-
[hal-04997560] Data paper: A goat behaviour dataset combining labelled behaviours and accelerometer data for training Machine Learning detection models
This paper presents a dataset of accelerometer data and corresponding video-annotated behaviours from eight indoor dairy Alpine goats. Animals were equipped with 3D-accelerometers attached to their ears for 24 consecutive hours and recorded at a frequency of 5 Hz. Video recordings for this period were also obtained. Activities associated with positional, feeding and social behaviours were annotated over two daylight periods, for a total of 11 hours per goat, by a trained observer assuring high precision and consistency. This dataset can be used independently or complement an existing dataset for training supervised Machine Learning models for the detection of goat behaviour. It contributes to improving the robustness of such models by incorporating behavioural signals specific to indoor-housed goats.
ano.nymous@ccsd.cnrs.fr.invalid (Sarah Mauny) 19 Mar 2025
https://hal.inrae.fr/hal-04997560v1
-
[hal-05178193] Spectral indices in remote sensing of soil: definition, popularity, and issues. A critical overview
Serving as a powerful proxy in remote sensing studies, spectral indices can generate meaningful environmental interpretation from either raw or atmospherically corrected spectral data, and characterise and quantify some important properties of various objects on Earth’s surface. However, while numerous spectral indices have been developed over time, since the very launch of civilian satellites until now, some critical issues in their usage, such as comparability, remain scarcely studied, which may lead to incorrect, inconsistent, and unreliable results. In this study, we collected 471 spectral indices of various environment components (vegetation, water, and soil) that might be leveraged for soil studies, and traced their popularity in scientific publications over the past decades. The bibliometric analysis revealed a growing interest and utilisation of spectral indices as Earthobserving satellite technology advanced. Based on both literature and, for sake of complementation and illustration, some targeted regional-scale case studies, we discuss the issues of naming confusion, comparability, applicability, accuracy trade-offs, and reproducibility of using spectral indices. Overall, this overview provides an extensive list of spectral indices, both soil indices and soil-related indices, that can be useful for characterising these environment components by remote sensing. It draws attention to some misuses and confusions that must be avoided to prevent scientific pitfalls. The comparisons between different spectral indices, sensors, and correction methods, highlight the confusing effects that the misuse and non-standardised practices of the spectral indices useful for soil, may have on soil property mapping and monitoring. Insights to the judicious and appropriate usage of spectral indices in the remote sensing of soil are provided.
ano.nymous@ccsd.cnrs.fr.invalid (Qianqian Chen) 24 Jul 2025
https://hal.inrae.fr/hal-05178193v1
-
[hal-05110984] Advancing agroecology and sustainability with agricultural robots at field level: A scoping review
Agricultural robots show a growing potential to improve resource management and reduce the environmental impacts of farming. However, the evaluation of robots’ contribution to support sustainable farming is still lacking. This study specifically reviewed the operationalization of four agroecological principles at the field level: recycling, soil health, biodiversity and synergy. To this aim, a scoping review was conducted on the Scopus database, with a query within titles, abstracts, and author keywords mentioning robots, and agroecology or sustainability. The body of literature was screened to include only open field robots. The resulting 78 documents were coded inductively on three macro areas: (1) academic background, (2) robot operations, (3) contribution to agroecology principles, whether explicitly or implicitly mentioned. The results highlight that robots operationalize agroecology principles through non-chemical and selective weeding to preserve diversity and soil health, lighter designs that reduce soil compaction, and advanced data collection systems to optimize resource use and synergy. Solar-powered robots represent early steps toward recycling, but this principle remains understudied. The discussion expands on the potential of robotics in other innovative approaches for sustainable agriculture, such as agroforestry, conservation agriculture, and novel farming system design. Key challenges include ensuring farmers are enabled to master data collection and management, as well as integrating high-tech robotics with low-tech solutions. These efforts are critical for leveraging agricultural robotics to advance agroecology and sustainability across diverse farming systems.
ano.nymous@ccsd.cnrs.fr.invalid (Mohammad Naim) 13 Jun 2025
https://hal.science/hal-05110984v1
-
[hal-05161584] Cross-Species Predictions of Chromatin Annotations using Neural Networks
A better knowledge of functional annotations of livestock species can be a lever to link genome to phenome. The genomes of most livestock species have already been sequenced. However, data describing gene regulation mechanisms and chromatin state are insufficient. In contrast, abundant human and mouse data allowed the training of powerful deep learning algorithms. Here, we propose to use 3 artificial neural networks (Deepbind, DeepSEA and Enformer), trained with human and mouse data, to predict annotations on the pig, cattle, chicken and European seabass genomes. The predictions are then compared with experimental data to evaluate the cross-species performance of the neural networks. First, human-trained neural network predictions performed on the mouse reference genome showed varying levels of accuracy depending on the experiment, with the higher performance for H3K4me3 (auPRC=0.624). Second, the predictions on the pig, cattle and chicken genomes showed similar (lower mean auPRC=0.385+/-0.233) and better performances than those on the seabass genome (mean auPRC=0.144+/-0.096). Third, the evaluation of the impact of genomic features on the predictions highlighted better performances for CpG island and 5'UTR than other features. Finally, the comparison of predictions between different pig breeds with high genetic diversity demonstrated that genetic variability does not affect the performance, but rather observations. To conclude, we showed that the 3 neural networks evaluated can be used to predict annotations on non-mammalian genomes with similar performances (chicken), but not on genomes of organisms phylogenetically too distant (seabass).
ano.nymous@ccsd.cnrs.fr.invalid (Noémien Maillard) 14 Jul 2025
https://hal.inrae.fr/hal-05161584v1
-
[hal-05161904] Generation of metabolomic-informed models of metabolism for microbial communities
The generation of genome-wide metabolic networks has become a routine analysis for individual organisms or communities communities. However, these automatically generated metabolic networks are incomplete because they are constructed by based on the combination of gene annotation and reactions available in generic available in generic databases (Metacyc, BIGG, ModelSEED...). These are oriented towards well-known organisms or organisms or model organisms and miss out on important functions secondary metabolism. We propose to combine metabolomic data analysis, metabolic modelling and annotation metabolic modelling and annotation mining to build high-quality models of high quality models of microbial metabolism with the long-term aim of better understanding of microbial communities. In terms of application of the methods to plant microbial communities, we hope that the plant microbial communities, we hope that the newly developed models will provide a better understanding of the process of microbial recruitment by the plant: metabolic functions involved, micro-organisms associated with these functions.
