Change search
Refine search result
1 - 24 of 24
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Aminjafari, Saeid
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Monitoring Water Availability in Northern Inland Waters from Space2023Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    River deltas and lakes support biodiversity and offer crucial ecosystem services such as freshwater provision, flood control, and fishing. However, climate change and human activities have affected deltas and lakes globally, altering the services they provide. Since delta and lake surface water occurrence and water levels respond to climate change and anthropogenic activities, we need to monitor their variations to understand the potential drivers for effective water management strategies. However, important deltas like the Selenga River Delta (SRD) in Russia lack a detailed analysis of water occurrence. Regarding lake water level, there has been a decline in the number of gauging stations globally, due to installation and maintenance costs. For example, Sweden has ~100,000 lakes which are sources of freshwater and hydro-power, but only 38 lakes have long and continuous in-situ records of water level.

    As satellite data are reliable alternatives for conventional methods to monitor deltas and lakes, I employed Earth Observations (EO) to quantify changes in surface water occurrence in the SRD and water levels in Swedish lakes and identify their main drivers. I also developed and explored a novel methodology for lake water level estimation based on Differential Interferometric Synthetic Aperture Radar (D-InSAR) by calculating the six-day phase differences in 30 Swedish lakes.

    To achieve these objectives, I trained and applied a Maximum Likelihood classification to Landsat images from 1987 to 2020 and quantified surface water occurrence and its changes in the SRD. I found that surface water occurrence in 51% of the delta experienced a decrease. As the Selenga River is the only river flowing into the SRD, the change in surface water occurrence in the SRD correlated with river discharge, but not with the river suspended sediment concentration, the lake water level in the outlet of the SRD, or evapotranspiration over the delta.

    In Sweden, I used satellite altimetry data from ERS-2, ENVISAT, JASON-1,2,3, SARAL, and Sentinel-3A/B to quantify water levels in 144 lakes from 1995-2022. I found that 52% of the lakes showed increasing trends (mostly in the north) and 43% decreasing trends (mostly in the south). Water level trends and variabilities did not correlate strongly with hydroclimatic changes (precipitation and temperature) but differed in regulated lakes compared to unregulated ones, both in the north and in the south of Sweden.

    The results of the D-InSAR method for water level estimation in two Swedish lakes (Hjälmaren and Solnen) showed that with water level changes smaller than a complete SAR phase, the phase changes correlate with in-situ water level changes with a minimum Root Mean Square Error of 0.43 cm in some pixels. In all 30 lakes, I accumulated the phase changes of each pixel throughout the whole number of interferograms to construct water levels. This method replicated the direction of water level changes shown by high Pearson’s correlations in at least one pixel in each lake.

    This thesis highlights the importance of EO for estimating surface water occurrence and lake water levels and brings focus to the future of EO through advanced space missions such as Surface Water and Ocean Topography (SWOT) and NASA-ISRO Synthetic Aperture Radar (NISAR). The findings underscore the need to continuously monitor lake water level and occurrence to adapt to climate change and understand the effects of water-regulatory schemes.

    Download full text (pdf)
    Monitoring Water Availability in Northern Inland Waters from Space
    Download (jpg)
    presentationsbild
  • 2.
    Aminjafari, Saeid
    et al.
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Brown, Ian
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Jaramillo, Fernando
    Stockholm University, Faculty of Science, Department of Physical Geography. Stockholm University, Faculty of Science, Stockholm University Baltic Sea Centre. Stockholm University, Faculty of Science, Stockholm Resilience Centre. Stockholm University, Faculty of Science, The Bolin Centre for Climate Research (together with KTH & SMHI).
    Evaluating D-InSAR Performance to Detect Small Water Level Fluctuations in LakesManuscript (preprint) (Other academic)
    Abstract [en]

    It is essential to track lake water level fluctuations, however, the number of conventional gauging stations is declining worldwide due to impractical installation and maintenance procedures. Satellite altimetry is a substitute for traditional gauges. Nevertheless, altimetry sensors cannot identify small lakes owing to poor spatial coverage. Their application is limited to lakes falling exactly below the path of the altimeter. Differential Interferometric Synthetic Aperture Radar (D-InSAR) is commonly used to track land deformation and water surface changes, with the latter being comparatively limited and focused mainly on wetlands. We here explore the potential of D-InSAR to track water level changes in two Swedish lakes, focusing on the shoreline in search of potential double-bounce backscattering and analyzing pixel phase changes and coherence. We use Sentinel-1A and Sentinel-1B data from 2019, generate six-day interferograms, and exclude those when corresponding to in-situ water level changes exceeding one phase cycle. We find that D-InSAR is sensitive to minor water level changes, obtaining Lin's correlations of up to 0.63 and 0.89 (RMSE = 9 & 4 mm, respectively). These results evidence the potential of future L-band SAR missions with larger wavelengths, such as NISAR, to track water level changes in lakes and aid water tracking missions such as the SWOT.

