Browsing by Subject "SPACE"

Sort by: Order: Results:

Now showing items 1-20 of 43
  • Kukkakorpi, Mariia; Pantti, Mervi (2021)
    Virtual reality (VR) and other immersive technologies introduce new opportunities for emotionally compelling narratives and user agency. Virtually mediated environments lie at the heart of immersive journalism (IJ) experiences, foregrounding a sense of presence and bridging the connection between the user and the character. Mediated environments in VR stories provide more than a setting since the user can interact with and respond to the surroundings. Drawing on the theory of spatial narrative, documentary and cinema literature and studies on media morality, this article examines the meaning of place in VR news stories and its ability to engage the user with the story. This study contributes to the discussion of creating and communicating places in journalism studies by examining spatial storytelling in immersive news stories, which are available in the NYT VR smartphone application. This paper argues that spatial storytelling eventually affects what is experienced and how it is experienced either by demonstrating the circumstances with aesthetical elements or via the selection of spaces.
  • Haikala, L. K.; Salinas, R.; Richtler, T.; Gomez, M.; Gahm, G. F.; Mattila, K. (2021)
    Context. An intriguing silhouette of a small dust patch can be seen against the disk of the S0 galaxy NGC 3269 in the Antlia cluster in optical images. The images do not provide any clue as to whether the patch is a local Jupiter mass-scale cloudlet or a large extragalactic dust complex.Aims. We aim to resolve the nature of this object: is it a small Galactic cloudlet or an extragalactic dust complex?Methods. ALMA and APEX spectroscopy and Gemini GMOS long-slit spectroscopy were used to measure the velocity of the patch and the NGC 3269 disk radial velocity curve.Results. A weak 16 2.5 km s(-1) wide (CO)-C-12(2-1) T-MB 19 +/- 2.5. mK line in a 2 .('') . '' 2 by 2 .('') .'' 12 beam associated with the object was detected with ALMA. The observed heliocentric velocity, V-r,V- hel=3878 +/- 5.0 km s(-1), immediately establishes the extragalactic nature of the object. The patch velocity is consistent with the velocity of the nucleus of NGC 3269, but not with the radial velocity of the NGC 3269 disk of the galaxy at its position. The similar to 4 '' angular size of the patch corresponds to a linear size of similar to 1 kpc at the galaxy's Hubble distance of 50.7 Mpc. The mass estimated from the (CO)-C-12(2-1) emission is similar to 1.4x10(6)(d/50.7 Mpc)M-2(circle dot), while the attenuation derived from the optical spectrum implies a dust mass of similar to 2.6x10(4)(d/50.7 Mpc)M-2(circle dot). The derived attenuation ratio A ' (B)/(A ' (B)-A ' (R)) of 1.6 +/- 0.11 is substantially lower than the corresponding value for the mean Milky Way extinction curve for point sources (2.3).Conclusions. We established the extragalactic nature of the patch, but its origin remains elusive. One possibility is that the dust patch is left over from the removal of interstellar matter in NGC 3269 through the interaction with its neighbour, NGC 3268.
  • Soininvaara, Ilppo (2020)
    In this article, I analyze the politics of urbanization and competitiveness-led state spatial transformations through political narratives. By analyzing empirical material, I search for ways of reasoning and rationalities that disclose the dynamics of the depoliticization and politicization of different spatial transformations of urbanization. Based on extensive interviews, I argue that a general understanding of urbanization as an external, global inevitability and as a force prevails among political elites. This key rationality and other sedimented knowledge duly opens up new political debates on the proper political management of urbanization and national adaptation. The order of reasoning is clear: the political elites argue that the perceived inevitability, common good and state of crisis necessitate national spatial transformations in order to secure the competitiveness of the state. As a result, new spatial hierarchies are forming as an adaptive strategy.
  • Niu, Pingping; Helin, Tapio; Zhang, Zhidong (2020)
    In this work the authors consider an inverse source problem the stochastic fractional diffusion equation. The interested inverse problem is to reconstruct the unknown spatial functions f and g (the latter up to the sign) in the source by the statistics of the final time data u(x, T). Some direct problem results are proved at first, such as the existence, uniqueness, representation and regularity of the solution. Then a reconstruction scheme for f and g up to the sign is given. To tackle the ill-posedness, Tikhonov regularization is adopted and some numerical results are displayed.