ano.nymous@ccsd.cnrs.fr.invalid (Coralie Muller) 15 Jul 2025
https://inria.hal.science/hal-05161904v1
-
[hal-05163368] Statistical method inference cMFA for multi-omics data integration in microbial community models
Understanding microbial community functions is challenging due to complex interactions and assembly mechanisms; however, advances in sequencing have enabled the collection of multi-omics data, including population counts and metabolomic or metatranscriptomic data. Our main objective is to develop a mathematical model capable of integrating time series of multiomics data at a community scale. We introduce the community metabolic flux analysis (cMFA) method, which generalizes metabolic flux analyses,, using a list of time series data of experimentally measured production and consumption rates of metabolites and microorganism growth. We aim to infer, for each member of the microbial community, the intracellular distribution of metabolic fluxes. This is a high-dimensional constrained linear regression problem, informed by mass conservation constraints and metatranscriptomic data, encoded in the penalty term. The difficulty here is in accurately inferring latent internal rates from a few observations of exchange fluxes. We evaluated the cMFA method on synthetic data from dynamic models of increasingly complex microbial communities, based on metabolic models of different mutants of Escherichia coli using dynamic flux balance analysis (dFBA). Synthetic metatranscriptomic data were obtained from internal metabolic fluxes in the dynamic model. Different regularization terms were tested, including different levels of sparsity, for the selected penalty weight . To evaluate the robustness of the method, multiple benchmarks were tested. These included assessments of the robustness of the method to data noise, incomplete meta-transcriptomic data, and inaccurate prior knowledge of metabolic import rates. Currently, we are working with real data and expanding the study to a larger microbial community.
ano.nymous@ccsd.cnrs.fr.invalid (Sthyve Junior Tatho Djeanou) 15 Jul 2025
https://inria.hal.science/hal-05163368v1
-
[hal-05194387] Bread wheat pangenome Graphs
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Pauline Lasserre) 31 Jul 2025
https://hal.inrae.fr/hal-05194387v1
-
[hal-05086840] Spatiotemporal modeling of host–pathogen interactions using level-set method
<div><p>Phenotyping host-pathogen interactions is crucial for understanding infectious diseases in plants. Traditionally, this process has relied on visual assessments or manual measurements, which can be subjective and labor-intensive. Recent advances in image processing and mathematical modeling enable the precise and high-throughput phenotyping of plant symptoms. Among many challenges, considering local deformations of symptoms and host tissues is difficult in plant pathology. In this study, we address this question using a level-set method. We propose an innovative approach in plant pathology that allows one to reconstruct the continuous deformation of leaf and lesion contours from daily image sequences of inoculated leaves. We consider pea stipules inoculated by the fungal pathogen Peyronellaea pinodes as an example pathosystem. After extracting lesion and stipule contours from daily visible images, we use the level-set method to track their deformations within image sequences. The visual assessment of model adequacy, along with the Jaccard Index and relative error metrics, demonstrated strong overall performance. Results showed a gradual decrease in model accuracy over time for leaf contours, while lesion contours exhibited a higher relative error on the first targeted date. These findings highlight the robustness of our method while identifying specific challenges in early lesion detection. We finish by discussing the interest in this method based on partial differential equations for the study of host-pathogen interactions, especially the development of original phenotyping methods in plant pathology.</p></div>
ano.nymous@ccsd.cnrs.fr.invalid (Sheila Rae Permanes) 02 Jun 2025
https://hal.inrae.fr/hal-05086840v2
-
[hal-05156704] A systematic classification of agrobots to inform farmers’ choice and clarify market development
The agricultural robots (agrobots) market is rapidly expanding yet remains fragmented with limited categorisation to inform farmers’ choices. This study analysed the commercial description of 71 currently available robots on the market through a cluster analysis. K-means clustering allowed the identification of five clusters characterised by significant differences in turning radius and energy source (p&gt;0.05), and in weight and battery life (p&lt;0.1). Results also highlighted that energy sources significantly impact price, with endothermic agrobots generally being more expensive than electric ones and hybrid models showing intermediate pricing. This categorisation illustrates current market trends while providing an updated reference framework for key stakeholders such as agritech companies, farmers, investors, and policymakers.
ano.nymous@ccsd.cnrs.fr.invalid (Mohammad Naim) 10 Jul 2025
https://hal.inrae.fr/hal-05156704v1
-
[hal-05117608] The future of systems genetics in farm animal sciences
Farm animal species are under intense selection on relatively small population sizes. Genetic and genomic selection has provided remarkable genetic gains in the last century. Nevertheless, current methods aiming to link genome to phenome in such populations remain limited, notably due to the difficulty to identify causal variants for complex traits. The diversity of species as well as breeds in livestock has diluted the number of genomic datasets available for each genome as compared to model organisms or human diseases. In this article we propose a systems genetics approach as an opportunity to go beyond current limits, taking advantage of novel computational development allowing integration of omics datasets from different analyses across species. A major challenge is that systems genetics requires careful but efficient data and metadata management, as well as rigorous statistical and strategies on which approach to use. Here, we highlight examples of the broad contribution systems genetics can bring to farm animal sciences, particularly across species, notably in the genome-to-phenome field within the larger scope of agricultural challenges including adaptation to environmental changes and animal welfare.
ano.nymous@ccsd.cnrs.fr.invalid (Guillaume Devailly) 17 Jun 2025
https://hal.science/hal-05117608v1
-
[hal-05105798] Inference Method cMFA for multi-omics data integration in microbial community models
Understanding microbial community functions is challenging due to complex interactions and assembly mechanisms. However, advances in sequencing technologies have enabled the collection of multi-omics data, including population counts and metabolomic or metatranscriptomic profiles. Our main objective is to develop a mathematical model capable of integrating time series of multi-omics data at the community scale. We introduce the community Metabolic Flux Analysis (cMFA) method: a biology-informed inference approach that generalizes classical Metabolic Flux Analysis. This high-dimensional analytical framework aims to estimate metabolic fluxes by integrating multi-omics data. Specifically, we aim to (i) quantify, for each member of the microbial community, their individual contributions to overall community dynamics based on external measurements of metabolite dynamics, and (ii) infer their intracellular distribution of metabolic fluxes. The difficulty here is in accurately inferring latent internal rates from a few observations of community-scale consumption and production rates for extracellular metabolites. We evaluated the cMFA method using synthetic data generated from dynamic models of microbial communities of increasing complexity using dynamic flux balance analysis, based on metabolic models of different Escherichia coli mutants. Synthetic metatranscriptomic data were obtained from internal metabolic fluxes simulated in the dynamic model. To assess the robustness of the method, we benchmarked its performance under varying levels of experimental noise.
