Accueil
Résultat de la recherche
3 résultat(s) recherche sur le mot-clé 'TECHNIQUE DE PREVISION' 
trié(s) par (Pertinence décroissant(e), Titre croissant(e)) Ajouter le résultat dans votre panier Affiner la recherche Générer le flux rss de la recherche
Partager le résultat de cette rechercheDevelopment of a data-assimilation system to forecast agricultural systems: a case study of constraining soil water and soil nitrogen dynamics in the APSIM model / M.S. Kivi in Science of the Total Environment, vol. 820 (10 May 2022)
Titre : Development of a data-assimilation system to forecast agricultural systems: a case study of constraining soil water and soil nitrogen dynamics in the APSIM model Type de document : objet à 3 dimensions, artefacts, ... Auteurs : M.S. Kivi ; H. Dokoohaki ; F.E. Miguez ; C.J. Bernacchi ; M. Masters ; B. Blakely Année de publication : 2022 Article en page(s) : p. 1-14 Langues : Anglais (eng) Langues originales : Anglais (eng) Catégories : A HISTOIRE - Pays et ensemble de pays:Histoire du Monde Rural:Agriculture ; F POPULATIONS - ETUDES DE CAS:Models ; J CULTURE - ART - LOISIRS - ANIMATION:J.26 Technologie de l'information (logiciels):Traitement des données:Analyse de données ; S SCIENCES ET TECHNIQUES:Approche scientifique:Méthode scientifique:Prévision Mots-clés : 06 - AGRICULTURE. FORÊTS. PÊCHES 6.5 - Gestion des Exploitations FORECAST FORECASTING TECHNIQUE DE PREVISION MODELE DATA ANALYSIS Résumé : As we face today's large-scale agricultural issues, the need for robust methods of agricultural forecasting has never been clearer. Yet, the accuracy and precision of our forecasts remains limited by current tools and methods. To overcome the limitations of process-based models and observed data, we iteratively designed and tested a generalizable and robust data-assimilation system that systematically constrains state variables in the APSIM model to improve forecast accuracy and precision. Our final novel system utilizes the Ensemble Kalman Filter to constrain model states and update model parameters at observed time steps and incorporates an algorithm that improves system performance through the joint estimation of system error matrices. We tested this system at the Energy Farm, a well-monitored research site in central Illinois, where we assimilated observed in situ soil moisture at daily time steps for two years and evaluated how assimilation impacted model forecasts of soil moisture, yield, leaf area index, tile flow, and nitrate leaching by comparing estimates with in situ observations. The system improved the accuracy and precision of soil moisture estimates for the assimilation layers by an average of 42% and 48%, respectively, when compared to the free model. Such improvements led to changes in the model's soil water and nitrogen processes and, on average, increased accuracy in forecasts of annual tile flow by 43% and annual nitrate loads by 10%. Forecasts of aboveground measures did not dramatically change with assimilation, a fact which highlights the limited potential of soil moisture as a constraint for a site with no water stress. Extending the scope of previous work, our results demonstrate the power of data assimilation to constrain important model estimates beyond the assimilated state variable, such as nitrate leaching. Replication of this study is necessary to further define the limitations and opportunities of the developed system. En ligne : https://doi.org/10.1016/j.scitotenv.2022.153192 Permalink : https://cs.iut.univ-tours.fr/index.php?lvl=notice_display&id=279729
in Science of the Total Environment > vol. 820 (10 May 2022) . - p. 1-14[article] Development of a data-assimilation system to forecast agricultural systems: a case study of constraining soil water and soil nitrogen dynamics in the APSIM model [objet à 3 dimensions, artefacts, ...] / M.S. Kivi ; H. Dokoohaki ; F.E. Miguez ; C.J. Bernacchi ; M. Masters ; B. Blakely . - 2022 . - p. 1-14.
