Abstract
Automated sound-event detection is crucial for large-scale passive acoustic monitoring of wildlife, but the availability of ready-to-use tools is narrow across taxa. Machine learning is currently the state-of-the-art framework for developing sound-event detection tools tailored to specific wildlife calls. Gray wolves (Canis lupus), a species with intricate management necessities, howl spontaneously for long-distance intra- and inter-pack communication, which makes them a prime target for passive acoustic monitoring. Yet, there is currently no pre-trained, open-access tool that allows reliable automated detection of wolf howls in recorded soundscapes. We collected 50 137 h of soundscape data, where we manually labeled 841 unique howling events. We used this dataset to fine-tune VGGish-a convolutional neural network trained for audio classification-effectively retraining it for wolf howl detection. HOWLish correctly classified 77% of the wolf howling examples present on our test set, with a false positive rate of 1.74%; still, precision was low (0.006) granted extreme class imbalance (7124:1). During field tests, HOWLish retrieved 81.3% of the observed howling events while offering a 15-fold reduction in operator time when compared to fully manual detection. This work establishes the baseline for open-access automated wolf howl detection. HOWLish facilitates remote sensing of wild wolf populations, offering new opportunities in non-invasive large-scale monitoring and communication research of wolves. The knowledge gap we addressed here spans across many soniferous taxa, to which our approach also tallies.

Abstract
Predictive maintenance applications have increasingly been approached with deep learning techniques in recent years due to their high predictive performance. However, as in other real-world application scenarios, the need for explainability is often stated but not sufficiently addressed, which can limit adoption in practice. In this study, we will focus on predicting failures of trains operating in Porto, Portugal. While recent works have found high-performing deep neural network architectures that feature a parallel explainability pipeline, we find that the generated explanations can be hard to comprehend in practice due to their low support over the failure range. In this work, we propose a novel online rule-learning approach that is able to generate simple rules that cover the entirety of the detected failures. We evaluate our method against AMRules, a state-of-the-art online rule-learning approach, on two datasets gathered from trains operated by Metro do Porto. Our experiments show that our approach consistently generates rules with very high support that are simultaneously short and interpretable.

Abstract
Building 3D maps in agricultural environments is challenging due to dense vegetation, irregular terrain, lack of landmarks, and unreliable GPS. This paper proposes a Bounding Box-Based 3D Mapping method using collaboration between an Unmanned Ground Vehicle (UGV) and an Unmanned Aerial Vehicle (UAV). The method simplifies crop rows and tree canopies by enclosing their point clouds in 3D bounding boxes, fused with original UAV and UGV data, producing compact maps that preserve essential structures for autonomous navigation and trajectory planning. Evaluation in a simulated Orchard scenario shows that the method could reduce map size by up to 60% while maintaining 83.6% coverage. Multi-robot collaboration proved crucial, with the UGV contributing 74% and the UAV 26% of the merged map. Overall, the proposed method demonstrates potential and deserves further investigation in more complex agricultural scenarios. © 2026 IEEE.

Abstract

Phenological monitoring of Actinidia chinensis is critical for optimising operational costs and yield prediction. However, current manual assessment methods are time-consuming, making them impractical for large-scale precision agriculture applications. Most existing phenological datasets focus exclusively on image data without spatial validation. The Multi-Modal Actinidia chinensis Phenology Dataset is composed of (i) 1 665 annotated images of phenological stages from bud to fruit set and (ii) georeferenced videos with systematic manual ground truth of spatial stage distributions. The dataset employs an adapted 17-class BBCH system that consolidates visually similar stages, excludes problematic categories, and introduces generic structural classes to address practical annotation difficulties. Additionally, the data is organised hierarchically across various plant structures, genders, and phenological stages. The annotated images offer versatility for a range of applications, including training data for computer vision models to detect phenological stages. Furthermore, the georeferenced videos facilitate the validation of automated counting algorithms. This combined approach enables plant-level detection accuracy and provides an illustrative methodology for spatial validation that users can extend to additional orchards, promoting the development and benchmarking of automated phenological monitoring systems for precision agriculture applications in kiwifruit production.

Abstract
The integration of Deep Learning techniques for grapevine yield estimation has led to significant advancements in Precision Viticulture. The accurate detection and counting of berries per bunch is a critical task that can explain up to 30% of yield variability, thereby enabling improved yield estimation. This study proposes a YOLO-based approach for the automated detection and counting of visible grapevine berries, using a dataset of more than 1500 images collected over three phenological stages. The selected YOLO models performed well in both detection and counting tasks, with all models achieving high detection accuracy (G-mAP ' 0.95) and estimation of visible berries (R2 ' 0.97). Among the evaluated models, YOLOv11n exhibited the highest detection performance (F1-Score = 0.954, G-mAP = 0.962), while YOLOv10n demonstrated the most consistent and reliable counting accuracy (MAPE = 4.764, MSE = 12.203, RMSE = 3.493). Beyond overall performance, the analysis revealed that ampelographic features such as berry size, occlusion, and bunch morphology can influence accuracy, although YOLOv10n showed no significant disparities across categories. To extend the scope, a complementary analysis demonstrated a strong linear relationship (R2 = 0.860) between visible counts and the total number of berries per bunch, supporting the potential of correction models to address occlusion. By systematically evaluating model behaviour across diverse viticultural conditions and incorporating correlation with total berry counts, this study provides a deeper understanding of the robustness and limitations of Deep Learning models, offering critical insights for future applications in vineyard monitoring, yield estimation, harvest optimisation, and management. © 2026 The Authors.

Abstract
In the evolving field of machine learning, ensuring group fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. Group fairness refers to the principle that a model's decisions should be equitable across different groups defined by sensitive attributes such as gender or race, ensuring that individuals from privileged groups and unprivileged groups are treated fairly and receive similar outcomes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time, while another does not, leading to a decrease in fairness even if accuracy (ACC) remains fairly stable. Within the framework of federated learning (FL), where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the field of fairness. In addition, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift, which uses a multimodel approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine learning.