ano.nymous@ccsd.cnrs.fr.invalid (Sthyve Junior Tatho Djeanou) 10 Jun 2025
https://hal.science/hal-05105798v1
-
[hal-05099666] Lucerne genetic diversity for living mulch: identifying key traits and evaluating their impacts on wheat development
Context Lucerne (Medicago sativa) can offer ecosystem services as a perennial living mulch, supporting annual cash crops through weed suppression and nitrogen fixation. However, trials with wheat have shown that current lucerne varieties are excessively competitive, leading to reduced wheat yields. Aims This study aimed to analyse the diversity within the M. sativa complex to identify traits that enhance lucerne effectiveness as a living mulch, focusing on the competition for light and nitrogen among lucerne, wheat and weeds. Methods Thirty diverse lucerne accessions were cultivated as living mulch with a winter wheat, over 2 years. Lucerne dormancy and growth habit effects were evaluated on wheat relative dominance during the early stages and on weed abundance. In later stages, the effects of lucerne height and lodging on wheat biomass and nitrogen status were also assessed. Key results Results indicated that lucerne dormancy and growth habit influenced wheat growth during early stages, with dormant and prostrate lucerne accessions reducing competition and enhancing wheat dominance. However, non-dormant and erect lucerne accessions effectively suppressed weeds but competed intensely with wheat. Tall and erect lucerne accessions supported wheat nitrogen status in the second year only. Lucerne lodging affected wheat growth, with tall lucerne reducing wheat biomass in the first year. Conclusions Lucerne should exhibit slow growth, moderate height, and low lodging to optimise its benefits. No variety in our panel exhibited all these desirable traits. Implications These findings highlight the need for breeding programs to combine lucerne beneficial traits as a living mulch into new varieties.
ano.nymous@ccsd.cnrs.fr.invalid (Zineb El Ghazzal) 05 Jun 2025
https://hal.inrae.fr/hal-05099666v1
-
[hal-05105572] cMFA Inference method for multi-omics data integration in microbial community models
Understanding the functioning of microbial communities is challenging due to the complexity of their interactions and assembly mechanisms. However, advances in sequencing technologies have enabled the collection of multi-omics data, including population counts and metabolomic or metatranscriptomic profiles. Our main objective is to develop a mathematical model capable of integrating time series of multi-omics data at the community scale. We introduce the community Metabolic Flux Analysis (cMFA) method: a biology-informed inference approach that generalizes classical Metabolic Flux Analysis. This high-dimensional analytical framework aims to estimate metabolic fluxes by integrating multi-omics data. Specifically, we aim to (i) quantify, for each member of the microbial community, their individual contributions to overall community dynamics based on external measurements of metabolite dynamics, and (ii) infer their intracellular distribution of metabolic fluxes. The difficulty here is in accurately inferring latent internal rates from a few observations of community-scale consumption and production rates for extracellular metabolites. We evaluated the cMFA method using synthetic data generated from dynamic models of microbial communities of increasing complexity using dynamic flux balance analysis, based on metabolic models of different Escherichia coli mutants. Synthetic metatranscriptomic data were obtained from internal metabolic fluxes simulated in the dynamic model. To evaluate the robustness of the method, multiple benchmarks were tested. These included assessments of the robustness of the method to data noise,incomplete meta-transcriptomic data, inaccurate prior knowledge of metabolic import rates, and larger of microbial communities. We are currently finalizing various benchmarks and working with real experimental data.
ano.nymous@ccsd.cnrs.fr.invalid (Sthyve Junior Tatho Djeanou) 10 Jun 2025
https://hal.science/hal-05105572v1
-
[hal-05086556] De nouveaux outils et algorithmes au service de la mesure du bien-être des animaux face au changement climatique – exemples chez les bovins
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Florence Gondret) 27 May 2025
https://hal.inrae.fr/hal-05086556v1
-
[hal-05073304] Generation of metabolomic-informed models of metabolism in complex microbial communities
The generation of genome-wide metabolic networks has become a routine analysis for individual organisms or communities communities. However, these automatically generated metabolic networks are incomplete because they are constructed by based on the combination of gene annotation and reactions available in generic available in generic databases (Metacyc, BIGG, ModelSEED...). These are oriented towards well-known organisms or organisms or model organisms and miss out on important functions secondary metabolism. We propose to combine metabolomic data analysis, metabolic modelling and annotation metabolic modelling and annotation mining to build high-quality models of high quality models of microbial metabolism with the long-term aim of better understanding of microbial communities. In terms of application of the methods to plant microbial communities, we hope that the plant microbial communities, we hope that the newly developed models will provide a better understanding of the process of microbial recruitment by the plant: metabolic functions involved, micro-organisms associated with these functions.