  • 3.
    Aminjafari, Saeid
    et al.
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Brown, Ian
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Vahidi Mayamey, Farzad
    Jaramillo, Fernando
    Stockholm University, Faculty of Science, Department of Physical Geography. Stockholm University, Faculty of Science, Stockholm University Baltic Sea Centre. Stockholm University, Faculty of Science, Stockholm Resilience Centre. Stockholm University, Faculty of Science, The Bolin Centre for Climate Research (together with KTH & SMHI).
    The Potential of D-InSAR for Water Level Estimation in Swedish LakesManuscript (preprint) (Other academic)
    Abstract [en]

    Lakes are valuable water resources that support aquatic and terrestrial ecosystems and supply fresh water for the agricultural, industrial, and urban sectors worldwide. Although water levels should be tracked to monitor these services, conventional gauging is unfeasible in most lakes. This study explores the potential, advantages, and limitations of using Differential Interferometric Synthetic Aperture Radar (D-InSAR) to estimate small water level changes in lakes (i.e., less than the full cycle of the SAR signal) and overall long-term direction of change. We validated the method across the shores of 30 Swedish lakes with gauged observations during 2019. We used Sentinel-1A/B images with a six-day temporal separation to construct consecutive interferograms and accumulated the phase changes in pixels of high coherence to build time series of water levels. We find that the accumulated phase change replicates the magnitude of water levels in seven lakes in Southern Sweden, where water level changes seldom exceed a complete SAR phase (i.e., 1.8 cm in the vertical direction), evident from the Concordance Correlation Coefficients (0.30 < CCC < 0.55). Furthermore, D-InSAR can estimate the long-term direction of water level change (i.e., increase or decrease) in all 30 lakes. We elaborate on the possible explanation for this last finding. The novel methodology could be used to validate future altimetry missions such as SWOT in lakes worldwide and can be improved with upcoming SAR missions with longer wavelengths.

  • 4.
    Andersson, Marcus
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Estimating Phosphorus in rivers of Central Sweden using Landsat TM data2012Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Phosphorus flowing via rivers into the Baltic Sea is a major source of nutrients, and in some cases the limiting factor for the growth of algae which causes the phenomenon known as eutrophication. Remote sensing of phosphorus, here using Landsat TM-data, can help to give a better understanding of the process of eutrophication. Since Landsat TM-data is used, this could form a basis for further spatio-temporal analysis in the Baltic Sea region. A method originally described and previously applied for a Chinese river is here transferred and applied to three different rivers flowing into the Baltic Sea. The results show that by measuring the proxy variables of Secchi Depth and Chloryphyll-a the remote sensing model is able to explain 41% of the variance in total- phosphorus for the rivers Dalälven, Norrström and Gavleån without any consideration taken to CDOM, turbidity or other local features.

    Download full text (pdf)
    fulltext
  • 5.
    Arslan, Nat
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Assessment of coastal erosion to create a seagrass vulnerability index in northwestern Madagascar using automated quantification analysis2020Independent thesis Advanced level (degree of Master (Two Years)), 80 credits / 120 HE creditsStudent thesis
    Abstract [en]

    The seagrass extent has been declining globally. The human activities that are most likely to cause seagrass loss are those which affect the water quality and clarity. However, turbidity following coastal erosion is often left out from marine ecosystem vulnerability indices. This study quantified the coastal erosion for Tsimipaika Bay in northwestern Madagascar by using change detection analysis of satellite imageries. The annual coastal erosion data was then used to create an index for seagrass vulnerability to turbidity following coastal erosion. Considering that the height of seagrass species plays an important role in their survival following turbidity, the seagrass vulnerability index (SVI) was based on two factors; seagrass species height and their distance to the nearest possible erosion place. The results for the coastal erosion showed that the amount of erosion was particularly high in 1996, 2001 and 2009 for Tsimipaika Bay. The highest erosion occurred in 2001 with a land loss area of about 6.2 km2 . The SVI maps revealed that 40% of the seagrass communities had minimum mean SVI values in 2001 and 50% had the maximum mean SVI during the year 2009. This study showed that it is possible to use coastal erosion to measure seagrass vulnerability; however, the index requires configuration such as including the total amount of annual coastal erosion and incorporating bathymetric data. The entire project was built and automated in Jupyter Notebook using Python programming language, which creates a ground for future studies to develop and modify the project.

    Download full text (pdf)
    fulltext
  • 6.
    Baggström, Adrian
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Predicting biodiverse semi-natural grasslands through satellite imagery and machine learning2021Independent thesis Advanced level (degree of Master (One Year)), 40 credits / 60 HE creditsStudent thesis
    Abstract [en]

    Semi-natural grasslands are amongst the most biodiverse ecosystems in Europe, though their importance they are experiencing a declining trend. To monitor and assess the health of these ecosystems is generally costly, personnel demanding and time-consuming. With satellite imagery and machine learning becoming more accessible, this can offer a cheap and effective way to gain ecological information about semi-natural grasslands.This thesis explores the possibilities to predict plant species richness in semi-natural grasslands with high resolution satellite imagery through machine learning. Five different machine learning models were employed with various subsets of spectral- and geographical features to see how they performed and why. The study area was in southern Sweden with satellite and survey data from the summer of 2019.Geographical features were the features that influenced the machine learning models most. This can be explained by the geographical spread of the semi-natural grasslands, as well as difficulties in finding correlations in the relatively noisy satellite data. The most important spectral features were found in the red edge- and the short-wave infrared spectrums. These spectrums represent leaf chlorophyll content and water content in vegetation, respectively. The most accurate machine learning model was Random Forest when it was trained using with all the spectral- and geographical features. The other models; Logistic Regression, Support Vector Machine, Voting Classifier and Neural Network, showed general inabilities to interpret feature subsets containing the spectral data.This thesis shows that with deeper knowledge about the satellite-biodiversity relationship and how to apply it with machine learning have the possibilities of cheaper, more efficient and standardized monitoring of ecologically valuable areas such as semi-natural grasslands.

