The method to extract phenological information for different land cover types is presented. Phenological features are two
different start dates of growing season, date of maximum growth, end of growing season and two growing season
lengths. Also, quality indicators are estimated for some phenological features. The method is based on NDVI-time series
extracted from MODIS-images. The errors between extracted dates and in-situ measurements are reasonably small. For
example, the residuals of the estimation of the start of Flux Growing Season are on only 2 days for broadleaf forest in
one Southern Finland hydrological drainage basin. The method has been tested on Northern Boreal forest zone, where
there are freezing temperatures and snow during winter.
This paper describes the ideas, data and methods to produce Finnish Corine Land Cover 2006 (CLC2006) classification.
This version is based on use of existing national GIS data and satellite images and their automated processing, instead of
visual interpretation of satellite images. The main idea is that land use information is based on GIS datasets and land
cover information interpretation of satellite images. Because Finland participated to CLC2000-project, also changes
between years 2000 and 2006 are determined. Finnish approach is good example how national GIS data is used to
produce data fulfilling European needs in bottom-up fashion.
Today, different carbon sources are producing more carbon dioxide than is being absorbed by carbon sinks, contributing
towards the instability in the natural balance of carbon dioxide. The goal of the SnowCarbo-project is to improve the
model predictions of carbon dioxide by using a variety of Earth Observation, GIS and in situ data in constraining and
calibrating the models. The aim of this article is to present different alternatives for land cover data needed in climate
and carbon balance modeling, and some preliminary evaluation in the context of climate modeling. The regional climate
model REMO developed at Max Planck Institute has been used to simulate the past, present and future climates over
wide range of spatial resolutions. These models use Olson ecosystem classification as land cover data, which represents
Finnish environment quite badly. Therefore, new versions of land cover data have been constructed based on higher
resolution GlobCover and Corine Land Cover classifications as well as classifying different MODIS-products. The
results are preliminary, but new versions seem to work better.
Markus Haakana, Suvi Hatunen, Pekka Härmä, Minna Kallio, Matti Katila, Tiia Kiiski, Kai Mäkisara, Jouni Peräsaari, Hanna Piepponen, Riikka Repo, Riitta Teiniranta, Erkki Tomppo, Markus Törmä
The European Comission introduced the CORINE Programme in 1985 in order to gather information relating to the
environment for the European Union. CORINE land cover classification is produced using satellite images and visual
interpretation. In Finland, CORINE has been made differently in order to produce more detailed national land cover
information at the same time. Finnish CORINE 2000 was based on automated interpretation of satellite images and data
integration with existing digital map data. Same process will be repeated with CORINE 2006 as well as possible. The
outputs are IMAGE2006 satellite images and mosaics, CORINE 2006 land cover classification and changes 2000-2006. These will be produced in different spatial resolutions: national raster data with spatial resolution of satellite images and European LC and LC changes with MMU of 25 and 5 hectares produced using mainly automated generalization
procedures.
SYKE is performing new CORINE 2006-classification for Finland. One of the aims is to make CORINE classification
in Northern Finland, meaning that classes like Natural grasslands and Moors and heathlands should be classified with
higher accuracy. Also, some specific classes need to be interpreted for national purposes like mountain birch forests.
This paper documents the first experiments made using decision tree classifier, optical and microwave remote sensing
data as well as DEM and soil information. Classes are pine, spruce, deciduous tree forests, two classes of mountain birch,
open bog, grasslands, heathlands and open rocks. The best overall accuracies were about 73%, when the overall accuracy
of Maximum Likelihood Classification was about 58%.
Cluster analysis is an important part of pattern recognition. In this paper we present the applicability of one neural network model, namely Kohonen self-organizing feature map, to cluster analysis. The aim is to develop a method which could determine the correct number of clusters by itself. First, the general concept of neural networks and detailed introduction to Kohonen self-organizing feature map are discussed. Then, the suitability of Kohonen self- organizing feature map to cluster analysis is discussed and some simulations are presented.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.