångar i varje podcast) och att hitta en rimlig kontextstorlek (hur många meningar som modellen ser för varje inferens). Den tränade modellen var bättre än en slumpmässig referensmodell i både kvantitativa mätningar samt i en mänsklig utvärdering för 100 kapitelövergångar. Slutligen, detta examensarbete har resulterat i en lösning som kan kapitelindela podcasts, vilket har många applikationer såsom sortering av segment, summering, och informationssökning.

The agricultural sector is the main contributor for the warming from non-CO2 gases, especially methane and nitrous oxide. Existing measures to mitigate these emissions can only reduce but not eliminate these emissions. Owing to the diffused nature of these emissions, it is hard to design a single point measure to address the emissions from the agricultural sector. In our work, we present the first-of-a-kind direct air capture-based process to mitigate these diverse emissions. The process is designed based on thermal catalytic route for the methane conversion, which is coupled to a direct air capture unit for CO2 capture. The process was modelled based on steady state assumptions to estimate the energy requirement per tonne of CO2 equivalent mitigated. Energy estimations were later compared for the two methane removal systems with and without CO2 capture unit. The energy demand per tonne CO2-equivalent removed from the system without CO2 capture unit (only CH4 removal) was found to be 16.54 GJ. For the methane removal system with CO2 capture unit (co-removal of CO2 and CH4), the energy demand is 15.42 GJ per tonne-CO2 equivalent. QC 20230120