Development of Willow Tree Yield-Mapping Technology.

Area of Science:

• Agricultural Engineering
• Forestry Science
• Sustainable Energy

Background:

• Growing environmental concerns necessitate sustainable energy solutions.
• Woody biomass, particularly from short-rotation forestry (SRF), is a key area of research for renewable energy.
• Accurate yield mapping is essential for optimizing SRF operations.

Purpose of the Study:

• To develop and evaluate a novel technology for on-the-go yield mapping of willow trees in SRF systems.
• To assess the system's ability to capture physical characteristics like tree count and diameter during harvest.
• To integrate geospatial data for precise yield localization.

Main Methods:

• A machine-vision system utilizing an RGB-D stereovision camera was designed and implemented.
• The system captured tree count and diameter data during the harvesting process.
• Geographical coordinates were obtained using a Global Navigation Satellite System (GNSS) receiver for data tagging.

Main Results:

• The yield-mapping system demonstrated a 90% detection rate for manually observed trees in a row.
• The overall correct tree detection rate within scenes was 71.8% due to branch misidentification.
• Diameter estimation showed a low coefficient of determination and a root mean square error (RMSE) of 10.7 mm.

Conclusions:

• The developed system shows potential for mapping willow tree yield in SRF, despite challenges with complex environments and branch detection.
• Further refinement is needed to improve diameter estimation accuracy and reduce false positives.
• This technology can contribute to more efficient management of biomass resources for sustainable energy.