References of "Destain, Marie-France"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailRisk assessment of soil compaction in Walloon Region
D'Or, Dimitri; Destain, Marie-France ULg

in Proceedings of geoENV2014 (2014, July)

It is well established that soil compaction affects the growth and functioning of roots and disrupts the activity of microfauna and soil microorganisms, resulting in a loss of yields. Agriculture and ... [more ▼]

It is well established that soil compaction affects the growth and functioning of roots and disrupts the activity of microfauna and soil microorganisms, resulting in a loss of yields. Agriculture and forestry using increasingly heavy machines, the risk of soil compaction is increasing accordingly. Chosen as indicator of the susceptibility of soils to compaction, the precompression stress (Pc) is calculated using the pedotransfer functions (PTFs) proposed by Horn and Fleige (2003). These PTFs involve eight parameters linked to the hydraulic and mechanical behaviour of soils: organic matter content, bulk density, air capacity, available and non-plant available water capacity, saturated hydraulic conductivity, cohesion and angle of internal friction. The challenge consists in producing Pc maps at the regional scale for Wallonia. Those maps should also be accompanied by estimation uncertainty map. Finally, the results should be exploited to produce compaction risk maps according to various frequent scenarios. In this paper, a methodology is proposed, combining geostatistics and Monte Carlo simulations, to achieve these goals. [less ▲]

Detailed reference viewed: 13 (4 ULg)
Peer Reviewed
See detailPredicting Grain Protein Content of Winter Wheat
Mansouri, Majdi ULg; Dumont, Benjamin ULg; Destain, Marie-France ULg

in ESANN 2014 Proceedings (2014, April 24)

Detailed reference viewed: 10 (1 ULg)
Full Text
Peer Reviewed
See detailBayesian methods for predicting and modelling winter wheat biomass
Mansouri, Majdi ULg; Dumont, Benjamin ULg; Destain, Marie-France ULg

Poster (2014, February)

The objectives of this paper are threefold. The first objective is to propose to use an Improved Particle Filtering (IPF) based on minimizing Kullback-Leibler divergence for crop models' predictions. The ... [more ▼]

The objectives of this paper are threefold. The first objective is to propose to use an Improved Particle Filtering (IPF) based on minimizing Kullback-Leibler divergence for crop models' predictions. The performances of the proposed technique are compared with those of the conventional Particle Filtering (PF) for improving nonlinear crop model predictions. The main novelty of this task is to develop a Bayesian algorithm for nonlinear and non-Gaussian state and parameter estimation with better proposal distribution. The second objective is to investigate the effects of practical challenges on the performances of state estimation algorithms PF and IPF. Such practical challenges include (i) the effect of measurement noise on the estimation performances and (ii) the number of states and parameters to be estimated. The third objective is to use the state estimation techniques PF and IPF for updating prediction of nonlinear crop model in order to predict winter wheat biomass. PF and IPF are applied at a dynamic crop model with the aim to predict a state variable, namely the winter wheat biomass, and to estimate several model parameters. Furthermore, the effect of measurement noise (e.g., different signal-to-noise ratios) on the performances of PF and IPF is investigated. The results of the comparative studies show that the IPF provides a significant improvement over the PF because, unlike the PF which depends on the choice of sampling distribution used to estimate the posterior distribution, the IPF yields an optimum choice of the sampling distribution, which also accounts for the observed data. [less ▲]

Detailed reference viewed: 11 (2 ULg)
Full Text
Peer Reviewed
See detailParameter identification of the STICS crop model, using an accelerated formal MCMC approach
Dumont, Benjamin ULg; Leemans, Vincent ULg; Mansouri, Majdi ULg et al

in Environmental Modelling & Software (2014), 52

This study presents a Bayesian approach for the parameters’ identification of the STICS crop model based on the recently developed Differential Evolution Adaptive Metropolis (DREAM) algorithm. The ... [more ▼]

