Classifying soil stoniness based on the excavator boom vibration data in mounding operations
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. Kn...
| Main Authors: | , , |
|---|---|
| Formato: | Artigo |
| Idioma: | English |
| Publicado em: |
Finnish Society of Forest Science
2019-06-01
|
| Colecção: | Silva Fennica |
| Assuntos: |
| _version_ | 1828529149846749184 |
|---|---|
| author | Lari Melander Risto Ritala Markus Strandström |
| author_facet | Lari Melander Risto Ritala Markus Strandström |
| author_sort | Lari Melander |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-11T22:03:56Z |
| format | Article |
| id | doaj.art-1dff2061a6db4b8c84a03c3c7635b44f |
| institution | Directory Open Access Journal |
| issn | 2242-4075 2242-4075 |
| language | English |
| last_indexed | 2024-12-11T22:03:56Z |
| publishDate | 2019-06-01 |
| publisher | Finnish Society of Forest Science |
| record_format | Article |
| series | Silva Fennica |
| spelling | doaj.art-1dff2061a6db4b8c84a03c3c7635b44f2022-12-22T00:49:01ZengFinnish Society of Forest ScienceSilva Fennica2242-40752242-40752019-06-0153210.14214/sf.10068Classifying soil stoniness based on the excavator boom vibration data in mounding operationsLari Melander0Risto Ritala1Markus Strandström2Automation Technology and Mechanical Engineering, Tampere University, FI-33014 Tampere University, FinlandAutomation Technology and Mechanical Engineering, Tampere University, FI-33014 Tampere University, FinlandMetsäteho Oy, Vernissakatu 1, FI-01300 Vantaa, FinlandThe 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.spot moundingactivity recognitionstoniness classificationsupervised machine learning |
| spellingShingle | Lari Melander Risto Ritala Markus Strandström Classifying soil stoniness based on the excavator boom vibration data in mounding operations Silva Fennica spot mounding activity recognition stoniness classification supervised machine learning |
| title | Classifying soil stoniness based on the excavator boom vibration data in mounding operations |
| title_full | Classifying soil stoniness based on the excavator boom vibration data in mounding operations |
| title_fullStr | Classifying soil stoniness based on the excavator boom vibration data in mounding operations |
| title_full_unstemmed | Classifying soil stoniness based on the excavator boom vibration data in mounding operations |
| title_short | Classifying soil stoniness based on the excavator boom vibration data in mounding operations |
| title_sort | classifying soil stoniness based on the excavator boom vibration data in mounding operations |
| topic | spot mounding activity recognition stoniness classification supervised machine learning |
| work_keys_str_mv | AT larimelander classifyingsoilstoninessbasedontheexcavatorboomvibrationdatainmoundingoperations AT ristoritala classifyingsoilstoninessbasedontheexcavatorboomvibrationdatainmoundingoperations AT markusstrandstrom classifyingsoilstoninessbasedontheexcavatorboomvibrationdatainmoundingoperations |