Attributes | Values |
---|
rdf:type
| |
Description
| - Data from traditional soil survey present an important source of information on soils. This contribution presents an attempt to apply modern artificial neural networks method to data from soil survey carried in the 1960’s. The main objective was to find a quantitative procedure of soil classification comparable to traditional classification. Data on basic soil characteristics and morphological description of more than 600 sampling points in the district of Tabor were used as input variables. Traditional soil classes were set as the output variables. Several models of neural networks, with different inputs and structures, were selected. The models were compared with other classification methods (cluster analysis, fuzzy k-means). The effect of different input data was evaluated. The following problems were found to be the most important: 1) Forest soils that were not included in the original survey, which therefore causes some discontinuity in data; however, this is a problem rather for spatial analysi
- Data from traditional soil survey present an important source of information on soils. This contribution presents an attempt to apply modern artificial neural networks method to data from soil survey carried in the 1960’s. The main objective was to find a quantitative procedure of soil classification comparable to traditional classification. Data on basic soil characteristics and morphological description of more than 600 sampling points in the district of Tabor were used as input variables. Traditional soil classes were set as the output variables. Several models of neural networks, with different inputs and structures, were selected. The models were compared with other classification methods (cluster analysis, fuzzy k-means). The effect of different input data was evaluated. The following problems were found to be the most important: 1) Forest soils that were not included in the original survey, which therefore causes some discontinuity in data; however, this is a problem rather for spatial analysi (en)
- Data from traditional soil survey present an important source of information on soils. This contribution presents an attempt to apply modern artificial neural networks method to data from soil survey carried in the 1960’s. The main objective was to find a quantitative procedure of soil classification comparable to traditional classification. Data on basic soil characteristics and morphological description of more than 600 sampling points in the district of Tabor were used as input variables. Traditional soil classes were set as the output variables. Several models of neural networks, with different inputs and structures, were selected. The models were compared with other classification methods (cluster analysis, fuzzy k-means). The effect of different input data was evaluated. The following problems were found to be the most important: 1) Forest soils that were not included in the original survey, which therefore causes some discontinuity in data; however, this is a problem rather for spatial analysi (cs)
|
Title
| - Artificial neural networks as an aid in soil classification.
- Artificial neural networks as an aid in soil classification. (en)
- Umělé neuronové sítě jako nástroj v klasifikaci půd (cs)
|
skos:prefLabel
| - Artificial neural networks as an aid in soil classification.
- Artificial neural networks as an aid in soil classification. (en)
- Umělé neuronové sítě jako nástroj v klasifikaci půd (cs)
|
skos:notation
| - RIV/60460709:41210/04:8392!RIV/2005/GA0/412105/N
|
http://linked.open.../vavai/riv/strany
| |
http://linked.open...avai/riv/aktivita
| |
http://linked.open...avai/riv/aktivity
| |
http://linked.open...vai/riv/dodaniDat
| |
http://linked.open...aciTvurceVysledku
| |
http://linked.open.../riv/druhVysledku
| |
http://linked.open...iv/duvernostUdaju
| |
http://linked.open...titaPredkladatele
| |
http://linked.open...dnocenehoVysledku
| |
http://linked.open...ai/riv/idVysledku
| - RIV/60460709:41210/04:8392
|
http://linked.open...riv/jazykVysledku
| |
http://linked.open.../riv/klicovaSlova
| - soil classification, artificial neural networks, pedometrics, soil data (en)
|
http://linked.open.../riv/klicoveSlovo
| |
http://linked.open...ontrolniKodProRIV
| |
http://linked.open...v/mistoKonaniAkce
| |
http://linked.open...i/riv/mistoVydani
| |
http://linked.open...i/riv/nazevZdroje
| |
http://linked.open...in/vavai/riv/obor
| |
http://linked.open...ichTvurcuVysledku
| |
http://linked.open...cetTvurcuVysledku
| |
http://linked.open...vavai/riv/projekt
| |
http://linked.open...UplatneniVysledku
| |
http://linked.open...iv/tvurceVysledku
| - Borůvka, Luboš
- Penížek, Vít
- Kozák, Josef
|
http://linked.open...vavai/riv/typAkce
| |
http://linked.open.../riv/zahajeniAkce
| |
number of pages
| |
http://purl.org/ne...btex#hasPublisher
| |
https://schema.org/isbn
| |
http://localhost/t...ganizacniJednotka
| |