Centre dedocumentation
scientifique

Can machine learning improve small area population forecasts? A forecast combination approach / Irina Grossman in Computers, Environment and Urban Systems, vol 95 (July 2022)  

Public [article]  inComputers, Environment and Urban Systems > vol 95 (July 2022) . - n° 101806 Titre : Can machine learning improve small area population forecasts? A forecast combination approach Type de document : Article/Communication Auteurs : Irina Grossman, Auteur ; Kasun Bandara, Auteur ; Tom Wilson, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 101806 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] analyse en composantes principales [Termes IGN] apprentissage automatique [Termes IGN] Australie [Termes IGN] démographie [Termes IGN] Extreme Gradient Machine [Termes IGN] infrastructure [Termes IGN] lissage de données [Termes IGN] modèle de simulation [Termes IGN] modèle empirique [Termes IGN] Nouvelle-Zélande [Termes IGN] planification stratégique [Termes IGN] pondération [Termes IGN] série temporelle Résumé : (auteur) Generating accurate small area population forecasts is vital for governments and businesses as it provides better grounds for decision making and strategic planning of future demand for services and infrastructure. Small area population forecasting faces numerous challenges, including complex underlying demographic processes, data sparsity, and short time series due to changing geographic boundaries. In this paper, we propose a novel framework for small area forecasting which combines proven demographic forecasting methods, an exponential smoothing based algorithm, and a machine learning based forecasting technique. The proposed forecasting combination contains four base models commonly used in demographic forecasting, a univariate forecasting model specifically suitable for forecasting yearly data, and a globally trained Light Gradient Boosting Model (LGBM) that exploits the similarities between a collection of population time series. In this study, three forecast combination techniques are investigated to weight the forecasts generated by these base models. We empirically evaluate our method, by preparing small area population forecasts for Australia and New Zealand. The proposed framework is able to achieve competitive results in terms of forecasting accuracy. Moreover, we show that the inclusion of the LGBM model always improves the accuracy of combination models on both datasets, relative to combination models which only include the demographic models. In particular, the results indicate that the proposed combination framework decreases the prevalence of relatively poor forecasts, while improving the reliability of small area population forecasts. Numéro de notice : A2022-374 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2022.101806 Date de publication en ligne : 19/04/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2022.101806 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100621 [article]

Estimating generalized measures of local neighbourhood context from multispectral satellite images using a convolutional neural network / Alex David Singleton in Computers, Environment and Urban Systems, vol 95 (July 2022)  

Public [article]  inComputers, Environment and Urban Systems > vol 95 (July 2022) . - n° 101802 Titre : Estimating generalized measures of local neighbourhood context from multispectral satellite images using a convolutional neural network Type de document : Article/Communication Auteurs : Alex David Singleton, Auteur ; Dani Arribas-Bel, Auteur ; John Murray, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 101802 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] analyse en composantes principales [Termes IGN] apprentissage automatique [Termes IGN] bâtiment [Termes IGN] carte d'occupation du sol [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] Grande-Bretagne [Termes IGN] image multibande [Termes IGN] image Sentinel-MSI [Termes IGN] morphologie urbaine [Termes IGN] pondération [Termes IGN] processeur graphique Résumé : (auteur) The increased availability of high-resolution multispectral imagery captured by remote sensing platforms provides new opportunities for the characterisation and differentiation of urban context. The discovery of generalized latent representations from such data are however under researched within the social sciences. As such, this paper exploits advances in machine learning to implement a new method of capturing measures of urban context from multispectral satellite imagery at a very small area level through the application of a convolutional autoencoder (CAE). The utility of outputs from the CAE is enhanced through the application of spatial weighting, and the smoothed outputs are then summarised using cluster analysis to generate a typology comprising seven groups describing salient patterns of differentiated urban context. The limits of the technique are discussed with reference to the resolution of the satellite data utilised within the study and the interaction between the geography of the input data and the learned structure. The method is implemented within the context of Great Britain, however, is applicable to any location where similar high resolution multispectral imagery are available. Numéro de notice : A2022-370 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2022.101802 Date de publication en ligne : 19/04/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2022.101802 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100606 [article]

Application of catastrophe theory to spatial analysis of groundwater potential in a sub-humid tropical region: a hybrid approach / Laishram Kanta Singh in Geocarto international, vol 37 n° 3 ([01/03/2022])  

