Fast and efficient identification is critical for reducing the likelihood of weed establishment and for appropriately managing established weeds. Traditional identification tools require either knowledge of technical morphological terminology or time-consuming image matching by the user. In recent years, deep learning computer vision models have become mature enough to enable automatic identification. The major remaining bottlenecks are the availability of a sufficient number of high-quality, reliably identified training images and the user-friendly, mobile operationalization of the technology. Here, we present the first weed identification and reporting app and website for all of Australia. It includes an image classification model covering more than 400 species of weeds and some Australian native relatives, with a focus on emerging biosecurity threats and spreading weeds that can still be eradicated or contained. It links the user to additional information provided by state and territory governments, flags species that are locally reportable or notifiable, and allows the creation of observation records in a central database. State and local weed officers can create notification profiles to be alerted of relevant weed observations in their area. We discuss the background of the WeedScan project, the approach taken in design and software development, the photo library used for training the WeedScan image classifier, the model itself and its accuracy, and technical challenges and how these were overcome.

Current jurisprudential trends empower the International Criminal Court (ICC) Prosecutor to override domestic investigative authorities in a manner that violates the letter and spirit of the Rome Statute. Sovereign states have primary responsibility to document, investigate and prevent atrocity crimes. Yet, current ICC practice subverts domestic enforcement efforts. No provision of the Rome Statute permits the Office of the Prosecutor (OTP) to substitute its unfettered judgment over the good-faith discretion of domestic prosecutors. ICC judges have created de facto institutional jurisdictional primacy by relying upon mere assertions regarding the insufficiency of domestic efforts. This trend is particularly problematic at the liminal phase from the preliminary examination (PE) to an authorised investigation because OTP policy preferences supersede good-faith domestic investigations and prosecutorial assessments. Juridical templates for assessing admissibility have been extrapolated from later phases of particularised cases into the PE phase. Current practice effectively eliminates sovereign prosecutorial discretion. Good-faith exercises of domestic prosecutorial discretion should not be constrained by post hoc Court-created straitjackets. This article dissects this problematic arc and proffers a model for harmonising domestic investigative efforts within the structure and intent of the Rome Statute. Its conclusions recommend reforms to ameliorate a foreseeable crisis of cooperation that could cripple an unreformed Court.

Reforestation in the Inland Northwest, including northeastern Oregon, USA, is often limited by a dry climate and soil moisture availability during the summer months. Reduction of competing vegetative cover in forest plantations is a common method for retaining available soil moisture. Several spring and summer site preparation (applied prior to planting) herbicide treatments were evaluated to determine their efficacy in reducing competing cover, thus retaining soil moisture, on three sites in northeastern Oregon. Results varied by site, year, and season of application. In general, sulfometuron (0.14 kg ai ha–1 alone and in various mixtures), imazapyr (0.42 ae kg ha–1), and hexazinone (1.68 kg ai ha–1) resulted in 3 to 17% cover of forbs and grasses in the first-year when applied in spring. Sulfometuron+glyphosate (2.2 kg ha–1) consistently reduced grasses and forbs for the first year when applied in summer, but forbs recovered in the second year on two of three sites. Aminopyralid (0.12 kg ae ha–1)+sulfometuron applied in summer also led to comparable control of forb cover. In the second year after treatment, forb cover in treated plots was similar to levels in nontreated plots, and some species of forbs had increased relative to nontreated plots. Imazapyr (0.21 and 0.42 kg ha–1) at either rate, spring or summer 2007, or at lower rate (0.14 kg ha–1) with glyphosate in summer, provided the best control of shrubs, of which snowberry was the dominant species. Total vegetative cover was similar across all treatments seven and eight years after application, and differences in vegetation were related to site rather than treatment. In the first year after treatment, rates of soil moisture depletion in the 0- to 23-cm depth were correlated with vegetative cover, particularly late season soil moisture, suggesting increased water availability for tree seedling growth.