Langues : Anglais (eng) Langues originales : Anglais (eng)
in Science of the Total Environment > vol. 820 (10 May 2022) . - p. 1-14
Catégories : A HISTOIRE - Pays et ensemble de pays:Histoire du Monde Rural:Agriculture ; F POPULATIONS - ETUDES DE CAS:Models ; J CULTURE - ART - LOISIRS - ANIMATION:J.26 Technologie de l'information (logiciels):Traitement des données:Analyse de données ; S SCIENCES ET TECHNIQUES:Approche scientifique:Méthode scientifique:Prévision Mots-clés : 06 - AGRICULTURE. FORÊTS. PÊCHES 6.5 - Gestion des Exploitations FORECAST FORECASTING TECHNIQUE DE PREVISION MODELE DATA ANALYSIS Résumé : As we face today's large-scale agricultural issues, the need for robust methods of agricultural forecasting has never been clearer. Yet, the accuracy and precision of our forecasts remains limited by current tools and methods. To overcome the limitations of process-based models and observed data, we iteratively designed and tested a generalizable and robust data-assimilation system that systematically constrains state variables in the APSIM model to improve forecast accuracy and precision. Our final novel system utilizes the Ensemble Kalman Filter to constrain model states and update model parameters at observed time steps and incorporates an algorithm that improves system performance through the joint estimation of system error matrices. We tested this system at the Energy Farm, a well-monitored research site in central Illinois, where we assimilated observed in situ soil moisture at daily time steps for two years and evaluated how assimilation impacted model forecasts of soil moisture, yield, leaf area index, tile flow, and nitrate leaching by comparing estimates with in situ observations. The system improved the accuracy and precision of soil moisture estimates for the assimilation layers by an average of 42% and 48%, respectively, when compared to the free model. Such improvements led to changes in the model's soil water and nitrogen processes and, on average, increased accuracy in forecasts of annual tile flow by 43% and annual nitrate loads by 10%. Forecasts of aboveground measures did not dramatically change with assimilation, a fact which highlights the limited potential of soil moisture as a constraint for a site with no water stress. Extending the scope of previous work, our results demonstrate the power of data assimilation to constrain important model estimates beyond the assimilated state variable, such as nitrate leaching. Replication of this study is necessary to further define the limitations and opportunities of the developed system. En ligne : https://doi.org/10.1016/j.scitotenv.2022.153192 Permalink : https://cs.iut.univ-tours.fr/index.php?lvl=notice_display&id=279729
Titre : Prévoir les sécheresses du XXIe siècle Type de document : objet à 3 dimensions, artefacts, ... Auteurs : K. Laval Année de publication : 2018 Article en page(s) : p. 23-28 Langues : Français (fre) Catégories : S SCIENCES ET TECHNIQUES:Approche scientifique:Méthode scientifique:Modèle de simulation Use only in connection with research and planning.; S SCIENCES ET TECHNIQUES:Pollution, catastrophes et sécurité:Catastrophe:Catastrophe naturelle:Sécheresse ; S SCIENCES ET TECHNIQUES:Pollution, catastrophes et sécurité:Dégradation de l'environnement:Changement climatiqueMots-clés : 07 - ENVIRONNEMENT 7.6 - Changement Climatique DROUGHT FORECASTING TECHNIQUE DE PREVISION SIMULATION MODELS CLIMATIC CHANGE RESEARCH METHOD METHODE DE RECHERCHE Résumé : Les recherches sur le climat s’affinent au fil des rapports du GIEC. Des conclusions peuvent ainsi être différentes d’un rapport à l’autre, alimentant quelques controverses sur la réalité des phénomènes. Il importe alors d’éclairer ces controverses, d’expliquer le travail des chercheurs, de rappeler que l’essence même de la science est d’être réfutable.
Katia Laval montre ici que les variations des conclusions scientifiques concernant les sécheresses ne sont pas dues au caractère chaotique du système climatique qui rend les résultats incertains, mais bien aux équations utilisées pour décrire le bilan d’eau et l’évaporation continentaleEn ligne : https://www.academie-agriculture.fr/publications/revue-aaf Permalink : https://cs.iut.univ-tours.fr/index.php?lvl=notice_display&id=208776
in Revue de l'Académie d'agriculture / SUDOC > n. 16 (01/10/2018) . - p. 23-28[article] Prévoir les sécheresses du XXIe siècle [objet à 3 dimensions, artefacts, ...] / K. Laval . - 2018 . - p. 23-28.
Langues : Français (fre)
in Revue de l'Académie d'agriculture / SUDOC > n. 16 (01/10/2018) . - p. 23-28
Catégories : S SCIENCES ET TECHNIQUES:Approche scientifique:Méthode scientifique:Modèle de simulation Use only in connection with research and planning.; S SCIENCES ET TECHNIQUES:Pollution, catastrophes et sécurité:Catastrophe:Catastrophe naturelle:Sécheresse ; S SCIENCES ET TECHNIQUES:Pollution, catastrophes et sécurité:Dégradation de l'environnement:Changement climatiqueMots-clés : 07 - ENVIRONNEMENT 7.6 - Changement Climatique DROUGHT FORECASTING TECHNIQUE DE PREVISION SIMULATION MODELS CLIMATIC CHANGE RESEARCH METHOD METHODE DE RECHERCHE Résumé : Les recherches sur le climat s’affinent au fil des rapports du GIEC. Des conclusions peuvent ainsi être différentes d’un rapport à l’autre, alimentant quelques controverses sur la réalité des phénomènes. Il importe alors d’éclairer ces controverses, d’expliquer le travail des chercheurs, de rappeler que l’essence même de la science est d’être réfutable.
