Centre dedocumentation
scientifique

Analysis of plot-level volume increment models developed from machine learning methods applied to an uneven-aged mixed forest / Seyedeh Kosar Hamidi in Annals of Forest Science [en ligne], vol 78 n° 1 (March 2021)  

Public [article]  inAnnals of Forest Science [en ligne] > vol 78 n° 1 (March 2021) . - n° 4 Titre : Analysis of plot-level volume increment models developed from machine learning methods applied to an uneven-aged mixed forest Type de document : Article/Communication Auteurs : Seyedeh Kosar Hamidi, Auteur ; Eric K. Zenner, Auteur ; Mahmoud Bayat, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 4 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] Acer velutinum [Termes descripteurs IGN] alnus cordata [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] carpinus betulus [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] classification par réseau neuronal [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] dynamique de la végétation [Termes descripteurs IGN] écosystème forestier [Termes descripteurs IGN] Fagus orientalis [Termes descripteurs IGN] forêt inéquienne [Termes descripteurs IGN] inventaire forestier étranger (données) [Termes descripteurs IGN] Iran [Termes descripteurs IGN] modèle de croissance [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] peuplement mélangé [Termes descripteurs IGN] régression linéaire [Termes descripteurs IGN] volume en bois [Vedettes matières IGN] Sylviculture Résumé : (auteur) Key message: We modeled 10-year net stand volume growth with four machine learning (ML) methods, i.e., artificial neural networks (ANN), support vector machines (SVM), random forests (RF), and nearest neighbor analysis (NN), and with linear regression analysis. Incorporating interactions of multiple variables, the ML methods ANN and SVM predicted nonlinear system behavior and unraveled complex relations with greater accuracy than regression analysis. Context: Investigating the quantitative and qualitative characteristics of short-term forest dynamics is essential for testing whether the desired goals in forest-ecosystem conservation and restoration are achieved. Inventory data from the Jojadeh section of the Farim Forest located in the uneven-aged, mixed Hyrcanian Forest were used to model and predict 10-year net annual stand volume increment with new machine learning technologies. Aims: The main objective of this study was to predict net annual stand volume increment as the preeminent factor of forest growth and yield models. Methods: In the current study, volume increment was modeled from two consecutive inventories in 2003 and 2013 using four machine learning techniques that used physiographic data of the forest as input for model development: (i) artificial neural networks (ANN), (ii) support vector machines (SVM), (iii) random forests (RF), and (iv) nearest neighbor analysis (NN). Results from the various machine learning technologies were compared against results produced with regression analysis. Results: ANNs and SVMs with a linear kernel function that incorporated field-measurements of terrain slope and aspect as input variables were able to predict plot-level volume increment with a greater accuracy (94%) than regression analysis (87%). Conclusion: These results provide compelling evidence for the added utility of machine learning technologies for modeling plot-level volume increment in the context of forest dynamics and management. Numéro de notice : A2021-071 Affiliation des auteurs : non IGN Thématique : FORET/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s13595-020-01011-6 date de publication en ligne : 12/01/2021 En ligne : https://doi.org/10.1007/s13595-020-01011-6 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96794 [article]

Modelling the effect of landmarks on pedestrian dynamics in urban environments / Gabriele Filomena in Computers, Environment and Urban Systems, vol 86 (March 2021)  

Public [article]  inComputers, Environment and Urban Systems > vol 86 (March 2021) . - n° 101573 Titre : Modelling the effect of landmarks on pedestrian dynamics in urban environments Type de document : Article/Communication Auteurs : Gabriele Filomena, Auteur ; Judith A. Verstegen, Auteur Année de publication : 2021 Article en page(s) : n° 101573 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] carte cognitive [Termes descripteurs IGN] itinéraire piétionnier [Termes descripteurs IGN] Londres [Termes descripteurs IGN] milieu urbain [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] modèle orienté agent [Termes descripteurs IGN] navigation pédestre [Termes descripteurs IGN] point de repère Résumé : (auteur) Landmarks have been identified as relevant and prominent urban elements, explicitly involved in human navigation processes. Despite the understanding accumulated around their functions, landmarks have not been included in simulation models of pedestrian movement in urban environments. In this paper, we describe an Agent-Based Model (ABM) for pedestrian movement simulation that incorporates the role of on-route and distant landmarks in agents' route choice behaviour. Route choice models with and without landmarks were compared by using four scenarios: road distance minimisation, least cumulative angular change, road distance minimisation and landmarks, least cumulative angular change and landmarks. The city centre of London was used as a case study and a set of GPS trajectories was employed to evaluate the model. The introduction of landmarks led to more heterogeneous patterns that diverge from the minimisation models. Landmark-based navigation brought about high pedestrian volumes along the river (up to 13% of agents) and the boundaries of the parks (around 8% of the agents). Moreover, the model evaluation showed that the results of the landmark-based scenarios were not significantly different from the GPS trajectories in terms of cumulative landmarkness, whereas the other scenarios were. This implies that our proposed landmark-based route choice approach was better able to reproduce human navigation. At the street-segment level, the pedestrian volumes emerging from the scenarios were comparable to the trajectories' volumes in most of the case study area; yet, under- and over-estimation were observed along the banks of the rivers and across green areas (up to +7%, −11% of volumes) in the landmark-based scenarios, and along major roads (up to +11% of volumes) in the least cumulative angular change scenario. While our model could be expanded in relation to the agents' cognitive representation of the environment, e.g. by considering other relevant urban elements and accounting for individual spatial knowledge differences, the inclusion of landmarks in route choice models results in more plausible agents that make use of relevant urban information. Numéro de notice : A2021-118 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.compenvurbsys.2020.101573 date de publication en ligne : 13/01/2021 En ligne : https://doi.org/10.1016/j.compenvurbsys.2020.101573 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96943 [article]