ano.nymous@ccsd.cnrs.fr.invalid (Coralie Muller) 19 May 2025
https://inria.hal.science/hal-05073304v1
-
[hal-05089855] Hierarchical Long Short Term Memory Recurrent Neural Network for Goats Behaviour Prediction from Accelerometer Data
Gastrointestinal parasitism is a major challenge in small grazing ruminants, affecting animal welfare and farmers’ income. In this regard, monitoring individual animal behaviour could help to develop new selection schemes that favor animals with a lower risk of larval infestation, but also support the targeted use of anthelmintic by focusing only on infested animals. Accelerometer sensors are widely used in combination with statistical models to predict the behaviour of grazing ruminants, but the lack of generalization of the models and the limited range of well-predicted behaviours are still challenging. In our study, we introduce an innovative methodology based on hierarchical long short term memory (LSTM) recurrent neural networks to predict the main behaviours of goats on pasture. For that purpose, we collected accelerometer data from the horns of 59 Creole goats and annotated the behaviour over 144 hours of data. We defined 13 moving features that are mathematical combinations of the raw data to get more information while preserving the temporal structure of the accelerometer time-series. A data augmentation technique involving the addition of random noise was applied to sequences from the minority behaviour labels. A hierarchical LSTM model was then built to derive behaviours from a given accelerometer signal, by sequentially combining several models that first tackle simple classification tasks (e.g., grazing or non-grazing segments), then increasingly complex ones (e.g., displacement or other activities), progressively withdrawing segments that have already been identified. The hierarchical LSTM model was validated using a testing set consisting of goats not seen during model training, and carefully selected to maximize behavioural labels heterogeneity. Performance of the hierarchical LSTM model was also compared to those of a regular LSTM model which directly classified the raw signal into the 5 behaviours, used as the baseline. Highest performance was obtained with the hierarchical LSTM model, reaching a Fscore of 87.84%, a precision of 89.44% and a recall of 86.3%. Best performance was obtained for grazing prediction (recall: 99.5%; precision: 99.4%), following by resting (recall: 98.0%; precision: 98.4%) and ruminating (recall: 95.2%; precision: 89%). Most confusions occurred with the displacement (recall: 51.2%; precision: 67.8%), likely due to the low number of sequences in the dataset (0.42% of the dataset). While other avenues remain to be explored for improving the prediction of such rare behaviours, our approach introduces key innovations that not only address the methodological limitations identified in the literature, but also facilitate further exploration of the role of goat behaviour in managing gastrointestinal parasitism on pasture.
ano.nymous@ccsd.cnrs.fr.invalid (Mathieu Bonneau) 02 Jun 2025
https://hal.inrae.fr/hal-05089855v1
-
[hal-04963112] 3-D shape control of deformable linear objects for branch handling using an adaptive Lyapunov-based scheme
Despite its various applications, robotic manipulation of deformable objects in agriculture has experienced limited development so far. This is due to the specific challenges in this domain, i.e., the variety of objects in this field is wide, and the deformation properties of the objects cannot be easily recognized in advance. In addition, deformable objects generally have complex dynamics and high-dimensional configuration space. In this paper, the manipulation of deformable linear objects (DLOs) is addressed by considering these challenges. Concretely, a new indirect adaptive control method is proposed to manipulate DLOs by controlling their shape in 3-D space towards previously defined targets, with a specific focus on agricultural applications. The proposed method can follow a desired dynamic evolution of the shape with a smooth deformation that brings about a stable gripper motion. This property of the method can protect the object from possible damages, even under large deformations, which is crucial in agricultural scenarios. An adaptation law is leveraged for estimating the system parameters, and Lyapunov analysis is employed to study the validity of the proposed control scheme. The scheme can be applied to diverse objects that can be modeled as linear, including tree branches or other rod-like structures. The effectiveness of the scheme is demonstrated through various experiments where, using shape feedback obtained from a 3-D camera, a robotic arm controls the shape of a flexible foam rod and of branches of different plants. © 2025
ano.nymous@ccsd.cnrs.fr.invalid (Omid Aghajanzadeh) 24 Feb 2025
https://hal.inrae.fr/hal-04963112v1
-
[hal-05035257] rs-pancat-compare
Program that calculates the distance between two GFA (Graphical Fragment Assembly) files. It takes in the file paths of the two GFA files. The program first identifies the common paths between the two graphs by finding the intersection of their path names. For each common path, the program reads those and output differences in segmentation in-between them. The purpose is to output the necessary operations (merges and splits) required to transform the graph represented by the first GFA file into the graph represented by the second GFA file.
ano.nymous@ccsd.cnrs.fr.invalid (Siegfried Dubois) 15 Apr 2025
https://hal.science/hal-05035257v1
-
[hal-05053970] Comparing three classification methods for plants and plant parts consumed by small ruminants in Mediterranean rangelands
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Thomas Dochier) 02 May 2025
https://hal.inrae.fr/hal-05053970v1
-
[hal-05026689] Des problèmes de coopération dans la gestion de Communs aux organisations biosociales
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Julie Labatut) 09 Apr 2025
https://hal.inrae.fr/hal-05026689v1
-
[hal-05026612] Repenser les organisations comme des devenirs biosociaux
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Julie Labatut) 09 Apr 2025
https://hal.inrae.fr/hal-05026612v1
-
[hal-05163083] Bare soil mosaicking optimisation for soil organic carbon prediction in Centre-Val de Loire
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Qianqian Chen) 15 Jul 2025
https://hal.science/hal-05163083v1
-
[hal-05066058] Assessing the impact of incorporating soil moisture and roughness as co-variables to improve soil organic carbon content prediction from hyperspectral data
Predicting soil organic carbon (SOC) content is of critical importance for both environmental policies and monitoring issues [Criscuoli et al., 2024]. Traditional field soil sampling methods are tedious and cost-prohibitive, making remote sensing an attractive alternative for simplifying estimates, particularly at large scales. The EnMAP satellite offers great potential, as it captures a broad spectral range and high spectral resolution, both essential for accurately assessing SOC content [Chabrillat et al., 2023]. However, remote sensing acquisitions face many challenges, and optimal soil surface conditions are rarely achieved. Soils are often not fully bare; they may be moist and/or rough, which significantly impacts reflectance and, consequently, the ability to predict SOC content. Only few studies accounted for soil roughness [Denis et al., 2014; Piekarczyk et al., 2016] and this in isolation, from soil moisture, which was primarily accounted for under controlled laboratory conditions [see review by Knadel et al., 2023]. This study aims to evaluate the benefit of incorporating co-variables related to soil moisture and surface roughness into SOC prediction models based on field spectroscopy and other in situ simultaneous measurements. A joint objective is to assess whether using EnMAP simulations of these spectra can improve model performance compared to other selections of specific wavelengths.
ano.nymous@ccsd.cnrs.fr.invalid (Hugues Merlet) 13 May 2025
https://hal.science/hal-05066058v1
-
[hal-04993468] CabriTrack: Accelerometer data for automated behavioural monitoring of grazing Creole goats
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Laura Faillot) 17 Mar 2025
https://hal.inrae.fr/hal-04993468v1
-
[hal-05175887] Suivi satellitaire du C du sol – potentialités d’application au secteur viticole
Cette communication porte sur les objectifs du projet MELICERTES ainsi que les principes généraux pour le suivi spectral du C, puis sur les premiers résultats issus de séries satellitaires. Elle aborde ensuite les acquis antérieurs en vignobles et applications au secteur viticole, puis les perspectives d'application au secteur viticole et les travaux en cours dans le cadre du projet SANCHOSTHIRST d'EJP SOIL.
