Buildings are not only central to the day-to-day activities but also serve as critical indicators of urban development and transformation. The automatic extraction of building footprints from high-resolution Remote Sensing Imagery (RSI) has emerged as an important and popular tool in urban studies. It helps to enhance the understanding and management of urban sprawl, urban planning, population estimation, resource allocation, and post-disaster damage assessment. In this context, having an automated and robust building detection model is crucial. Deep Learning (DL) model and Object-Based Image Analysis (OBIA) techniques are the main and commonly used for automated building detection. This study investigates the efficacy of a pre-trained DL model and a rule-based model OBIA techniques in building detection across varied resolutions and geographic settings. Employing orthophotos from Luleå, Gävle, and Stockholm, the research assesses the adaptability and robustness of these methods under image properties and urban densities. The DL model was initially trained on 0.25m resolution data of Sweden by Lantmäteriet (Sweden mapping agency). The rule-based model was developed by applying OBIA techniques on behalf of this study. Models were analyzed through six feature agreement statistics including Critical Success Index (CSI), Precision, and Detection Probability (POD). The findings reveal that the DL model consistently outperformed the OBIA approach across all study areas, particularly at the original 25 cm resolution. Gävle showed superior precision with a CSI of 0.8139 for the DL model against a CSI of 0.7493 for OBIA at 25 cm.  The evaluation was improved by considering 50*50 sq. m subsets and building sizes. These evaluations highlight that building size and urban density significantly influence detection accuracy. Larger (> 2500 sq. m) buildings and less dense areas tend to yield higher accuracy across both detection methods. The DL model exhibited high CSI values for very large buildings (>5500 sq. m) in Gävle, surpassing 0.8, while the detection of very small (< 50 sq. m) buildings remained challenging for both methods. Overall, the pre-trained DL model is very sensitive to resolution changes compared to OBIA. Importantly, both give their best performance at the original resolution while DL is superior than OBIA. A rule-based OBIA model is affected by the geographical characteristics more heavily than a DL model. Both models have their best performance in the area with medium building density when medium to very large buildings exist. This study highlights how big the impact of building size, geographic characteristics, and image resolution on the performance of DL and OBIA techniques. However, further investigation is recommended to draw a strong conclusion regarding the impact of resolution on the model performance.

Runtom i Sverige och Europa skapar igenvuxna sjöar och vattendrag allt fler problem, vilket bland annat beror på klimatförändringar och mänsklig påverkan. En av de främsta anledningarna till igenväxning av sjöar och vattendrag är övergödning. Studiens syfte är att utvärdera om det är möjligt att på ett automatiskt sätt identifiera utbredning av vattenvegetation i sjöar och vattendrag med hjälp av fjärranalys och GIS. En analys av vegetationsförändringar i sjön Sottern i Uppland genomförs, där utbredd igenväxning skapar problem och där röjningsmaskiner används för att hantera vegetationen, som främst består av bladvass, näckrosor och annan flytande vatten-vegetation. Genom tillämpning av olika klassificeringsalgoritmer, bandkombinationer och vegetationsindex undersöks förändringar i sjöns tillstånd genom att klassa Sottern i två huvudklasser, vatten och vattenvegetation. Studien baseras på fjärranalysdata från den optiska satellitkonstellationen Sentinel-2 och en högupplöst referensbild från Google Earth Pro. Data samlades in under växtsäsongen, maj till oktober, för åren 2021 och 2022 för att analysera om och hur vattenvegetationen förändras över tid. Resultaten visar att Maximum Likelihood Classification (MLC) framträder som den mest effektiva algoritmen för att studera vegetationsförändringar, särskilt om den appliceras på en "False color" bandkombination bestående av banden 8 (NIR), 4 (rött) och 3 (grönt). MLC visar högre (94%) noggrannhet jämfört med Random Trees (RT) och Support Vector Machine (SVM). Genom att tillämpa vegetationsindexet NDVI (Normalized Difference Vegetation Index) ger studien en fördjupad förståelse för hur vegetationen förändras över tid. Genom att kombinera resultaten från dessa metoder går det att dra slutsatser om hur vattenvegetationen breder ut sig över tid i sjön Sottern, där en tydlig ökning av vattenvegetation sker mellan mitten av maj till mitten av juni, medan minskningen av vattenvegetationen inte är lika konsekvent. / In Europe, overgrown lakes and watercourses are creating increasing problems, which are partly due to climate change and human impact. One of the main reasons for the overgrowth of lakes and watercourses is eutrophication. The aim of the study is to evaluate the possibility of automatically identifying overgrown lakes and watercourses using remote sensing and GIS. An analysis of vegetation changes in Lake Sottern in Uppland county, Sweden is conducted, where overgrowth creates problems and where clearing machines are used to manage the vegetation, primarily consisting of reeds, water lilies, and other aquatic vegetation. By applying various classification algorithms, band combinations and vegetation indices, changes in the lake's condition are investigated by classifying Sottern into two main classes: water and aquatic vegetation. The study is based on remote sensing data from the optical satellite constellation Sentinel-2 and a high-resolution reference image from Google Earth Pro. Data were collected during the growing season, from May to October, for the years 2021 and 2022 to analyze if and how aquatic vegetation changes over time. The results show that Maximum Likelihood Classification (MLC) emerges as the most effective algorithm for identifying aquatic vegetation, especially when combined with a "False color" band combination consisting of bands 8 (NIR), 4 (red), and 3 (green). MLC shows higher accuracy compared to Random Trees (RT) and Support Vector Machine (SVM). By applying the Normalized Difference Vegetation Index (NDVI), the study provides a deeper understanding of how vegetation changes over time. By combining the results from these methods, it is possible to draw conclusions about how aquatic vegetation changes over time in lakes like Sottern, where a clear increase in aquatic vegetation occurs between May and June, while the decrease in aquatic vegetation is not as consistent.