A dynamic bidirectional coupled surface flow model for flood inundation simulation / Chunbo Jiang in Natural Hazards and Earth System Sciences, Vol 21 n° 2 (February 2021)  

Public [article]  inNatural Hazards and Earth System Sciences > Vol 21 n° 2 (February 2021) . - pp 497 - 515 Titre : A dynamic bidirectional coupled surface flow model for flood inundation simulation Type de document : Article/Communication Auteurs : Chunbo Jiang, Auteur ; Qi Zhou, Auteur ; Wangyang Yu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 497 - 515 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] Chine [Termes descripteurs IGN] crue [Termes descripteurs IGN] inondation [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] modèle dynamique [Termes descripteurs IGN] modèle hydrographique [Termes descripteurs IGN] prévention des risques Résumé : (auteur) Flood disasters frequently threaten people and property all over the world. Therefore, an effective numerical model is required to predict the impacts of floods. In this study, a dynamic bidirectional coupled hydrologic–hydrodynamic model (DBCM) is developed with the implementation of characteristic wave theory, in which the boundary between these two models can dynamically adapt according to local flow conditions. The proposed model accounts for both mass and momentum transfer on the coupling boundary and was validated via several benchmark tests. The results show that the DBCM can effectively reproduce the process of flood propagation and also account for surface flow interaction between non-inundation and inundation regions. The DBCM was implemented for the floods simulation that occurred at Helin Town located in Chongqing, China, which shows the capability of the model for flood risk early warning and future management. Numéro de notice : A2021-168 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.5194/nhess-21-497-2021 date de publication en ligne : 03/02/2021 En ligne : https://doi.org/10.5194/nhess-21-497-2021 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97107 [article]

Optimization of multi-ecosystem model ensembles to simulate vegetation growth at the global scale / Linling Tang in IEEE Transactions on geoscience and remote sensing, vol 59 n° 2 (February 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 2 (February 2021) . - pp 962 - 978 Titre : Optimization of multi-ecosystem model ensembles to simulate vegetation growth at the global scale Type de document : Article/Communication Auteurs : Linling Tang, Auteur ; Qian Lei, Auteur ; Weizhe Liu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 962 - 978 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] croissance végétale [Termes descripteurs IGN] écosystème [Termes descripteurs IGN] estimation bayesienne [Termes descripteurs IGN] Leaf Area Index [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] optimisation (mathématiques) [Termes descripteurs IGN] optimisation par essaim de particules Résumé : (auteur) Process-based ecosystem models are increasingly used to simulate the effects of a changing environment on vegetation growth in the past, present, and future. To improve the simulation, the multimodel ensemble mean (MME) and ensemble Bayesian model averaging (EBMA) methods are often used in optimizing the integration of ecosystem model ensemble. These two methods were compared with four other optimization techniques, including genetic algorithm (GA), particle swarm optimization (PSO), cuckoo search (CS), and interior-point method (IPM), to evaluate their efficiency in this article. Here, we focused on eight commonly used ecosystem models to simulate vegetation growth, represented by the growing season leaf area index (LAIgs), collected globally from 2000 to 2014. The performances of the multimodel ensembles and individual models were compared using the satellite-observed LAI products as the reference. Generally, ensemble simulations provide more accurate estimates than individual models. There were significant performance differences among the six tested methods. The IPM ensemble model simulated LAIgs more accurately than the other tested models, as the reduction in the root-mean-square error was 84.99% higher than the MME results and 61.50% higher than the EBMA results. Thus, IPM optimization can reproduce LAIgs trends accurately for 91.62% of the global vegetated area, which is double the area of the results from MME. Furthermore, the contributions and uncertainties of the individual models in the final simulated IPM LAIgs changes indicated that the best individual model (CABLE) showed the greatest area fraction for the maximum IPM weight (32.49%), especially in the low-lalitude to midlatitude areas. Numéro de notice : A2021-111 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.12.014 date de publication en ligne : 03/06/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.12.014 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96913 [article]