    Download full text (pdf)
    fulltext
  • 7.
    Boström, Henrik
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Forests of probability estimation trees2012In: International journal of pattern recognition and artificial intelligence, ISSN 0218-0014, Vol. 26, no 2, p. 1251001-Article in journal (Refereed)
    Abstract [en]

    Probability estimation trees (PETs) generalize classification trees in that they assign class probability distributions instead of class labels to examples that are to be classified. This property has been demonstrated to allow PETs to outperform classification trees with respect to ranking performance, as measured by the area under the ROC curve (AUC). It has further been shown that the use of probability correction improves the performance of PETs. This has lead to the use of probability correction also in forests of PETs. However, it was recently observed that probability correction may in fact deteriorate performance of forests of PETs. A more detailed study of the phenomenon is presented and the reasons behind this observation are analyzed. An empirical investigation is presented, comparing forests of classification trees to forests of both corrected and uncorrected PETS on 34 data sets from the UCI repository. The experiment shows that a small forest (10 trees) of probability corrected PETs gives a higher AUC than a similar-sized forest of classification trees, hence providing evidence in favor of using forests of probability corrected PETs. However, the picture changes when increasing the forest size, as the AUC is no longer improved by probability correction. For accuracy and squared error of predicted class probabilities (Brier score), probability correction even leads to a negative effect. An analysis of the mean squared error of the trees in the forests and their variance, shows that although probability correction results in trees that are more correct on average, the variance is reduced at the same time, leading to an overall loss of performance for larger forests. The main conclusions are that probability correction should only be employed in small forests of PETs, and that for larger forests, classification trees and PETs are equally good alternatives.

  • 8. Hentati-Sundberg, Jonas
    et al.
    Olin, Agnes
    Stockholm University, Faculty of Science, Department of Ecology, Environment and Plant Sciences. Swedish University of Agricultural Sciences, Sweden.
    Reddy, Sheetal
    Berglund, Per-Arvid
    Svensson, Erik
    Reddy, Mareddy
    Kasarareni, Siddharta
    Carlsen, Astrid A.
    Hanes, Matilda
    Kad, Shreyash
    Olsson, Olof
    Stockholm University, Faculty of Science, Stockholm Resilience Centre.
    Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research2023In: Remote Sensing in Ecology and Conservation, E-ISSN 2056-3485, Vol. 9, no 4, p. 568-581Article in journal (Refereed)
    Abstract [en]

    Ecological research and monitoring need to be able to rapidly convey information that can form the basis of scientifically sound management. Automated sensor systems, especially if combined with artificial intelligence, can contribute to such rapid high-resolution data retrieval. Here, we explore the prospects of automated methods to generate insights for seabirds, which are often monitored for their high conservation value and for being sentinels for marine ecosystem changes. We have developed a system of video surveillance combined with automated image processing, which we apply to common murres Uria aalge. The system uses a deep learning algorithm for object detection (YOLOv5) that has been trained on annotated images of adult birds, chicks and eggs, and outputs time, location, size and confidence level of all detections, frame-by-frame, in the supplied video material. A total of 144 million bird detections were generated from a breeding cliff over three complete breeding seasons (2019–2021). We demonstrate how object detection can be used to accurately monitor breeding phenology and chick growth. Our automated monitoring approach can also identify and quantify rare events that are easily missed in traditional monitoring, such as disturbances from predators. Further, combining automated video analysis with continuous measurements from a temperature logger allows us to study impacts of heat waves on nest attendance in high detail. Our automated system thus produces comparable, and in several cases significantly more detailed, data than those generated from observational field studies. By running in real time on the camera streams, it has the potential to supply researchers and managers with high-resolution up-to-date information on seabird population status. We describe how the system can be modified to fit various types of ecological research and monitoring goals and thereby provide up-to-date support for conservation and ecosystem management. 

  • 9.
    Hommersom, Annelies
    et al.
    Stockholm University, Faculty of Science, Department of Systems Ecology. Water Insight, The Netherlands.
    Kratzer, Susanne
    Stockholm University, Faculty of Science, Department of Systems Ecology.
    Laanen, Marnix
    Ansko, Ilmar
    Ligi, Martin
    Bresciani, Mariano
    Giardino, Claudia
    Beltrán-Abaunza, José M.
    Stockholm University, Faculty of Science, Department of Systems Ecology.
    Moore, Gerald
    Wernand, Marcel
    Peters, Steef
    Intercomparison in the field between the new WISP-3 and other radiometers (TriOS Ramses, ASD FieldSpec, and TACCS)2012In: Journal of Applied Remote Sensing, ISSN 1931-3195, E-ISSN 1931-3195, Vol. 6, article id 063615Article in journal (Refereed)
    Abstract [en]

