Kenji Ose

Kenji Ose
French National Institute for Agriculture, Food, and Environment (INRAE) | INRAE · Department of Territories

About

65
Publications
9,942
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,051
Citations
Citations since 2017
33 Research Items
698 Citations
2017201820192020202120222023050100150
2017201820192020202120222023050100150
2017201820192020202120222023050100150
2017201820192020202120222023050100150
Introduction
Kenji Ose currently works at the Department of Territories, National Research Institute of Science and Technology for Environment and Agriculture. Kenji does research in Biogeography, Geoinformatics (GIS) and Remote Sensing.

Publications

Publications (65)
Poster
Full-text available
The THEIA data and services centre (www.theia-land.fr) is a consortium of 12 French public institutions involved in Earth observation and environmental sciences (CEA,CEREMA, CIRAD, CNES, IGN, INRA, CNRS, IRD, Irstea, Météo France, AgroParisTech, and ONERA). THEIA was initiated in 2012 with the objective of increasing the use of space data by the sc...
Article
Cet article propose un cadre d'évaluation des impacts économiques des Infrastructures de Données Géographiques et Spatiales (IDGS), à partir de l'exemple de GEOSUD et des cartes de coupes rases relatives à la gestion des forêts. L'évaluation est réalisée à partir d'une enquête en ligne auprès des services de l'État chargés du contrôle des coupes ra...
Article
Full-text available
This letter introduces the new European Settlement Map (ESM) production workflow, presents some indicatory results, and discusses the validation process. Unlike the previous ESM versions, the built-up (BU) extraction is realized through supervised learning (not only by means of image filtering and processing techniques) based on textural and morpho...
Conference Paper
Full-text available
A major issue affecting optical imagery is the presence ofclouds. The need of cloud-free scenes at specific date is cru-cial in a number of operational monitoring applications. Onthe other hand, the cloud-insensitive SAR sensors are a solidasset and they provide orthogonal information with respect tooptical satellite, that enable the retrieval of i...
Conference Paper
In this work we introduce and evaluate a deep learning model, mbCNN, that combines together satellite imagery and Volunteer Geographical Information (VGI) data to deal with different types of built-up surfaces. Differently from most of the previous works that only consider Urban/Non-Urban settings involving only one urban LULC class, here, we inves...
Article
Nowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is represented by the Sentinel-2 mission, which provides images at high spatial resolution (up to 10 m) with high temporal revisit period (every 5 days), which can be organized in Satellite Image Time Series (SITS). While the use of SITS has bee...
Article
The expansion of satellite technologies makes remote sensing data abundantly available. While the access to such data is no longer an issue, the analysis of this kind of data is still challenging and time consuming. In this paper, we present an object-oriented methodology designed to handle multi-annual Satellite Image Time Series (SITS). This meth...
Article
Full-text available
Modern Earth Observation systems provide remote sensing data at different temporal and spatial resolutions. Among all the available spatial mission, today the Sentinel-2 program supplies high temporal (every five days) and high spatial resolution (HSR) (10 m) images that can be useful to monitor land cover dynamics. On the other hand, very HSR (VHS...
Book
In this work we introduce and evaluate a deep learning model, mbCNN, that combines together satellite imagery and Volunteer Geographical Information (VGI) data to deal with different types of built-up surfaces. Differently from most of the previous works that only consider Urban/Non-Urban settings involving only one urban LULC class, here, we inves...
Preprint
Full-text available
Radar and Optical Satellite Image Time Series (SITS) are sources of information that are commonly employed to monitor earth surfaces for tasks related to ecology, agriculture, mobility, land management planning and land cover monitoring. Many studies have been conducted using one of the two sources, but how to smartly combine the complementary info...
Article
Full-text available
The use of Very High Spatial Resolution (VHSR) imagery in remote sensing applications is nowadays a current practice whenever fine-scale monitoring of the earth’s surface is concerned. VHSR Land Cover classification, in particular, is currently a well-established tool to support decisions in several domains, including urban monitoring, agriculture,...
Preprint
Nowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is represented by the Sentinel-2 mission, which provides images at high spatial resolution (up to 10m) with high temporal revisit period (every 5 days), which can be organized in Satellite Image Time Series (SITS). While the use of SITS has been...
Preprint
