Evaluation of a predictive model for Mycosphaerella graminicola for economic and environmental benefits

A method was developed to evaluate crop disease predictive models for their economic and environmental benefits. Benefits were quantified as the value of a prediction measured by costs saved and fungicide dose saved. The value of prediction was defined as the net gain made by using predictions, measured as the difference between a scenario where predictions are available and used and a scenario without prediction. Comparable 'with' and 'without' scenarios were created with the use of risk levels. These risk levels were derived from a probability distribution fitted to observed disease severities. These distributions were used to calculate the probability that a certain disease induced economic loss was incurred. The method was exemplified by using it to evaluate a model developed for Mycosphaerella graminicola risk prediction. Based on the value of prediction, the tested model may have economic and environmental benefits to growers if used to guide treatment decisions on resistant cultivars. It is shown that the value of prediction measured by fungicide dose saved and costs saved is constant with the risk level. The model could also be used to evaluate similar crop disease predictive models.

A predictive model for early-warning of Septoria leaf blotch on winter wheat

Disease-weather relationships influencing Septoria leaf blotch (SLB) preceding growth stage (GS) 31 were identified using data from 12 sites in the UK covering 8 years. Based on these relationships, an early-warning predictive model for SLB on winter wheat was formulated to predict the occurrence of a damaging epidemic (defined as disease severity of 5% or > 5% on the top three leaf layers). The final model was based on accumulated rain > 3 mm in the 80-day period preceding GS 31 (roughly from early-February to the end of April) and accumulated minimum temperature with a 0A degrees C base in the 50-day period starting from 120 days preceding GS 31 (approximately January and February). The model was validated on an independent data set on which the prediction accuracy was influenced by cultivar resistance. Over all observations, the model had a true positive proportion of 0.61, a true negative proportion of 0.73, a sensitivity of 0.83, and a specificity of 0.18. True negative proportion increased to 0.85 for resistant cultivars and decreased to 0.50 for susceptible cultivars. Potential fungicide savings are most likely to be made with resistant cultivars, but such benefits would need to be identified with an in-depth evaluation.

Automatic nonlinear predictive model-construction algorithm using forward regression and the PRESS statistic

An automatic nonlinear predictive model-construction algorithm is introduced based on forward regression and the predicted-residual-sums-of-squares (PRESS) statistic. The proposed algorithm is based on the fundamental concept of evaluating a model's generalisation capability through crossvalidation. This is achieved by using the PRESS statistic as a cost function to optimise model structure. In particular, the proposed algorithm is developed with the aim of achieving computational efficiency, such that the computational effort, which would usually be extensive in the computation of the PRESS statistic, is reduced or minimised. The computation of PRESS is simplified by avoiding a matrix inversion through the use of the orthogonalisation procedure inherent in forward regression, and is further reduced significantly by the introduction of a forward-recursive formula. Based on the properties of the PRESS statistic, the proposed algorithm can achieve a fully automated procedure without resort to any other validation data set for iterative model evaluation. Numerical examples are used to demonstrate the efficacy of the algorithm.

Towards cost-sensitive adaptation: when is it worth updating your predictive model?

Our digital universe is rapidly expanding,more and more daily activities are digitally recorded, data arrives in streams, it needs to be analyzed in real time and may evolve over time. In the last decade many adaptive learning algorithms and prediction systems, which can automatically update themselves with the new incoming data, have been developed. The majority of those algorithms focus on improving the predictive performance and assume that model update is always desired as soon as possible and as frequently as possible. In this study we consider potential model update as an investment decision, which, as in the financial markets, should be taken only if a certain return on investment is expected. We introduce and motivate a new research problem for data streams ? cost-sensitive adaptation. We propose a reference framework for analyzing adaptation strategies in terms of costs and benefits. Our framework allows to characterize and decompose the costs of model updates, and to asses and interpret the gains in performance due to model adaptation for a given learning algorithm on a given prediction task. Our proof-of-concept experiment demonstrates how the framework can aid in analyzing and managing adaptation decisions in the chemical industry.

Modelling trade contractor information production

Design management research usually deals with the processes within the professional design team and yet, in the UK, the volume of the total project information produced by the specialist trade contractors equals or exceeds that produced by the design team. There is a need to understand the scale of this production task and to plan and manage it accordingly. The model of the process on which the plan is to be based, while generic, must be sufficiently robust to cover the majority of instances. An approach using design elements, in sufficient depth to possibly develop tools for a predictive model of the process, is described. The starting point is that each construction element and its components have a generic sequence of design activities. Specific requirements tailor the element's application to the building. Then there are the constraints produced due to the interaction with other elements. Therefore, the selection of a component within the element may impose a set of constraints that will affect the choice of other design elements. Thus, a design decision can be seen as an interrelated element-constraint-element (ECE) sub-net. To illustrate this approach, an example of the process within precast concrete cladding has been used.