  • Asvestari, E.; Willamo, T.; Gil, A.; Usoskin, I. G.; Kovaltsov, G. A.; Mikhailov, V. V.; Mayorov, A. (2017)
    Nearly 70 Ground Level Enhancements (GLEs) of cosmic rays have been recorded by the worldwide neutron monitor network since the 1950s depicting a big variety of energy spectra of solar energetic particles (SEP). Here we studied a statistical relation between the event-integrated intensity of GLEs (calculated as count-rate relative excess, averaged over all available polar neutron monitors, and expressed in percent-hours) and the hardness of the solar particle energy spectra. For each event the integral omnidirectional event integrated fluences of particles with energy above 30 MeV (F-30) and above 200 MeV (F-200) were computed using the reconstructed spectra, and the ratio between the two fluences was considered as a simple index of the event's hardness. We also provided a justification of the spectrum estimate in the form of the Band-function, using direct PAMELA data for GLE 71 (17-May-2012). We found that, while there is no clear relation between the intensity and the hardness for weak events, all strong events with the intensity greater 100 % h are characterized by a very hard spectrum. This implies that a hard spectrum can be securely assumed for all extreme GLE events, e.g., those studied using cosmogenic isotope data in the past. (C) 2016 COSPAR. Published by Elsevier Ltd. All rights reserved.
  • Jalkanen, Joel; Fabritius, Henna; Vierikko, Kati; Moilanen, Atte; Toivonen, Tuuli (2020)
    Maintaining enough green areas and ensuring fair access to them is a common planning challenge in growing and densifying cities. Evaluations of green area access typically use metrics like population around green areas (within a certain buffer), but these do not fully ensure equitable access. We propose that using systematic and complementarity-driven spatial prioritization, often used in nature conservation planning, could assist in the complex planning challenge. Here, we demonstrate the use of spatial prioritization to identify green areas with highest recreational potential based on their type and their accessibility for the residents of the Helsinki Metropolitan area, the capital district of Finland. We calculated travel times from each city district to each green area. Travel times were calculated separately to local green areas using active travel modes (walking and biking), and to large forests (attracting people from near and far) using public transport. We prioritized the green areas using these multimodal travel times from each district and weighting the prioritization with population data with Zonation, conservation prioritization software. Compared to a typical buffer analysis (population within a 500 m buffer from green areas), our approach identified areas of high recreational potential in different parts of the study area. This approach allows systematic integration of travel-time-based accessibility measures into equitable spatial prioritization of recreational green areas. It can help urban planners to identify sets of green areas that best support the recreational needs of the residents across the city.
  • Liu, Jia; Vanhatalo, Jarno (2020)
    In geostatistics, the spatiotemporal design for data collection is central for accurate prediction and parameter inference. An important class of geostatistical models is log-Gaussian Cox process (LGCP) but there are no formal analyses on spatial or spatiotemporal survey designs for them. In this work, we study traditional balanced and uniform random designs in situations where analyst has prior information on intensity function of LGCP and show that the traditional balanced and random designs are not efficient in such situations. We also propose a new design sampling method, a rejection sampling design, which extends the traditional balanced and random designs by directing survey sites to locations that are a priori expected to provide most information. We compare our proposal to the traditional balanced and uniform random designs using the expected average predictive variance (APV) loss and the expected Kullback-Leibler (KL) divergence between the prior and the posterior for the LGCP intensity function in simulation experiments and in a real world case study. The APV informs about expected accuracy of a survey design in point-wise predictions and the KL-divergence measures the expected gain in information about the joint distribution of the intensity field. The case study concerns planning a survey design for analyzing larval areas of two commercially important fish stocks on Finnish coastal region. Our experiments show that the designs generated by the proposed rejection sampling method clearly outperform the traditional balanced and uniform random survey designs. Moreover, the method is easily applicable to other models in general. (C) 2019 The Author(s). Published by Elsevier B.V.
