Search results for "kartoitus"
showing 10 items of 61 documents
Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks
2020
Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep neural networks (DNN) have shown superior results when comparing with conventional machine learning methods such as multi-layer perceptron (MLP) in cases of huge input data. The objective of this research is to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were emp…
Standardised spider (Arachnida, Araneae) inventory of Lammi, Finland
2020
In June 2019, an ecology field course of the University of Helsinki was held at Lammi Biological Station, Southern Finland. Within this course, the students familiarised themselves with field work and identification of spiders and explored the diversity of species in the area. Three sampling plots were chosen, one in grassland and two in boreal forest, to demonstrate the sampling techniques and, by applying a standardised protocol (COBRA), contribute to a global spider biodiversity project. The collected samples contained a total of 3445 spiders, of which 1956 (57%) were adult. Only adult spiders were accounted for in the inventory due to the impossibility of identification of juveniles. A …
Airborne-laser-scanning-derived auxiliary information discriminating between broadleaf and conifer trees improves the accuracy of models for predicti…
2020
Managing forests for ecosystem services and biodiversity requires accurate and spatially explicit forest inventory data. A major objective of forest management inventories is to estimate the standing timber volume for certain forest areas. In order to improve the efficiency of an inventory, field based sample-plots can be statistically combined with remote sensing data. Such models usually incorporate auxiliary variables derived from canopy height models. The inclusion of forest type variables, which quantify broadleaf and conifer volume proportions, has been shown to further improve model performance. Currently, the most common way of quantifying broadleaf and conifer forest types is by ca…
Cost-efficiency assessments of marine monitoring methods lack rigor—a systematic mapping of literature and an end-user view on optimal cost-efficienc…
2021
Global deterioration of marine ecosystems, together with increasing pressure to use them, has created a demand for new, more efficient and cost-efficient monitoring tools that enable assessing changes in the status of marine ecosystems. However, demonstrating the cost-efficiency of a monitoring method is not straightforward as there are no generally applicable guidelines. Our study provides a systematic literature mapping of methods and criteria that have been proposed or used since the year 2000 to evaluate the cost-efficiency of marine monitoring methods. We aimed to investigate these methods but discovered that examples of actual cost-efficiency assessments in literature were rare, contr…
Atlas of Finnish bats
2019
This atlas is based on information in museum collections, literature, databases and unpublished data. In the last 150 years, the number of bat species in Finland increased from six to thirteen. Of these, five are common and regularly breeding (Eptesicus nilssonii, Myotis brandtii, Myotis daubentonii, Myotis mystacinus, Plecotus auritus), and eight rare (Eptesicus serotinus, Myotis dasycneme, Myotis nattereri, Nyctalus noctula, Pipistrellus nathusii, Pipistrellus pipistrellus, Pipistrellus pygmaeus, Vespertilio murinus), of which breeding of two (M. nattereri, P. nathusii) have been confirmed. The total number of records in the study is 11 234, of which 9717 are identified to species. The re…
Macrophytes shape trophic niche variation among generalist fishes.
2017
Generalist species commonly have a fundamental role in ecosystems as they can integrate spatially distinct habitats and food-web compartments, as well as control the composition, abundance and behavior of organisms at different trophic levels. Generalist populations typically consist of specialized individuals, but the potential for and hence degree of individual niche variation can be largely determined by habitat complexity. We compared individual niche variation within three generalist fishes between two comparable lakes in the Czech Republic differing in macrophyte cover, i.e. macrophyte-rich Milada and macrophyte-poor Most. We tested the hypothesis that large individual niche variation…
Chlorophyll a fluorescence illuminates a path connecting plant molecular biology to Earth-system science
2021
Remote sensing methods enable detection of solar-induced chlorophyll a fluorescence. However, to unleash the full potential of this signal, intensive cross-disciplinary work is required to harmonize biophysical and ecophysiological studies. For decades, the dynamic nature of chlorophyll a fluorescence (ChlaF) has provided insight into the biophysics and ecophysiology of the light reactions of photosynthesis from the subcellular to leaf scales. Recent advances in remote sensing methods enable detection of ChlaF induced by sunlight across a range of larger scales, from using instruments mounted on towers above plant canopies to Earth-orbiting satellites. This signal is referred to as solar-in…
Updates to Finnish aphyllophoroid funga (Basidiomycota):new species and range extensions
2018
Abstract The knowledge of Finnish aphyllophoroid funga has increased substantially in recent years. In this article we present six species new to Finland: Cristinia (cf.) rhenana Grosse-Brauckm., Hyphodontiella hauerslevii K.H. Larss. & Hjortstam, Leptosporomyces montanus (Jülich) Ginns & M.N.L Lefebvre, Osteina obducta (Berk.) Donk, Sebacina helvelloides (Schwein.) Burt, and Tulasnella brinkmannii sensu lato Bres. The finding of Osteina obducta is the first record in Northern Europe. The article also contributes new records of 56 nationally rare species (maximum ten previous records in Finland). Additionally, we list 110 regionally new species, found for the first time from a certa…
Chlorophyll Concentration Retrieval by Training Convolutional Neural Network for Stochastic Model of Leaf Optical Properties (SLOP) Inversion
2020
Miniaturized hyperspectral imaging techniques have developed rapidly in recent years and have become widely available for different applications. Combining calibrated hyperspectral imagery with inverse physically based reflectance models is an interesting approach for estimating chlorophyll concentrations that are good indicators of vegetation health. The objective of this study was to develop a novel approach for retrieving chlorophyll a and b values from remotely sensed data by inverting the stochastic model of leaf optical properties using a one-dimensional convolutional neural network. The inversion results and retrieved values are validated in two ways: A classical machine learning val…
Using Aerial Platforms in Predicting Water Quality Parameters from Hyperspectral Imaging Data with Deep Neural Networks
2020
In near future it is assumable that automated unmanned aerial platforms are coming more common. There are visions that transportation of different goods would be done with large planes, which can handle over 1000 kg payloads. While these planes are used for transportation they could similarly be used for remote sensing applications by adding sensors to the planes. Hyperspectral imagers are one this kind of sensor types. There is need for the efficient methods to interpret hyperspectral data to the wanted water quality parameters. In this work we survey the performance of neural networks in the prediction of water quality parameters from remotely sensed hyperspectral data in freshwater basin…