Change detection in boreal forests using bi-temporal aerial photographs

[Abstract]

Temporal trends in chemical parameters of upland forest soils in southern Finland

Abstract

Differential evolution based classification with pool of distances and aggregation operators

The objective of this thesis is to develop and generalize further the differential evolution based data classification method. For many years, evolutionary algorithms have been successfully applied to many classification tasks. Evolution algorithms are population based, stochastic search algorithms that mimic natural selection and genetics. Differential evolution is an evolutionary algorithm that has gained popularity because of its simplicity and good observed performance. In this thesis a differential evolution classifier with pool of distances is proposed, demonstrated and initially evaluated. The differential evolution classifier is a nearest prototype vector based classifier that applies a global optimization algorithm, differential evolution, to determine the optimal values for all free parameters of the classifier model during the training phase of the classifier. The differential evolution classifier applies the individually optimized distance measure for each new data set to be classified is generalized to cover a pool of distances. Instead of optimizing a single distance measure for the given data set, the selection of the optimal distance measure from a predefined pool of alternative measures is attempted systematically and automatically. Furthermore, instead of only selecting the optimal distance measure from a set of alternatives, an attempt is made to optimize the values of the possible control parameters related with the selected distance measure. Specifically, a pool of alternative distance measures is first created and then the differential evolution algorithm is applied to select the optimal distance measure that yields the highest classification accuracy with the current data. After determining the optimal distance measures for the given data set together with their optimal parameters, all determined distance measures are aggregated to form a single total distance measure. The total distance measure is applied to the final classification decisions. The actual classification process is still based on the nearest prototype vector principle; a sample belongs to the class represented by the nearest prototype vector when measured with the optimized total distance measure. During the training process the differential evolution algorithm determines the optimal class vectors, selects optimal distance metrics, and determines the optimal values for the free parameters of each selected distance measure. The results obtained with the above method confirm that the choice of distance measure is one of the most crucial factors for obtaining higher classification accuracy. The results also demonstrate that it is possible to build a classifier that is able to select the optimal distance measure for the given data set automatically and systematically. After finding optimal distance measures together with optimal parameters from the particular distance measure results are then aggregated to form a total distance, which will be used to form the deviation between the class vectors and samples and thus classify the samples. This thesis also discusses two types of aggregation operators, namely, ordered weighted averaging (OWA) based multi-distances and generalized ordered weighted averaging (GOWA). These aggregation operators were applied in this work to the aggregation of the normalized distance values. The results demonstrate that a proper combination of aggregation operator and weight generation scheme play an important role in obtaining good classification accuracy. The main outcomes of the work are the six new generalized versions of previous method called differential evolution classifier. All these DE classifier demonstrated good results in the classification tasks.

Spatial and temporal variation in fish populations and assemblages in coastal waters of the northern Baltic Proper

The distribution and traits of fish are of interest both ecologically and socio-economically. In this thesis, phenotypic and structural variation in fish populations and assemblages was studied on multiple spatial and temporal scales in shallow coastal areas in the archipelago of the northern Baltic Proper. In Lumparn basin in Åland Islands, the fish assemblage displayed significant seasonal variation in depth zone distribution. The results indicate that investigating both spatial and temporal variation in small scale is crucial for understanding patterns in fish distribution and community structure in large scale. The local population of Eurasian perch Perca fluviatilis L displayed habitat-specific morphological and dietary variation. Perch in the pelagic zone were on average deeper in their body shape than the littoral ones and fed on fish and benthic invertebrates. The results differ from previous studies conducted in freshwater habitats, where the pelagic perch typically are streamlined in body shape and zooplanktivorous. Stable isotopes of carbon and nitrogen differed between perch with different stomach contents, suggesting differentiation of individual diet preferences. In the study areas Lumparn and Ivarskärsfjärden in Åland Islands and Galtfjärden in Swedish east coast, the development in fish assemblages during the 2000’s indicated a general shift towards higher abundances of small-bodied lower-order consumers, especially cyprinids. For European pikeperch Sander lucioperca L., recent declines in adult fish abundances and high mortalities (Z = 1.06–1.16) were observed, which suggests unsustainably high fishing pressure on pikeperch. Based on the results it can be hypothesized that fishing has reduced the abundances of large predatory fish, which together with bottom-up forcing by eutrophication has allowed the lower-order consumer species to increase in abundances. This thesis contributes to the scientific understanding of aquatic ecosystems with new descriptions on morphological and dietary adaptations in perch in brackish water, and on the seasonal variation in small-scale spatial fish distribution. The results also demonstrate anthropogenic effects on coastal fish communities and underline the urgency of further reducing nutrient inputs and regulating fisheries in the Baltic Sea region.