Cloud detection on satellite imagery is an essential pre-processing step for several remote sensing applications. In general, machine learning based methods for cloud detection perform well, especially the ones based on deep learning as they consider both spatial and spectral features of the input image. However, false alarms become a major issue in winter images, wherein bright objects like snow/ice are also detected as cloud. This affects further image analysis like urban change detection, weather forecast, disaster risk management. In this thesis, we consider optical remote sensing images from small satellites constellation of PlanetScope. These have limited multispectral capacity of four bands: Red, Green, Blue (RGB) and Near-Infrared (NIR) bands. Detection algorithms tend to be more efficient when considering information from more than one spectral band to perform the detection. This study explores the data diversity provided by NIR band to RGB band images in terms of improvement in cloud detection accuracy. Two deep learning algorithms based on convolutional neural networks with different architectures are trained on RGB, NIR and RGB+NIR image data, resulting in six trained models. Each of these networks is tested with winter images of varying amounts of clouds and land covered with snow and ice. The evaluation is done based on performance metrics for accuracy and Intersection-over-Union (IoU) scores, as well as visual inspection. A total of eighteen experiments are performed, and it is observed that NIR band provides significant data diversity when combined with RGB bands, by reducing the false alarms and improving the accuracy. In terms of processing time, there is no significant increase for the algorithms evaluated, therefore better cloud detection can be achieved without significantly increasing the computational costs. Based on this analysis, Unibap iX10-100 embedded system is a possible choice for implementing these algorithms as it is suitable for AI applications. / Detektering av moln på satellitbilder är ett viktigt bearbetningssteg för flera fjärr analysapplikationer. I allmänhet fungerar maskininlärningsbaserade metoder för molndetektering bra, särskilt de som är baserade på djupinlärning eftersom de tar hänsyn till både spatiala och spektrala egenskaper i input bilder. Men falsklarm blir ett stort problem i vinterbilder, där medbringande föremål som snö/is också upptäcks som moln. Detta påverkar ytterligare bildanalyser som upptäckt av stadsförändringar, väderprognos, katastrofrisk-hantering. I denna avhandling tar vi hänsyn till optiska fjärranalysbilder från små satellitkonstellationer PlanetScope. Dessa har begränsad multispektral kapacitet på fyra band: röda, gröna, blå (RGB) och near-infrared (NIR) band. Detektionsalgoritmer tenderar att vara mer effektiva när man överväger information från mer än ett spektralband för att utföra detekteringen. Denna studie utforskar datadiversiteten som tillhandahålls av NIR-band till RGB-bandbilder när det gäller förbättring av molndetekteringsnoggrannheten. Två djupinlärningsalgoritmer baserade på konvolutionella neurala nätverk med olika arkitekturer tränas på RGB-, NIR- och RGB+NIR-bilddata, vilket resulterar i sex tränade modeller. Vart och ett av dessa nätverk testas med vinterbilder av varierande mängder moln och land täckt med snö och is. Utvärderingen görs baserat på prestandamått för noggrannhet och Intersection-over-Union (IoU) poäng, samt visuell inspektion. Totalt arton experiment utförs, och det observeras att NIR-bandet ger betydande datadiversitet när det kombineras med RGB-band, genom att minska de falska larmen och förbättra noggrannheten. När det gäller bearbetningstid finns det ingen signifikant ökning av den för de utvärderade algoritmerna, därför kan bättre molndetektering uppnås utan att nämnvärt öka beräkningskostnaderna. Baserat på denna analys är Unibap iX10-100 inbyggt system ett möjligt val för implementera dessa algoritmer eftersom det är lämpligt för AI-tillämpningar.

This thesis is the product of the author’s personal experience as a gay person working in the humanitarian sector who has experience of the challenges faced in countries of conflict and in countries where the rights of LGBTQ people are not assured. LGBTQ people have specific needs that are documented through research, highlighting the risks they face while working in high risk locations. With such limitations in the way that LGBTQ people are supported in the field, or in their home nations, with particular relevance to religiously supported heteronormativity which is relevent especially given the particular needs and concerns that LGBTQ people face in everyday life, these issues are exacerbated in conflict or hazardous settings. To establish the experiences of LGBTQ people, semi structured qualitative interviews have been used to illicit nuanced details from differing LGBTQ perspectives to provide some supportive insight into the conditions that individuals work in. These interviews were triangulated against the current data that exists, and an online quantitative and qualitative survey which investigated in more specificity the experiences of LGBTQ people and what support mechanisms would benefit them. Motivations, experience, health implications and support to LGBT staff are discussed from the point of view of LGBTQ staff, represented as much as possible by individuals of varying gender, sexual orientation, and race. The findings are used to provide recommendations for what agencies can do to provide a level of support to their own LGBTQ staff, a concept for which there are still significant gaps in literature, data, and practice.