    Optical close-range instruments can be applied to derive water quality parameters for monitoring purposes and for validation of optical satellite data. In situ radiometers are often difficult to deploy, especially from a small boat or a remote location. The water insight spectrometer (WISP-3) is a new hand-held radiometer for monitoring water quality, which automatically performs measurements with three radiometers (L-sky, L-u, E-d) and does not need to be connected with cables and electrical power during measurements. The instrument is described and its performance is assessed by an intercomparison to well-known radiometers, under real fieldwork conditions using a small boat and with sometimes windy and cloudy weather. Root mean squared percentage errors relative to those of the TriOS system were generally between 20% and 30% for remote sensing reflection, which was comparable to those of the other instruments included in this study. From this assessment, it can be stated that for the tested conditions, the WISP-3 can be used to obtain reflection spectra with accuracies in the same range as well-known instruments. When tuned with suitable regional algorithms, it can be used for quick scans for water quality monitoring of Chl, SPM, and aCDOM.

  • 10.
    Höhle, Michael
    et al.
    Stockholm University, Faculty of Science, Department of Mathematics.
    Höhle, Joachim
    Aalborg University.
    Generation and Assessment of Urban Land Cover Maps Using High-Resolution Multispectral Aerial Cameras2013In: International Journal On Advances in Software, ISSN 1942-2628, E-ISSN 1942-2628, Vol. 6, no 3-4, p. 272-282Article in journal (Refereed)
    Abstract [en]

    New aerial cameras and new advanced geoprocessingtools improve the generation of urban land covermaps. Elevations can be derived from stereo pairs with highdensity, positional accuracy, and efficiency. The combinationof multispectral high-resolution imagery and high-densityelevations enable a unique method for the automaticgeneration of urban land cover maps. In the present paper,imagery of a new medium-format aerial camera and advancedgeoprocessing software are applied to derive normalizeddigital surface models and vegetation maps. These twointermediate products then become input to a tree structuredclassifier, which automatically derives land cover maps in 2Dor 3D. We investigate the thematic accuracy of the producedland cover map by a class-wise stratified design and provide amethod for deriving necessary sample sizes. Correspondingsurvey adjusted accuracy measures and their associatedconfidence intervals are used to adequately reflect uncertaintyin the assessment based on the chosen sample size. Proof ofconcept for the method is given for an urban area inSwitzerland. Here, the produced land cover map with sixclasses (building, wall and carport, road and parking lot, hedgeand bush, grass) has an overall accuracy of 86% (95%confidence interval: 83-88%) and a kappa coefficient of 0.82(95% confidence interval: 0.78-0.85). The classification ofbuildings is correct with 99% and of road and parking lot with95%. To possibly improve the classification further,classification tree learning based on recursive partitioning isinvestigated. We conclude that the open source software “R”provides all the tools needed for performing statistical prudentclassification and accuracy evaluations of urban land covermaps.

    Download full text (pdf)
    fulltext
  • 11.
    Karlsson, Johanna Mård
    et al.
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Lyon, Steve W.
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Destouni, Georgia
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Temporal Behavior of Lake Size-Distribution in a Thawing Permafrost Landscape in Northwestern Siberia2014In: Remote Sensing, E-ISSN 2072-4292, Vol. 6, no 1, p. 621-636Article in journal (Refereed)
    Abstract [en]

    Arctic warming alters regional hydrological systems, as permafrost thaw increases active layer thickness and in turn alters the pathways of water flow through the landscape. Further, permafrost thaw may change the connectivity between deeper and shallower groundwater and surface water altering the terrestrial water balance and distribution. Thermokarst lakes and wetlands in the Arctic offer a window into such changes as these landscape elements depend on permafrost and are some of the most dynamic and widespread features in Arctic lowland regions. In this study we used Landsat remotely sensed imagery to investigate potential shifts in thermokarst lake size-distributions, which may be brought about by permafrost thaw, over three distinct time periods (1973, 1987-1988, and 2007-2009) in three hydrological basins in northwestern Siberia. Results revealed fluctuations in total area and number of lakes over time, with both appearing and disappearing lakes alongside stable lakes. On the whole basin scales, there is no indication of any sustained long-term change in thermokarst lake area or lake size abundance over time. This statistical temporal consistency indicates that spatially variable change effects on local permafrost conditions have driven the individual lake changes that have indeed occurred over time. The results highlight the importance of using multi-temporal remote sensing data that can reveal complex spatiotemporal variations distinguishing fluctuations from sustained change trends, for accurate interpretation of thermokarst lake changes and their possible drivers in periods of climate and permafrost change.