  • Kankainen, Matti; Ojala, Teija; Holm, Liisa (2012)
  • Nygaard, Malene; Kemppainen, Petri; Speed, James D. M.; Elven, Reidar; Flatberg, Kjell Ivar; Galten, Leif P.; Yousefi, Narjes; Solstad, Heidi; Bendiksby, Mika (2021)
    Carex section Ceratocystis (Cyperaceae) is a group of recently evolved plant species, in which hybridization is frequent, introgression is documented, taxonomy is complex, and morphological boundaries are vague. Within this section, a unified taxonomic treatment of the Carex jemtlandica-Carex lepidocarpa species complex does not exist, and Norway may currently be the sole country accepting species rank for both. Carex jemtlandica is mainly confined to Fennoscandia and is thus a Fennoscandian conservation responsibility. This motivated us to test the principal hypothesis that both C. jemtlandica and C. lepidocarpa represent evolutionary significant units, and that both deserve their current recognition at species level. We investigated their evolutionary distinctiveness in Norway, using restriction site-associated DNA sequencing and ecological niche modeling. Our genomic results reveal two genetic clusters, largely corresponding to C. jemtlandica and C. lepidocarpa that also remain distinct in sympatry, despite clear indications of ongoing hybridization and introgression. The ecological niche modeling suggests that they occupy different environmental niches. Jointly, our results clearly show that C. jemtlandica and C. lepidocarpa represent separately evolving entities that should qualify recognition as evolutionary significant units. Given the high level of introgression compared to other hybridizing species pairs in Carex we recommend treating C. jemtlandica as a subspecies of C. lepidocarpa.
  • Sabater, Neus; Vicent, Jorge; Alonso, Luis; Verrelst, Jochem; Middleton, Elizabeth M.; Porcar-Castell, Albert; Moreno, José (2018)
    Estimates of Sun-Induced vegetation chlorophyll Fluorescence (SIF) using remote sensing techniques are commonly determined by exploiting solar and/or telluric absorption features. When SIF is retrieved in the strong oxygen (O) absorption features, atmospheric effects must always be compensated. Whereas correction of atmospheric effects is a standard airborne or satellite data processing step, there is no consensus regarding whether it is required for SIF proximal-sensing measurements nor what is the best strategy to be followed. Thus, by using simulated data, this work provides a comprehensive analysis about how atmospheric effects impact SIF estimations on proximal sensing, regarding: (1) the sensor height above the vegetated canopy; (2) the SIF retrieval technique used, e.g., Fraunhofer Line Discriminator (FLD) family or Spectral Fitting Methods (SFM); and (3) the instrument's spectral resolution. We demonstrate that for proximal-sensing scenarios compensating for atmospheric effects by simply introducing the O transmittance function into the FLD or SFM formulations improves SIF estimations. However, these simplistic corrections still lead to inaccurate SIF estimations due to the multiplication of spectrally convolved atmospheric transfer functions with absorption features. Consequently, a more rigorous oxygen compensation strategy is proposed and assessed by following a classic airborne atmospheric correction scheme adapted to proximal sensing. This approach allows compensating for the O absorption effects and, at the same time, convolving the high spectral resolution data according to the corresponding Instrumental Spectral Response Function (ISRF) through the use of an atmospheric radiative transfer model. Finally, due to the key role of O absorption on the evaluated proximal-sensing SIF retrieval strategies, its dependency on surface pressure (p) and air temperature (T) was also assessed. As an example, we combined simulated spectral data with p and T measurements obtained for a one-year period in the Hyytiala Forestry Field Station in Finland. Of importance hereby is that seasonal dynamics in terms of T and p, if not appropriately considered as part of the retrieval strategy, can result in erroneous SIF seasonal trends that mimic those of known dynamics for temperature-dependent physiological responses of vegetation.
  • Gurarie, Eliezer; Fleming, Christen H.; Fagan, William F.; Laidre, Kristin L.; Hernandez-Pliego, Jesus; Ovaskainen, Otso (2017)
    Background: Continuous time movement models resolve many of the problems with scaling, sampling, and interpretation that affect discrete movement models. They can, however, be challenging to estimate, have been presented in inconsistent ways, and are not widely used. Methods: We review the literature on integrated Ornstein-Uhlenbeck velocity models and propose four fundamental correlated velocity movement models (CVM's): random, advective, rotational, and rotational-advective. The models are defined in terms of biologically meaningful speeds and time scales of autocorrelation. We summarize several approaches to estimating the models, and apply these tools for the higher order task of behavioral partitioning via change point analysis. Results: An array of simulation illustrate the precision and accuracy of the estimation tools. An analysis of a swimming track of a bowhead whale (Balaena mysticetus) illustrates their robustness to irregular and sparse sampling and identifies switches between slower and faster, and directed vs. random movements. An analysis of a short flight of a lesser kestrel (Falco naumanni) identifies exact moments when switches occur between loopy, thermal soaring and directed flapping or gliding flights. Conclusions: We provide tools to estimate parameters and perform change point analyses in continuous time movement models as an R package (smoove). These resources, together with the synthesis, should facilitate the wider application and development of correlated velocity models among movement ecologists.
  • Caro, Pedro; Helin, Tapio; Kujanpää, Antti; Lassas, Matti (2019)
    Scattering from a non-smooth random field on the time domain is studied for plane waves that propagate simultaneously through the potential in variable angles. We first derive sufficient conditions for stochastic moments of the field to be recovered from empirical correlations between amplitude measurements of the leading singularities, detected in the exterior of a region where the potential is almost surely supported. The result is then applied to show that if two sufficiently regular random fields yield the same correlations, they have identical laws as function-valued random variables.
  • Halonen, Jaana; Pulakka, Anna; Pentti, Jaana; Kallio, Minna; Koskela, Sofia; Kivimäki, Mika; Kawachi, Ichiro; Vahtera, Jussi; Stenholm, Sari (2020)
    Objective Neighbourhood characteristics may affect the level of physical activity (PA) of the residents. Few studies have examined the combined effects of distinctive neighbourhood characteristics on PA using objective data or differentiated between activity during working or non-working days. We examined the associations of socioeconomic disadvantage and greenness with accelerometer-measured leisure-time PA during working and non-working days. Design Cross-sectional study. Setting Finnish Retirement and Aging (FIREA) study. Participants 708 workers (604 women, mean age 62.4 ranging from 58 to 64 years,) participating in the FIREA study who provided PA measurement data for at least 1 working and non-working day. Primary and secondary outcomes PA was measured with wrist-worn accelerometer on average of 4 working and 2 non-working days. Outcomes were total PA, light PA (LPA) and moderate-to-vigorous PA (MVPA). These measurements were linked to data on neighbourhood socioeconomic disadvantage and greenness within the home neighbourhood (750x750 m). Generalised linear models were adjusted for possible confounders. Results On non-working days, higher neighbourhood disadvantage associated with lower levels of total PA (p value=0.07) and higher level of neighbourhood greenness associated with higher level of total PA (p value=0.04). Neighbourhood disadvantage and greenness had an interaction (p value=0.02); in areas of low disadvantage higher greenness did not associate with the level of total PA. However, in areas of high disadvantage, 2 SD higher greenness associated with 46 min/day (95% CI 8.4 to 85) higher total PA. Slightly stronger interaction was observed for LPA (p=0.03) than for the MVPA (p=0.09). During working days, there were no associations between neighbourhood characteristics and leisure-time total PA. Conclusions Of the disadvantaged neighbourhoods, those characterised by high levels of greenness seem to associate with higher levels of leisure-time PA during non-working days. These findings suggest that efforts to add greenness to socioeconomically disadvantaged neighbourhoods might reduce inequalities in PA.
  • Quist, Liina-Maija; Nygren, Anja (2019)
    Marine extraction accounts for one third of the world's hydrocarbon production. Several analyses suggest that seismic surveys employed in oil exploration harm marine life; however, their long-term impacts have not been extensively studied. We examine debates between fishers, the oil industry, and governmental authorities over the effects of oil explorations in Tabasco, Mexico. The study employs ideas from historical ontology in tracing the contested production of truth-claims about exploration in the context of scientific uncertainty. It shows how actors, through their different engagements with the sea, and with different degrees of power, frame claims about the relations between exploration and fish. We argue that fishers, through their efforts to "think like fish" produce situated knowledges about the effects of oil exploration. They explain a disappearance of fish by their understanding that seismic surveys disturb fish migration, impair the hearing of fish and cause fish death. Oil company and governmental representatives frame the impacts of oil exploration as insignificant by separating environmental and social dimensions, by isolating individual exploration events, and by arguing that possible effects are transitional. Due to scientific indeterminacy, oil exploration is malleable in the hands of powerful political representations that understate its possible impacts on marine socio-environments.
  • Egashira, Yuka; Kaga, Yoshimi; Gunji, Atsuko; Kita, Yosuke; Kimura, Motohiro; Hironaga, Naruhito; Takeichi, Hiroshige; Hayashi, Sayuri; Kaneko, Yuu; Takahashi, Hidetoshi; Hanakawa, Takashi; Okada, Takashi; Inagaki, Masumi (2022)
    Reading fluency is based on the automatic visual recognition of words. As a manifestation of the automatic processing of words, an automatic deviance detection of visual word stimuli can be observed in the early stages of visual recognition. To clarify whether this phenomenon occurs with Japanese kanji compounds-since their lexicality is related to semantic association-we investigated the brain response by utilizing three types of deviants: differences in font type, lexically correct or incorrect Japanese kanji compound words and pseudo-kanji characters modified from correct and incorrect compounds. We employed magnetoencephalography (MEG) to evaluate the spatiotemporal profiles of the related brain regions. The study included 22 adult native Japanese speakers (16 females). The abovementioned three kinds of stimuli containing 20% deviants were presented during the MEG measurement. Activity in the occipital pole region of the brain was observed upon the detection of font-type deviance within 250 ms of stimulus onset. Although no significant activity upon detecting lexically correct/incorrect kanji compounds or pseudo-kanji character deviations was observed, the activity in the posterior transverse region of the collateral sulcus (pCoS)-which is a fusiform neighboring area-was larger when detecting lexically correct kanji compounds than when detecting pseudo-kanji characters. Taken together, these results support the notion that the automatic detection of deviance in kanji compounds may be limited to a low-level feature, such as the stimulus stroke thickness.
  • Järv, Olle; Tenkanen, Henrikki Toivo Olavi; Salonen, Maria Pauliina; Ahas, Rein; Toivonen, Tuuli Kaarina (2018)
    The concept of accessibility- the potential of opportunities for interaction- binds together the key physical components of urban structure: people, transport and social activity locations. Most often these components are dynamic in nature and hence the accessibility landscape changes in space and time based on people's mobilities and the temporality of the transport network and activity locations (e.g. services). Person-based accessibility approaches have been successful in incorporating time and space in the analyses and models. Still, the more broadly applied location-based accessibility modelling approaches have, on the other hand, often been static/atemporal in their nature. Here, we present a conceptual framework of dynamic location-based accessibility modelling that captures the dynamic temporality of all three accessibility components. Furthermore, we empirically test the proposed framework using novel data sources and tools. We demonstrate the impact of temporal aspects in accessibility modelling with two examples: by investigating food accessibility and its spatial equity. Our case study demonstrates how the conventional static location-based accessibility models tend to overestimate the access of people to potential opportunities. The proposed framework is universally applicable beyond the urban context, from local to global scale and on different temporal scales and multimodal transport systems. It also bridges the gap between location-based accessibility and person-based accessibility research.
  • Guerra, André; Koch, Lukas; Lindberg, Sauli (2021)
    We consider the class of planar maps with Jacobian prescribed to be a fixed radially symmetric function f and which, moreover, fixes the boundary of a ball; we then study maps which minimise the 2p-Dirichlet energy in this class. We find a quantity lambda[f] which controls the symmetry, uniqueness and regularity of minimisers: if lambda[f]
  • Euclid Collaboration; Pocino, A.; Tutusaus, I.; Gozaliasl, G.; Keihänen, E.; Kirkpatrick , C. C.; Kurki-Suonio, H.; Väliviita, J. (2021)
    Photometric redshifts (photo-zs) are one of the main ingredients in the analysis of cosmological probes. Their accuracy particularly affects the results of the analyses of galaxy clustering with photometrically selected galaxies (GC(ph)) and weak lensing. In the next decade, space missions such as Euclid will collect precise and accurate photometric measurements for millions of galaxies. These data should be complemented with upcoming ground-based observations to derive precise and accurate photo-zs. In this article we explore how the tomographic redshift binning and depth of ground-based observations will affect the cosmological constraints expected from the Euclid mission. We focus on GC(ph) and extend the study to include galaxy-galaxy lensing (GGL). We add a layer of complexity to the analysis by simulating several realistic photo-z distributions based on the Euclid Consortium Flagship simulation and using a machine learning photo-z algorithm. We then use the Fisher matrix formalism together with these galaxy samples to study the cosmological constraining power as a function of redshift binning, survey depth, and photo-z accuracy. We find that bins with an equal width in redshift provide a higher figure of merit (FoM) than equipopulated bins and that increasing the number of redshift bins from ten to 13 improves the FoM by 35% and 15% for GC(ph) and its combination with GGL, respectively. For GC(ph), an increase in the survey depth provides a higher FoM. However, when we include faint galaxies beyond the limit of the spectroscopic training data, the resulting FoM decreases because of the spurious photo-zs. When combining GC(ph) and GGL, the number density of the sample, which is set by the survey depth, is the main factor driving the variations in the FoM. Adding galaxies at faint magnitudes and high redshift increases the FoM, even when they are beyond the spectroscopic limit, since the number density increase compensates for the photo-z degradation in this case. We conclude that there is more information that can be extracted beyond the nominal ten tomographic redshift bins of Euclid and that we should be cautious when adding faint galaxies into our sample since they can degrade the cosmological constraints.