Katia Laval montre ici que les variations des conclusions scientifiques concernant les sécheresses ne sont pas dues au caractère chaotique du système climatique qui rend les résultats incertains, mais bien aux équations utilisées pour décrire le bilan d’eau et l’évaporation continentaleEn ligne : https://www.academie-agriculture.fr/publications/revue-aaf Permalink : https://cs.iut.univ-tours.fr/index.php?lvl=notice_display&id=208776
Titre : The current and future uses of machine learning in ecosystem service research Type de document : objet à 3 dimensions, artefacts, ... Auteurs : M. Scowen ; S. Willcock ; F. Eigenbrod ; J.M. Bullock ; I.N. Athanasiadis Année de publication : 2021 Article en page(s) : p. 1-9 Langues : Anglais (eng) Langues originales : Anglais (eng) Catégories : F POPULATIONS - ETUDES DE CAS:Models ; S SCIENCES ET TECHNIQUES:Administration de la science et de la recherche:Développement scientifique:Changement technologique:Automatisation The act or practice of using machines that need little or no human control, especially to replace workers.; S SCIENCES ET TECHNIQUES:Administration de la science et de la recherche:RechercheMots-clés : 07 - ENVIRONNEMENT 7.1 - Généralités. Situation Environnementale ECOSYSTEM SERVICES SERVICE ECOSYSTEMIQUE RESEARCH BIG DATA MEGADONNEES MODELE FORECASTING TECHNIQUE DE PREVISION AUTOMATION Résumé : Machine learning (ML) expands traditional data analysis and presents a range of opportunities in ecosystem service (ES) research, offering rapid processing of ?big data? and enabling significant advances in data description and predictive modelling. Descriptive ML techniques group data with little or no prior domain specific assumptions; they can generate hypotheses and automatically sort data prior to other analyses. Predictive ML techniques allow for the predictive modelling of highly non-linear systems where casual mechanisms are poorly understood, as is often the case for ES. We conducted a review to explore how ML is used in ES research and to identify and quantify trends in the different ML approaches that are used. We reviewed 308 peer-reviewed publications and identified that ES studies implemented machine learning techniques in data description (64%; n = 308) and predictive modelling (44%), with some papers containing both categories. Classification and Regression Trees were the most popular techniques (60%), but unsupervised learning techniques were also used for descriptive tasks such as clustering to group or split data without prior assumptions (19%). Whilst there are examples of ES publications that apply ML with rigour, many studies do not have robust or repeatable methods. Some studies fail to report model settings (43%) or software used (28%), and many studies do not report carrying out any form of model hyperparameter tuning (67%) or test model generalisability (59%). Whilst studies use ML to analyse very large and complex datasets, ES research is generally not taking full advantage of the capacity of ML to model big data (1138 medium number of data points; 13 median quantity of variables). There is great further opportunity to utilise ML in ES research, to make better use of big data and to develop detailed modelling of spatial-temporal dynamics that meet stakeholder demands. En ligne : https://doi.org/10.1016/j.scitotenv.2021.149263 Permalink : https://cs.iut.univ-tours.fr/index.php?lvl=notice_display&id=277193
in Science of the Total Environment > vol. 799 (10 December 2021) . - p. 1-9[article] The current and future uses of machine learning in ecosystem service research [objet à 3 dimensions, artefacts, ...] / M. Scowen ; S. Willcock ; F. Eigenbrod ; J.M. Bullock ; I.N. Athanasiadis . - 2021 . - p. 1-9.
Langues : Anglais (eng) Langues originales : Anglais (eng)
in Science of the Total Environment > vol. 799 (10 December 2021) . - p. 1-9
Catégories : F POPULATIONS - ETUDES DE CAS:Models ; S SCIENCES ET TECHNIQUES:Administration de la science et de la recherche:Développement scientifique:Changement technologique:Automatisation The act or practice of using machines that need little or no human control, especially to replace workers.; S SCIENCES ET TECHNIQUES:Administration de la science et de la recherche:RechercheMots-clés : 07 - ENVIRONNEMENT 7.1 - Généralités. Situation Environnementale ECOSYSTEM SERVICES SERVICE ECOSYSTEMIQUE RESEARCH BIG DATA MEGADONNEES MODELE FORECASTING TECHNIQUE DE PREVISION AUTOMATION Résumé : Machine learning (ML) expands traditional data analysis and presents a range of opportunities in ecosystem service (ES) research, offering rapid processing of ?big data? and enabling significant advances in data description and predictive modelling. Descriptive ML techniques group data with little or no prior domain specific assumptions; they can generate hypotheses and automatically sort data prior to other analyses. Predictive ML techniques allow for the predictive modelling of highly non-linear systems where casual mechanisms are poorly understood, as is often the case for ES. We conducted a review to explore how ML is used in ES research and to identify and quantify trends in the different ML approaches that are used. We reviewed 308 peer-reviewed publications and identified that ES studies implemented machine learning techniques in data description (64%; n = 308) and predictive modelling (44%), with some papers containing both categories. Classification and Regression Trees were the most popular techniques (60%), but unsupervised learning techniques were also used for descriptive tasks such as clustering to group or split data without prior assumptions (19%). Whilst there are examples of ES publications that apply ML with rigour, many studies do not have robust or repeatable methods. Some studies fail to report model settings (43%) or software used (28%), and many studies do not report carrying out any form of model hyperparameter tuning (67%) or test model generalisability (59%). Whilst studies use ML to analyse very large and complex datasets, ES research is generally not taking full advantage of the capacity of ML to model big data (1138 medium number of data points; 13 median quantity of variables). There is great further opportunity to utilise ML in ES research, to make better use of big data and to develop detailed modelling of spatial-temporal dynamics that meet stakeholder demands. En ligne : https://doi.org/10.1016/j.scitotenv.2021.149263 Permalink : https://cs.iut.univ-tours.fr/index.php?lvl=notice_display&id=277193