This study presents a Bayesian approach for the parameters’ identification of the STICS crop model based on the recently developed Differential Evolution Adaptive Metropolis (DREAM) algorithm. The posterior distributions of nine specific crop parameters of the STICS model were sampled with the aim to improve the growth simulations of a winter wheat (Triticum aestivum L.) culture. The results obtained with the DREAM algorithm were initially compared to those obtained with a Nelder-Mead Simplex algorithm embedded within the OptimiSTICS package. Then, three types of likelihood functions implemented within the DREAM algorithm were compared, namely the standard least square, the weighted least square, and a transformed likelihood function that makes explicit use of the coefficient of variation (CV). The results showed that the proposed CV likelihood function allowed taking into account both noise on measurements and heteroscedasticity which are regularly encountered in crop modelling [less ▲]

Detailed reference viewed: 38 (13 ULg)
Full Text
Peer Reviewed
See detailBayesian methods for predicting LAI and soil water content
Mansouri, Majdi ULg; Dumont, Benjamin ULg; Leemans, Vincent ULg et al

in Precision Agriculture (2014), 15(2), 184-201

LAI of winter wheat (Triticum aestivum L.) and soil water content of the topsoil (200 mm) and of the subsoil (500 mm) were considered as state variables of a dynamic soil-crop system. This system was ... [more ▼]

LAI of winter wheat (Triticum aestivum L.) and soil water content of the topsoil (200 mm) and of the subsoil (500 mm) were considered as state variables of a dynamic soil-crop system. This system was assumed to progress according to a Bayesian probabilistic state space model, in which real values of LAI and soil water content were daily introduced in order to correct the model trajectory and reach better future evolution. The chosen crop model was mini STICS which can reduce the computing and execution times while ensuring the robustness of data processing and estimation. To predict simultaneously state variables and model parameters in this non-linear environment, three techniques were used: Extended Kalman Filtering (EKF), Particle Filtering (PF), and Variational Filtering (VF). The significantly improved performance of the VF method when compared to EKF and PF is demonstrated. The variational filter has a low computational complexity and the convergence speed of states and parameters estimation can be adjusted independently. Detailed case studies demonstrated that the root mean square error (RMSE) of the three estimated states (LAI and soil water content of two soil layers) was smaller and that the convergence of all considered parameters was ensured when using VF. Assimilating measurements in a crop model allows accurate prediction of LAI and soil water content at a local scale. As these biophysical properties are key parameters in the crop-plant system characterization, the system has the potential to be used in precision farming to aid farmers and decision makers in developing strategies for site-specific management of inputs, such as fertilizers and water irrigation. [less ▲]

Detailed reference viewed: 29 (11 ULg)
Full Text
See detailULTRASONIC WAVES THROUGH AGRICULTURAL SOILS TO DETERMINE THEIR COMPACTION AND POROSITY LEVEL 
Luong, Jeanne ULg; Mercatoris, Benoît ULg; Destain, Marie-France ULg

Poster (2014)

Compaction is one of the major causes of the physical degradation of agricultural soils. The traffic of more and more heavy machines leads to a decrease of the porosity at both the topsoil and subsoil ... [more ▼]

Compaction is one of the major causes of the physical degradation of agricultural soils. The traffic of more and more heavy machines leads to a decrease of the porosity at both the topsoil and subsoil levels. This has negative impacts in agricultural and environmental contexts such as the reduction of soil fertility and water infiltration. This project aims at characterizing in a fast and non-destructive way the state of compaction of an agricultural soil at a local scale using ultrasonic wave propagation. Acoustic signatures of soil samples will be correlated to their compaction level and their porosity distribution. This should allow a better comprehension of the compaction process and help to define critical threshold. As a result, this methodology could assist in taking restrictive measures such as load limitation of agricultural engines and implementing remedial methods. This poster presents the experimental protocol implement for this research. [less ▲]

Detailed reference viewed: 16 (0 ULg)
Full Text
Peer Reviewed
See detailAssessing the potential of an algorithm based on mean climatic data to predict wheat yield
Dumont, Benjamin ULg; Leemans, Vincent ULg; Ferrandis, Salvador et al

in Precision Agriculture (2014)