ano.nymous@ccsd.cnrs.fr.invalid (Emmanuelle Vaudour) 22 Jul 2025
https://hal.science/hal-05175887v1
-
[hal-04996131] Comment créer des variétés moins gourmandes en pesticides pour l’arboriculture? Exemple des recherches sur l’abricotier et le pêcher à INRAE
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Morgane Roth) 18 Mar 2025
https://hal.science/hal-04996131v1
-
[hal-04993862] Mapler: Assessing assembly quality in taxonomically rich metagenomes sequenced with HiFi reads
Metagenome assembly seeks to reconstruct the most high-quality genomes from sequencing data of microbial ecosystems. Despite technological advancements that facilitate assembly, such as Hi-Fi long reads, the process remains challenging in complex environmental samples consisting of hundreds to thousands of populations. Mapler is a metagenome assembly and evaluation pipeline with a focus on evaluating the quality of Hi-Fi long read metagenome assemblies. It incorporates several state-of-the-art metrics, as well as novel metrics assessing the diversity that remains uncaptured by the assembly process. Mapler facilitates the comparison of assembly strategies and helps identify methodological bottlenecks that hinder genome reconstruction.
ano.nymous@ccsd.cnrs.fr.invalid (Nicolas Maurice) 18 Mar 2025
https://hal.science/hal-04993862v1
-
[hal-05006930] How can digitalisation contribute to sustainability of business models in agri-food value chains? A systematic literature review
The expectations of digital technologies in sustainable agricultural development are considerable. However, applying these technologies in agri-food value chains can have downsides, which are still barely studied. The main objectives of this systematic literature review were to discover the state of the art of the research in the use of digital technologies in business models contributing to sustainability in the agri-food sector, and to make recommendations for future research and management practice. In order to bring concepts together and develop a theoretical framework and advance knowledge, performing a literature review is conducive. Here, the commonly-used PRISMA-method was used to develop a systematic literature review. From this review, an overview of business model innovations, and drivers, benefits and drawbacks of digitalisation in agri-food value chains were distinguished. Key themes found in the literature were the effects of COVID-19 on digitalisation and business resilience, the economic sustainability of business models, and the importance of communication technologies in agri-food value chains. This article recommends for future research and management practice to use a framework that looks through a value co-creation and open innovation perspective to the individual business model level and the interaction between (sustainable) business models in local and global food systems.
ano.nymous@ccsd.cnrs.fr.invalid (Laura Eline Slot) 26 Mar 2025
https://hal.inrae.fr/hal-05006930v1
-
[hal-04996155] cMFA for multi-omics data integration in microbial community models
Microbial communities are an essential component of plant health, helping in nutrient acquisition and defense against pathogens. Despite their importance, the mechanisms behind their assembly and regulation remain poorly understood. Advances in sequencing and measuring technologies have enabled the collection of multi-omics data, including population counts on the abundance of microorganisms, metabolomic data on metabolite consumption and production, and metatranscriptomic data on gene activity within these communities. In order to answer the question of how these microorganisms function in the community and interact with one another, our main objective is to develop a mathematical model of dynamic systems capable of integrating these time series of multi-omics data at a community scale. Such a model will help to better decipher the functioning of the microbial community and understand its composition, knowing what each individual consume and produces. To achieve this goal, we introduce the community-scale metabolic flux analysis (cMFA) method. In this poster, we introduced the cMFA method, that we assessed on synthetic data from a dynamic model of increasingly complex microbial communities, built upon metabolic models of microorganisms. The observed growth rates were obtained from the spline smoothing of several replicates of the community dynamics. Synthetic meta-transcriptomic data were produced from metabolic fluxes in the dynamic model. Different regularization terms were tested, including different levels of sparsity, for a cross-validated penalty weight. The cMFA method, implemented in Python with OSQP, a software package dedicated to quadratic programming problems, allows for the recovery of the functioning of microbial individuals from multi-omics data acquired at the community scale during growth experiments.
ano.nymous@ccsd.cnrs.fr.invalid (Sthyve Junior Tatho Djeanou) 18 Mar 2025
https://inria.hal.science/hal-04996155v1
-
[hal-05008533] Inferring Kernel ϵ-Machines: Discovering Structure in Complex Systems
<div><p>Previously, we showed that computational mechanic's causal states-predictively-equivalent trajectory classes for a stochastic dynamical system-can be cast into a reproducing kernel Hilbert space. The result is a widely-applicable method that infers causal structure directly from very different kinds of observations and systems. Here, we expand this method to explicitly introduce the causal diffusion components it produces. These encode the kernel causal-state estimates as a set of coordinates in a reduced dimension space. We show how each component extracts predictive features from data and demonstrate their application on four examples: first, a simple pendulum-an exactly solvable system; second, a molecular-dynamic trajectory of n-butane-a high-dimensional system with a well-studied energy landscape; third, the monthly sunspot sequence-the longest-running available time series of direct observations; and fourth, multi-year observations of an active crop field-a set of heterogeneous observations of the same ecosystem taken for over a decade. In this way, we demonstrate that the empirical kernel causal-states algorithm robustly discovers predictive structures for systems with widely varying dimensionality and stochasticity.</p><p>Science progresses by discovering new structures and behaviors in the natural world. However, decades of success in nonlinear dynamics have driven home the message that systems in the world are nonlinear and high dimensional. Moreover, appropriately representing their emergent complexity and stochasticity makes structure discovery quite challenging. We recently introduced a discovery algorithm that learns optimal predictive features from measurement data as components in a reproducing kernel Hilbert space. The algorithm identifies predictive features in data series consisting of disparate data types, from categorical and discrete to fractal and continuous. In this way, the methodology exploits modern advances in machine learning fundamentals, resulting in a highly flexible and practicable algorithm for finding a system's effective state space-the minimal optimally predictive model. Notably, this offers a new geometric interpretation of the predictive structure of computational mechanic's ϵ-machines. Here, we demonstrate its use on four distinct examples including both simulated and real experimental over a variety of data types.</p></div>
ano.nymous@ccsd.cnrs.fr.invalid (Alexandra Jurgens) 27 Mar 2025
https://inria.hal.science/hal-05008533v1
-
[hal-04983681] IMPO: Interpretable Memory-based Prototypical Pooling
Graph Neural Networks (GNNs) have proven their effectiveness in various graph-structured data applications. However, one of the significant challenges in the realm of GNNs is representation learning, a critical concept that bridges graph pooling, aimed at creating compressed graph representations, and explainable artificial intelligence, which focuses on building models with transparent reasoning mechanisms. This research paper introduces a novel approach called Interpretable Memory-based Prototypical Pooling (IMPO) to address this challenge. IMPO is a graph pooling layer designed to enhance the interpretability of GNNs while maintaining high performance in graph classification tasks. It builds upon the MemPool algorithm and incorporates prototypical components to cluster nodes around class-aware centroids. This approach allows IMPO to selectively aggregate relevant substructures, paving the way for generating more interpretable graph representations. The experimental results in our study underscore the potential of pooling architectures in constructing inherently explainable GNNs. Notably, IMPO achieves state-of-the-art results in both classification and explanatory capacities across a diverse set of graph classification datasets.
