B-spline and neuro-fuzzy models design with function and derivative equalities

The design of neuro-fuzzy models is still a complex problem, as it involves not only the determination of the model parameters, but also its structure. Of special importance is the incorporation of a priori information in the design process. In this paper two known design algorithms for B-spline models will be updated to account for function and derivatives equality restrictions, which are important when the neural model is used for performing single or multi-objective optimization on-line.

Effect of nitrogen and potassium fertilisation on vegetative growth and flowering of mature carob trees (Ceratonia siliqua): variations in leaf area index and water use indices

This work aimed to assess how potassium (K) and nitrogen (N) fertilisation may affect the use of precipitation in terms of vegetative and flowering response of 15-year-old carob trees during a 3-year experiment. A field trial was conducted in 1997, 1998 and 1999 in Algarve (Southern Portugal) in a calcareous soil. Four fertilisation treatments were tested: no fertiliser (control); 0.8 kg N/tree (N treatment); 1 kg K 2 O/tree (K treatment) and 0.8 kg N/tree plus 1 kg K 2 O/tree (NK treatment). No irrigation was applied during the experimental period. Branch length increments were measured every month throughout the growing season and inflorescence number was registered once per year. There was a strong seasonal effect on vegetative growth, since low levels of precipitation (115 mm) during October 1998–March 1999 suppressed the increment in branch length. N supplied to the trees (N and NK treatments) tended to increase water use indices in terms of vegetative growth. No response to K alone was observed in trees fertilised only with K. The number of inflorescences increased throughout the experimental period, particularly for N and NK treatments, and a reduction of the precipitation amount during April, May and June, may also enhance flowering. This knowledge could be important when making decisions concerning fertilisation under dry conditions. The results reported here indicate that tree growth (expressed as the branch growth) and flower production under dry-farming conditions, may be achieved by applying 0.8 kg of N (as ammonium nitrate) per tree during the growing season. However, N uptake and use depends on soil water availability.