Dominic Palmer-Brown

An international cooperative programme indicates the widespread occurrence of ozone injury on crops

The UN/ECE ICP-Vegetation 1 routinely investigates the effects of ambient ozone pollution on crops throughout Europe. Each year, a series of co-ordinated ambient air experiments are conducted over a large area of Europe and a range of crop species are observed for the occurrence of injury following ozone episodes. In 1995 and 1996, ozone injury was observed at sites throughout Europe from United Kingdom (Nottingham) to the Russian Federation (Moscow) and from Sweden (Ostad) to Italy (Naples). The only site participating in the ICP-Vegetation where it was not observed was that at Finland (Jokioinen). Injury was identified on subterranean and white clover, French bean, soybean, tomato, and watermelon at one or more sites. Injury was also detected in gardens and on crops growing in commercial fields. Two short-term critical levels which incorporate ozone dose and air saturation vapour pressure deficit (VPD) were derived from the 1995 data. These were (i) an AOT40 2 of 200 ppb.h over 5 days when mean VPD (0930‐1630 h) is below 1.5 kPa and (ii) an AOT40 of 500 ppb.h over 5 days when mean VPD (0930‐1630 h) is above 1.5 kPa. In general, the 1996 data supported these critical levels although injury did occur on two occasions when the AOT40 was less than 50 ppb.h, and the VPD was less than 0.6 kPa. Thus, ICP-Vegetation experiments have shown that ozone injury can occur over much of Europe and that plants are most at risk in conditions of high atmospheric humidity. ©2000 Elsevier Science B.V. All rights reserved.

Modeling complex environmental data

Artificial neural networks (ANNs) are used to model the interactions that occur between ozone pollution, climatic conditions, and the sensitivity of crops and other plants to ozone. A number of generic methods for analysis and modeling are presented. These methods are applicable to the modeling and analysis of any data where an effect (in this case damage to plants) is caused by a number of variables that have a nonlinear influence. Multilayer perceptron ANNs are used to model data from a number of sources and analysis of the trained optimized models determines the accuracy of the models predictions. The models are sufficiently general and accurate to be employed as decision support systems by United Nations Economic Commission for Europe (UNECE) in determining the critical acceptable levels of ozone in Europe. Comparison is made of the accuracy of predictions for a number of modeling approaches. It is shown that the ANN approach is more accurate than other methods and that the use of principal components analysis on the inputs can improve the model. The validation of the models relies on more than simply an error measure on the test data. The relative importance of the causal agents in the model is established in the first instance by summing absolute weight values. This indicates whether the model is consistent with domain knowledge. The application of a range of conditions to the model then allows predictions to be made about the nonlinear influences of the individual principal inputs and of combinations of two inputs viewed as a three-dimensional graph. Equations are synthesized from the ANN to represent the model in an explicit mathematical form. Models are formed with essential parameters and other inputs are added as necessary, in order of decreasing priority, until an acceptable error level is reached. Secondary indicators substituting for primary indicators with which they are strongly correlated can be removed. From the synthesized equations both known and novel aspects of the process modeled can be identified. Known effects validate the model. Novel effects form the basis of hypotheses which can then be tested.

Performance-guided neural network for rapidly self-organising active network management

We present a neural network for real-time learning and mapping of patterns using an external performance indicator. In a non-stationary environment where new patterns are introduced over time, the learning process utilises a novel snap-drift algorithm that performs fast, convergent, minimalist learning (snap) when the overall network performance is poor and slower, more cautious learning (drift) when the performance is good. Snap is based on a modified form of Adaptive Resonance Theory (CGIP 37(1987)54); and drift is based on Learning Vector Quantization (LVQ) (Proc. IJCNN 1(1990a)545). The two are combined within a semi-supervised learning system that shifts its learning style whenever it receives a significant change in performance feedback. The learning is capable of rapid re-learning and re-stabilisation, according to changes in external feedback or input patterns. We have incorporated this algorithm into the design of a modular neural network system, Performance-guided Adaptive Resonance Theory (P-ART) (Proc. IJCNN 2(2003)1412; Soft computing systems: Design, Management and application, IOS Press, Netherland, 2002; pp. 21-31). Simulation results show that the system discovers alternative solutions in response to significant changes in the input patterns and/or in the environment, which may require similar patterns to be treated differently over time. The simulations involve attempting to optimise the selection of network services in a non-stationary, real-time active computer network environment, in which the factors influencing the required selections are subject to change.

Identification of non-linear influences on the seasonal ozone dose-response of sensitive and resistant clover clones using artificial neural networks.

Abstract Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (Trifolium repens L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.

Connectionist natural language parsing

The key developments of two decades of connectionist parsing are reviewed. Connectionist parsers are assessed according to their ability to learn to represent syntactic structures from examples automatically, without being presented with symbolic grammar rules. This review also considers the extent to which connectionist parsers offer computational models of human sentence processing and provide plausible accounts of psycholinguistic data. In considering these issues, special attention is paid to the level of realism, the nature of the modularity, and the type of processing that is to be found in a wide range of parsers.

