Spatial neural networks (SNNs)Spatial neural networks (SNNs) constitute a supercategory of tailored neural networks (NNs) for representing and predicting geographic phenomena. They generally improve both the statistical accuracy
Accuracy and precision are two measures of '' observational error''.
''Accuracy'' is how close a given set of measurements (observations or readings) are to their '' true value'', while ''precision'' is how close the measurements are to each ot ...
and reliability
Reliability, reliable, or unreliable may refer to:
Science, technology, and mathematics Computing
* Data reliability (disambiguation), a property of some disk arrays in computer storage
* High availability
* Reliability (computer networking), ...
of the a-spatial/classic NNs whenever they handle geo-spatial datasets, and also of the other spatial (statistical) models (e.g. spatial regression models) whenever the geo-spatial datasets' variables depict non-linear relations.
History
Openshaw
Openshaw is a suburb of Manchester, England, about three miles east of the city centre. Historically part of Lancashire, Openshaw was incorporated into the city of Manchester in 1890. Its name derives from the Old English ''Opinschawe'', which m ...
(1993) and Hewitson et al. (1994) started investigating the applications of the a-spatial/classic NNs to geographic phenomena.
They observed that a-spatial/classic NNs outperform the other extensively applied a-spatial/classic statistical models (e.g. regression models, clustering algorithms, maximum likelihood classifications) in
geography
Geography (from Greek: , ''geographia''. Combination of Greek words ‘Geo’ (The Earth) and ‘Graphien’ (to describe), literally "earth description") is a field of science devoted to the study of the lands, features, inhabitants, a ...
, especially when there exist non-linear
relations
Relation or relations may refer to:
General uses
*International relations, the study of interconnection of politics, economics, and law on a global level
*Interpersonal relationship, association or acquaintance between two or more people
*Public ...
between the geo-spatial datasets'
variables.
Thereafter, Openshaw (1998) also compared these a-spatial/classic NNs with other modern and original a-spatial statistical models at that time (i.e. fuzzy logic models, genetic algorithm models); he concluded that the a-spatial/classic NNs are statistically competitive.
Thereafter scientists developed several categories of SNNs – see below.
Spatial models
Spatial statistical models (aka geographically weighted models, or merely spatial models) like the geographically weighted regressions (GWRs), SNNs, etc., are spatially tailored (a-spatial/classic) statistical models, so to learn and model the deterministic components of the
spatial variability
Spatial variability occurs when a quantity that is measured at different spatial locations exhibits values that differ across the locations. Spatial variability can be assessed using spatial descriptive statistics such as the range.
Let us sup ...
(i.e.
spatial dependence/autocorrelation,
spatial heterogeneity
Spatial heterogeneity is a property generally ascribed to a landscape or to a population. It refers to the uneven distribution of various concentrations of each species within an area. A landscape with spatial heterogeneity has a mix of concentra ...
,
spatial association/cross-correlation) from the geo-locations of the geo-spatial datasets’
(statistical) individuals/units.
Categories
There exist several categories of methods/approaches for designing and applying SNNs.
*One-Size-Fits-all (OSFA) spatial neural networks, use the OSFA method/approach for globally computing the spatial
weights
Weight is a measurement of the gravitational force acting on an object.
Weight or The Weight may also refer to:
Mathematics
* Weight (graph theory) a number associated to an edge or to a vertex of a graph
* Weight (representation theory), a t ...
and designing a spatial
structure from the originally a-spatial/classic neural networks.
*Spatial Variability Aware Neural Networks (SVANNs) use an enhanced OSFA method/approach that locally recomputes the spatial weights and redesigns the spatial structure of the originally a-spatial/classic NNs, at each geo-location of the (statistical) individuals/units' attributes' values.
They generally outperform the OSFA spatial neural networks, but they do not consistently handle the spatial heterogeneity at multiple scales.
*Geographically Weighted Neural Networks (GWNNs) are similar to the SVANNs but they use the so-called Geographically Weighted Model (GWM) method/approach by Lu et al. (2023), so to locally recompute the spatial weights and redesign the spatial structure of the originally a-spatial/classic neural networks.
Like the SVANNs, they do not consistently handle spatial heterogeneity at multiple scales.
Applications
There exist
case-study
A case study is an in-depth, detailed examination of a particular case (or cases) within a real-world context. For example, case studies in medicine may focus on an individual patient or ailment; case studies in business might cover a particular fi ...
applications of SNNs in:
*
energy
In physics, energy (from Ancient Greek: ἐνέργεια, ''enérgeia'', “activity”) is the quantitative property that is transferred to a body or to a physical system, recognizable in the performance of work and in the form of hea ...
for predicting the
electricity consumption
Electric energy consumption is the form of energy consumption that uses electrical energy. Electric energy consumption is the actual energy demand made on existing electricity supply for transportation, residential, industrial, commercial, and ot ...
;
*
agriculture
Agriculture or farming is the practice of cultivating plants and livestock. Agriculture was the key development in the rise of sedentary human civilization, whereby farming of domesticated species created food surpluses that enabled peop ...
for classifying the
vegetation
Vegetation is an assemblage of plant species and the ground cover they provide. It is a general term, without specific reference to particular taxa, life forms, structure, spatial extent, or any other specific botanical or geographic charact ...
;
*
real estate
Real estate is property consisting of land and the buildings on it, along with its natural resources such as crops, minerals or water; immovable property of this nature; an interest vested in this (also) an item of real property, (more genera ...
for appraising the
premises
Premises are land and buildings together considered as a property. This usage arose from property owners finding the word in their title deeds, where it originally correctly meant "the aforementioned; what this document is about", from Latin ''pr ...
.
See also
*
Statistics
*
Neural networks' supercategories
*
Statistical software
Statistical software are specialized computer programs for analysis in statistics and econometrics.
Open-source
* ADaMSoft – a generalized statistical software with data mining algorithms and methods for data management
* ADMB – a softwa ...
*
Quantitative geography
Quantitative geography is a subfield of geography that develops, tests, and uses mathematical and statistical methods to analyze and model geographic phenomena and patterns. It aims to explain and predict the distribution and dynamics of human and ...
*
Spatial analysis
Spatial analysis or spatial statistics includes any of the formal techniques
Technique or techniques may refer to:
Music
* The Techniques, a Jamaican rocksteady vocal group of the 1960s
*Technique (band), a British female synth pop band in the ...
*
GIS software
A GIS software program is a computer program to support the use of a geographic information system, providing the ability to create, store, manage, query, analyze, and visualize geographic data, that is, data representing phenomena for which loc ...
References
{{reflist
Neural network architectures
Spatial analysis