Inferencing hourly traffic volume using data-driven machine learning and graph theory / Zhiyan Yi in Computers, Environment and Urban Systems, vol 85 (January 2021)  

Public [article]  inComputers, Environment and Urban Systems > vol 85 (January 2021) . - n° 101548 Titre : Inferencing hourly traffic volume using data-driven machine learning and graph theory Type de document : Article/Communication Auteurs : Zhiyan Yi, Auteur ; Xiaoyue Cathy Liu, Auteur ; Nikola Markovic, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 101548 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] échantillonnage de données [Termes descripteurs IGN] Extreme Gradient Machine [Termes descripteurs IGN] inférence statistique [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] planification [Termes descripteurs IGN] théorie des graphes [Termes descripteurs IGN] trafic routier [Termes descripteurs IGN] Utah (Etas-Unis) Résumé : (auteur) Traffic volume is a critical piece of information in many applications, such as transportation long-range planning and traffic operation analysis. Effectively capturing traffic volumes on a network scale is beneficial to Transportation Systems Management & Operations (TSM&O). Yet it is impractical to install sensors to cover a large road network. To address this issue, spatial prediction techniques are widely performed to estimate traffic volumes at sites without sensors. In retrospect, most relevant studies resort to machine learning methods and treat each prediction location independently during the training process, ignoring the potential spatial dependency among them. This paper presents an innovative spatial prediction method of hourly traffic volume on a network scale. To achieve this, we applied a state-of-the-art tree ensemble model - extreme gradient boosting tree (XGBoost) - to handle the large-scale features and hourly traffic volume samples, due to the model's powerful scalability. Moreover, spatial dependency among road segments is taken into account in the proposed model using graph theory. Specifically, we created a traffic network graph leveraging probe trajectory data, and implemented a graph-based approach - breadth first search (BFS) - to search neighboring sites in this graph for computing spatial dependency. The proposed spatial dependency feature is subsequently incorporated as a new feature fed into XGBoost. The proposed model is tested on the road network in the state of Utah. Numerical results not only indicate high computational efficiency of the proposed model, but also demonstrate significant improvement in prediction accuracy of hourly traffic volume comparing with the benchmarked models. Numéro de notice : A2021-004 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2020.101548 date de publication en ligne : 24/09/2020 En ligne : https://doi.org/10.1016/j.compenvurbsys.2020.101548 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96271 [article]

Integrating multilayer perceptron neural nets with hybrid ensemble classifiers for deforestation probability assessment in Eastern India / Sunil Saha in Geomatics, Natural Hazards and Risk, vol 12 n° 1 (2021)  

Permalink

Modeling the risk of robbery in the city of Tshwane, South Africa / Nicolas Kemp in Cartography and Geographic Information Science, vol 48 n° 1 (January 2021)  

Permalink

Modelling landslide hazards under global changes: the case of a Pyrenean valley / Séverine Bernardie in Natural Hazards and Earth System Sciences, vol 21 n° 1 (January 2021)  

Permalink

RegNet: a neural network model for predicting regional desirability with VGI data / Wenzhong Shi in International journal of geographical information science IJGIS, vol 35 n° 1 (January 2021)  

Permalink

Turgor – a limiting factor for radial growth in mature conifers along an elevational gradient / Richard L. Peters in New phytologist, vol 229 n° 1 (January 2021)  

Permalink

Bioclimatic modeling of potential vegetation types as an alternative to species distribution models for projecting plant species shifts under changing climates / Robert E. Keane in Forest ecology and management, vol 477 ([01/12/2020])  

Permalink

Exploring the heterogeneity of human urban movements using geo-tagged tweets / Ding Ma in International journal of geographical information science IJGIS, vol 34 n° 12 (December 2020)  

Permalink

Semantic‐based urban growth prediction / Marvin Mc Cutchan in Transactions in GIS, Vol 24 n° 6 (December 2020)  

Permalink

The utility of fused airborne laser scanning and multispectral data for improved wind damage risk assessment over a managed forest landscape in Finland / Ranjith Gopalakrishnan in Annals of Forest Science [en ligne], vol 77 n° 4 (December 2020)  

Permalink

Using multi-agent simulation to predict natural crossing points for pedestrians and choose locations for mid-block crosswalks / Egor Smirrnov in Geo-spatial Information Science, vol 23 n° 4 (December 2020)  

Permalink