  • 12. Knudby, Anders
    et al.
    Nordlund, Lina
    Stockholm University, Faculty of Science, Department of Systems Ecology.
    Remote sensing of seagrasses in a patchy multi-species environment2011In: International Journal of Remote Sensing, ISSN 0143-1161, E-ISSN 1366-5901, Vol. 32, no 8, p. 2227-2244Article in journal (Refereed)
    Abstract [en]

    We tested the utility of IKONOS satellite imagery to map seagrass distribution and biomass in a 4.1 km2 area around Chumbe Island, Zanzibar, Tanzania. Considered to be a challenging environment to map, this area is characterized by a diverse mix of inter- and subtidal habitat types. Our mapped distribution of seagrasses corresponded well to field data, although the total seagrass area was underestimated due to spectral confusion and misclassification of areas with sparse seagrass patches as sparse coral and algae-covered limestone rock. Seagrass biomass was also accurately estimated (r2 = 0.83), except in areas with Thalassodendron ciliatum (r2 = 0.57), as the stems of T. ciliatum change the relationship between light interception and biomass from that of other species in the area. We recommend the use of remote sensing over field-based methods for seagrass mapping because of the comprehensive coverage, high accuracy and ability to estimate biomass. The results obtained with IKONOS imagery in our complex study area are encouraging, and support the use of this data source for seagrass mapping in similar areas.

  • 13.
    Kommana, Karteek
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Implementation of a Geoserver Applicatoin For GIS Data Distribution and Manipulation2013Independent thesis Advanced level (degree of Master (Two Years)), 30 credits / 45 HE creditsStudent thesis
    Abstract [en]

    Accessibility and Interactivity are keywords of information today and that is equally important in science as anywhere else. When scientists share information it benefits if it is intuitive, informative and simple and does not demand expert skills in complicated formats. This master thesis has the aim to investigate open source software tools to design a web map application that can be used by any institute or NGO to distribute their data over internet.

    The Java platform to be implemented is the open source OpenLayers which allow users to view and potentially manipulate GIS map data through a web map application. Whatever GIS data made available on the Geoserver (the host site for the application) can be shared to users worldwide. The user can then: add from a list of available data layers, choose background (e.g. Google Earth, Open Street Map, etc.), zoom in and out, pan, change symbols and colors, add their own data on top and start animation (if applicable).

    The data distributed from the Geoserver can also be viewed and accessed from smartphones whichopens the possibility to make the public part of the larger data gathering task of specific scientific inventories like observations of migrating birds, or whatever indicator a specific scientist is interested in. Data is uploaded to the Geoserver and can then be analyzed and the result is distributed to the public.

    Download full text (pdf)
    GIS Web Mapping
  • 14. Mansourmoghaddam, Mohammad
    et al.
    Rousta, Iman
    Ghafarian Malamiri, Hamidreza
    Sadeghnejad, Mostafa
    Krzyszczak, Jaromir
    Santos Ferreira, Carla Sofia
    Stockholm University, Faculty of Science, Department of Physical Geography. Stockholm University, Faculty of Science, The Bolin Centre for Climate Research (together with KTH & SMHI). Polytechnic Institute of Coimbra, Portugal.
    Modeling and Estimating the Land Surface Temperature (LST) Using Remote Sensing and Machine Learning (Case Study: Yazd, Iran)2024In: Remote Sensing, E-ISSN 2072-4292, Vol. 16, no 3, article id 454Article in journal (Refereed)
    Abstract [en]

    The pressing issue of global warming is particularly evident in urban areas, where urban thermal islands amplify the warming effect. Understanding land surface temperature (LST) changes is crucial in mitigating and adapting to the effect of urban heat islands, and ultimately addressing the broader challenge of global warming. This study estimates LST in the city of Yazd, Iran, where field and high-resolution thermal image data are scarce. LST is assessed through surface parameters (indices) available from Landsat-8 satellite images for two contrasting seasons—winter and summer of 2019 and 2020, and then it is estimated for 2021. The LST is modeled using six machine learning algorithms implemented in R software (version 4.0.2). The accuracy of the models is measured using root mean square error (RMSE), mean absolute error (MAE), root mean square logarithmic error (RMSLE), and mean and standard deviation of the different performance indicators. The results show that the gradient boosting model (GBM) machine learning algorithm is the most accurate in estimating LST. The albedo and NDVI are the surface features with the greatest impact on LST for both the summer (with 80.3% and 11.27% of importance) and winter (with 72.74% and 17.21% of importance). The estimated LST for 2021 showed acceptable accuracy for both seasons. The GBM models for each of the seasons are useful for modeling and estimating the LST based on surface parameters using machine learning, and to support decision-making related to spatial variations in urban surface temperatures. The method developed can help to better understand the urban heat island effect and ultimately support mitigation strategies to improve human well-being and enhance resilience to climate change.

  • 15.
    Mård Karlsson, Johanna
    et al.
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Arnberg, Wolter
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Quality analysis of SRTM and HYDRO1K: a case study of flood inundation in Mozambique2011In: International Journal of Remote Sensing, ISSN 0143-1161, E-ISSN 1366-5901, Vol. 32, no 1, p. 267-285Article in journal (Refereed)
    Abstract [en]

    Many countries still lack national digital elevation models (DEMs) and have to rely on global datasets, which can negatively influence the reliability of flood model results. Mozambique is considered the most risk prone country for floods in Southern Africa. In this study a quality and accuracy assessment of two global DEMs (Shuttle Radar Topography Mission (SRTM) and HYDRO1K) is presented for a simple static flood inundation model of lower Limpopo Basin. This is accomplished with a local fit and vertical accuracy assessment of global datasets on a local scale as well as simulations of flood extent in the floodplain carried out by filling the DEMs with water according to the 2000 flood event. The results from the vertical accuracy assessment show that global DEMs can be used on a local scale. However, flood simulations performed on original DEMs contain inadequacies and are misleading with both under-and overestimation of the flooded area, while simulation performed on locally fitted DEMs shows a better agreement with the actual event. This study clearly shows that DEMs with questionable accuracy and resolution should be used with great caution in flood inundation modelling because they could result in deceptive model predictions, and lead to devastating after-effects in risk prone areas.

