Efforts to prevent the introduction and spread of new invasive plants are most effective when regulated species are consistent across jurisdictional boundaries and proactively prohibit species before they arrive or in the earliest stages of invasion. Consistent and proactive regulation is particularly important in the northeastern United States, which is susceptible to many new invasive plants due to climate change. Unfortunately, recent analyses of state regulated plant lists show that regulated species are neither consistent nor proactive. To understand why, we focus on two steps leading to invasive plant regulation across six northeastern states (Connecticut, Maine, Massachusetts, New Hampshire, New York, and Vermont): which sets of species are evaluated and how risk is assessed. Our analysis confirms previous findings that invasive plant regulations are inconsistent and reactive. Of the 128 plants regulated by one or more states, 54 were regulated by a single state and only 16 were regulated by all six states; regulated species tended to be widespread across the region (not proactive). These outcomes are largely driven by different sets of evaluated species. For example, neighboring states Vermont and New Hampshire evaluated 92 species in total, but only 26 overlapped. In addition, states rarely evaluated species that were absent from the state. Risk assessment protocols varied considerably across states, but consistently included criteria related to ecological impact, potential to establish, dispersal mechanisms, and life history traits. While none of the assessments explicitly consider climate change, they also did not contain language that would preclude regulating species that have not yet arrived in the state. To increase consistency and proactivity, states would benefit from (1) evaluating species identified as high risk by neighboring states and high‐risk, range‐shifting invasive species, both of which we compiled here, and (2) explicitly considering climate change when assessing “potential distribution” or “potential impact” of target species. Additionally, a mechanism for sharing knowledge and risk assessments regionally would benefit states with fewer resources to address invasive species threats. Presenting a unified defense against current and future threats is critical for reducing impacts from invasive species and is achievable with better state‐to‐state coordination.

Development of a biological control program for invasive Phagmites australis australis in North America required 20 years of careful research, and consideration of management alternatives. A recent paper by Kiviat et al. (Biol Invasions

The rise of neural networks has opened the door for automatic analysis of remote sensing data. A challenge to using this machinery for computational sustainability is the necessity of massive labeled data sets, which can be cost-prohibitive for many non-profit organizations. The primary motivation for this work is one such problem; the efficient management of invasive species -- invading flora and fauna that are estimated to cause damages in the billions of dollars annually. As an ongoing collaboration with the New York Natural Heritage Program, we consider the use of unsupervised deep learning techniques for dimensionality reduction of remote sensing images, which can reduce sample complexity for downstream tasks and decreases the need for large labeled data sets. We consider spatially augmenting contrastive learning by training neural networks to correctly classify two nearby patches of a landscape as such. We demonstrate that this approach improves upon previous methods and naive classification for a large-scale data set of remote sensing images derived from invasive species observations obtained over 30 years. Additionally, we simulate deployment in the field via active learning and evaluate this method on another important challenge in computational sustainability -- landcover classification -- and again find that it outperforms previous baselines.

Effective natural resource management and policy is contingent on information generated by research. Conversely, the applicability of research depends on whether it is responsive to the needs and constraints of resource managers and policy makers. However, many scientific fields including invasion ecology suffer from a disconnect between research and practice. Despite strong socio-political imperatives, evidenced by extensive funding dedicated to addressing invasive species, the pairing of invasion ecology with stakeholder needs to support effective management and policy is lacking. As a potential solution, we propose translational invasion ecology (TIE). As an extension of translational ecology, as a framework to increase collaboration among scientists, practitioners, and policy makers to reduce negative impacts of invasive species. As an extension of translational ecology, TIE is an approach that embodies an intentional and inclusive process in which researchers, stakeholders, and decision makers collaborate to develop and implement ecological research via joint consideration of the ecological, sociological, economic, and/or political contexts in order to improve invasive species management. TIE ideally results in improved outcomes as well as shared benefits between researchers and managers. We delineate the steps of our proposed TIE approach and describe successful examples of ongoing TIE projects from the US and internationally. We suggest practical ways to begin incorporating TIE into research and management practices, including supporting boundary-spanning organizations and activities, expanding networks, sharing translational experiences, and measuring outcomes. We find that there is a need for strengthened boundary spanning, as well as funding and recognition for advancing translational approaches. As climate change and globalization exacerbate invasive species impacts, TIE provides a promising approach to generate actionable ecological research while improving outcomes of invasive species management and policy decisions.