ano.nymous@ccsd.cnrs.fr.invalid (Alessio Ragno) 09 Mar 2025
https://hal.science/hal-04983681v1
-
[hal-04996135] cMFA for multi-omics data integration in microbial community models
Microbial communities are an essential component of plant health, helping in nutrient acquisition and defense against pathogens. Despite their importance, the mechanisms behind their assembly and regulation remain poorly understood. Advances in sequencing and measuring technologies have enabled the collection of multi-omics data, including population counts on the abundance of microorganisms, metabolomic data on metabolite consumption and production, and metatranscriptomic data on gene activity within these communities. In order to answer the question of how these microorganisms function in the community and interact with one another, our main objective is to develop a mathematical model of dynamic systems capable of integrating these time series of multi-omics data at a community scale. Such a model will help to better decipher the functioning of the microbial community and understand its composition, knowing what each individual consume and produces. To achieve this goal, we introduce the community-scale metabolic flux analysis (cMFA) method. In this poster, we introduced the cMFA method, that we assessed on synthetic data from a dynamic model of increasingly complex microbial communities, built upon metabolic models of microorganisms. The observed growth rates were obtained from the spline smoothing of several replicates of the community dynamics. Synthetic meta-transcriptomic data were produced from metabolic fluxes in the dynamic model. Different regularization terms were tested, including different levels of sparsity, for a cross-validated penalty weight. The cMFA method, implemented in Python with OSQP, a software package dedicated to quadratic programming problems, allows for the recovery of the functioning of microbial individuals from multi-omics data acquired at the community scale during growth experiments.
ano.nymous@ccsd.cnrs.fr.invalid (Sthyve Junior Tatho Djeanou) 18 Mar 2025
https://inria.hal.science/hal-04996135v1
-
[hal-05162236] GrAnnoT, a tool for efficient and reliable annotation transfer through pangenome graph
The increasing availability of genome sequences has highlighted the limitations of using a single reference genome to represent the diversity within a species. Pangenomes, encompassing the genomic information from multiple genomes, offer thus a more comprehensive representation of intraspecific diversity. However, pangenomes in form of graph often lack annotation information, which limits their utility for forward analyses. We introduce here GrAnnoT, a tool designed for efficient and reliable annotation transfer using such graphs, by projecting existing annotations from a source genome to the graph and subsequently to other embedded genomes. GrAnnoT was benchmarked against state-of-the-art tools on pangenome graphs and linear genomes from rice, human, and E. coli . The results demonstrate that GrAnnoT is consensual, conservative, and fast, outperforming alignment-based methods in accuracy or speed or both. It provides informative outputs, such as presence-absence matrices for genes, and alignments of transferred features between source and target genomes, aiding in the study of genomic variations and evolution. GrAnnoT’s robustness and replicability across different species make it a valuable tool for enhancing pangenome analyses. GrAnnoT is available under the GNU GPLv3 licence at https://forge.ird.fr/diade/dynadiv/grannot .
ano.nymous@ccsd.cnrs.fr.invalid (Nina Marthe) 15 Jul 2025
https://hal.science/hal-05162236v1
-
[hal-05017656] PlantAIM: A new baseline model integrating global attention and local features for enhanced plant disease identification
Plant diseases significantly affect the quality and yield of agricultural production. Conventionally, detection has relied on plant pathologists, but recent advances in deep learning, particularly the Vision Transformer (ViT) and Convolutional Neural Network (CNN), have made it feasible for automated plant disease identification. Despite their prominence, there are still significant gaps in our understanding of how these models differ in feature extraction and representation, particularly in complex multi-crop disease identification tasks. This challenge arises from the simultaneous need to learn crop-specific and disease-specific features for accurate identification of crop species and its associated diseases. To address this, we introduce Plant Disease Global-Local Features Fusion Attention Model (PlantAIM), a new hybrid framework that fuses global attention mechanisms of ViT with local feature extraction capabilities of CNN. PlantAIM aims to improve the model's ability to simultaneously learn and focus on crop-specific and disease-specific features. We conduct extensive evaluations to assess the robustness and generalizability of PlantAIM compared to state-of-the-art (SOTA) models, including scenarios with limited training samples and real-world environmental data. Our results show that PlantAIM achieves superior performance. This research not only deepens our understanding of feature learning for ViT and CNN models, but also sets a new benchmark in the dynamic field of plant disease identification. The code is available at github: PlantAIM
ano.nymous@ccsd.cnrs.fr.invalid (Abel Yu Hao Chai) 02 Apr 2025
https://hal.inrae.fr/hal-05017656v1
-
[hal-05108055] Development of a microfluidic quantitative PCR chip to monitor the dynamics of a synthetic microbial community on grapevine with potential biocontrol effects against downy mildew
A synthetic microbial community with potential biocontrol effects against downy mildew was developed as part of Aarti Jaswa’s PhD research. To monitor the establishment of this community on grapevine leaves, a microfluidic quantitative PCR (qPCR) chip was developed. Primers targeting each microorganism individually were designed to enable absolute quantification of each strain over time. This chip is also intended for use on environmental samples, particularly those collected by spore traps from the VISA network. It could thus provide insight into the “health status” of the vineyard by indicating the presence or absence of sentinel microorganisms targeted by the chip.
ano.nymous@ccsd.cnrs.fr.invalid (Manon Chargy) 11 Jun 2025
https://hal.science/hal-05108055v1
-
[hal-04603038] Cooperative learning of Pl@ntNet's Artificial Intelligence algorithm: how does it work and how can we improve it?