  • 16.
    Norinder, Ulf
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences. Örebro University, Sweden.
    Lowry, Stephanie
    Örebro University, Sweden.
    Predicting Larch Casebearer damage with confidence using Yolo network models and conformal prediction2023In: Remote Sensing Letters, ISSN 2150-704X, E-ISSN 2150-7058, Vol. 14, no 10, p. 1023-1035Article in journal (Refereed)
    Abstract [en]

    This investigation shows that successful forecasting models for monitoring forest health status with respect to Larch Casebearer damages can be derived using a combination of a confidence predictor framework (Conformal Prediction) in combination with a deep learning architecture (Yolo v5). A confidence predictor framework can predict the current types of diseases used to develop the model and also provide indication of new, unseen, types or degrees of disease. The user of the models is also, at the same time, provided with reliable predictions and a well-established applicability domain for the model where such reliable predictions can and cannot be expected. Furthermore, the framework gracefully handles class imbalances without explicit over- or under-sampling or category weighting which may be of crucial importance in cases of highly imbalanced datasets. The present approach also provides indication of when insufficient information has been provided as input to the model at the level of accuracy (reliability) need by the user to make subsequent decisions based on the model predictions. 

  • 17. Padmanaban, Rajchandar
    et al.
    Bhowmik, Avit K.
    Stockholm University, Faculty of Science, Stockholm Resilience Centre.
    Cabral, Pedro
    Zamyatin, Alexander
    Almegdadi, Oraib
    Wang, Shuangao
    Modelling Urban Sprawl Using Remotely Sensed Data: A Case Study of Chennai City, Tamilnadu2017In: Entropy, E-ISSN 1099-4300, Vol. 19, no 4, article id 163Article in journal (Refereed)
    Abstract [en]

    Urban sprawl (US), propelled by rapid population growth leads to the shrinkage of productive agricultural lands and pristine forests in the suburban areas and, in turn, adversely affects the provision of ecosystem services. The quantification of US is thus crucial for effective urban planning and environmental management. Like many megacities in fast growing developing countries, Chennai, the capital of Tamilnadu and one of the business hubs in India, has experienced extensive US triggered by the doubling of total population over the past three decades. However, the extent and level of US has not yet been quantified and a prediction for future extent of US is lacking. We employed the Random Forest (RF) classification on Landsat imageries from 1991, 2003, and 2016, and computed six landscape metrics to delineate the extent of urban areas within a 10 km suburban buffer of Chennai. The level of US was then quantified using Renyi's entropy. A land change model was subsequently used to project land cover for 2027. A 70.35% expansion in urban areas was observed mainly towards the suburban periphery of Chennai between 1991 and 2016. The Renyi's entropy value for year 2016 was 0.9, exhibiting a two-fold level of US when compared to 1991. The spatial metrics values indicate that the existing urban areas became denser and the suburban agricultural, forests and particularly barren lands were transformed into fragmented urban settlements. The forecasted land cover for 2027 indicates a conversion of 13,670.33 ha (16.57% of the total landscape) of existing forests and agricultural lands into urban areas with an associated increase in the entropy value to 1.7, indicating a tremendous level of US. Our study provides useful metrics for urban planning authorities to address the social-ecological consequences of US and to protect ecosystem services.

  • 18.
    Palm, Fredrik
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Urban Vegetation Mapping Using Remote Sensing Techniques: A Comparison of Methods2015Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The aim of this study is to compare remote sensing methods in the context of a vegetation mapping of an urban environment. The methods used was (1) a traditional per-pixel based method; maximum likelihood supervised classification (ENVI), (2) a standard object based method; example based feature extraction (ENVI) and (3) a newly developed method; Window Independent Contextual Segmentation (WICS) (Choros Cognition). A four-band SPOT5 image with a pixel size of 10x10m was used for the classifications. A validation data-set was created using a ortho corrected aerial image with a pixel size of 1x1m. Error matrices was created by cross-tabulating the classified images with the validation data-set. From the error matrices, overall accuracy and kappa coefficient was calculated. The object-based method performed best with a overall accuracy of 80% and a kappa value of 0.6, followed by the WICS method with an overall accuracy of 77% and a kappa value of 0.53, placing the supervised classification last with an overall accuracy of 71% and a kappa value of 0.38. The results of this study suggests object-based method and WICS to perform better than the supervised classification in an urban environment.  