Nowadays, Earth Observation systems provide a multitude of heterogeneous remote sensing data. How to manage such richness leveraging its complementarity is a crucial chal- lenge in modern remote sensing analysis. Data Fusion techniques deal with this point proposing method to combine and exploit complementarity among the different data sensors. Con...
Article
Full-text available
The last millennium is defined as a “stable” climatic period with anomalies such as the Little Ice Age (LIA: ~1450 AD to 1850 AD), a period marked by low temperatures and associated with a glacier advance. Also the Medieval Climate Anomaly (MCA: ~950 AD to 1250 AD), considered as a period at least as warm as nowadays and associated with glacier ret...
Preprint
Full-text available
Modern Earth Observation systems provide sensing data at different temporal and spatial resolutions. Among optical sensors, today the Sentinel-2 program supplies high-resolution temporal (every 5 days) and high spatial resolution (10m) images that can be useful to monitor land cover dynamics. On the other hand, Very High Spatial Resolution images (...
Article
Full-text available
Modern Earth Observation systems provide sensing data at different temporal and spatial resolutions. Among optical sensors, today the Sentinel-2 program supplies high-resolution temporal (every 5 days) and high spatial resolution (10m) images that can be useful to monitor land cover dynamics. On the other hand, Very High Spatial Resolution images (...
Chapter
This chapter presents the various treatments offered by QGIS for network analysis and routing. After a quick definition of networks and graphs, it discusses the rules for construction and verification of networks using GIS. The chapter focuses on the presentation of examples of hydrographic network development and analysis. It consists of several p...
Chapter
Geospatial data abstraction library (GDAL) is a free library dedicated to the reading and writing of geospatial data in both raster and vector format. GDAL runs on all modern operating systems (Unix-like OS, Windows). Quantum geographic information system (QGIS) also provides access to most GDAL utility programs, giving users the ability to process...
Chapter
The French Ministry of Agriculture, in charge of forest policies, has commissioned the development of a clear-cuts detection method with optical satellite images. Mapping the clear-cuts relies on a change detection method based on two satellite images acquired between two consecutive years, during summer when trees show their leaves. This chapter p...
Book
This chapter presents the various treatments offered by QGIS for network analysis and routing. After a quick definition of networks and graphs, it discusses the rules for construction and verification of networks using GIS. The chapter focuses on the presentation of examples of hydrographic network development and analysis. It consists of several p...
Book
Geospatial data abstraction library (GDAL) is a free library dedicated to the reading and writing of geospatial data in both raster and vector format. GDAL runs on all modern operating systems (Unix-like OS, Windows). Quantum geographic information system (QGIS) also provides access to most GDAL utility programs, giving users the ability to process...
Book
This chapter presents the various treatments offered by QGIS for network analysis and routing. After a quick definition of networks and graphs, it discusses the rules for construction and verification of networks using GIS. The chapter focuses on the presentation of examples of hydrographic network development and analysis. It consists of several p...
Book
Geospatial data abstraction library (GDAL) is a free library dedicated to the reading and writing of geospatial data in both raster and vector format. GDAL runs on all modern operating systems (Unix‐like OS, Windows). Quantum geographic information system (QGIS) also provides access to most GDAL utility programs, giving users the ability to process...
Book
The French Ministry of Agriculture, in charge of forest policies, has commissioned the development of a clear‐cuts detection method with optical satellite images. Mapping the clear‐cuts relies on a change detection method based on two satellite images acquired between two consecutive years, during summer when trees show their leaves. This chapter p...
Book
The French Ministry of Agriculture, in charge of forest policies, has commissioned the development of a clear‐cuts detection method with optical satellite images. Mapping the clear‐cuts relies on a change detection method based on two satellite images acquired between two consecutive years, during summer when trees show their leaves. This chapter p...
Chapter
Having begun in the 1970s with the American Landsat program, the use of optical satellite images for civilian purposes has since experienced significant technological advancements. In the space of 10 years, the images provided by Earth observation satellites have gone from high to very high spatial resolution, from a decametric resolution to a subm...
