Centre de documentation
scientifique

Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks / Sina Mohammadi in ISPRS Journal of photogrammetry and remote sensing, vol 198 (April 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 198 (April 2023) . - pp 272 - 283 Titre : Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks Type de document : Article/Communication Auteurs : Sina Mohammadi, Auteur ; Mariana Belgiu, Auteur ; Alfred Stein, Auteur Année de publication : 2023 Article en page(s) : pp 272 - 283 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage profond [Termes IGN] carte de la végétation [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] cultures [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] série temporelle Résumé : (auteur) Deep learning methods have achieved promising results in crop mapping using satellite image time series. A challenge still remains on how to better learn discriminative feature representations to detect crop types when the model is applied to unseen data. To address this challenge and reveal the importance of proper supervision of deep neural networks in improving performance, we propose to supervise intermediate layers of a designed 3D Fully Convolutional Neural Network (FCN) by employing two middle supervision methods: Cross-entropy loss Middle Supervision (CE-MidS) and a novel middle supervision method, namely Supervised Contrastive loss Middle Supervision (SupCon-MidS). This method pulls together features belonging to the same class in embedding space, while pushing apart features from different classes. We demonstrate that SupCon-MidS enhances feature discrimination and clustering throughout the network, thereby improving the network performance. In addition, we employ two output supervision methods, namely F1 loss and Intersection Over Union (IOU) loss. Our experiments on identifying corn, soybean, and the class Other from Landsat image time series in the U.S. corn belt show that the best set-up of our method, namely IOU+SupCon-MidS, is able to outperform the state-of-the-art methods by scores of 3.5% and 0.5% on average when testing its accuracy across a different year (local test) and different regions (spatial test), respectively. Further, adding SupCon-MidS to the output supervision methods improves scores by 1.2% and 7.6% on average in local and spatial tests, respectively. We conclude that proper supervision of deep neural networks plays a significant role in improving crop mapping performance. The code and data are available at: https://github.com/Sina-Mohammadi/CropSupervision. Numéro de notice : A2023-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2023.03.007 Date de publication en ligne : 29/03/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.03.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103105 [article]

A GIS-based model for automated land suitability assessment for main crops in north-western desert of Egypt (case study: south of Al-Dabaa Corridor) / Adel Shalaby in Applied geomatics, vol 15 n° 1 (March 2023)  

Public [article]  inApplied geomatics > vol 15 n° 1 (March 2023) . - pp 15 - 28 Titre : A GIS-based model for automated land suitability assessment for main crops in north-western desert of Egypt (case study: south of Al-Dabaa Corridor) Type de document : Article/Communication Auteurs : Adel Shalaby, Auteur ; Hossam Khedr, Auteur ; Ehab Youssef, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 15 - 28 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] cultures [Termes IGN] désert [Termes IGN] Egypte [Termes IGN] production agricole [Termes IGN] système d'information géographique [Termes IGN] utilisation du sol Résumé : (auteur) The ever-increasing population causes huge pressure on the areas already inhabited and causes a decrease in an area per capita. This fact necessitates an essential demand for evaluating and classifying the soil according to its agricultural productivity for different crops. This research aimed to evaluate lands which proposed to use in the agricultural field in the south of Al-Dabaa Corridor based on remote sensed data and GIS techniques. Moreover, the future optimum agricultural use planning will be projected based on the land assessments in the study area. Land suitability was evaluated using ALES-arid software for six crops. It was found that 74% of the study area was suitable for one fruit crop, date palm, and about 77.3% for one crop, alfalfa, and also suitable for one vegetable crop, tomato, by 77.1%. Furthermore, it was found that the study area was moderately suitable for other two crops, faba bean and maize (72.7 and 67.8%), and one fruit crop, citrus (70.1%). On the other hand, it was found that the characteristics that most affected the suitability class of fruit crops were soil salinity, soil depth, ESP, slope, and coarse texture. Finally, the study area should go under major reclamation process (removal of the excess salts and improvement of the drainage conditions) in order to obtain the highest production. Numéro de notice : A2023-217 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1007/s12518-022-00474-8 Date de publication en ligne : 30/11/2022 En ligne : https://doi.org/10.1007/s12518-022-00474-8 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103149 [article]

Vine canopy reconstruction and assessment with terrestrial Lidar and aerial imaging / Igor Petrovic in Remote sensing, vol 14 n° 22 (November-2 2022)  

