Explore the vast range of titles available.

Traditional methods for assessing honey storage in beehives predominantly rely on manual visual inspection, which often leads to inconsistencies and inefficiencies. This study presents an automated deep learning approach utilizing the YOLOv11 model to detect, classify, and quantify honey cells within Apis mellifera frames across monthly sampling periods. The model’s performance varied depending on image resolution and dataset partitioning. Using the free version of YOLOv11 with high-resolution images (960 × 960 resolution) and a dataset split of 90:5:5 for training, validating, and testing, the model achieved a mean average precision at IoU threshold of 0.5 (mAP@0.5) of 83.4% for uncapped honey cells and 80.5% for capped honey cells. A strong correlation (r = 0.94) was observed between the 90:5:5 and 80:10:10 dataset splits, indicating that increasing the volume of training data enhances classification accuracy. In parallel, the study investigated the relationship between the physical properties of honey and image-based honey storage detection. Of the four tested properties, electrical conductivity (R2 = 0.19) and color (R2 = 0.21) showed weak predictive power for honey storage area estimation, with even weaker associations found for pH and moisture content. The honey storage areas via 90:5:5 and 80:10:10 datasets moderately correlated (r = 0.44–0.46) with increasing electrical conductivity and color. Especially, electrical conductivity exhibited statistically significant correlations with dataset performance across different dataset splits (p < 0.05), suggesting some potential influence of chemical composition on model accuracy. Our findings demonstrate the viability of image-based honey classification as a reliable technique for monitoring beehive productivity. Additionally, the research on image-based honey detection can be a non-invasive solution for improved honey production, beehive productivity, and optimized beekeeping practices.

Erosion and sedimentation are global environmental threats that cause land degradation, reduced agricultural productivity and increased flooding risks, leading to the loss of 75 billion tons of fertile soil annually. This study employs advanced remote sensing and machine learning techniques to analyze land use changes and their impacts on erosion and sedimentation at the sub-watershed level. Sentinel-2A images from multiple years were used and classified into 17 distinct land use classes through a supervised classification technique. The baseline land use data served as the foundation for future predictions, with a business-as-usual scenario modelled using cellular automata and artificial neural networks (CA-ANN). Land use factors were incorporated into the USLE model to generate an erosion map and to perform sediment retention analysis using the InVEST model. By 2025, over 35% of the total area is projected to experience significant deforestation, with forested areas being converted into orchards, shrubs, bare land, agricultural dry land and settlements. In 2022, forest area transformation resulted in a 25% increase in erosion and an 18% rise in sedimentation, with these figures expected to climb further by 2025. Our study recommends the CA-ANN model as a tool to predict land use changes and guide interventions, ensuring sustainable management of sub-watershed areas.

In the United Nations Decade on Ecosystem Restoration 1 , large knowledge gaps persist on how to increase biodiversity and ecosystem functioning in cash crop-dominated tropical landscapes 2 . Here, we present findings from a large-scale, 5-year ecosystem restoration experiment in an oil palm landscape enriched with 52 tree islands, encompassing assessments of ten indicators of biodiversity and 19 indicators of ecosystem functioning. Overall, indicators of biodiversity and ecosystem functioning, as well as multidiversity and ecosystem multifunctionality, were higher in tree islands compared to conventionally managed oil palm. Larger tree islands led to larger gains in multidiversity through changes in vegetation structure. Furthermore, tree enrichment did not decrease landscape-scale oil palm yield. Our results demonstrate that enriching oil palm-dominated landscapes with tree islands is a promising ecological restoration strategy, yet should not replace the protection of remaining forests. A large-scale, five-year study in Indonesia finds that enriching oil palm-dominated landscapes with patches of trees bolsters biodiversity and ecosystem functioning without impairing oil palm yields but should not replace forest protection.

Oil palm monocultures are highly productive, but there are widespread negative impacts on biodiversity and ecosystem functions. Some of these negative impacts might be mitigated by mixed-species tree interplanting to create agroforestry systems, but there is little experience with the performance of trees planted in oil palm plantations. We studied a biodiversity enrichment experiment in the lowlands of Sumatra that was established in a 6- to 12-year-old oil palm plantation by planting six tree species in different mixtures on 48 plots. Three years after tree planting, canopy cover was assessed by drone-based photogrammetry using the structure-from-motion technique. Drone-derived canopy cover estimates were highly correlated with traditional ground-based hemispherical photography along the equality line, indicating the usefulness and comparability of the approach. Canopy cover was further partitioned between oil palm and tree canopies. Thinning of oil palms before tree planting created a more open and heterogeneous canopy cover. Oil palm canopy cover was then extracted at the level of oil palms and individual trees and combined with ground-based mortality assessment for all 3,819 planted trees. For three tree species (Archidendron pauciflorum, Durio zibethinus, and Shorea leprosula), the probability of mortality during the year of the study was dependent on the amount of oil palm canopy cover. We regard the drone-based method for deriving and partitioning spatially explicit information as a promising way for many questions addressing canopy cover in ecological applications and the management of agroforestry systems.

Given a set of \\(n\\) nonoverlapping circular discs on a plane, we aim to determine possible positions of points (referred to as cameras) that could fully illuminate all the circular discs' boundaries. This work presents a geometric approach for determining feasible camera positions that would provide total illumination of all circular discs. The Laguerre Delaunay triangulation, coupled with the intersection of slabs formed by the boundaries of circular discs, is employed to form the region that satisfies the given conditions. The experiment is conducted using a set of randomly positioned circular discs on a plane. This study has the potential to address the issue of illumination in forests by utilizing a LiDAR camera to determine the possible number and placement of cameras that can effectively illuminate trees within a forest.

Optimizing restoration outcomes is crucial for enhancing multifaceted diversity, resilience, and ecosystem functioning in monoculture-dominated landscapes globally. Here, we experimentally tested the performance of passive and active restoration strategies to recover taxonomic, phylogenetic, and functional diversity by establishing 52 tree islands in an oil palm landscape. Tree diversity via natural regeneration was shaped by local rather than landscape properties, with the diversity of planted tree species and tree island size driving higher multifaceted diversity. We show that large tree islands with higher initial planted diversity catalyze the recovery of multifaceted diversity at both the local and landscape level, including forest-associated species. Our results demonstrate that planted diversity begets regenerating diversity, overcoming major limitations of natural regeneration in highly modified landscapes. By elucidating the contribution of experimental, local, and landscape drivers to natural regeneration, these findings provide practical insights to make oil palm landscapes more biodiversity-friendly by enhancing functional and phylogenetic diversity within plantations.Competing Interest StatementThe authors have declared no competing interest.

Enhancing biodiversity in monoculture-dominated landscapes is a pressing restoration challenge. Tree islands can enhance biodiversity locally, but the role of scale-dependent processes on local biodiversity remains unclear. Using a multi-scale approach, we explored how scale-dependent processes influence the diversity of seven taxa (woody plants, understory arthropods, birds, herbaceous plants and soil bacteria, fauna, and fungi) within 52 experimental tree islands embedded in an oil palm landscape. We show that local, metacommunity (between islands), and landscape properties shaped above- and below-ground taxa diversity, with the stronger effects on above-ground taxa. The spatial extent that best-predicted diversity ranged from 150 m for woody plants to 700 m for understory arthropods with below-ground taxa responding at large spatial extents. Our results underscore the need for multi-scale approaches to restoration. Additionally, our findings contribute to understanding the complex processes shaping multi-taxa diversity and offer insights for targeted conservation and restoration strategies.