Water quality monitoring is crucial globally due to the vital role of freshwater in providing drinking water, irrigation, and ecosystem services. Highly polluted water poses risks to both ecosystems and human health. Current water quality monitoring methods deployed in the field are often expensive, labor-intensive, and invasive. To overcome these issues, this degree project investigated the use of remote sensing to assess critical water quality parameters in the Swedish river Indalsälven. The research questions focus on determining the accuracy of predicting chemical oxygen demand (COD), river color, turbidity, and total phosphorus (TP) using satellite data and machine learning algorithms. The findings revealed that COD can be predicted with a cross-validated coefficient of determination (R²CV) of 0.7, indicating a robust predictive capability. The study suggests that while approximate quantitative prediction of COD in oligotrophic rivers is feasible using Sentinel-2 imagery, predictions for the other parameters remain challenging in the context of Indalsälven. Improvements in prediction accuracy were achieved through optimized band combinations, reduced datasets encompassing satellite data collected within two days of field measurements, and suitable pre-processing methods. / Airborne Monitoring of Water Quality in Remote Regions

Avalanche forecasters need precise knowledge about avalanche activity in large remote areas. Manual methods for gathering this data have scalability issues. Synthetic aperture radar satellites may provide much needed complementary data. This report describes Avanor, a system presenting change detection images of such satellite data in a web map client. Field validation suggests that the data in Avanor show at least 75 percent of the largest avalanches in Scandinavia with some small avalanches visible as well. / Lavinprognosmakare är i stort behov av detaljerad data gällande lavinaktivitet i stora och avlägsna områden. Manuella metoder för observation är svåra att skala upp, och rymdbaserad syntetisk aperturradar kan tillhandahålla ett välbehövt komplement till existerande datainsamling. Den här rapporten beskriver Avanor, en mjukvaruplattform som visualiserar förändringsbilder av sådan radardata i en webbkarta. Fältvalidering visar att datan som presenteras i Avanor kan synliggöra minst 75 procent av de största lavinerna i Skandinavien och även vissa mindre laviner.

It is well known that archaeological sites are important sources for understanding past human activity. However, those sites yet to be identified and further investigated are under a great risk of being lost or damaged before their archaeological significance is fully recognized. The aim of this research was to analyze the potential use of remote sensing and aerial archaeology techniques integrated within a geographic information system (GIS) for the purpose of remotely studying pit house archaeology. As pit house archaeological sites in North America have rarely been studied with a focus in remote sensing, this study intended to identify these features by processing very high resolution satellite imagery and assessing how accurately the identified features could be automatically mapped with the use of a GIS. A Worldview-2 satellite image of the Bridge River pit house village in Lillooet, south-central British Columbia, was processed within ArcGIS 10.1 (ESRI), ERDAS Imagine 2011 (Intergraph) and eCognition Developer 8 (Trimble) to identify spatial and spectral queues representing the pit house features. The study outlined three different feature extraction methods (GIS-based, pixel-based and object-based) and evaluated which method presented the best results. Though all three methods produced similar results, the potential for performing object-based feature extraction for research in aerial archaeology proved to be more advantageous than the other two extraction methods tested.