Modelling trade contractor information production

Design management research usually deals with the processes within the professional design team and yet, in the UK, the volume of the total project information produced by the specialist trade contractors equals or exceeds that produced by the design team. There is a need to understand the scale of this production task and to plan and manage it accordingly. The model of the process on which the plan is to be based, while generic, must be sufficiently robust to cover the majority of instances. An approach using design elements, in sufficient depth to possibly develop tools for a predictive model of the process, is described. The starting point is that each construction element and its components have a generic sequence of design activities. Specific requirements tailor the element's application to the building. Then there are the constraints produced due to the interaction with other elements. Therefore, the selection of a component within the element may impose a set of constraints that will affect the choice of other design elements. Thus, a design decision can be seen as an interrelated element-constraint-element (ECE) sub-net. To illustrate this approach, an example of the process within precast concrete cladding has been used.

UK construction orders and output: A comparison of government and commercially available data 1995-2001

Because of the importance and potential usefulness of construction market statistics to firms and government, consistency between different sources of data is examined with a view to building a predictive model of construction output using construction data alone. However, a comparison of Department of Trade and Industry (DTI) and Office for National Statistics (ONS) series shows that the correlation coefcient (used as a measure of consistency) of the DTI output and DTI orders data and the correlation coefficient of the DTI output and ONS output data are low. It is not possible to derive a predictive model of DTI output based on DTI orders data alone. The question arises whether or not an alternative independent source of data may be used to predict DTI output data. Independent data produced by Emap Glenigan (EG), based on planning applications, potentially offers such a source of information. The EG data records the value of planning applications and their planned start and finish dates. However, as this data is ex ante and is not correlated with DTI output it is not possible to use this data to describe the volume of actual construction output. Nor is it possible to use the EG planning data to predict DTI construc-tion orders data. Further consideration of the issues raised reveal that it is not practically possible to develop a consistent predictive model of construction output using construction statistics gathered at different stages in the development process.

Predicting space climate change

The recent decline in the open magnetic flux of the Sun heralds the end of the Grand Solar Maximum (GSM) that has persisted throughout the space age, during which the largest‐fluence Solar Energetic Particle (SEP) events have been rare and Galactic Cosmic Ray (GCR) fluxes have been relatively low. In the absence of a predictive model of the solar dynamo, we here make analogue forecasts by studying past variations of solar activity in order to evaluate how long‐term change in space climate may influence the hazardous energetic particle environment of the Earth in the future. We predict the probable future variations in GCR flux, near‐Earth interplanetary magnetic field (IMF), sunspot number, and the probability of large SEP events, all deduced from cosmogenic isotope abundance changes following 24 GSMs in a 9300‐year record.

Parameter sensitivity and predictive uncertainty in a new water quality model, Q(2)

A new dynamic model of water quality, Q(2), has recently been developed, capable of simulating large branched river systems. This paper describes the application of a generalized sensitivity analysis (GSA) to Q(2) for single reaches of the River Thames in southern England. Focusing on the simulation of dissolved oxygen (DO) (since this may be regarded as a proxy for the overall health of a river); the GSA is used to identify key parameters controlling model behavior and provide a probabilistic procedure for model calibration. It is shown that, in the River Thames at least, it is more important to obtain high quality forcing functions than to obtain improved parameter estimates once approximate values have been estimated. Furthermore, there is a need to ensure reasonable simulation of a range of water quality determinands, since a focus only on DO increases predictive uncertainty in the DO simulations. The Q(2) model has been applied here to the River Thames, but it has a broad utility for evaluating other systems in Europe and around the world.

Enhancing model predictive control using dynamic data reconciliation

The use of data reconciliation techniques can considerably reduce the inaccuracy of process data due to measurement errors. This in turn results in improved control system performance and process knowledge. Dynamic data reconciliation techniques are applied to a model-based predictive control scheme. It is shown through simulations on a chemical reactor system that the overall performance of the model-based predictive controller is enhanced considerably when data reconciliation is applied. The dynamic data reconciliation techniques used include a combined strategy for the simultaneous identification of outliers and systematic bias.

Model predictive control using dynamic integrated system optimisation and parameter estimation (DISOPE)

DISOPE is a technique for solving optimal control problems where there are differences in structure and parameter values between reality and the model employed in the computations. The model reality differences can also allow for deliberate simplification of model characteristics and performance indices in order to facilitate the solution of the optimal control problem. The technique was developed originally in continuous time and later extended to discrete time. The main property of the procedure is that by iterating on appropriately modified model based problems the correct optimal solution is achieved in spite of the model-reality differences. Algorithms have been developed in both continuous and discrete time for a general nonlinear optimal control problem with terminal weighting, bounded controls and terminal constraints. The aim of this paper is to show how the DISOPE technique can aid receding horizon optimal control computation in nonlinear model predictive control.

