Search results for "geoinformatics"
showing 10 items of 11 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…
Identifying potential areas of expansion for the endangered brown bear (Ursus arctos) population in the cantabrian mountains (NW Spain)
2019
Many large carnivore populations are expanding into human-modified landscapes and the subsequent increase in coexistence between humans and large carnivores may intensify various types of conflicts. A proactive management approach is critical to successful mitigation of such conflicts. The Cantabrian Mountains in Northern Spain are home to the last remaining native brown bear (Ursus arctos) population of the Iberian Peninsula, which is also amongst the most severely threatened European populations, with an important core group residing in the province of Asturias. There are indications that this small population is demographically expanding its range. The identification of the potential are…
Large Spatial Scale of the Phenotype-Environment Color Matching in Two Cryptic Species of African Desert Jerboas (Dipodidae: Jaculus)
2014
We tested the camouflage hypothesis, or the linkage between animal (Saharan rodent) and habitat coloration, on the largest geographical scale yet conducted. We aimed to determine whether phenotypic variation is explained by micro-habitat variation and/or genetic polymorphism to determine 1) the strength of linkage between fur color and local substrate color, and 2) the divergence in fur coloration between two genetic clades, representing cryptic species, throughout the complete range of the African desert jerboas (Jaculus jaculus). We used a combination of museum and field-collected specimens, remote sensing tools, satellite and digital photography and molecular genetic and phylogenetic met…
CHANGING THE NATIONAL HEIGHT SYSTEM AND GEOID MODEL IN LATVIA
2016
According to the decision of IAG Reference Frame Sub-commission for Europe (EUREF) the EVRF2007 solution as the vertical reference has to be deployed in EU countries.The new height system LAS-2000,5 had been enacted as the European Vertical Reference System‘s EVRF2007 realization in Latvia and the new geoid model LV‘14 had been introduced by Latvian authority Latvian Geospatial Information Agency. However, the appreciation of the quality of quasi-geoid model LV‘14 is rather contradictious among the users in Latvia. The independent estimate and comparison of the two Latvian geoid models developed till now has been performed by the Institute of Geodesy and Geoinformatics. Previous geoid model…
Field tests of astrometric subsystem
2016
The paper presents results of astrometric subsystem’s functionality tests for space object laser ranging and astrometric position determination device, which is under construction in the Institute of Geodesy and Geoinformatics (GGI) of the University of Latvia. Properties of hardware performance for astrometric image acquisition were evaluated and optimal parameters have been selected. Software for image processing and calculation of instrument orientation was tested and adjustments have been made for real-time operation support. Object tracking properties were evaluated, and mount error model parameters were calculated, using test measurements.
Digital zenith camera of the University of Latvia
2016
Design of digital zenith camera in Institute of Geodesy and Geoinformatics of the University of Latvia started in 2009. Now, after tests of a prototype, improvements of design and manufacturing of the second version, it has reached operational status. The paper describes construction of camera, features of it‘s control software. Vertical deflection determination results are discussed.
Digital Zenith Cameras Results and Its Use in DFHRS v.4.3 Software for Quasi-Geoid Determination
2017
The design of digital zenith camera was started in 2010 by Institute of Geodesy and Geoinformatics. Since then the prototype of digital zenith camera has been developed. Now, after improvements of design and manufacturing of the second version, it has reached operational status. This paper describes the construction of zenith camera and features of its control software. The results of vertical deflections' measurements are discussed. At the moment measurements are done in Riga region and are used in DFHRS v.4.3 software in order to check and improve local quasigeoid model. It is a new method of quasigeoid model determination and has not been used in Latvia before. DFHRS (Digital Finite Elem…
Anger while driving in Mexico City
2019
This study aims to analyze the level of anger developed by drivers in Mexico City and also understand the behavior that those drivers use to express that anger, using four different survey methods. The first focuses on personal information, the second Driving Anger Expression Inventory (DAX), the third refers to a shorten version of Driving Anger Scale (DAS) and the fourth being the Dula Dangerous Driving Index (DDDI). These have previously been applied and validated in several different countries. The questionnaires were filled out online by 626 drivers. Using the data collected through the online platform, it was possible to identify the kind of reactions volunteers displayed while drivin…
Parameters for automated star identification
2014
The determination of parameters for identifying stars sensed by charge-coupled device (CCD) is discussed. Numerical experiments are summarized which support the parameter space bound estimation practicality of the proposed star pattern recognition and identification by matching with coordinate list in star catalogue. The parameter analysis performed to apply them for proper identification algorithm which is developed and used at the Institute of Geodesy and Geoinformatics. This algorithm is applied for identification of large volume star sets.
Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility U…
2020
Piping erosion is one form of water erosion that leads to significant changes in the landscape and environmental degradation. In the present study, we evaluated piping erosion modeling in the Zarandieh watershed of Markazi province in Iran based on random forest (RF), support vector machine (SVM), and Bayesian generalized linear models (Bayesian GLM) machine learning algorithms. For this goal, due to the importance of various geo-environmental and soil properties in the evolution and creation of piping erosion, 18 variables were considered for modeling the piping erosion susceptibility in the Zarandieh watershed. A total of 152 points of piping erosion were recognized in the study area that…