The real-time non-invasive determination of crop biomass and yield prediction is one of the major challenges in agriculture. An interesting approach lies in using process-based crop yield models in ... [more ▼]

The real-time non-invasive determination of crop biomass and yield prediction is one of the major challenges in agriculture. An interesting approach lies in using process-based crop yield models in combination with real-time monitoring of the input climatic data of these models, but unknown future weather remains the main obstacle to reliable yield prediction. Since accurate weather forecasts can be made only a short time in advance, much information can be derived from analyzing past weather data. This paper presents a methodology that addresses the problem of unknown future weather by using a daily mean climatic database, based exclusively on available past measurements. It involves building climate matrix ensembles, combining different time ranges of projected mean climate data and real measured weather data originating from the historical database or from real-time measurements performed in the field. Used as an input for the STICS crop model, the datasets thus computed were used to perform statistical within-season biomass and yield prediction. This work demonstrated that a reliable predictive delay of 3-4 weeks could be obtained. In combination with a local micrometeorological station that monitors climate data in real-time, the approach also enabled us to (i) predict potential yield at the local level, (ii) detect stress occurrence and (iii) quantify yield loss (or gain) drawing on real monitored climatic conditions of the previous few days. [less ▲]

Detailed reference viewed: 13 (3 ULg)
Full Text
Peer Reviewed
See detailA comparison of within-season yield prediction methodologies
Dumont, Benjamin ULg; Basso, Bruno; Bodson, Bernard ULg et al

Conference (2013, November)

/

Detailed reference viewed: 17 (2 ULg)
Peer Reviewed
See detailPrediction of non-linear time-variant dynamic crop model using bayesian methods
Mansouri, Majdi ULg; Dumont, Benjamin ULg; Destain, Marie-France ULg

in John Stafford (Ed.) Precision agriculture '13 (2013, July)

This work addresses the problem of predicting a non-linear time-variant leaf area index and soil moisture model (LSM) using state estimation. These techniques include the extended Kalman filter (EKF ... [more ▼]

This work addresses the problem of predicting a non-linear time-variant leaf area index and soil moisture model (LSM) using state estimation. These techniques include the extended Kalman filter (EKF), particle filter (PF) and the more recently developed technique, variational filter (VF). In the comparative study, the state variables (the leaf-area index LAI, the volumetric water content of the layer 1, HUR1 and the volumetric water content of the layer 2, HUR2) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error with respect to the noise-free data. The results show that VF provides a significant improvement over EKF and PF. [less ▲]

Detailed reference viewed: 30 (6 ULg)
Full Text
Peer Reviewed
See detailYield variability linked to climate uncertainty and nitrogen fertilisation
Dumont, Benjamin ULg; Basso, Bruno; Leemans, Vincent ULg et al

in Stafford, John V. (Ed.) Precision agriculture '13 (2013, July)

At the parcel scale, crop models such as STICS are powerful tools to study the effects of variable inputs such as management practices (e.g. nitrogen (N) fertilisation). In combination with a weather ... [more ▼]

At the parcel scale, crop models such as STICS are powerful tools to study the effects of variable inputs such as management practices (e.g. nitrogen (N) fertilisation). In combination with a weather generator, we built up a general methodology that allows studying the yield variability linked to climate uncertainty, in order to assess the best N practice. Our study highlighted that, applying the Belgian farmer current N practice (60 60 60 kgN.ha-1), the yield distribution was found to be very asymmetric with a skewness of -1.02 and a difference of 5% between the mean (10.5 t.ha-1) and the median (11.05 t.ha-1) of the distribution. Which implied that, under such practice, the probability for farmers to achieve decent yields, in comparison of the mean of the distribution, was the highest. [less ▲]

Detailed reference viewed: 48 (17 ULg)
Full Text
Peer Reviewed
See detailA Site-Specific Grain Yield Response Surface : Computing the Identity Card of a Crop Under Different Nitrogen Management Scenarios
Dumont, Benjamin ULg; Basso, Bruno; Leemans, Vincent ULg et al

in The acts of the EFITA2013 congress (2013, June)