Book
Having begun in the 1970s with the American Landsat program, the use of optical satellite images for civilian purposes has since experienced significant technological advancements. In the space of 10 years, the images provided by Earth observation satellites have gone from high to very high spatial resolution, from a decametric resolution to a subm...
Article
Full-text available
The Phased Array L-band Synthetic Aperture Radar (PALSAR-1) has provided very useful images dataset for several applications such as forestry. L-band radar measurements have been widely used but with somewhat contradictory conclusions on the potential of this radar wavelength to estimate the aboveground biomass. The first objective of this study wa...
Conference Paper
The objective of this study was to analyze the L-band SAR backscatter sensitivity to forest biomass for Eucalyptus plantations. The results showed that the radar signal is highly dependent on biomass only for values lower than 50 t/ha, which corresponds to plantations of approximately three years of age. Next, Random Forest regressions were perform...
Article
Full-text available
TerraSAR-X data are processed for an “operational” mapping of bare soils moisture in agricultural areas. Empirical relationships between TerraSAR-X signal and soil moisture were established and validated over different North European agricultural study sites. The results show that the mean error on the soil moisture estimation is less than 4% regar...
Book
Full-text available
Une énergie facilement disponible et bon marché a permis l'amélioration de notre qualité de vie au cours des deux derniers siècles. Cette disponibilité constitue un pilier fondateur de notre société technologique actuelle. Avec la croissance démographique mondiale qui portera à 9 milliards le nombre d'habitants sur la planète en 2050, comment faire...
Book
Dans ce livre, le Cemagref, institut de recherche en sciences et technologies pour l'environnement, fait le point de ses travaux scientifiques menés sur la forêt. Pourquoi une recherche sur la forêt ? D'abord parce qu'elle occupe plus d'un quart de la surface de notre territoire métropolitain. Ensuite, parce qu'elle fournit tout un ensemble de serv...
Data
Maps showing the geographic location of occurrence records of 18 anopheline species across Cameroon. Collections were conducted inside human dwellings in 386 villages throughout Cameroon between 1998 and 2007 (Updated from Antonio-Nkondjio et al [22]). Asterisks indicate known malaria vectors.
Article
Full-text available
Suitability of environmental conditions determines a species distribution in space and time. Understanding and modelling the ecological niche of mosquito disease vectors can, therefore, be a powerful predictor of the risk of exposure to the pathogens they transmit. In Africa, five anophelines are responsible for over 95% of total malaria transmissi...
Conference Paper
The chief aim of the PARAGE project is to help public institutions and organizations to observe and analyze the impact of farming practices on the natural and urban environment using satellite data in combination with existing data and expertise. The project's 3 pilot sites in French Guiana, Martinique and Guadeloupe have permit to generate map pro...
Article
Full-text available
Ongoing lineage splitting within the African malaria mosquito Anopheles gambiae is compatible with ecological speciation, the evolution of reproductive isolation by divergent natural selection acting on two populations exploiting alternative resources. Divergence between two molecular forms (M and S) identified by fixed differences in rDNA, and cha...
Article
Full-text available
Speciation among members of the Anopheles gambiae complex is thought to be promoted by disruptive selection and ecological divergence acting on sets of adaptation genes protected from recombination by polymorphic paracentric chromosomal inversions. However, shared chromosomal polymorphisms between the M and S molecular forms of An. gambiae and insu...
Data
Full-text available
Distribution of chromosomal arrangements and molecular forms of An. gambiae for the most likely number of genetic clusters in the population (K = 3). Arrangement frequencies in each genetic cluster, and proportion of membership of each molecular form to the three genetic clusters identified as the most likely outcome by the Bayesian multilocus assi...
Data
Full-text available
Ecological Niche Factor Analysis of Anopheles arabiensis in Cameroon. Correlation between the ENFA factors and the eco-geographical variables (EGVs, see Methods) for An. arabiensis. Factor I explains 100% of the marginality. The percentages indicate the amount of specialization accounted for by each factor.
Data
Full-text available
Ecological Niche Factor Analysis of Anopheles gambiae molecular form M in Cameroon. Correlation between the ENFA factors and the eco-geographical variables (EGVs, see Methods) for An. gambiae molecular form M. Factor I explains 100% of the marginality. The percentages indicate the amount of specialization accounted for by each factor.