    Download full text (pdf)
    fulltext
  • 19.
    Peña, Francisco J.
    et al.
    Stockholm University, Faculty of Science, Department of Physical Geography. KTH Royal Institute of Technology, Sweden.
    Hübinger, Clara
    Stockholm University, Faculty of Science, Department of Physical Geography.
    Payberah, Amir H.
    Jaramillo, Fernando
    Stockholm University, Faculty of Science, Department of Physical Geography.
    DEEPAQUA: Semantic segmentation of wetland water surfaces with SAR imagery using deep neural networks without manually annotated data2024In: International Journal of Applied Earth Observation and Geoinformation, ISSN 1569-8432, E-ISSN 1872-826X, Vol. 126, article id 103624Article in journal (Refereed)
    Abstract [en]

    Deep learning and remote sensing techniques have significantly advanced water surface monitoring; however, the need for annotated data remains a challenge. This is particularly problematic in wetland detection, where water extent varies over time and space, demanding multiple annotations for the same area. In this paper, we present DeepAqua, a deep learning model inspired by knowledge distillation (a.k.a. teacher–student model) to generate labeled data automatically and eliminate the need for manual annotations during the training phase. We utilize the Normalized Difference Water Index (NDWI) as a teacher model to train a Convolutional Neural Network (CNN) for segmenting water from Synthetic Aperture Radar (SAR) images. To train the student model, we exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. DeepAqua represents a significant advancement in computer vision techniques for water detection by effectively training semantic segmentation models without any manually annotated data. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 3%, Intersection Over Union by 11%, and F1-score by 6%. This approach offers a practical solution for monitoring wetland water extent changes without the need of ground truth data, making it highly adaptable and scalable for wetland monitoring.

  • 20. Santoro, Maurizio
    et al.
    Cartus, Oliver
    Fransson, Johan E. S.
    Shvidenko, Anatoly
    McCallum, Ian
    Hall, Ronald J.
    Beaudoin, Andre
    Beer, Christian
    Stockholm University, Faculty of Science, Department of Applied Environmental Science (ITM).
    Schmullius, Christiane
    Estimates of Forest Growing Stock Volume for Sweden, Central Siberia, and Quebec Using Envisat Advanced Synthetic Aperture Radar Backscatter Data2013In: Remote Sensing, E-ISSN 2072-4292, Vol. 5, no 9, p. 4503-4532Article in journal (Refereed)
    Abstract [en]

    A study was undertaken to assess Envisat Advanced Synthetic Aperture Radar (ASAR) ScanSAR data for quantifying forest growing stock volume (GSV) across three boreal regions with varying forest types, composition, and structure (Sweden, Central Siberia, and Quebec). Estimates of GSV were obtained using hyper-temporal observations of the radar backscatter acquired by Envisat ASAR with the BIOMASAR algorithm. In total, 5.310(6) km(2) were mapped with a 0.01 degrees pixel size to obtain estimates representative for the year of 2005. Comparing the SAR-based estimates to spatially explicit datasets of GSV, generated from forest field inventory and/or Earth Observation data, revealed similar spatial distributions of GSV. Nonetheless, the weak sensitivity of C-band backscatter to forest structural parameters introduced significant uncertainty to the estimated GSV at full resolution. Further discrepancies were observed in the case of different scales of the ASAR and the reference GSV and in areas of fragmented landscapes. Aggregation to 0.1 degrees and 0.5 degrees was then undertaken to generate coarse scale estimates of GSV. The agreement between ASAR and the reference GSV datasets improved; the relative difference at 0.5 degrees was consistently within a magnitude of 20-30%. The results indicate an improvement of the characterization of forest GSV in the boreal zone with respect to currently available information.

  • 21.
    Singh, Chandrakant
    et al.
    Stockholm University, Faculty of Science, Stockholm Resilience Centre. Indian Institute of Technology (Indian School of Mines), India.
    Karan, Shivesh Kishore
    Sardar, Purnendu
    Samadder, Sukha Ranjan
    Remote sensing-based biomass estimation of dry deciduous tropical forest using machine learning and ensemble analysis2022In: Journal of Environmental Management, ISSN 0301-4797, E-ISSN 1095-8630, Vol. 308, article id 114639Article in journal (Refereed)
    Abstract [en]

    Forests play a vital role in maintaining the global carbon balance. However, globally, forest ecosystems are increasingly threatened by climate change and deforestation in recent years. Monitoring forests, specifically forest biomass is essential for tracking changes in carbon stocks and the global carbon cycle. However, developing countries lack the capacity to actively monitor forest carbon stocks, which ultimately adds uncertainties in estimating country specific contribution to the global carbon emissions. In India, authorities use field-based measurements to estimate biomass, which becomes unfeasible to implement at finer scales due to higher costs. To address this, the present study proposed a framework to monitor above-ground biomass (AGB) at finer scales using open-source satellite data. The framework integrated four machine learning (ML) techniques with field surveys and satellite data to provide continuous spatial estimates of AGB at finer resolution. The application of this framework is exemplified as a case study for a dry deciduous tropical forest in India. The results revealed that for wet season Sentinel-2 satellite data, the Random Forest (adjusted R2 = 0.91) and Artificial Neural Network (adjusted R2 = 0.77) ML models were better-suited for estimating AGB in the study area. For dry season satellite data, all the ML models failed to estimate AGB adequately (adjusted R2 between −0.05 – 0.43). Ensemble analysis of ML predictions not only made the results more reliable, but also quantified spatial uncertainty in the predictions as a metric to identify its robustness.

