Jonne Pohjankukka

Arctic Soil Hydraulic Conductivity and Soil Type Recognition Based on Aerial Gamma-Ray Spectroscopy and Topographical Data

A central characteristic of soil in the arctic is its load bearing capacity since that property influences forest harvester mobility, flooding dynamics and infrastructure potential. The hydraulic conductivity has the greatest dynamical influence to bearing capacity and hence is essential to measure or estimate. In addition, the arctic soil type information is needed in many cases, e.g. in roads and railways building planning. In this paper we propose a method for hydraulic conductivity estimation via linear regression on aerial gamma-ray spectroscopy and publicly available topographical data with derived elevation based features. The same data is also utilized for the arctic soil type recognition, both logistics regression and nearest neighbor classification results are reported. The classification results for logistic regression resulted in 44.5% prediction performance and 50.5% for 8-nearest neighbor classifier respectively. Linear regression results for estimating the hydraulic conductivity of the soil resulted in C-index value of 0.63. The hydraulic conductivity and soil type estimation results are promising and the proposed topographic elevation features are apparently new for remote sensing community and should also have a wider general interest.

Predicting Water Permeability of the Soil Based on Open Data

Water permeability is a key concept when estimating load bearing capacity, mobility and infrastructure potential of a terrain. Northern sub-arctic areas have rather similar dominant soil types and thus prediction methods successful at Northern Finland may generalize to other arctic areas. In this paper we have predicted water permeability using publicly available natural resource data with regression analysis. The data categories used for regression were: airborne electro-magnetic and radiation, topographic height, national forest inventory data, and peat bog thickness. Various additional features were derived from original data to enable better predictions. The regression performances indicate that the prediction capability exists up to 120 meters from the closest direct measurement points. The results were measured using leave-one-out cross-validation with a dead zone between the training and testing data sets.

Estimating the prediction performance of spatial models via spatial k-fold cross validation

ABSTRACT In machine learning, one often assumes the data are independent when evaluating model performance. However, this rarely holds in practice. Geographic information datasets are an example where the data points have stronger dependencies among each other the closer they are geographically. This phenomenon known as spatial autocorrelation (SAC) causes the standard cross validation (CV) methods to produce optimistically biased prediction performance estimates for spatial models, which can result in increased costs and accidents in practical applications. To overcome this problem, we propose a modified version of the CV method called spatial k-fold cross validation (SKCV), which provides a useful estimate for model prediction performance without optimistic bias due to SAC. We test SKCV with three real-world cases involving open natural data showing that the estimates produced by the ordinary CV are up to 40% more optimistic than those of SKCV. Both regression and classification cases are considered in our experiments. In addition, we will show how the SKCV method can be applied as a criterion for selecting data sampling density for new research area.

Real-Time Swimmer Tracking on Sparse Camera Array

A swimmer detection and tracking is an essential first step in a video-based athletics performance analysis. A real-time algorithm is presented, with the following capabilities: performing the planar projection of the image, fading the background to protect the intimacy of other swimmers, framing the swimmer at a specific swimming lane, and eliminating the redundant video stream from idle cameras. The generated video stream is a basis for further analysis at the batch-mode. The geometric video transform accommodates a sparse camera array and enables geometric observations of swimmer silhouette. The tracking component allows real-time feedback and combination of different video streams to a single one. Swimming cycle registration algorithm based on markerless tracking is presented. The methodology allows unknown camera positions and can be installed in many types of public swimming pools.

Parallel applications and on-chip traffic distributions: Observation, implication and modelling

We study the traffic characteristics of parallel and high performance computing applications in this paper. Applications that utilize multiple cores are more and more common nowadays due to the emergence of multicore processors. However the design nature of single-threaded applications and multi-threaded applications can vary significantly. Furthermore the on-chip communication profile of multicore systems should be analysed and modelled for characterization and simulation purposes. We investigate several applications running on a full system simulation environment. The on-chip communication traces are gathered and analysed. We study the detailed low-level profiles of these applications. The applications are categorized into different groups according to various parallel programming paradigms. We discover that the trace data follow different parameters of power-law model. The problem is solved by applying least-squares linear regression. We propose a generic synthetic traffic model based on the analysis results.

Comparison of estimators and feature selection procedures in forest inventory based on airborne laser scanning and digital aerial imagery

ABSTRACT Digital maps of forest resources are a crucial factor in successful forestry applications. Since manual measurement of this data on large areas is infeasible, maps must be constructed using a sample field data set and a prediction model constructed from remote sensing materials, of which airborne laser scanning (ALS) data and aerial images are currently widely used in management planning inventories. ALS data is suitable for the prediction of variables related to the size and volume of trees, whereas optical imagery helps in improving distinction between tree species. We studied the prediction of forest attributes using field data from National Forest Inventory complemented with ad hoc field plots in combination with ALS and aerial imagery data in Aland province, Finland. We applied feature selection with genetic algorithm and greedy forward selection and compared multiple linear and nonlinear estimators. Maximally around 40 features from a total of 154 were required to achieve the best prediction performances. Tree height was predicted with normalized root mean squared error value of 0.1 and tree volume with a value around 0.25. Predicting the volumes of spruce and broadleaved trees was the most challenging due to small proportions of these tree species in the study area.

Triangular Curvature Approximation of Surfaces - Filtering the Spurious Mode.

Curvature spectrum is a useful feature in surface classification but is difficult to apply to cases with high noise typical e.g. to natural resource point clouds. We propose two methods to estimate the mean and the Gaussian curvature with filtering properties specific to triangulated surfaces. Methods completely filter a highest shape mode away but leave single vertical pikes only partially dampened. Also an elaborate computation of nodal dual areas used by the Laplace-Beltrami mean curvature can be avoided. All computation is based on triangular setting, and a weighted summation procedure using projected tip angles sums up the vertex values. A simplified principal curvature direction definition is given to avoid computation of the full second fundamental form. Qualitative evaluation is based on numerical experiments over two synthetical examples and a prostata tumor example. Results indicate the proposed methods are more robust to presence of noise than other four reference formulations.