As we move towards a digital based society, technology continues to improve. It is important to take advantage of this to inform and facilitate our sustainable development goals in the most cost-effective and time efficient manner. By utilising the best available technologies, not only can time savings be achieved, but scope of works can be dramatically increased, particularly with ecological data collection. This study will focus on collecting ecological data (tree species) using developing modern technologies (satellites) with the aim of reaching classification accuracies comparable with ground truthed (real life) records. The study area is in central Burkina Faso approximately 30km south of the capital and is generally described as an agroforestry parklands area. The region suffers greatly from poverty and many people are heavily dependent on the agricultural sector and subsistence farming. As these agroforestry parklands are so critical to many people’s livelihoods, it is important to assess the natural resources available within them to provide the best food security management for the people. Tree species locations were overlayed on two satellite images acquired during different stages of the annual growing periods in the agroforestry parklands of the study area. From these images, segmentation of individual tree crowns was done manually and used as the reference data for an object-based classification model, which were assessed for the classification accuracies that can be achieved. Three satellite image scenarios were assessed for classification accuracy, including two single image scenarios and a multi-imagery dataset combining both images. Results indicate that combined images perform the best in terms of overall classification accuracies, closely followed by the end of the wet season growing period. The image acquisition from the end of the dry season was quite poor in comparison, having an overall classification accuracy more than 10% lower than the other scenarios. Of the focus species assessed in this study, Azadirachta Indica was the clear loser in terms of the number of correctly classified individuals from each model scenario. All other focus species were relatively well classified achieving close to or above 60% accuracies in the multi-imagery classification scenario.

The alkaline fen is a particularly valuable type of wetland with unique characteristics.Due to anthropogenic risk factors and the sensitive nature of the fens, protection is highlyprioritized with identification and mapping of current locations being important parts ofthis process. To accomplish this in a cost effective manner for large areas, remote sensingmethods using satellite images might be very effective. Following the rapid developmentin computer vision, deep learning using convolutional neural networks (CNN) is thecurrent state of the art for satellite image classification. Accordingly, this study evaluatesthe combination of different CNN architectures and multispectral Sentinel 2 satelliteimages for identification of alkaline fens using semantic segmentation. The implementedmodels are different variations of the proven U-net network design. In addition, a RandomForest classifier was trained for baseline comparison. The best result was produced bya spatial attention U-net with a IoU-score of 0.31 for the alkaline fen class and a meanIoU-score of 0.61. These findings suggest that identification of alkaline fens is possiblewith the current method even with a small dataset. However, an optimal solution tothis task may require deeper research. The results also further establish deep learningto be the superior choice over traditional machine learning algorithms for satellite imageclassification.

The thesis investigates above-ground biomass (AGB) with terrestrial laser scanning (TLS) for estimating AGB in a study area in Valls Hage, Gävle. The study used TLS for field measurements to collect highly detailed point clouds of two tree species for AGB estimation and comparison against validation data. TLS-derived data were validated using a non-destructive method involving direct field measurements using tape measures and a Trimble SX12 for extracting diameter at breast height (DBH), tree height, and crown diameter. Wood density was obtained from the literature. Data processing for segmentation, filtering, and generation of the quantitative structure model (QSM) was performed by using SimpleForest tool in Computree software. A statistical analysis was performed using linear regression, and AGB was estimated using QSM-derived volume multiplied by wood density. The finding in the results for the comparison of AGB estimation between TLS QSM and field validation from DBH-based tree-specific allometric equation had an RMSE of 154 kg, with a near-perfect agreement of 0.997 %, and RMSE of 189 kg, with the agreement of 0.990% for TLS QSM and TLS validation DBH-based tree specific equation. The comparison between TLS-derived DBH and field validation was accurate, leaving with insignificant differences, while the tree height had noticeable differences, and crown diameter had relatively low differences. The challenges during data processing were highlighted and the importance of TLS data for accurate AGB estimation, with the potential for refinement and integrating internal tree structure information to improve allometric models for future studies.