Towards unravelling the complex interactions between microclimate, ozone dose, and ozone injury in clover

This paper describes the results of a series of experiments designed to identify the relative importance of various factors which modify the responses of a sensitive species to ozone. The experiments were conducted in a closed chamber exposure system, enabling clover plants (Trifolium subterraneum L. cv Geraldton) to be exposed to ozone doses ranging from 0 to 1800 ppb.h, accumulated over 40 ppb (AOT40), for 7 h d−1, over 1 to 3 days. Microclimatic conditions during exposure ranged from 80 to 460 μmol m−2 s−1 photosynthetically active radiation (PAR), 26 to 61 percent relative humidity (%RJH) and 16 to 36 °C temperature. No clear dose response relationships were established for 1, 2 or 3 day exposures due to the influence of microclimatic and other factors during exposure. Artificial Neural Networks were used as a tool to identify patterns within the dose response data set and to clarify the effects of various microclimatic and dose topography responses, during multiple day exposures. Analysis of the trained neural network revealed that AOT40 on individual exposure days was the most important influences PAR on the first and third days of exposure, the mean relative humidity and the mean temperature for all days also had strong influences. Leaf age also had an influence but this was weaker. This paper describes these results in relation to the influences acting upon the plant and how these affect ozone uptake and resulting ozone injury.

(S)RAAM : An analytical technique for fast and reliable derivation of connectionist symbol structure representations

Recursive auto-associative memory (RAAM) has become established in the connectionist literature as a key contribution in the strive to develop connectionist representations of symbol structures. However, RAAMs use the backpropagation algorithm and therefore can be difficult to train and slow to learn. In addition, it is often hard to analyze exactly what a network has learnt and, therefore, it is difficult to state what composition mechanism is used by a RAAM for constructing representations. In this paper, we present an analytical version of RAAM, denoted as simplified RAAM or (S)RAAM. (S)RAAM models a RAAM very closely in that a single constructor matrix is derived which can be applied recursively to construct connectionist representations of symbol structures. The derivation, like RAAM, exhibits a moving target effect because training patterns adjust during learning but, unlike RAAM, the training is very fast. The analytical model allows a clear statement to be made about generalization characteristics...

ADFUNN: An Adaptive Function Neural Network

An adaptive function neural network (ADFUNN) is introduced. It is based on a linear piecewise artificial neuron activation function that is modified by a novel gradient descent supervised learning algorithm. This Δf process is carried out in parallel with the traditional Δw process. Linearly inseparable problems can be learned with ADFUNN, rapidly and without hidden neurons. The Iris dataset classification problem is learned as an example. An additional benefit of ADFUNN is that the learned functions can support intelligent data analysis.

A corpus-based connectionist architecture for large-scale natural language parsing

We describe a deterministic shift-reduce parsing model that combines the advantages of connectionism with those of traditional symbolic models for parsing realistic sub-domains of natural language. It is a modular system that learns to annotate natural language texts with syntactic structure. The parser acquires its linguistic knowledge directly from pre-parsed sentence examples extracted from an annotated corpus. The connectionist modules enable the automatic learning of linguistic constraints and provide a distributed representation of linguistic information that exhibits tolerance to grammatical variation. The inputs and outputs of the connectionist modules represent symbolic information which can be easily manipulated and interpreted and provide the basis for organizing the parse. Performance is evaluated using labelled precision and recall. (For a test set of 4128 words, precision and recall of 75% and 69%, respectively, were achieved.) The work presented represents a significant step towards demonstrating that broad coverage parsing of natural language can be achieved with simple hybrid connectionist architectures which approximate shift-reduce parsing behaviours. Crucially, the model is adaptable to the grammatical framework of the training corpus used and so is not predisposed to a particular grammatical formalism.

Illusions in action.

A recent study investigates the influence of visual illusions on childrens arm movements [Gentilucci, M. et al. (2001) Visual illusions and the control of childrens arm movements. Neuropsychologia 39, 132–139]. In these experiments, children and adults were asked to point to the ends of Muller-Lyer configurations, as well as to the ends of a control configuration. (see p. 109 of this issue of TICS for an article on illusion and action in which other experiments with similar configurations are reviewed and interpreted.) Gentilucci et al.s experiments involved two conditions: a visual condition, in which subjects saw both the configuration and their hand before and during movement; and a memory condition, in which they saw the configuration and their hand prior to movement but not during movement. The illusion affected pointing in both children and adults, causing them to under or overshoot the ends of the Muller-Lyer configurations but not the control. This effect was present under the visual condition and to a greater extent under the memory condition. The results suggest an interaction between visual object-centred perception and motor control systems. The principal difference between adults and children was that only the adults limited the duration of their acceleration to maintain constant movement time, indicating that they had an ability to coordinate acceleration and deceleration that the children had yet to develop. DPB