Public [article]  inGeocarto international > vol 37 n° 3 [01/03/2022] . - pp 700 - 719 Titre : Application of catastrophe theory to spatial analysis of groundwater potential in a sub-humid tropical region: a hybrid approach Type de document : Article/Communication Auteurs : Laishram Kanta Singh, Auteur ; Madan K. Jha, Auteur ; V.M. Chowdary, Auteur Année de publication : 2022 Article en page(s) : pp 700 - 719 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] analyse multicritère [Termes IGN] analyse spatiale [Termes IGN] couche thématique [Termes IGN] drainage [Termes IGN] eau souterraine [Termes IGN] gestion de l'eau [Termes IGN] Inde [Termes IGN] pondération [Termes IGN] processus de hiérarchisation analytique [Termes IGN] zone tropicale humide Résumé : (auteur) Geospatial techniques and Multi-Criteria Decision Analysis (MCDA) play a crucial role in the planning and management of land and water resources. GIS-based MCDA technique "Catastrophe theory" has been recently proposed for evaluating groundwater potential. However, the major limitation of "Catastrophe theory" is that only quantitative factors/thematic layers can be used for assessing groundwater potential, though qualitative factors are equally important. To overcome this inherent limitation, a novel GIS-based MCDA approach named "Hybrid Catastrophe" technique is proposed in this study. The "Hybrid Catastrophe" technique integrates the original "Catastrophe theory" with the "Analytic Hierarchy Process (AHP)" to take into account both qualitative and quantitative thematic layers for assessing groundwater potential, thereby improving the reliability and versatility of the original Catastrophe technique. The applicability of "Hybrid Catastrophe" technique is demonstrated through a case study wherein 8 influential thematic layers (both quantitative and qualitative) were considered for assessing groundwater potential. The four quantitative layers were assigned weights based on the "Catastrophe theory" and the remaining four qualitative layers were assigned weights based on the "AHP theory". These thematic layers were integrated in GIS to delineate groundwater potential zones. The "Hybrid Catastrophe" technique yields four groundwater potential zones in the study area: (i) "very good" (covering 16% of the study area), (ii) "good" (54%), (iii) "moderate" (29%) and (iv) "poor" (1%) and its accuracy was found to be 77% that is reasonably high. The proposed "Hybrid Catastrophe" technique is versatile and it can be successfully applied to other parts of the world for evaluating groundwater potential at diverse spatial scales irrespective of agro-climatic, hydrologic and hydrogeologic conditions. Numéro de notice : A2022-343 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2020.1737970 Date de publication en ligne : 11/03/2020 En ligne : https://doi.org/10.1080/10106049.2020.1737970 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100524 [article]

Adaptive feature weighted fusion nested U-Net with discrete wavelet transform for change detection of high-resolution remote sensing images / Congcong Wang in Remote sensing, vol 13 n° 24 (December-2 2021)  

Public [article]  inRemote sensing > vol 13 n° 24 (December-2 2021) . - n° Titre : Adaptive feature weighted fusion nested U-Net with discrete wavelet transform for change detection of high-resolution remote sensing images Type de document : Article/Communication Auteurs : Congcong Wang, Auteur ; Wenbin Sun, Auteur ; Deqin Fan, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] détection de changement [Termes IGN] fusion de données [Termes IGN] image à haute résolution [Termes IGN] pondération [Termes IGN] réseau neuronal siamois [Termes IGN] transformation en ondelettes Résumé : (auteur) The characteristics of a wide variety of scales about objects and complex texture features of high-resolution remote sensing images make deep learning-based change detection methods the mainstream method. However, existing deep learning methods have problems with spatial information loss and insufficient feature representation, resulting in unsatisfactory effects of small objects detection and boundary positioning in high-resolution remote sensing images change detection. To address the problems, a network architecture based on 2-dimensional discrete wavelet transform and adaptive feature weighted fusion is proposed. The proposed network takes Siamese network and Nested U-Net as the backbone; 2-dimensional discrete wavelet transform is used to replace the pooling layer; and the inverse transform is used to replace the upsampling to realize image reconstruction, reduce the loss of spatial information, and fully retain the original image information. In this way, the proposed network can accurately detect changed objects of different scales and reconstruct change maps with clear boundaries. Furthermore, different feature fusion methods of different stages are proposed to fully integrate multi-scale and multi-level features and improve the comprehensive representation ability of features, so as to achieve a more refined change detection effect while reducing pseudo-changes. To verify the effectiveness and advancement of the proposed method, it is compared with seven state-of-the-art methods on two datasets of Lebedev and SenseTime from the three aspects of quantitative analysis, qualitative analysis, and efficiency analysis, and the effectiveness of proposed modules is validated by an ablation study. The results of quantitative analysis and efficiency analysis show that, under the premise of taking into account the operation efficiency, our method can improve the recall while ensuring the detection precision, and realize the improvement of the overall detection performance. Specifically, it shows an average improvement of 37.9% and 12.35% on recall, and 34.76% and 11.88% on F1 with the Lebedev and SenseTime datasets, respectively, compared to other methods. The qualitative analysis shows that our method has better performance on small objects detection and boundary positioning than other methods, and a more refined change map can be obtained. Numéro de notice : A2021-920 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13244971 Date de publication en ligne : 07/12/2021 En ligne : https://doi.org/10.3390/rs13244971 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99244 [article]

