Spatial modeling of electrical conductivity with neural network

Many policy decisions for agricultural management in the coastal region closely depend on the extent of intrusion of sea water. In this study, Artificial Neural Network (ANN) is used to model the spatial variation of Electrical Conductivity to determine the extent of sea water intrusion in the coastal area of Brisbane, Australia. Quarterly EC data obtained from the observation (monitoring) wells located along the coast is used for training ANN architecture. The study demonstrates that ANN is able to model the spatial variation of EC with very good accuracy (even with very less training records) when some spatial information is used as one of the inputs in the network training. The results considerable improvement when compared with the network trained without the distance information.

Preserving the environment and traditional communities : a land use change modeling approach

Human populations can cause serious damage to the natural environment. This, however, depends on the type of society and its size. Many traditional communities have a balanced relation with the environment, using practices for managing the soil, water and natural resources in order to satisfy their needs that are compatible to the general goals of environmental preservation.

The most usual approach to environmental conservation in the world sees human beings as intruders, potentially destroyers of the nature and, as a consequence, generally requires local population to be expelled from the protected regions. This situation has generated social conflicts because many protected areas, particularly in developing countries, are inhabited by indigenous or other traditional communities.

The disagreement about expelling or maintaining traditional communities in environmental conservation areas is strengthened by the lack of diagnostics on which changes are produced or suffered by communities in the region where they live. This paper presents a methodology developed to analyse land use dynamics in region with environmental conservation and traditional communities. We seek a better understanding of the way traditional communities use their space, the spatial pattern of land uses, which factors drive land use change, which impacts can be seen in those regions and identify the effects of conservation policies on land use dynamics.

The application of the method to the National Park of Superagui, Brazil, has successfully performed characterisation, analysis and simulation of land use dynamics in a region of environmental importance. Testing different scenarios has suggested that the adoption of a less restrictive policy for environmental conservation would have resulted in less social conflict with the same environmental efficiency than the established current policy.

Improved particle swarm optimization-based artificial neural network for rainfall-runoff modeling

This paper presents the application of an improved particle swarm optimization (PSO) technique for training an artificial neural network (ANN) to predict water levels for the Heshui watershed, China. Daily values of rainfall and water levels from 1988 to 2000 were first analyzed using ANNs trained with the conjugate-gradient, gradient descent and Levenberg-Marquardt neural network (LM-NN) algorithms. The best results were obtained from LM-NN and these results were then compared with those from PSO-based ANNs, including conventional PSO neural network (CPSONN) and improved PSO neural network (IPSONN) with passive congregation. The IPSONN algorithm improves PSO convergence by using the selfish herd concept in swarm behavior. Our results show that the PSO-based ANNs performed better than LM-NN. For models run using a single parameter (rainfall) as input, the root mean square error (RMSE) of the testing dataset for IPSONN was the lowest (0.152 m) compared to those for CPSONN (0.161 m) and LM-NN (0.205 m). For multi-parameter (rainfall and water level) inputs, the RMSE of the testing dataset for IPSONN was also the lowest (0.089 m) compared to those for CPSONN (0.105 m) and LM-NN (0.145 m). The results also indicate that the LM-NN model performed poorly in predicting the low and peak water levels, in comparison to the PSO-based ANNs. Moreover, the IPSONN model was superior to CPSONN in predicting extreme water levels. Lastly, IPSONN had a quicker convergence rate compared to CPSONN.

The actiheart in adolescents: a doubly labelled water validation

Background/Objective: This study investigated the validity of the Actiheart device for estimating free-living physical activity energy expenditure (PAEE) in adolescents. Subjects/Methods: Total energy expenditure (TEE) was measured in eighteen Canadian adolescents, aged 15–18 years, by DLW. Physical activity energy expenditure was calculated as 0.9 X TEE minus resting energy expenditure, assuming 10% for the thermic effect of feeding. Participants wore the chest mounted Actiheart device which records simultaneously minute-by-minute acceleration (ACC) and heart rate (HR). Using both children and adult branched equation modeling, derived from laboratory-based activity, PAEE was estimated from the ACC and HR data. Linear regression analyses examined the association between PAEE derived from the Actiheart and DLW method where DLW PAEE served as the dependent variable. Measurement of agreement between the two methods was analyzed using the Bland-Altman procedure. Results: A nonsignificant association was found between the children derived Actiheart and DLW PAEE values (R = .23, R2 = .05, p = .36); whereas a significant association was found between the adult derived Actiheart and DLW PAEE values (R = .53, R2 = .29, p < .05). Both the children and adult equation models lead to overestimations of PAEE by the Actiheart compared with the DLW method, by a mean difference of 31.42 kcal·kg−·d−1 (95% limits of agreement: −45.70 to −17.15 kcal·kg−1·d−1 and 9.80 kcal·kg−1·d−1 (95% limits of agreement: −21.22-1.72 kcal·kg−1·d−1), respectively. Conclusion: There is relatively poor measurement of agreement between the Actiheart and DLW for assessing free-living PAEE in adolescents. Future work should develop group based branched equation models specifically for adolescents to improve the utility of the device in this population.

Evaporation, seepage and water quality management in storage dams: a review of research methods

One of the most significant sources of water wastage in Australia is loss from small storage dams, either by seepage or evaporation. Over much of Australia, evaporative demand routinely exceeds precipitation. This paper outlines first, methodologies and measurement techniques to quantify the rate of evaporative loss from fresh water storages. These encompass high-accuracy water balance monitoring; determination of the validity of alternative estimation equations, in particular the FAO56 Penman- Monteith ETo methodology; and the commencement of CFD modeling to determine a 'dam factor' in relation to practical atmospheric measurement techniques. Second, because the application of chemical monolayers is the only feasible alternative to the high cost of physically covering the storages to retard evaporation, the use of cetyl alcohol-based monolayers is reviewed, and preliminary research on their degradation by photolytic action, by wind break-up and by microbial degradation reported. Similarly, preliminary research on monolayer visualisation techniques for field application is reported; and potential enhancement of monolayers by other chemicals and attendant water quality issues are considered.

Preformed and sprayable polymeric mulch film to improve agricultural water use efficiency

Plastic mulch films are widely used in agriculture to enhance crop production by suppressing weeds, conserving soil water and increasing soil temperature. The majority of plastic mulch films are however not biodegradable and are typically removed after each growing season. Recovery of these plastics from the soil is difficult and can affect successive crop yields while causing substantive cost to the environment and farmers. Due to increasingly stringent regulations regarding use of non-degradable plastic in agriculture they are likely to be phased out in the near future. In the past 10 years several classes of 'biodegradable' materials have been studied but most of these films are reported to be relatively weak in mechanical properties, not efficiently degradable and cost prohibitive.More recently, researchers have turned their attention to sprayable biodegradable polymer coatings for use on soils due to their easy application and versatility. The ability to mix natural additives, plasticizers and fillers to control and improve the mechanical and biodegradation properties of the core polymeric mulch film has been the driving force behind the development of these next generation sprayable polymeric mulch films.There have been many excellent review articles and papers written about polymeric mulch film, but the developing sprayable polymer systems have not been reviewed to the same extent. This paper focusses on the research progress in the area of biodegradable and sprayable polymer mulch film with emphasis on polymer formulations, properties and application. It also discusses current research to highlight the importance, potential benefits and future challenges in developing a cost effective biodegradable sprayable film for use in production agriculture.