Lari Melander, Risto Ritala, Markus Strandström. (2019). Classifying soil stoniness based on the excavator boom vibration data in mounding operations. Silva Fennica vol. 53 no. 2 article id 10068. https://doi.org/10.14214/sf.10068

Keywords: spot mounding; activity recognition; stoniness classification; supervised machine learning

Highlights: An excavator was equipped with an inertial measurement unit for taking automatic measurements of soil stoniness during mounding work; Supervised machine-learning classifiers were trained utilizing both the automatically measured data and manual stoniness measurements; The class prediction for the soil stoniness achieved an accuracy of 70% when assigned to constant grid cells.

Abstract | Full text in HTML | Full text in PDF | Author Info

The stoniness index of forest soil describes the stone content in the upper soil layer at depths of 20–30 centimeters. This index is not available in any existing map databases, and traditional measurements for the stoniness of the soil have always necessitated laborious soil-penetration methods. Knowledge of the stone content of a forest site could be of use in a variety of forestry operations. This paper presents a novel approach to obtaining automatic measurements of soil stoniness during an excavator-based mounding operation. The excavator was equipped with only a low-cost inertial measurement unit and a satellite navigation receiver. Using the data from these sensors and manually conducted soil stoniness measurements, supervised machine learning methods were utilized to build a model that is capable of predicting the stoniness class of a given mounding location. This study compares different classifiers and feature selection methods to find the most promising solution for this learning problem. The discussion includes a proposition for a meaningful measurement resolution of the soil’s stoniness, and a practical method for evaluating the variability of the stone content of the soil. The results indicate that it is possible to predict the soil stoniness class with 70% accuracy using only the inertial and location measurements.

Melander, Automation Technology and Mechanical Engineering, Tampere University, FI-33014 Tampere University, Finland http://orcid.org/0000-0003-3662-5187 E-mail: lari.melander@tuni.fi
Ritala, Automation Technology and Mechanical Engineering, Tampere University, FI-33014 Tampere University, Finland http://orcid.org/0000-0003-0721-9948 E-mail: risto.ritala@tuni.fi
Strandström, Metsäteho Oy, Vernissakatu 1, FI-01300 Vantaa, Finland E-mail: markus.strandstrom@metsateho.fi

article id 146, category Research article

Karri Uotila, Juho Rantala, Timo Saksa, Pertti Harstela. (2010). Effect of soil preparation method on economic result of Norway spruce regeneration chain. Silva Fennica vol. 44 no. 3 article id 146. https://doi.org/10.14214/sf.146

Keywords: Picea abies; soil preparation; cleaning; disc trenching; forestry investment analysis; pre-commercial thinning; regeneration chain; spot mounding; sprouting

Abstract | View details | Full text in PDF | Author Info

Economic result of forest regeneration chains, based either on spot mounding or on disc trenching and planting of Norway spruce (Picea abies [L.] Karst.) seedlings, were clarified and compared to each other. First, effects of soil preparation method on early development of Norway spruce stands were measured from field experiments. Second, the effects of soil preparation method on stand level management programs were modelled. The modelling was based on growth simulation and investment calculations. The soil preparation methods substantially affected early development of a stand. The density of the removed trees in early cleaning was 56% higher on the disc-trenched area compared to the spot-mounded area. The difference was especially high (120%), close by (< 25 cm) the remained spruce seedlings. There was also a difference between the methods in the growth of crop spruces; at biological age of 8 years, the mean height of spruce was 110 cm on the spot-mounded area and 68 cm on the disc-trenched area. The differences led to divergent management programs between the areas. The disc-trenched area needed three young stand management operations whereas two was enough at the spot-mounded area. Although disc trenching is a less expensive method than spot mounding, the total management costs were higher in disc trenching than in spot mounding. Furthermore, incomes from the first commercial thinning were higher when regeneration based on spot mounding. At the interest rate of 3%, the investment in spot mounding had 329 EUR ha^–1 higher net present value than the investment in disc trenching.

Uotila, Finnish Forest Research Institute, Suonenjoki, Finland E-mail: karri.uotila@metla.fi
Rantala, Finnish Forest Research Institute, Suonenjoki, Finland E-mail: jr@nn.fi
Saksa, Finnish Forest Research Institute, Suonenjoki, Finland E-mail: ts@nn.fi
Harstela, Finnish Forest Research Institute, Suonenjoki, Finland E-mail: ph@nn.fi

Click this link to register to Silva Fennica.

If you are a registered user, log in to save your selected articles for later access.

Contents alert

Your selected articles

Follow @SilvaFennica