Classification of crops across heterogeneous agricultural landscape in Kenya using AisaEAGLE imaging spectroscopy data

Rami Piiroinen (Corresponding Author), Janne Heiskanen, Matti Mõttus, Petri Pellikka

Research output: Contribution to journalArticleScientificpeer-review

23 Citations (Scopus)

Abstract

Land use practices are changing at a fast pace in the tropics. In sub-Saharan Africa forests, woodlands and bushlands are being transformed for agricultural use to produce food for the rapidly growing population. The objective of this study was to assess the prospects of mapping the common agricultural crops in highly heterogeneous study area in south-eastern Kenya using high spatial and spectral resolution AisaEAGLE imaging spectroscopy data. Minimum noise fraction transformation was used to pack the coherent information in smaller set of bands and the data was classified with support vector machine (SVM) algorithm. A total of 35 plant species were mapped in the field and seven most dominant ones were used as classification targets. Five of the targets were agricultural crops. The overall accuracy (OA) for the classification was 90.8%. To assess the possibility of excluding the remaining 28 plant species from the classification results, 10 different probability thresholds (PT) were tried with SVM. The impact of PT was assessed with validation polygons of all 35 mapped plant species. The results showed that while PT was increased more pixels were excluded from non-target polygons than from the polygons of the seven classification targets. This increased the OA and reduced salt-and-pepper effects in the classification results. Very high spatial resolution imagery and pixel-based classification approach worked well with small targets such as maize while there was mixing of classes on the sides of the tree crowns.
Original languageEnglish
Pages (from-to)1-8
JournalInternational Journal of Applied Earth Observation and Geoinformation
Volume39
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Crops
agricultural land
spectroscopy
Spectroscopy
Imaging techniques
crop
polygon
Support vector machines
pixel
spatial resolution
Pixels
bushland
Tropics
Spectral resolution
spectral resolution
Land use
woodland
imagery
maize
Salts

Keywords

  • Land cover classification
  • Imaging spectroscopy
  • Heterogeneous landscape
  • Support vector machine
  • Minimum noise fraction

Cite this

@article{bbebf78f36a34510ad7513916ee4ade0,
title = "Classification of crops across heterogeneous agricultural landscape in Kenya using AisaEAGLE imaging spectroscopy data",
abstract = "Land use practices are changing at a fast pace in the tropics. In sub-Saharan Africa forests, woodlands and bushlands are being transformed for agricultural use to produce food for the rapidly growing population. The objective of this study was to assess the prospects of mapping the common agricultural crops in highly heterogeneous study area in south-eastern Kenya using high spatial and spectral resolution AisaEAGLE imaging spectroscopy data. Minimum noise fraction transformation was used to pack the coherent information in smaller set of bands and the data was classified with support vector machine (SVM) algorithm. A total of 35 plant species were mapped in the field and seven most dominant ones were used as classification targets. Five of the targets were agricultural crops. The overall accuracy (OA) for the classification was 90.8{\%}. To assess the possibility of excluding the remaining 28 plant species from the classification results, 10 different probability thresholds (PT) were tried with SVM. The impact of PT was assessed with validation polygons of all 35 mapped plant species. The results showed that while PT was increased more pixels were excluded from non-target polygons than from the polygons of the seven classification targets. This increased the OA and reduced salt-and-pepper effects in the classification results. Very high spatial resolution imagery and pixel-based classification approach worked well with small targets such as maize while there was mixing of classes on the sides of the tree crowns.",
keywords = "Land cover classification, Imaging spectroscopy, Heterogeneous landscape, Support vector machine, Minimum noise fraction",
author = "Rami Piiroinen and Janne Heiskanen and Matti M{\~o}ttus and Petri Pellikka",
year = "2015",
doi = "10.1016/j.jag.2015.02.005",
language = "English",
volume = "39",
pages = "1--8",
journal = "International Journal of Applied Earth Observation and Geoinformation",
issn = "1569-8432",
publisher = "Elsevier",

}

Classification of crops across heterogeneous agricultural landscape in Kenya using AisaEAGLE imaging spectroscopy data. / Piiroinen, Rami (Corresponding Author); Heiskanen, Janne; Mõttus, Matti; Pellikka, Petri.

In: International Journal of Applied Earth Observation and Geoinformation, Vol. 39, 2015, p. 1-8.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Classification of crops across heterogeneous agricultural landscape in Kenya using AisaEAGLE imaging spectroscopy data

AU - Piiroinen, Rami

AU - Heiskanen, Janne

AU - Mõttus, Matti

AU - Pellikka, Petri

PY - 2015

Y1 - 2015

N2 - Land use practices are changing at a fast pace in the tropics. In sub-Saharan Africa forests, woodlands and bushlands are being transformed for agricultural use to produce food for the rapidly growing population. The objective of this study was to assess the prospects of mapping the common agricultural crops in highly heterogeneous study area in south-eastern Kenya using high spatial and spectral resolution AisaEAGLE imaging spectroscopy data. Minimum noise fraction transformation was used to pack the coherent information in smaller set of bands and the data was classified with support vector machine (SVM) algorithm. A total of 35 plant species were mapped in the field and seven most dominant ones were used as classification targets. Five of the targets were agricultural crops. The overall accuracy (OA) for the classification was 90.8%. To assess the possibility of excluding the remaining 28 plant species from the classification results, 10 different probability thresholds (PT) were tried with SVM. The impact of PT was assessed with validation polygons of all 35 mapped plant species. The results showed that while PT was increased more pixels were excluded from non-target polygons than from the polygons of the seven classification targets. This increased the OA and reduced salt-and-pepper effects in the classification results. Very high spatial resolution imagery and pixel-based classification approach worked well with small targets such as maize while there was mixing of classes on the sides of the tree crowns.

AB - Land use practices are changing at a fast pace in the tropics. In sub-Saharan Africa forests, woodlands and bushlands are being transformed for agricultural use to produce food for the rapidly growing population. The objective of this study was to assess the prospects of mapping the common agricultural crops in highly heterogeneous study area in south-eastern Kenya using high spatial and spectral resolution AisaEAGLE imaging spectroscopy data. Minimum noise fraction transformation was used to pack the coherent information in smaller set of bands and the data was classified with support vector machine (SVM) algorithm. A total of 35 plant species were mapped in the field and seven most dominant ones were used as classification targets. Five of the targets were agricultural crops. The overall accuracy (OA) for the classification was 90.8%. To assess the possibility of excluding the remaining 28 plant species from the classification results, 10 different probability thresholds (PT) were tried with SVM. The impact of PT was assessed with validation polygons of all 35 mapped plant species. The results showed that while PT was increased more pixels were excluded from non-target polygons than from the polygons of the seven classification targets. This increased the OA and reduced salt-and-pepper effects in the classification results. Very high spatial resolution imagery and pixel-based classification approach worked well with small targets such as maize while there was mixing of classes on the sides of the tree crowns.

KW - Land cover classification

KW - Imaging spectroscopy

KW - Heterogeneous landscape

KW - Support vector machine

KW - Minimum noise fraction

UR - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=ORCID&SrcApp=OrcidOrg&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=WOS:000355367900002&KeyUID=WOS:000355367900002

U2 - 10.1016/j.jag.2015.02.005

DO - 10.1016/j.jag.2015.02.005

M3 - Article

VL - 39

SP - 1

EP - 8

JO - International Journal of Applied Earth Observation and Geoinformation

JF - International Journal of Applied Earth Observation and Geoinformation

SN - 1569-8432

ER -