At the parcel scale, crop models such as STICS are powerful tools to study the effects of variable inputs such as management practices (e.g. nitrogen (N) fertilization). In combination with a weather ... [more ▼]

At the parcel scale, crop models such as STICS are powerful tools to study the effects of variable inputs such as management practices (e.g. nitrogen (N) fertilization). In combination with a weather generator, we propose a general methodology that allows studying the yield variability linked to climate uncertainty, in order to assess the best practices in applying fertilizers. Our study highlights that, using the usual practice of Belgian farmers, namely applying three doses of 60kgN/ha, the yield’s distribution presents the highest degree of asymmetry. This implies the highest probability to achieve yields superior to the mean. The computed return time of expected yield shows that 9 years out of 10, a grain yield of 7.26 tons.ha-1 could at least be achieved. [less ▲]

Detailed reference viewed: 29 (8 ULg)
Full Text
See detailZoom sur la rétention par les plantes
Lebeau, Frédéric ULg; Massinon, Mathieu ULg; Destain, Marie-France ULg

Conference given outside the academic context (2013)

This video aims to get an insight on the mechanisms involved in retention of pesticides on plants. Using high magnification lenses, high speed camera and led back-light, the elaboration of retention on ... [more ▼]

This video aims to get an insight on the mechanisms involved in retention of pesticides on plants. Using high magnification lenses, high speed camera and led back-light, the elaboration of retention on plant leaves is better understood. The behavior of different drops diameters and speed is observed and linked to the physics behind. The video is dedicated to plant protection products users and should give them a clear understanding of the relevant parameters to be mastered to avoid losses and reduce polution. [less ▲]

Detailed reference viewed: 27 (14 ULg)
Full Text
Peer Reviewed
See detailModeling and Prediction of Time-Varying Environmental Data Using Advanced Bayesian Methods
Mansouri, Majdi ULg; Dumont, Benjamin ULg; Destain, Marie-France ULg

in Masegosa, Antoçnio; Villacorta, Pablo; Cruz-Corona, Carlos (Eds.) et al Exploring Innovative and Successful Applications of Soft Computing (2013)

The problem of state/parameter estimation represents a key issue in crop models which are nonlinear, non-Gaussian and include a large number of parameters. The prediction errors are often important due to ... [more ▼]

The problem of state/parameter estimation represents a key issue in crop models which are nonlinear, non-Gaussian and include a large number of parameters. The prediction errors are often important due to uncertainties in the equations, the input variables, and the parameters. The measurements needed to run the model (input data), to perform calibration and validation are sometimes not numerous or known with some uncertainty. In these cases, estimating the state variables and/or parameters from easily obtained measurements can be extremely useful. In this work, we address the problem of modeling and prediction of leaf area index and soil moisture (LSM) using state estimation. The performances of various conventional and state-of-the-art state estimation techniques are compared when they are utilized to achieve this objective. These techniques include the extended Kalman filter (EKF), unscented Kalman filter (UKF), particle filter (PF), and the more recently developed technique variational Bayesian filter (VF). The objective of this work is to extend the state and parameter estimation techniques (i.e., EKF, UKF, PF and VF) to better handle nonlinear and non-Gaussian processes without a priori state information, by utilizing a time-varying assumption of statistical parameters. In this case, the state vector to be estimated at any instant is assumed to follow a Gaussian model, where the expectation and the covariance matrix are both random. The randomness of the expectation and the covariance of the state/parameter vector are assumed here to further capture the uncertainty of the state distribution. One practical choice of these distributions can be a Gaussian distribution for the expectation and a multi-dimensional Wishart distribution for the covariance matrix. The assumption of random mean and random covariance of the state leads to a probability distribution covering a wide range of tail behaviors, which allows discrete jumps in the state variables. [less ▲]

Detailed reference viewed: 70 (25 ULg)
Full Text
Peer Reviewed
See detailModeling and Prediction of Time-Varying Environmental Data Using Advanced Bayesian Methods
Mansouri, Majdi ULg; Dumont, Benjamin ULg; Destain, Marie-France ULg

in Masegosa, Antoçnio; Villacorta, Pablo; Cruz-Corona, Carlos (Eds.) et al Exploring Innovative and Successful Applications of Soft Computing (2013)