Data
Full-text available
Model validation statistics for Habitat Suitability maps. Model evaluation indices for the habitat suitability maps of the S and M molecular forms of An. gambiae and An. arabiensis in Cameroon, computed with 10-fold cross-validation. Higher means indicate a higher consistency with the evaluation datasets. The lower the standard deviation (SD), the...
Data
Full-text available
Bayesian assignment of An. gambiae karyotypes to genetic clusters using the software STRUCTURE. Posterior probabilities for K = 1 to K = 10 using chromosomal inversions (A) and systems of inversions (B), see text for details. In both cases, clustering of individuals into three groups (K = 3) was the most probable solution. Open symbols represent th...
Data
Full-text available
Admixture probabilities of different karyotypes. Average probability (± SD) that a given karyotype belongs to the population of origin, in this case the recorded molecular form.
Data
Full-text available
Vegetation Classes in Burkina Faso. Floristic associations defining the four main vegetation classes covering Burkina Faso that were used as supplementary EGVs in the DCA.
Data
Full-text available
Ecological Niche Factor Analysis coefficients for Anopheles gambiae molecular form M. Factor loads of the 15 environmental predictors (EGVs) for An. gambiae s.s. form M. Other symbols and explanations as for additional file 4.
Data
List of Sampled Locations. Names and geographical coordinates of sampled villages, dates of collection, and sample size of collected and identified mosquitoes.
Data
Full-text available
Ecological Niche Factor Analysis statistics. Marginality, Specialization, and Tolerance indices for the three taxa of the An. gambiae s.l. complex across Burkina Faso.
Data
Ecological Niche Factor Analysis coefficients for An. arabiensis. Factor loads of the 15 environmental predictors (EGVs). Factor 1 explains 100% of the marginality, the second and following factors explain increasing amounts of the specialization. Positive values of marginality indicate that An. arabiensis was found in locations with higher values...
Data
Full-text available
Ecological Niche Factor Analysis coefficients for Anopheles gambiae molecular form S. Factor loads of the 15 environmental predictors (EGVs) for An. gambiae s.s. form S. Other symbols and explanations as for additional file 4.
Data
Full-text available
Discriminant analysis of habitat partitioning. Relative frequency distribution of the cell scores occupied by forms/species of the An. gambiae complex in relation to the global distribution of all cells in the study area along the discriminant factor for which species pairs differed the most.
Data
Full-text available
Maximum likelihood estimates of population structure. Values of Ln [Pr(X|K)], representing the probability of obtaining the observed genetic data X conditional on the presence of K populations (i.e. "clusters"), plotted against the number of genetic clusters K assumed in the population. Error bars are standard deviations of five replicate analyses...
Article
Full-text available
In the context of mandatory European regulations regarding natural resources and territorial management, the rural and agricultural institutions of the French Caribbeans and French Guiana need reliable and up to date geo-information. The PARAGE Consortium (SpotImage, IRD, CIRAD and SIGbea) gathers operational means and scientific know-how to addres...

Network

Cited By

Projects

Projects (4)
Project
Modern Earth Observation systems provide huge amount of data from different sensors at different temporal, spatial and spectral resolutions. Such amount of information is commonly represented by means of multispectral imagery and, due to its complexity, it requires new techniques and method to be correctly exploited to extract valuable knowledge. The MDL4EO team (Machine and Deep Learning for Earth Observation) at the UMR TETIS (Montpellier, France) has the objective to scientifically contribute to this new era providing AI methods and algorithms to extract valuable knowledge from modern Earth Observation Data. The amount of data being collected by remote sensors is accelerating rapidly and we cannot manage them manually, this is why machine/deep learning lends itself well to remote sensing. More in detail, some of the research questions of the MDL4EO team are the follows: - How to intelligently exploit Time Series of Satellite Images to leverage temporal dynamics - How to combine/fusion together multi spectral/temporal/resolution/sensor information with the objective to add value to the information thanks to the combination of multi source - How to transfer knowledge from different geographical Area: transfer land cover classification model from one site (i.e. France) to another one geographically distant (i.e. Africa). It’s time to fill the gap between Remote Sensing and AI. MDL4EO is working on that direction bringing together different expertises: Data Science, Computer Vision, Machine Learning, Remote Sensing and Geoinformatics.