Digital Twins in Agriculture and Forestry: A Review.

Digital twins aim to optimize practices implemented in various sectors by bridging the gap between the physical and digital worlds. Focusing on open-field agriculture, livestock farming, and forestry and reviewing the current applications in these domains, this paper reveals the multifaceted roles of digital twins. Diverse key aspects are examined, including digital twin integration and maturity level, means of data acquisition, technological capabilities, and commonly used input and output features. Through the prism of four primary research questions, the state of the art of digital twins, the extent of their achieved integration, and an overview of the critical issues and potential advancements are provided in the landscape of the sectors under consideration. The paper concludes that in spite of the remarkable progress, there is a long way towards achieving full digital twin. Challenges still persist, while the key factor seems to be the integration of expert knowledge from different stakeholders. In light of the constraints identified in the review analysis, a new sector-specific definition for digital twins is also suggested to align with the distinctive characteristics of intricate biotic and abiotic systems. This research is anticipated to serve as a useful reference for stakeholders, enhancing awareness of the considerable benefits associated with digital twins and promoting a more systematic and comprehensive exploration of this transformative topic.

Orchard Mapping with Deep Learning Semantic Segmentation.

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.