The problem of state/parameter estimation represents a key issue in crop models which are nonlinear, non-Gaussian and include a large number of parameters. The prediction errors are often important due to ... [more ▼]

The problem of state/parameter estimation represents a key issue in crop models which are nonlinear, non-Gaussian and include a large number of parameters. The prediction errors are often important due to uncertainties in the equations, the input variables, and the parameters. The measurements needed to run the model (input data), to perform calibration and validation are sometimes not numerous or known with some uncertainty. In these cases, estimating the state variables and/or parameters from easily obtained measurements can be extremely useful. In this work, we address the problem of modeling and prediction of leaf area index and soil moisture (LSM) using state estimation. The performances of various conventional and state-of-the-art state estimation techniques are compared when they are utilized to achieve this objective. These techniques include the extended Kalman filter (EKF), unscented Kalman filter (UKF), particle filter (PF), and the more recently developed technique variational Bayesian filter (VF). The objective of this work is to extend the state and parameter estimation techniques (i.e., EKF, UKF, PF and VF) to better handle nonlinear and non-Gaussian processes without a priori state information, by utilizing a time-varying assumption of statistical parameters. In this case, the state vector to be estimated at any instant is assumed to follow a Gaussian model, where the expectation and the covariance matrix are both random. The randomness of the expectation and the covariance of the state/parameter vector are assumed here to further capture the uncertainty of the state distribution. One practical choice of these distributions can be a Gaussian distribution for the expectation and a multi-dimensional Wishart distribution for the covariance matrix. The assumption of random mean and random covariance of the state leads to a probability distribution covering a wide range of tail behaviors, which allows discrete jumps in the state variables. [less ▲]

Detailed reference viewed: 70 (25 ULg)
Full Text
Peer Reviewed
See detailModeling and Prediction of Nonlinear Environmental System Using Bayesian Methods
Mansouri, Majdi; Dumont, Benjamin ULg; Destain, Marie-France ULg

in Computers & Electronics in Agriculture (2013), 92

An environmental dynamic system is usually modeled as a nonlinear system described by a set of nonlinear ODEs. A central challenge in computational modeling of environmental systems is the determination ... [more ▼]

An environmental dynamic system is usually modeled as a nonlinear system described by a set of nonlinear ODEs. A central challenge in computational modeling of environmental systems is the determination of the model parameters. In these cases, estimating these variables or parameters from other easily obtained measurements can be extremely useful. This work addresses the problem of monitoring and modeling a leaf area index and soil moisture model (LSM) using state estimation. The performances of various conventional and state-of-the-art state estimation techniques are compared when they are utilized to achieve this objective. These techniques include the extended Kalman filter (EKF), the particle filter (PF), and the more recently developed technique variational filter (VF). Specifically, two comparative studies are performed. In the first comparative study, the state variables (the leaf-area index LAI , the volumetric water content of the soil layer 1, HUR1 and the volumetric water content of the soil layer 2, HUR2) are estimated from noisy measurements of these variables, and the various estimation techniques are compared by computing the estimation root mean square error (RMSE) with respect to the noise-free data. In the second comparative study, the state variables as well as the model parameters are simultaneously estimated. In this case, in addition to comparing the performances of the various state estimation techniques, the effect of number of estimated model parameters on the accuracy and convergence of these techniques are also assessed. The results of both comparative studies show that the PF provides a higher accuracy than the EKF, which is due to the limited ability of the EKF to handle highly nonlinear processes. The results also show that the VF provides a significant improvement over the PF because, unlike the PF which depends on the choice of sampling distribution used to estimate the posterior distribution, the VF yields an optimum choice of the sampling distribution, which also accounts for the observed data. The results of the second comparative study show that, for all techniques, estimating more model parameters affects the estimation accuracy as well as the convergence of the estimated states and parameters. However, the VF can still provide both convergence as well as accuracy related advantages over other estimation methods. [less ▲]

Detailed reference viewed: 66 (33 ULg)