Public [article]  inRemote sensing > vol 14 n° 22 (November-2 2022) . - n° 5894 Titre : Vine canopy reconstruction and assessment with terrestrial Lidar and aerial imaging Type de document : Article/Communication Auteurs : Igor Petrovic, Auteur ; Matej Sečnik, Auteur ; Marko Hočevar, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 5894 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] analyse comparative [Termes IGN] couvert végétal [Termes IGN] défoliation [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] échantillonnage de données [Termes IGN] épandage [Termes IGN] lasergrammétrie [Termes IGN] pas d'échantillonnage au sol [Termes IGN] photogrammétrie aérienne [Termes IGN] Slovénie [Termes IGN] viticulture Résumé : (auteur) For successful dosing of plant protection products, the characteristics of the vine canopies should be known, based on which the spray amount should be dosed. In the field experiment, we compared two optical experimental methods, terrestrial lidar and aerial photogrammetry, with manual defoliation of some selected vines. Like those of other authors, our results show that both terrestrial lidar and aerial photogrammetry were able to represent the canopy well with correlation coefficients around 0.9 between the measured variables and the number of leaves. We found that in the case of aerial photogrammetry, significantly more points were found in the point cloud, but this depended on the choice of the ground sampling distance. Our results show that in the case of aerial UAS photogrammetry, subdividing the vine canopy segments to 5 × 5 cm gives the best representation of the volume of vine canopies. Numéro de notice : A2022-881 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14225894 Date de publication en ligne : 21/11/2022 En ligne : https://doi.org/10.3390/rs14225894 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102203 [article]

Habitats, agricultural practices, and population dynamics of a threatened species: The European turtle dove in France / Christophe Sauser in Biological Conservation, vol 274 (octobre 2022)  

Public [article]  inBiological Conservation > vol 274 (octobre 2022) . - n° 109730 Titre : Habitats, agricultural practices, and population dynamics of a threatened species: The European turtle dove in France Type de document : Article/Communication Auteurs : Christophe Sauser, Auteur ; Loïc Commagnac , Auteur ; Cyril Eraud, Auteur ; et al., Auteur Année de publication : 2022 Projets : 1-Pas de projet / Article en page(s) : n° 109730 Note générale : bibliographie Addendum : "The authors add: This study was partly funded and forms part of OFB's contribution to the European Commission contract ENV.D.3/SER /2019/0021 “Development of a population model and adaptive harvest mechanism for Turtle Dove (Streptopelia turtur)”. The authors would like to apologise for any inconvenience caused." Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] agronomie [Termes IGN] analyse diachronique [Termes IGN] Aves [Termes IGN] habitat animal [Termes IGN] haie [Termes IGN] impact sur l'environnement [Termes IGN] jachère [Termes IGN] lisière [Termes IGN] modèle numérique [Termes IGN] politique de conservation (biodiversité) [Termes IGN] R (langage) Mots-clés libres : tourterelle des bois  Streptopelia turtur Résumé : (auteur) Agricultural changes in recent decades have led to a widespread loss of biodiversity, with habitat loss considered as the main factor in the decline. The European turtle dove is one of the farmland birds that has declined markedly in Europe, leading the IUCN to downgrade its status in 2015 from “Near Threatened” to “Vulnerable”. Knowledge of how habitat factors and agricultural practices influence the turtle dove population is crucial for the conservation of this species through the implementation of targeted measures. Here we investigate how foraging and nesting habitats influence the abundance of turtle doves at national and regional scales, using a 23-year dataset from point counts carried out throughout France, a stronghold country for this species during the breeding season. We found that turtle dove abondance was positively affected by fallow lands, both at national and regional scales. Turtle dove abundance was also negatively affected by fodder crop area at national scale, but the effect was detected in only four of the 13 French regions. We also showed that an increase in hedgerows length had a positive effect on turtle dove abundance. On the other hand, forest edges length showed a bell-shaped trend, suggesting that an increase in forest edges length may have a favourable effect on turtle dove abundance only up to a given threshold. We suggest that targeted conservation measures combining an increase in fallow lands and hedgerows length could allow the stabilisation or even an increase in turtle dove abundance in France, but also in European countries with similar landscapes. Numéro de notice : A2022-687 Affiliation des auteurs : IGN+Ext (2020- ) Autre URL associée : Addendum Thématique : BIODIVERSITE/GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.biocon.2022.109730 Date de publication en ligne : 09/09/2022 En ligne : https://doi.org/10.1016/j.biocon.2022.109730 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101612 [article]

Comparison of deep neural networks in detecting field grapevine diseases using transfer learning / Antonios Morellos in Remote sensing, vol 14 n° 18 (September-2 2022)  