Deep learning models for plant species identification rely on large annotated datasets. The PlantNet system enables global data collection by allowing users to upload and annotate plant observations, leading to noisy labels due to diverse user skills. Achieving consensus is crucial for training, but the vast scale of collected data makes traditional label aggregation strategies challenging. Existing methods either retain all observations, resulting in noisy training data or selectively keep those with sufficient votes, discarding valuable information. Additionally, as many species are rarely observed, user expertise can not be evaluated as an inter-user agreement: otherwise, botanical experts would have a lower weight in the AI training step than the average user. Our proposed label aggregation strategy aims to cooperatively train plant identification AI models. This strategy estimates user expertise as a trust score per user based on their ability to identify plant species from crowdsourced data. The trust score is recursively estimated from correctly identified species given the current estimated labels. This interpretable score exploits botanical experts' knowledge and the heterogeneity of users. Subsequently, our strategy removes unreliable observations but retains those with limited trusted annotations, unlike other approaches. We evaluate PlantNet's strategy on a released large subset of the PlantNet database focused on European flora, comprising over 6M observations and 800K users. We demonstrate that estimating users' skills based on the diversity of their expertise enhances labeling performance. Our findings emphasize the synergy of human annotation and data filtering in improving AI performance for a refined dataset. We explore incorporating AI-based votes alongside human input. This can further enhance human-AI interactions to detect unreliable observations.
ano.nymous@ccsd.cnrs.fr.invalid (Tanguy Lefort) 06 Dec 2024
https://hal.science/hal-04603038v2
-
[hal-05078590] New business models for a co-evolution of digital, agro-ecological and circular trajectories
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Laura Eline Slot) 22 May 2025
https://hal.inrae.fr/hal-05078590v1
-
[hal-04920249] Adaptation des porcs face à une vague de chaleur estivale : études physiologiques et comportementales via des outils numériques
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Caroline Xavier) 30 Jan 2025
https://hal.inrae.fr/hal-04920249v1
-
[hal-04920790] Enhancing Microbial Genome Reconstruction in Complex Environments by combining Short-and Long-read Sequencing
Soil is one of the most diverse microbial ecosystems, yet a significant portion of its microbial "dark matter" remains uncharacterised. Sequencing technologies have improved our understanding, but challenges persist in comprehensively characterising soil microbial diversity. In this study, we employed PacBio HiFi long-read (LR) and Illumina short-read (SR) whole-genome sequencing (WGS) to reconstruct metagenome-assembled genomes (MAGs) from a soil sample. Metabarcoding analyses complemented our approach by assessing microbial diversity and evaluating the proportion of taxa captured by WGS. Our results demonstrate that LR sequencing significantly enhances genome contiguity and completeness compared to SR methods, which yield more fragmented assemblies. By integrating SR and LR data, we improved binning accuracy, leading to a more precise taxonomic resolution of soil microbial diversity. While long-read sequencing provides the most comprehensive WGS representation, our findings highlight that low-abundant microbial taxa remain undetected due to sequencing depth limitations.
ano.nymous@ccsd.cnrs.fr.invalid (Carole Belliardo) 30 Jan 2025
https://hal.science/hal-04920790v1
-
[hal-04901135] L'IA au service de l'agroécologie : Application au phénotypage des cultures en mélange
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Mario Serouart) 20 Jan 2025
https://hal.inrae.fr/hal-04901135v1
-
[hal-05025754] PATASEL Phénotypage Animal pour la Transition Agroécologique des Systèmes d'ELevage
Le projet PATASEL (Phénotypage Animal pour la Transition Agroécologique des Systèmes d’Elevage) est porté par l'infrastructure de recherche (IR) LiPH4SAS (www.liph4sas.fr). LIPH4SAS est une IR distribuée, qui permet également de tirer parti de ressources génétiques, d’environnements et de systèmes d’élevage diversifiés (bocage normand vs moyenne montagne, système conventionnel vs bio). Elle permet à la fois une exploration fonctionnelle multi- échelle et des mesures, à l'échelle de l'animal, sur de grands lots d'animaux (phénotypage horizontal) au statut sanitaire contrôlé et situés dans des environnements maîtrisés et caractérisés. Le premier objectif du projet PATASEL est de doter LIPH4SAS d’équipements de phénotypage animal performants. L’essentiel des équipements prévus dans le cadre du projet a été acquis dès 2024, permettant le bon déroulement des projets de recherche associés (projets WAIT4, HOLOBIONTS, COBREEDING, AGRODIV notamment). Ils concernent notamment la mesure caractères clés pour la transition agroécologique et l’adaptation au changement climatique (ingestion d’aliments concentrés, de fourrages et d’eau, gaz à effets de serre, comportements , indicateurs de bien-être et santé, paramètres d’environnement). Le second objectif de PATASEL est d’assurer la FAIRisation des données produites, leur interopérabilité avec les données produites via d’autres infrastructures (RARe, France Génomique) et leur mise à disposition des communautés scientifiques. Une première version de SPIDER, plateforme permettant l’accès à l’ensemble des données collectées sur chaque animal, est actuellement en cours de test..
