ZIB

Hits per page

hits 1 - 2 | 2 hits

Sorting

Electronic Resource

The influence of soil variability on tree establishment at an experimental agroforestry site in North East Nigeria (1997)

Adderley, W. P. ; Jenkins, D. A. ; Sinclair, E. L. ; [et al.]

Oxford, UK : Blackwell Publishing Ltd

Soil use and management 13 (1997), S. 0

add to mindlist on the mindlist

Details

ISSN: 1475-2743

Source: Blackwell Publishing Journal Backfiles 1879-2005

Topics: Geosciences , Agriculture, Forestry, Horticulture, Fishery, Domestic Science, Nutrition

Notes: Abstract. The characteristics and variability of soils within a 30 ha experimental site in N. E. Nigeria are analysed in relation to tree establishment. Profile description and analyses for some 480 surface samples of the sandy to clayey surface soils from Lake Chad lacustrine sediments provide baseline properties against which any subsequent modifications resulting from agroforestry practices can be assessed and to which initial tree performance can be related. This has been undertaken using principal component and spatial analyses. Inherited soil properties show spatial variations across the site which can be related to the soil textural parameters. The initial survival of trees planted for agroforestry experimentation shows strong correlations with the inherited characteristics of the soil rather than with acquired soil properties.

Type of Medium: Electronic Resource

URL: http://dx.doi.org/10.1111/j.1475-2743.1997.tb00549.x

Permalink

Library	Location	Call Number	Volume/Issue/Year	Availability

Others were also interested in ...

Paper (German National Licenses)

Fulltext

Electronic Resource

A novel neural network technique for the valuation of residential property (1997)

Lewis, O. M. ; Ware, J. A. ; Jenkins, D.

Springer

Neural computing & applications 5 (1997), S. 224-229

add to mindlist on the mindlist

Details

ISSN: 1433-3058

Keywords: Kohonen feature map ; Class discriminants ; Gamma test ; Residential property appraisal ; Back propagation ; Variance estimation

Source: Springer Online Journal Archives 1860-2000

Topics: Computer Science , Mathematics

Notes: Abstract A number of published studies have investigated the application of neural network technology to residential property appraisal. The majority of these studies have concentrated on homogeneous areas (that is areas where properties are subject to the same environment and locational factors). This is generally done to restrict the data set to one local sub- market. However, the models created are specialised and not locationally portable. This paper presents a methodology, which builds on research reported by James [1], in which a Kohonen map is used to uncover sub-markets within a large data set that are subsequently independently used to train a series of back-propagation networks. (The paper also introduces a novel boundary detection algorithm for a Kohonen self organising map.) The study concludes that by modelling possible sub-markets an acceptable accuracy over a heterogeneous area can be achieved. The work presented in this paper is funded via a Realising Our Potential Award under the auspices of the ESRC.