The unprecedented growth of urban areas all over the globe is nowadays maybe most apparent in China having undergone rapid urbanization since the late 1970s. The need for new residential, commercial and industrial areas leads to new urban regions challenging sustainable development and the maintenance and creation of a high living standard as well as the preservation of ecological functionality. Therefore, timely and reliable information on land-cover changes and their consequent environmental impacts are needed to support sustainable urban development.The objective of this research is the analysis of land-cover changes, especially the development of urban areas in terms of speed, magnitude and resulting implications for the natural and rural environment using satellite imagery and the quantification of environmental impacts with the concepts of ecosystem services and landscape metrics. The study areas are the cities of Shanghai and Stockholm and the three highly-urbanized Chinese regions Jing-Jin-Ji, the Yangtze River Delta and the Pearl River Delta. The analyses are based on classification of optical satellite imagery (Landsat TM/ETM+ and HJ-1A/B) over the past two decades. The images were first co-registered and mosaicked, whereupon GLCM texture features were generated and tasseled cap transformations performed to improve class separabilities. The mosaics were classified with a pixel-based SVM and a random forest decision tree ensemble classifier. Based on the classification results, two urbanization indices were derived that indicate both the absolute amount of urban land and the speed of urban development. The spatial composition and configuration of the landscape was analysed by landscape metrics. Environmental impacts were quantified by attributing ecosystem service values to the classifications and the observation of value changes over time. ivThe results from the comparative study between Shanghai and Stockholm show a decrease in all natural land-cover classes and agricultural areas, whereas urban areas increased by approximately 120% in Shanghai, nearly ten times as much as in Stockholm where no significant land-cover changes other than a 12% urban expansion could be observed. From the landscape metrics analysis results, it appears that fragmentation in both study regions occurred mainly due to the growth of high density built-up areas in previously more natural environments, while the expansion of low density built-up areas was for the most part in conjunction with pre-existing patches. Urban growth resulted in ecosystem service value losses of ca. 445 million US dollars in Shanghai, mostly due to a decrease in natural coastal wetlands. In Stockholm, a 4 million US dollar increase in ecosystem service values could be observed that can be explained by the maintenance and development of urban green spaces. Total urban growth in Shanghai was 1,768 km2 compared to 100 km2 in Stockholm. Regarding the comparative study of urbanization in the three Chinese regions, a total increase in urban land of about 28,000 km2 could be detected with a simultaneous decrease in ecosystem service values corresponding to ca. 18.5 billion Chinese Yuan Renminbi. The speed and relative urban growth in Jing-Jin-Ji was highest, followed by the Yangtze River Delta and the Pearl River Delta. The increase in urban land occurred predominately at the expense of cropland. Wetlands decreased due to land reclamation in all study areas. An increase in landscape complexity in terms of land-cover composition and configuration could be detected. Urban growth in Jing-Jin-Ji contributed most to the decrease in ecosystem service values, closely followed by the Yangtze River Delta and the Pearl River Delta. / <p>QC 20130610</p>

Remote Sensing (RS) technology provides valuable information about Earth by enabling an overview of the planet from above, making it a much-needed resource for many applications. Given the abundance of RS data and continued urbanisation, there is a need for efficient approaches to leverage RS data and its unique characteristics for the assessment and management of urban areas. Consequently, employing Deep Learning (DL) for RS applications has attracted much attention over the past few years. In this thesis, novel datasets consisting of satellite RS images over urban areas in Sweden were compiled from Sentinel-2 multispectral, Sentinel-1 Synthetic Aperture Radar (SAR) and Urban Atlas 2018 Land Use/Land Cover (LULC) data. Then, DL was applied for multiband and multiclass semantic image segmentation of LULC. The contributions of complementary spectral, temporal and SAR data and spectral indices to LULC classification performance compared to using only Sentinel-2 data with red, green and blue spectral bands were investigated by implementing DL models based on the fully convolutional network-based architecture, U-Net, and performing data fusion. Promising results were achieved with 25 possible LULC classes. Furthermore, almost all DL models at an overall model level and all DL models at an individual class level for most LULC classes benefited from complementary satellite RS data with varying degrees of classification improvement. Additionally, practical knowledge and insights were gained from evaluating the results and are presented regarding satellite RS data characteristics and semantic segmentation of LULC in urban areas. The obtained results are helpful for practitioners and researchers applying or intending to apply DL for semantic segmentation of LULC in general and specifically in Swedish urban environments.