Drone data for decision making in regeneration forests: from raw data to actionable insights¹

Abstract

Unmanned aerial vehicle (UAV) photogrammetric data and data analytics were used to model stand-level immediate tending need and cost in regeneration forests. Field reference data were used to train and validate a logistic model for the binary classification of immediate tending need and a multiple linear regression model to predict the cost to perform the tending operation. The performance of the models derived from UAV data was compared to models utilizing the following alternative data sources: airborne laser scanning data (ALS), prior inventory information (Prior), and the combination of UAV and Prior and ALS and Prior. The use of UAV and Prior data outperformed the remaining alternatives in terms of classification of tending needs, while UAV alone produced the most accurate cost models. Our results are encouraging for further use of UAVs in the operational management of regeneration forests and show that UAV data and data analytics are useful for deriving actionable insights.

UAV-Supported Forest Regeneration: Current Trends, Challenges and Implications

“…Once the seedlings are well rooted in the soil, the post-plant monitoring phase starts, and the UAVs help keep track of the regeneration success and the seedling's growth consistently; for more information on the monitoring processes, including various stateof-art classification techniques, please refer to [32,[63][64][65]. Using spraying UAVs (e.g., DJI Agras), it is also possible to provide the water and nutrients (through fertilizers) that are crucial for the seedlings in their initial vegetation growth period.…”

A Systematic Review on Technologies and Industry 4.0 in the Forest Supply Chain: A Framework Identifying Challenges and Opportunities

“…Pichler et al [51] built a 3D forest model based on UAV and TLS technology for forest inventory, forest management and harvesting. Puliti and Granhus [52] performed data analytics with UAV data on the operational management of regeneration forests compared to the model with ALS data. Siipilehto et al [47] used the ALS-based method and a smartphone application called Trestima for forest inventory.…”

“…Simulation [36,69] IoT [54] UAV [51,52] Data analytics [52] TLS [51] GPS [51] Smartphone application [51] Forest inventory ALS [53] UAV [51] TLS [51] Smartphone application [53] Planning Simulation [40] Machine learning [55] Procurement Simulation [56,57] Blockchain [70] Harvesting Simulation [56] UAV [51] TLS [51] RFID [51] GPS [51] Smartphone application [51] Production-sawmill Simulation [36] AI [59,60] Machine learning [55] IoT [58] GPS [58] RFID [58] Smartphone application [58] Could technology [58] Production-biofuel factory Simulation [50,61] GIS [50,61] Production-bioethanol factory GIS [44] Production-biomass energy plants GIS [46] Transportation-forest chips Simulation [32,35,39,42,43,63], GPS [42], GIS [39,42,43,63] Transportation-wood/timber Simulation [33,…”

Robotics in Forest Inventories: SPOT’s First Steps

“…Although numerous studies over the past decade have explored UAVs equipped with different sensors for forestry applications [7][8][9], there has been relatively less interest in the use of UGVs. However, according to Oliveria et al [6], the development of robotic UGV systems capable of operating autonomously in forest environments is of considerable importance for the public and private sectors in the context of precision forestry.…”