Public [article]  inRemote sensing > vol 14 n° 18 (September-2 2022) . - n° 4648 Titre : Comparison of deep neural networks in detecting field grapevine diseases using transfer learning Type de document : Article/Communication Auteurs : Antonios Morellos, Auteur ; Xanthoula Eirini Pantazi, Auteur ; Charalampos Paraskevas, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4648 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection de changement [Termes IGN] extraction de traits caractéristiques [Termes IGN] Grèce [Termes IGN] jeu de données [Termes IGN] maladie cryptogamique [Termes IGN] maladie phytosanitaire [Termes IGN] viticulture Résumé : (auteur) Plants diseases constitute a substantial threat for farmers given the high economic and environmental impact of their treatment. Detecting possible pathogen threats in plants based on non-destructive remote sensing and computer vision methods offers an alternative to existing laboratory methods and leads to improved crop management. Vine is an important crop that is mainly affected by fungal diseases. In this study, photos from healthy leaves and leaves infected by a fungal disease of vine are used to create disease identification classifiers. The transfer learning technique was employed in this study and was used to train three different deep convolutional neural network (DCNN) approaches that were compared according to their classification accuracy, namely AlexNet, VGG-19, and Inception v3. The above-mentioned models were trained on the open-source PlantVillage dataset using two training approaches: feature extraction, where the weights of the base deep neural network model were frozen and only the ones on the newly added layers were updated, and fine tuning, where the weights of the base model were also updated during training. Then, the created models were validated on the PlantVillage dataset and retrained using a custom field-grown vine photo dataset. The results showed that the fine-tuning approach showed better validation and testing accuracy, for all DCNNs, compared to the feature extraction approach. As far as the results of DCNNs are concerned, the Inception v3 algorithm outperformed VGG-19 and AlexNet in almost all the cases, demonstrating a validation performance of 100% for the fine-tuned strategy on the PlantVillage dataset and an accuracy of 83.3% for the respective strategy on a custom vine disease use case dataset, while AlexNet achieved 87.5% validation and 66.7% accuracy for the respective scenarios. Regarding VGG-19, the validation performance reached 100%, with an accuracy of 76.7%. Numéro de notice : A2022-768 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs14184648 Date de publication en ligne : 17/09/2022 En ligne : https://doi.org/10.3390/rs14184648 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101794 [article]

Analysis of the land suitability for paddy fields in Tanzania using a GIS-based analytical hierarchy process / Ahmad Al-Hanbali in Geo-spatial Information Science, vol 25 n° 2 ([01/06/2022])  

Permalink

Precise crop classification of hyperspectral images using multi-branch feature fusion and dilation-based MLP / Haibin Wu in Remote sensing, vol 14 n° 11 (June-1 2022)  

Permalink

Spatial-temporal variation of satellite-based gross primary production estimation in wheat-maize rotation area during 2000–2015 / Wenquan Xie in Geocarto international, vol 37 n° 9 ([15/05/2022])  

Permalink

Alternative procedure to improve the positioning accuracy of orthomosaic images acquired with Agisoft Metashape and DJI P4 multispectral for crop growth observation / Toshihiro Sakamoto in Photogrammetric Engineering & Remote Sensing, PERS, vol 88 n° 5 (May 2022)  

Permalink

Crop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information / Murali Krishna Gumma in Geocarto international, vol 37 n° 7 ([15/04/2022])  

Permalink

Assessment of land suitability potentials for winter wheat cultivation by using a multi criteria decision Support-Geographic information system (MCDS-GIS) approach in Al-Yarmouk Basin (Syria) / Safwan Mohammed in Geocarto international, vol 37 n° 6 ([01/04/2022])  

Permalink

Parcel-based summer maize mapping and phenology estimation combined using Sentinel-2 and time series Sentinel-1 data / Yanyan Wang in International journal of applied Earth observation and geoinformation, vol 108 (April 2022)  

Permalink

Projections of climate change impacts on flowering-veraison water deficits for Riesling and Müller-Thurgau in Germany / Chenyao Yang in Remote sensing, vol 14 n° 6 (March-2 2022)  

Permalink

Comparing methods to extract crop height and estimate crop coefficient from UAV imagery using structure from motion / Nitzan Malachy in Remote sensing, vol 14 n° 4 (February-2 2022)  

Permalink

In situ C-band data for wheat physiological functioning monitoring in the South Mediterranean region / Nadia Ouaadi (2022)  

Permalink