Dermaptera (earwigs) from the Anisolabididae family may be important for pest control but their taxonomy and status in Australia is poorly studied. Here we used taxonomic information to assess the diversity of southern Australian Anisolabididae and then applied cox1 barcodes as well as additional gene fragments (mitochondrial and nuclear) to corroborate classification and assess the monophyly of the putative genera. Anisolabididae morphospecies fell into two genera, Anisolabis Fieber and Gonolabis Burr, based on paramere morphology. Combinations of paramere and forceps morphology distinguished seven morphospecies, which were further supported by morphometric analyses. The morphospecies were corroborated by barcode data; all showed within-species genetic distance < 4% and between-species genetic distance > 10%. Molecular phylogenies did not support monophyly of putative genera nor clades based on paramere shape, instead pointing to regional clades distinguishable by forceps morphology. This apparent endemism needs to be further tested by sampling of earwig diversity outside of agricultural production regions but points to a unique regional insect fauna potentially important in pest control.

Accurate weed mapping in cereal fields requires pixel-level segmentation from unmanned aerial vehicle (UAV) imagery that remains reliable across fields, seasons, and illumination. Existing multispectral pipelines often depend on thresholded vegetation indices, which are brittle under radiometric drift and mixed crop–weed pixels, or on single-stream convolutional neural network (CNN) and Transformer backbones that ingest stacked bands and indices, where radiance cues and normalized index cues interfere and reduce sensitivity to small weed clusters embedded in crop canopy. We propose VISA (Vegetation Index and Spectral Attention), a two-stream segmentation network that decouples these cues and fuses them at native resolution. The radiance stream learns from calibrated five-band reflectance using local residual convolutions, channel recalibration, spatial gating, and skip-connected decoding, which preserve fine textures, row boundaries, and small weed structures that are often weakened after ratio-based index compression. The index stream operates on vegetation-index maps with windowed self-attention to model local structure efficiently, state-space layers to propagate field-scale context without quadratic attention cost, and Slot Attention to form stable region descriptors that improve discrimination of sparse weeds under canopy mixing. To support supervised training and deployment-oriented evaluation, we introduce BAWSeg, a four-year UAV multispectral dataset collected over commercial barley paddocks in Western Australia, providing radiometrically calibrated blue, green, red, red edge, and near-infrared orthomosaics, derived vegetation indices, and dense crop, weed, and other labels with leakage-free block splits. On BAWSeg, VISA achieves 75.6% mean Intersection over Union (mIoU) and 63.5% weed Intersection over Union (IoU) with 22.8 M parameters, outperforming a multispectral SegFormer-B1 baseline by 1.2 mIoU and 1.9 weed IoU. Under cross-plot and cross-year protocols, VISA maintains 71.2% and 69.2% mIoU, respectively. The full BAWSeg benchmark dataset, VISA code, trained model weights, and protocol files will be released upon publication.

Despite the known benefits of integrated pest management, adoption in Australian broadacre crops has been slow, in part due to the lack of understanding about how pests and natural enemies interact. We use a previously developed process-based model to predict seasonal patterns in the population dynamics of a canola pest, the green peach aphid (Myzus persicae), and an associated common primary parasitic wasp (Diaeretiella rapae), found in this cropping landscape. The model predicted aphid population outbreaks in autumn and spring. Diaeretiella rapae was able to suppress these outbreaks, but only in scenarios with a sufficiently high number of female wasps in the field (a simulated aphid:wasp density ratio of at least 5:1 was required). Model simulations of aphid-specific foliar pesticide applications facilitated biological control. However, a broad-spectrum pesticide negated the control provided by D. rapae, in one case leading to a predicted 15% increase in aphid densities compared to simulations in which no pesticide was applied. Biological and chemical control could therefore be used in combination for the successful management of the aphid while conserving the wasp. This modelling framework provides a versatile tool for further exploring how chemical applications can impact pests and candidate species for biological control.