ano.nymous@ccsd.cnrs.fr.invalid (Jean Pierre Bidanel) 08 Apr 2025
https://hal.inrae.fr/hal-05025754v1
-
[hal-05010435] L'IA au service de l'agroécologie
<div>Application de l'IA à la détection des ravageurs<p>Entrainer un modèle de Deep Learning Librairies Python et modèle YOLOv8. Chaque saison le modèle s'enrichit. Performance du modèle : AUC 0.869 ; R² très élevé et une erreur régulièrement répartie sur l'axe. Erreur moyenne de 20 larves. Segmentation Sahi, tuiles de 640*640 pixels 16 000+ tuiles annotées.</p> <p> Application web de mise à disposition du modèle pour utilisateurs agriculteurs ou techniciens de coopératives, semenciers et conseil agricole. </p> </div>
ano.nymous@ccsd.cnrs.fr.invalid (Jean-Eudes Hollebecq) 28 Mar 2025
https://hal.science/hal-05010435v1
-
[hal-05006205] Phénotypage à haut débit des plantes pour l'agroécologie
La transition agroécologique nécessite des outils et des méthodes afin d'aider à évaluer aujourd’hui et prévoir pour demain les performances (productivité et stabilité) des combinaisons actuelles et futures d'espèces, de cultivars et de pratiques agricoles innovantes sous les climats actuels et futurs.Cette évaluation doit porter sur un large éventail de caractéristiques des couverts végétaux (phénotypage) et tenir compte non seulement de la productivité, mais aussi des régulations et des compromis écologiques. Les environnements agroécologiques étant plus variables que ceux de l'agriculture conventionnelle, ils doivent être caractérisés de manière précise dans le temps et dans l’espace (envirotypage). Ces dernières années, le phénotypage et l'envirotypage à haut débit ont considérablement progressé, grâce à l'utilisation de capteurs, à l'imagerie non destructive et au traitement automatisé des données. L'infrastructure nationale PHENOME-EMPHASIS, initialement axée sur les cultures annuelles et les stress abiotiques, s'est élargie pour inclure des caractéristiques liées à l'agroécologie, en particulier les interactions biotiques. Le projet AgroEcoPhen a été conçu comme une extension de PHENOME-EMPHASIS vers l'agroécologie en mettant en oeuvre phénotypage et envirotypage à haut débit dans un nombre élargi de stations expérimentales des partenaires dédiées aux cultures annuelles, mais aussi de manière à prendre en compte l’arboriculture et la viticulture, cultures fortement dépendantes de l’agrochimie. Il s’appuie sur le développement de capteurs connectés à faible coût, de vecteurs robotisés, de méthodes d'apprentissage profond pour l'imagerie de canopées complexes ou l'identification d'insectes, et l’amélioration du traitement massif des ensembles de données générées. Les premiers résultats du projet sont la conception et le déploiement de piquets connectés, les premiers tests d’un robot dédié aux vergers et vignobles, des méthodes d’identification des espèces dans des couverts complexes et une méthode d’identification d’insectes ravageurs. AgroEcoPhen permet ainsi d’explorer les voies les plus prometteuses pour guider, grâce aux outils numériques, l’agriculture vers l’agroécologie.
ano.nymous@ccsd.cnrs.fr.invalid (Bertrand Muller) 26 Mar 2025
https://hal.science/hal-05006205v1
-
[hal-04919231] Generation of metabolomic-informed models of metabolism in complex microbial communities
The generation of genome-wide metabolic networks has become a routine analysis for individual organisms or communities communities. However, these automatically generated metabolic networks are incomplete because they are constructed by based on the combination of gene annotation and reactions available in generic available in generic databases (Metacyc, BIGG, ModelSEED...). These are oriented towards well-known organisms or organisms or model organisms and miss out on important functions secondary metabolism. We propose to combine metabolomic data analysis, metabolic modelling and annotation metabolic modelling and annotation mining to build high-quality models of high quality models of microbial metabolism with the long-term aim of better understanding of microbial communities. In terms of application of the methods to plant microbial communities, we hope that the plant microbial communities, we hope that the newly developed models will provide a better understanding of the process of microbial recruitment by the plant: metabolic functions involved, micro-organisms associated with these functions.
ano.nymous@ccsd.cnrs.fr.invalid (Coralie Muller) 29 Jan 2025
https://inria.hal.science/hal-04919231v1
-
[hal-04941137] Mapler: Assessing assembly quality in taxonomically-rich metagenomes sequenced with HiFi reads
Evaluating the quality of metagenome assemblies can be a challenging task, especially when no reference genome is available and when comparing samples at various taxonomic complexity and sequencing depth. A high quality assembly is expected not only to produce high quality bins, but also to be representative of most of the read sequences, especially in complex samples where algorithms struggle reconstructing low-abundance genomes. Recent studies showed a great improvement in number and quality of bins obtained with highly accurate PacBio HiFi long reads. It remains however to be assessed how much of the sample these bins represent, especially in highly complex environmental samples. There is therefore a need to use and compare other evaluation methods. We designed and implemented Mapler, a metagenomic assembly and evaluation pipeline with a primary focus on evaluating the quality of HiFi-based metagenome assemblies. It incorporates state-of-the-art tools for assembly, binning, and assembly evaluation. In addition to classifying assembly bins in classical quality categories according to their marker gene content and taxonomic assignment, Mapler analyzes the alignment of reads on contigs. To do so, it calculates the ratio of mapped reads and bases, and separately analyzes mapped and unmapped reads via their k-mer frequency, read quality, and taxonomic assignment.
ano.nymous@ccsd.cnrs.fr.invalid (Nicolas Maurice) 11 Feb 2025
https://hal.science/hal-04941137v1
-
[hal-04916993] Transition écologique territoriale : Faire dialoguer expertise scientifique et concertation citoyenne
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Emmanuel Krieger) 28 Jan 2025
https://inria.hal.science/hal-04916993v1
-
[hal-04926181] Technology to support the agroecological transition : how farmers' needs are taken into account in a living lab?
A claim that living labs may support technology development for agroecological transitions, but several challenges. How farmers’ need are conceptualized and operationalized? What resources and barriers to take them into account?
ano.nymous@ccsd.cnrs.fr.invalid (Jean Larbaigt) 03 Feb 2025
https://hal.science/hal-04926181v1
-
[hal-04936942] Méta-modélisation des interactions plante-plante en 3D : application à l'association colza-féverole
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Meije Gawinowski) 09 Feb 2025
https://hal.science/hal-04936942v1
-
[hal-04879838] RITHMS : An advanced stochastic framework for the simulation of transgenerational hologenomic data
R Implementation of a Transgenerational Hologenomic Model-based Simulator (RITHMS) is a framework for simulating transgenerational hologenomic data that relies on MoBPS features for genomic data, accounts for the particularities of microbiota transmission, uses real genomic and microbiota data to construct a base population, and is flexible enough to cover a variety of scenarios defined by heritability, microbiability, and microbiota heritability.
ano.nymous@ccsd.cnrs.fr.invalid (Solène Pety) 10 Jan 2025
https://hal.science/hal-04879838v1
-
[hal-04916960] Conception d'alternatives socio-techniques grâce aux analyses de flux de matière et d'énergie (AFME)
[...]
ano.nymous@ccsd.cnrs.fr.invalid (Thibaut Coudroy) 28 Jan 2025
https://inria.hal.science/hal-04916960v1