Evaluation of watershed soil erosion hazard using combination weight and GIS: a case study from eroded soil in Southern China / Shifa Chen in Natural Hazards, vol 109 n° 2 (November 2021)  

Public [article]  inNatural Hazards > vol 109 n° 2 (November 2021) . - pp 1603 - 1628 Titre : Evaluation of watershed soil erosion hazard using combination weight and GIS: a case study from eroded soil in Southern China Type de document : Article/Communication Auteurs : Shifa Chen, Auteur ; Wen Liu, Auteur ; Yonghui Bai, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1603 - 1628 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] ArcGIS [Termes IGN] bassin hydrographique [Termes IGN] carte d'occupation du sol [Termes IGN] carte thématique [Termes IGN] cartographie des risques [Termes IGN] Chine [Termes IGN] combinaison linéaire ponderée [Termes IGN] entropie [Termes IGN] érosion hydrique [Termes IGN] modèle numérique de surface [Termes IGN] pondération [Termes IGN] processus de hiérarchisation analytique [Termes IGN] risque naturel Résumé : (auteur) Soil erosion is a type of land degradation caused by the interactive interaction of numerous factors, such as natural and socioeconomic conditions of a particular watershed. In this study, a comprehensive integrated methodology was used to evaluate the water erosion hazard in the Zhuxi watershed in Southern China, which is greatly affected by eroded soil. Ten indicators were selected, and a thematic layer map was generated for each indicator using Geographic Information System (GIS). The weight of each evaluation indicator was determined by combining analytic hierarchy process (AHP) with entropy method. Results show that the east and west sections of the Zhuxi watershed have very low and low grades of soil erosion hazards, respectively, and the middle part has the highest hazard. More than 60% of the area has high erosion hazard (moderate to very high). The intensity of soil erosion is lower than its hazard level, especially in high-grade hazard. The obtained results for erosion hazard level can be used to develop conservation strategies for the Zhuxi watershed. This study evaluates soil erosion hazard and offers reference for soil erosion control. Numéro de notice : A2021-851 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1007/s11069-021-04891-7 Date de publication en ligne : 05/07/2021 En ligne : https://doi.org/10.1007/s11069-021-04891-7 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99036 [article]

Geoid determination through the combined least-squares adjustment of GNSS/levelling/gravity networks – a case study in Linyi, China / Dongmei Guo in Survey review, Vol 53 n° 381 (November 2021)  

Permalink

A mean-squared-error condition for weighting ionospheric delays in GNSS baselines / Peter J.G. Teunissen in Journal of geodesy, vol 95 n° 11 (November 2021)  

Permalink

Least squares adjustment with a rank-deficient weight matrix and Its applicability to image/Lidar data processing / Radhika Ravi in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 10 (October 2021)  

Permalink

Observable quality assessment of broadband very long baseline interferometry system / Ming H. Xu in Journal of geodesy, vol 95 n° 5 (May 2021)  

Permalink

Susceptibilité aux glissements de terrain dans la ville d’Al Hoceima et sa périphérie : application de la méthode de la théorie de l’évidence / Taoufik Byou in Geomatica [en ligne], vol 75 n° 1 (Mars 2021)  

Permalink

A comparative study of heterogeneous ensemble-learning techniques for landslide susceptibility mapping / Zhice Fang in International journal of geographical information science IJGIS, vol 35 n° 2 (February 2021)  

Permalink

Identifying urban growth patterns through land-use/land-cover spatio-temporal metrics: Simulation and analysis / Marta Sapena Moll in International journal of geographical information science IJGIS, vol 35 n° 2 (February 2021)  

Permalink

A points of interest matching method using a multivariate weighting function with gradient descent optimization / Zhou Yang in Transactions in GIS, Vol 25 n° 1 (February 2021)  

Permalink

Determination of precise Galileo orbits using combined GNSS and SLR observations / Grzegorz Bury in GPS solutions, vol 25 n° 1 (January 2021)  

Permalink

Evaluation of a neural network with uncertainty for detection of ice and water in SAR imagery / Nazanin Asadi in IEEE Transactions on geoscience and remote sensing, vol 59 n° 1 (January 2021)  

Permalink