  • 22. Torbick, Nathan
    et al.
    Persson, Andreas
    Olefeldt, David
    Frolking, Steve
    Salas, William
    Hagen, Stephen
    Crill, Patrick M.
    Stockholm University, Faculty of Science, Department of Geological Sciences.
    Li, Changsheng
    High Resolution Mapping of Peatland Hydroperiod at a High-Latitude Swedish Mire2012In: Remote Sensing, E-ISSN 2072-4292, Vol. 4, no 7, p. 1974-1994Article in journal (Refereed)
    Abstract [en]

    Monitoring high latitude wetlands is required to understand feedbacks between terrestrial carbon pools and climate change. Hydrological variability is a key factor driving biogeochemical processes in these ecosystems and effective assessment tools are critical for accurate characterization of surface hydrology, soil moisture, and water table fluctuations. Operational satellite platforms provide opportunities to systematically monitor hydrological variability in high latitude wetlands. The objective of this research application was to integrate high temporal frequency Synthetic Aperture Radar (SAR) and high spatial resolution Light Detection and Ranging (LiDAR) observations to assess hydroperiod at a mire in northern Sweden. Geostatistical and polarimetric (PLR) techniques were applied to determine spatial structure of the wetland and imagery at respective scales (0.5 m to 25 m). Variogram, spatial regression, and decomposition approaches characterized the sensitivity of the two platforms (SAR and LiDAR) to wetland hydrogeomorphology, scattering mechanisms, and data interrelationships. A Classification and Regression Tree (CART), based on random forest, fused multi-mode (fine-beam single, dual, quad pol) Phased Array L-band Synthetic Aperture Radar (PALSAR) and LiDAR-derived elevation to effectively map hydroperiod attributes at the Swedish mire across an aggregated warm season (May-September, 2006-2010). Image derived estimates of water and peat moisture were sensitive (R-2 = 0.86) to field measurements of water table depth (cm). Peat areas that are underlain by permafrost were observed as areas with fluctuating soil moisture and water table changes.

  • 23. Wong, Tyler
    et al.
    Khanal, Sami
    Zhao, Kaiguang
    Lyon, Steve W.
    Stockholm University, Faculty of Science, Department of Physical Geography. Ohio State University, USA.
    Grain size estimation in fluvial gravel bars using uncrewed aerial vehicles: A comparison between methods based on imagery and topography2024In: Earth Surface Processes and Landforms, ISSN 0197-9337, E-ISSN 1096-9837, Vol. 49, no 1, p. 374-392Article in journal (Refereed)
    Abstract [en]

    Grain size assessments are necessary for understanding the various geomorphological, hydrological and ecological processes that occur within rivers. Recent research has shown that the application of Structure-from-Motion (SfM) photogrammetry to imagery from uncrewed aerial vehicles (UAVs) shows promise for rapidly characterising grain sizes along rivers in comparison to traditional field-based methods. Here, we evaluated the applicability of different methods for estimating grain sizes in gravel bars along a study reach in the Olentangy River in Columbus, Ohio. We collected imagery of these gravel bars with a UAV and processed those images with SfM photogrammetry software to produce three-dimensional point clouds and orthomosaics. Our evaluation compared statistical models calibrated on topographic roughness, which was computed from the point clouds, and to those based on image texture, which was computed from the orthomosaics. Our results showed that statistical models calibrated on image texture were more accurate than those based on topographic roughness. This might be because of site-specific patterns of grain size, shape and imbrication. Such patterns would have complicated the detection of topographic signatures associated with individual grains. Our work illustrates that UAV-SfM approaches show potential to be used as an accessible method for characterising surface grain sizes along rivers at higher spatial and temporal resolutions than those provided by traditional methods.

  • 24.
    Wästfelt, Anders
    et al.
    Section of Agrarian History, Department of Economics, Swedish University of Agricultural Science, Uppsala.
    Arnberg, Wolter
    Stockholm University, Faculty of Science, Department of Physical Geography and Quaternary Geology.
    Local spatial context measurements used to explore the relationship between land cover and land use functions2013In: International Journal of Applied Earth Observation and Geoinformation, ISSN 1569-8432, E-ISSN 1872-826X, Vol. 23, p. 234-244Article in journal (Refereed)
    Abstract [en]

    Research making use of satellite data for land change science has developed in the last decades. However, analysis of land use has not developed with the same speed as development of new satellite sensors and available land cover data. Improvement of land use analysis is possible, but more advanced methods are needed which make it possible to link image data to analysis of land use functions. To make this linking possible, variable which affect farmer's long term decisions must be taken into account in analysis as well as the relative importance of the landscape itself. A GIS-based tool for the measurement of local spatial context in satellite data is presented in this paper and used to explore the relationship between land covers present in satellite data and land use represented in official databases. By the use of the developed tool, a land configuration image (LCI) over the Siljan area in northern Sweden was produced and used for analysis. The results are twofold. First, the produced LCI holds new information about variables that are relevant for the interpretation of land use. Second, the comparison with statistics of agricultural production shows that production in the study area varies depending on the relative land configuration. Villages consisting of relatively large-scale arable fields and less diverse landscape are less diverse in production than villages which consist of smaller-scale and more heterogonous landscapes. The result is especially relevant for land use studies and policymakers working on environmental and agricultural policies. We conclude that local spatial context is an endogenous variable in the relation between landscape configuration and agricultural land use.

1 - 24 of 24
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf