Centre de documentation
scientifique

Transfer learning from citizen science photographs enables plant species identification in UAV imagery / Salim Soltani in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 5 (August 2022)  

Public [article]  inISPRS Open Journal of Photogrammetry and Remote Sensing > vol 5 (August 2022) . - n° 100016 Titre : Transfer learning from citizen science photographs enables plant species identification in UAV imagery Type de document : Article/Communication Auteurs : Salim Soltani, Auteur ; Hannes Feilhauer, Auteur ; Robbert Duker, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 100016 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] base de données naturalistes [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] distribution spatiale [Termes IGN] données localisées des bénévoles [Termes IGN] espèce végétale [Termes IGN] filtrage de la végétation [Termes IGN] identification de plantes [Termes IGN] image captée par drone [Termes IGN] orthoimage couleur [Termes IGN] science citoyenne [Termes IGN] segmentation sémantique Résumé : (auteur) Accurate information on the spatial distribution of plant species and communities is in high demand for various fields of application, such as nature conservation, forestry, and agriculture. A series of studies has shown that Convolutional Neural Networks (CNNs) accurately predict plant species and communities in high-resolution remote sensing data, in particular with data at the centimeter scale acquired with Unoccupied Aerial Vehicles (UAV). However, such tasks often require ample training data, which is commonly generated in the field via geocoded in-situ observations or labeling remote sensing data through visual interpretation. Both approaches are laborious and can present a critical bottleneck for CNN applications. An alternative source of training data is given by using knowledge on the appearance of plants in the form of plant photographs from citizen science projects such as the iNaturalist database. Such crowd-sourced plant photographs typically exhibit very different perspectives and great heterogeneity in various aspects, yet the sheer volume of data could reveal great potential for application to bird’s eye views from remote sensing platforms. Here, we explore the potential of transfer learning from such a crowd-sourced data treasure to the remote sensing context. Therefore, we investigate firstly, if we can use crowd-sourced plant photographs for CNN training and subsequent mapping of plant species in high-resolution remote sensing imagery. Secondly, we test if the predictive performance can be increased by a priori selecting photographs that share a more similar perspective to the remote sensing data. We used two case studies to test our proposed approach with multiple RGB orthoimages acquired from UAV with the target plant species Fallopia japonica and Portulacaria afra respectively. Our results demonstrate that CNN models trained with heterogeneous, crowd-sourced plant photographs can indeed predict the target species in UAV orthoimages with surprising accuracy. Filtering the crowd-sourced photographs used for training by acquisition properties increased the predictive performance. This study demonstrates that citizen science data can effectively anticipate a common bottleneck for vegetation assessments and provides an example on how we can effectively harness the ever-increasing availability of crowd-sourced and big data for remote sensing applications. Numéro de notice : A2022-488 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.ophoto.2022.100016 Date de publication en ligne : 23/05/2022 En ligne : https://doi.org/10.1016/j.ophoto.2022.100016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100956 [article]

Mapping abundance distributions of allergenic tree species in urbanized landscapes: A nation-wide study for Belgium using forest inventory and citizen science data / Sébastien Dujardin in Landscape and Urban Planning, vol 218 (February 2022)  

Public [article]  inLandscape and Urban Planning > vol 218 (February 2022) . - n° 104286 Titre : Mapping abundance distributions of allergenic tree species in urbanized landscapes: A nation-wide study for Belgium using forest inventory and citizen science data Type de document : Article/Communication Auteurs : Sébastien Dujardin, Auteur ; Michiel Stas, Auteur ; Camille Van Eupen, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 104286 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Alnus (genre) [Termes IGN] Belgique [Termes IGN] Betula (genre) [Termes IGN] carte de la végétation [Termes IGN] carte forestière [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] Corylus (genre) [Termes IGN] distribution spatiale [Termes IGN] inventaire forestier étranger (données) [Termes IGN] milieu urbain [Termes IGN] modèle mathématique [Termes IGN] régression [Termes IGN] santé [Termes IGN] science citoyenne [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) Mapping the distribution of allergenic plants in urbanized landscapes is of high importance to evaluate its impact on human health. However, data is not always available for the allergy-relevant species such as alder, birch, hazel, especially within cities where systematic inventories are often missing or not readily available. This research presents an approach to produce high-resolution abundance maps of allergenic tree species using existing forest inventories and opportunistic open-access citizen science data. Following a two-step approach, we first built species distribution models (SDMs) to predict species habitat suitability, using environmental characteristics as predictors. Second, we used statistical regressions to model the relationships between abundance, the habitat suitability predicted by the SDMs, and additional vegetation cover covariates. The combination of forest inventory data with citizen science data improves the accuracy of abundance distribution models of allergenic tree species. This produces a continuous, 1-hectare resolution map of alder, birch, and hazel showing spatial variations of abundance distributions both within the urban fabric and along the urban–rural gradient. Species abundance modelling can offer a better understanding of the existing and potential future allergy risk posed by green spaces and pave the way for a wide variety of applications at fine-scale, which is indispensable for evidence-based urban green space policy and planning in support of public health. Numéro de notice : A2022-248 Affiliation des auteurs : non IGN Thématique : FORET/GEOMATIQUE Nature : Article DOI : 10.1016/j.landurbplan.2021.104286 Date de publication en ligne : 31/10/2021 En ligne : https://doi.org/10.1016/j.landurbplan.2021.104286 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100196 [article]

The use of volunteer geographic information for producing and maintaining authoritative land use and land cover data / Ana-Maria Olteanu-Raimond (2022)  

Public Titre : The use of volunteer geographic information for producing and maintaining authoritative land use and land cover data : EuroSDR and LandSense Workshop, November 24th - 25th 2020, Online Conference Type de document : Actes de congrès Auteurs : Ana-Maria Olteanu-Raimond , Auteur ; Joep Crompvoets, Auteur ; Inian Moorthy, Auteur ; Clément Mallet , Auteur ; Bénédicte Bucher , Auteur Editeur : Dublin : European Spatial Data Research EuroSDR Année de publication : 2022 Collection : EuroSDR Workshop report Projets : Landsense / Raimond, Ana-Maria Conférence : VGI4LULC 2020, The use of volunteer geographic information for producing and maintaining authoritative land use and land cover data 24/11/2020 25/11/2020 online OA Proceedings Importance : 40 p. Format : 21 x 30 cm Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Termes IGN] approche participative [Termes IGN] cartographie collaborative [Termes IGN] collecte de données [Termes IGN] Corine Land Cover [Termes IGN] détection de changement [Termes IGN] données localisées des bénévoles [Termes IGN] intégration de données [Termes IGN] occupation du sol [Termes IGN] OpenStreetMap [Termes IGN] science citoyenne [Termes IGN] utilisation du sol Résumé : (éditeur) The report refers to the workshop that was organized on behalf of EuroSDR and the LandSense project (24-25 November 2020). LandSense aims to build a citizen observatory for Land Use and Land Cover (LULC) monitoring by proposing innovate technologies for data collection, change detection, data quality assessment and offering tools and systems to empower different communities (e.g., private companies, Non Governmental Organisation, National Mapping Agencies, research, public authorities) to monitor and report on LULC. The workshop was co-organized by the LASTIG laboratory of the University Gustave Eiffel and IGN-ENSG, the French National Mapping agency (Ana-Maria Olteanu-Raimond, Clément Mallet, Bénédicte Bucher), the Katholieke Universiteit Leuven (Joep Crompvoets), the International Institute for Applied Systems Analysis (Inian Moorthy) and EuroSDR. Note de contenu : INTRODUCTION GENERALE 1. Introduction 1.1 Land Use and Land Cover data: specificities and challenges 1.2 VGI and citizen science for LULC monitoring 2. Session 1: Use of VGI for LULC data production 2.1 National Land Cover and Land Use Information System of Spain (SIOSE)- Coordination, production, maintenance and VGI 2.2 A fusion data approach for integrating VGI to update and enrich authoritative LULC data 2.3 OpenStreetMap for Earth Observation (OSM4EO) land use application and benchmark 2.4 Using OpenStreetMap as a data source for training classifiers to generate LULC maps 3. Session 2: Data collection and validation 3.1 A mapping prototype for land use mapping by land users 3.2 A mobile application for collecting snow data in support to satellite remote sensing 3.3 Global land cover monitoring, validation and participation: experiences from several case studies 4. Session 3: Sustainability 4.1 Crowdsourcing reference data collection for land cover and land use mapping: Findings from Picture Pile and FotoquestGo 4.2 Land Cover Monitoring System with Sentinel-Hub and Python Machine Learning Library eo-learn. Is it possible to build a fast and cost-effective LCMS? 4.3 Regular monitoring of landscape changes with Copernicus data- The German land cover change detection service 4.4 Authentication as a Service - A LandSense contribution to improve the FAIR principle in Citizen Science 5. Conclusion Numéro de notice : 28680 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Actes nature-HAL : DirectOuvrColl/Actes DOI : sans En ligne : http://www.eurosdr.net/sites/default/files/uploaded_files/eurosdr_vgi4lulc.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99973

Role of maximum entropy and citizen science to study habitat suitability of jacobin cuckoo in different climate change scenarios / Priyinka Singh in ISPRS International journal of geo-information, vol 10 n° 7 (July 2021)  

Public [article]  inISPRS International journal of geo-information > vol 10 n° 7 (July 2021) . - n° 463 Titre : Role of maximum entropy and citizen science to study habitat suitability of jacobin cuckoo in different climate change scenarios Type de document : Article/Communication Auteurs : Priyinka Singh, Auteur ; Sameer Saran, Auteur ; Sultan Kocaman, Auteur Année de publication : 2021 Article en page(s) : n° 463 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] apprentissage automatique [Termes IGN] Aves [Termes IGN] changement climatique [Termes IGN] distribution spatiale [Termes IGN] données spatiotemporelles [Termes IGN] entropie maximale [Termes IGN] habitat animal [Termes IGN] migration animale [Termes IGN] mousson [Termes IGN] science citoyenne Résumé : (auteur) Recent advancements in spatial modelling and mapping methods have opened up new horizons for monitoring the migration of bird species, which have been altered due to the climate change. The rise of citizen science has also aided the spatiotemporal data collection with associated attributes. The biodiversity data from citizen observatories can be employed in machine learning algorithms for predicting suitable environmental conditions for species’ survival and their future migration behaviours. In this study, different environmental variables effective in birds’ migrations were analysed, and their habitat suitability was assessed for future understanding of their responses in different climate change scenarios. The Jacobin cuckoo (Clamator jacobinus) was selected as the subject species, since their arrival to India has been traditionally considered as a sign for the start of the Indian monsoon season. For suitability predictions in current and future scenarios, maximum entropy (Maxent) modelling was carried out with environmental variables and species occurrences observed in India and Africa. For modelling, the correlation test was performed on the environmental variables (bioclimatic, precipitation, minimum temperature, maximum temperature, precipitation, wind and elevation). The results showed that precipitation-related variables played a significant role in suitability, and through reclassified habitat suitability maps, it was observed that the suitable areas of India and Africa might decrease in future climatic scenarios (SSPs 2.6, 4.5, 7.0 and 8.5) of 2030 and 2050. In addition, the suitability and unsuitability areas were calculated (in km2) to observe the subtle changes in the ecosystem. Such climate change studies can support biodiversity research and improve the agricultural economy. Numéro de notice : A2021-545 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi10070463 Date de publication en ligne : 06/07/2021 En ligne : https://doi.org/10.3390/ijgi10070463 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98046 [article]

Crowdsourcing without data bias: Building a quality assurance system for air pollution symptom mapping / Marta Samulowska in ISPRS International journal of geo-information, vol 10 n° 2 (February 2021)  

Public [article]  inISPRS International journal of geo-information > vol 10 n° 2 (February 2021) . - n° 46 Titre : Crowdsourcing without data bias: Building a quality assurance system for air pollution symptom mapping Type de document : Article/Communication Auteurs : Marta Samulowska, Auteur ; Szymon Chmielewski, Auteur ; Edwin Raczko, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 46 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] assurance qualité [Termes IGN] carte sanitaire [Termes IGN] données localisées des bénévoles [Termes IGN] erreur systématique [Termes IGN] pollution atmosphérique [Termes IGN] production participative [Termes IGN] qualité de l'air [Termes IGN] qualité des données [Termes IGN] science citoyenne [Termes IGN] surveillance sanitaire [Termes IGN] zone urbaine Résumé : (auteur) Crowdsourcing is one of the spatial data sources, but due to its unstructured form, the quality of noisy crowd judgments is a challenge. In this study, we address the problem of detecting and removing crowdsourced data bias as a prerequisite for better-quality open-data output. This study aims to find the most robust data quality assurance system (QAs). To achieve this goal, we design logic-based QAs variants and test them on the air quality crowdsourcing database. By extending the paradigm of urban air pollution monitoring from particulate matter concentration levels to air-quality-related health symptom load, the study also builds a new perspective for citizen science (CS) air quality monitoring. The method includes the geospatial web (GeoWeb) platform as well as a QAs based on conditional statements. A four-month crowdsourcing campaign resulted in 1823 outdoor reports, with a rejection rate of up to 28%, depending on the applied. The focus of this study was not on digital sensors’ validation but on eliminating logically inconsistent surveys and technologically incorrect objects. As the QAs effectiveness may depend on the location and society structure, that opens up new cross-border opportunities for replication of the research in other geographical conditions. Numéro de notice : A2021-153 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi10020046 Date de publication en ligne : 22/01/2021 En ligne : https://doi.org/10.3390/ijgi10020046 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97064 [article]

Correcting misclassification errors in crowdsourced ecological data: A Bayesian perspective / Edgar Santos-Fernandez in Journal of the Royal Statistical Society: Series C Applied Statistics, vol 70 n° 1 (January 2021)  

Permalink

A citSci approach for rapid earthquake intensity mapping: a case study from Istanbul (Turkey) / Ilyas Yalcin in ISPRS International journal of geo-information, vol 9 n° 4 (April 2020)  

Permalink

Use of automated change detection and VGI sources for identifying and validating urban land use change / Ana-Maria Olteanu-Raimond in Remote sensing, vol 12 n° 7 (April 2020)  

Permalink

Can school children support ecological research? Lessons from the Oak Bodyguard citizen science project / Bastien Castagneyrol in Citizen Science: Theory and Practice, vol 5 (2020)  

Permalink

Promoting environmental justice through Integrated mapping approaches: the map of water conflicts in Andalusia (Spain) / Belen Pedregal in ISPRS International journal of geo-information, vol 9 n° 2 (February 2020)  

Permalink

Mapping crisis / Doug Specht (2020)  

Permalink

A representativeness-directed approach to mitigate spatial bias in VGI for the predictive mapping of geographic phenomena / Guiming Zhang in International journal of geographical information science IJGIS, vol 33 n° 9 (September 2019)  

Permalink

An experimental framework for integrating citizen and community science into land cover, land use, and land change detection processes in a national mapping agency / Ana-Maria Olteanu-Raimond in Land, vol 7 n° 3 (September 2018)  

Permalink

Opening GIScience : A process-based approach / Jerry Shannon in International journal of geographical information science IJGIS, vol 32 n° 9-10 (September - October 2018)  

Permalink

Historical collaborative geocoding / Rémi Cura in ISPRS International journal of geo-information, vol 7 n° 7 (July 2018)    

Permalink