  • Yrttimaa, Tuomas; Luoma, Ville; Saarinen, Ninni; Kankare, Elina; Junttila, Samuli; Holopainen, Markus; Hyyppa, Juha; Vastaranta, Mikko (2022)
    Tree growth is a physio-ecological phenomena of high interest among researchers across disciplines. Observing changes in tree characteristics has conventionally required either repeated measurements of the characteristics of living trees, retrospective measurements of destructively sampled trees, or modelling. The use of close-range sensing techniques such as terrestrial laser scanning (TLS) has enabled non-destructive approaches to reconstruct the three-dimensional (3D) structure of trees and tree communities in space and time. This study aims at improving the understanding of tree allometry in general and interactions between tree growth and its neighbourhood in particular by using two-date point clouds. We investigated how variation in the increments in basal area at the breast height (Delta g(1.3)), basal area at height corresponding to 60% of tree height (Delta g(0)(6h)), and volume of the stem section below 50% of tree height (Delta v(05h) ) can be explained with TLS point cloud-based attributes characterizing the spatiotemporal structure of a tree crown and crown neighbourhood, entailing the competitive status of a tree. The analyses were based on 218 trees on 16 sample plots whose 3D characteristics were obtained at the beginning (2014, T1) and at the end of the monitoring period (2019, T2) from multi-scan TLS point clouds using automatic point cloud processing methods. The results of this study showed that, within certain tree communities, strong relationships (vertical bar r vertical bar > 0.8) were observed between increments in the stem dimensions and the attributes characterizing crown structure and competition. Most often, attributes characterizing the competitive status of a tree, and the crown structure at T1, were the most important attributes to explain variation in the increments of stem dimensions. Linear mixed-effect modelling showed that single attributes could explain up to 35-60% of the observed variation in Delta g(1.3), Delta g(0)(6h) and Delta V-0(5h), depending on the tree species. This tree-level evidence of the allometric relationship between stem growth and crown dynamics can further be used to justify landscape-level analyses based on airborne remote sensing technologies to monitor stem growth through the structure and development of crown structure. This study contributes to the existing knowledge by showing that laser-based close-range sensing is a feasible technology to provide 3D characterization of stem and crown structure, enabling one to quantify structural changes and the competitive status of trees for improved understanding of the underlying growth processes.
  • Liu, Pengyuan; Koivisto, Sonja Maria; Hiippala, Tuomo; Van der Lijn, Charlotte Jacoba Cornelia; Väisänen, Tuomas Lauri Aleksanteri; Nurmi, Marisofia Kaarina; Toivonen, Tuuli; Vehkakoski, Kirsi; Pyykönen, Janne; Virmasalo, Ilkka; Simula, Mikko; Hasanen, Elina; Salmikangas, Anna-Katriina; Muukkonen, Petteri (2022)
    Sport and exercise contribute to health and well-being in cities. While previous research has mainly focused on activities at specific locations such as sport facilities, "informal sport" that occur at arbitrary locations across the city have been largely neglected. Such activities are more challenging to observe, but this challenge may be addressed using data collected from social media platforms, because social media users regularly generate content related to sports and exercise at given locations. This allows studying all sport, including those "informal sport" which are at arbitrary locations, to better understand sports and exercise-related activities in cities. However, user-generated geographical information available on social media platforms is becoming scarcer and coarser. This places increased emphasis on extracting location information from free-form text content on social media, which is complicated by multilingualism and informal language. To support this effort, this article presents an end-to-end deep learning-based bilingual toponym recognition model for extracting location information from social media content related to sports and exercise. We show that our approach outperforms five state-of-the-art deep learning and machine learning models. We further demonstrate how our model can be deployed in a geoparsing framework to support city planners in promoting healthy and active lifestyles.