Evaluating the century C model using long-term fertilizer trials in the Indo-Gangetic Plains, India

The GEFSOC Project developed a system for estimating soil carbon (C) stocks and changes at the national and sub-national scale. As part of the development of the system, the Century ecosystem model was evaluated for its ability to simulate soil organic C (SOC) changes in environmental conditions in the Indo-Gangetic Plains, India (IGP). Two long-term fertilizer trials (LTFT), with all necessary parameters needed to run Century, were used for this purpose: a jute (Corchorus capsularis L.), rice (Oryza sativa L.) and wheat (Triticum aestivum L.) trial at Barrackpore, West Bengal, and a rice-wheat trial at Ludhiana, Punjab. The trials represent two contrasting climates of the IGP, viz. semi-arid, dry with mean annual rainfall (MAR) of < 800 mm and humid with > 1600 turn. Both trials involved several different treatments with different organic and inorganic fertilizer inputs. In general, the model tended to overestimate treatment effects by approximately 15%. At the semi-arid site, modelled data simulated actual data reasonably well for all treatments, with the control and chemical N + farm yard manure showing the best agreement (RMSE = 7). At the humid site, Century performed less well. This could have been due to a range of factors including site history. During the study, Century was calibrated to simulate crop yields for the two sites considered using data from across the Indian IGP. However, further adjustments may improve model performance at these sites and others in the IGP. The availability of more longterm experimental data sets (especially those involving flooded lowland rice and triple cropping systems from the IGP) for testing and validation is critical to the application of the model's predictive capabilities for this area of the Indian sub-continent. (C) 2007 Elsevier B.V. All rights reserved.

A GIS-based empirical model for vegetation prediction in Lefka Ori, Crete

The aim of the study was to establish and verify a predictive vegetation model for plant community distribution in the alti-Mediterranean zone of the Lefka Ori massif, western Crete. Based on previous work three variables were identified as significant determinants of plant community distribution, namely altitude, slope angle and geomorphic landform. The response of four community types against these variables was tested using classification trees analysis in order to model community type occurrence. V-fold cross-validation plots were used to determine the length of the best fitting tree. The final 9node tree selected, classified correctly 92.5% of the samples. The results were used to provide decision rules for the construction of a spatial model for each community type. The model was implemented within a Geographical Information System (GIS) to predict the distribution of each community type in the study site. The evaluation of the model in the field using an error matrix gave an overall accuracy of 71%. The user's accuracy was higher for the Crepis-Cirsium (100%) and Telephium-Herniaria community type (66.7%) and relatively lower for the Peucedanum-Alyssum and Dianthus-Lomelosia community types (63.2% and 62.5%, respectively). Misclassification and field validation points to the need for improved geomorphological mapping and suggests the presence of transitional communities between existing community types.

Predictive vegetation mapping in the Mediterranean context: Considerations and methodological issues

The need to map vegetation communities over large areas for nature conservation and to predict the impact of environmental change on vegetation distributions, has stimulated the development of techniques for predictive vegetation mapping. Predictive vegetation studies start with the development of a model relating vegetation units and mapped physical data, followed by the application of that model to a geographic database and over a wide range of spatial scales. This field is particularly important for identifying sites for rare and endangered species and locations of high biodiversity such as many areas of the Mediterranean Basin. The potential of the approach is illustrated with a mapping exercise in the alti-meditterranean zone of Lefka Ori in Crete. The study established the nature of the relationship between vegetation communities and physical data including altitude, slope and geomorphology. In this way the knowledge of community distribution was improved enabling a GIS-based model capable of predicting community distribution to be constructed. The paper describes the development of the spatial model and the methodological problems of predictive mapping for monitoring Mediterranean ecosystems. The paper concludes with a discussion of the role of predictive vegetation mapping and other spatial techniques, such as fuzzy mapping and geostatistics, for improving our understanding of the dynamics of Mediterranean ecosystems and for practical management in a region that is under increasing pressure from human impact.

A GIS-based empirical model for vegetation prediction in Lefka Ori, Crete

The aim of the study was to establish and verify a predictive vegetation model for plant community distribution in the alti-Mediterranean zone of the Lefka Ori massif, western Crete. Based on previous work three variables were identified as significant determinants of plant community distribution, namely altitude, slope angle and geomorphic landform. The response of four community types against these variables was tested using classification trees analysis in order to model community type occurrence. V-fold cross-validation plots were used to determine the length of the best fitting tree. The final 9node tree selected, classified correctly 92.5% of the samples. The results were used to provide decision rules for the construction of a spatial model for each community type. The model was implemented within a Geographical Information System (GIS) to predict the distribution of each community type in the study site. The evaluation of the model in the field using an error matrix gave an overall accuracy of 71%. The user's accuracy was higher for the Crepis-Cirsium (100%) and Telephium-Herniaria community type (66.7%) and relatively lower for the Peucedanum-Alyssum and Dianthus-Lomelosia community types (63.2% and 62.5%, respectively). Misclassification and field validation points to the need for improved geomorphological mapping and suggests the presence of transitional communities between existing community types.