Search for: All records

In the context of pressing climate change challenges and the significant biodiversity loss among arthropods, automated taxonomic classification from organismal images is a subject of intense research. However, traditional AI pipelines based on deep neural visual architectures such as CNNs or ViTs face limitations such as degraded performance on the long-tail of classes and the inability to reason about their predictions. We integrate image captioning and retrieval-augmented generation (RAG) with large language models (LLMs) to enhance biodiversity monitoring, showing particular promise for characterizing rare and unknown arthropod species. While a naive Vision-Language Model (VLM) excels in classifying images of common species, the RAG model enables classification of rarer taxa by matching explicit textual descriptions of taxonomic features to contextual biodiversity text data from external sources. The RAG model shows promise in reducing overconfidence and enhancing accuracy relative to naive LLMs, suggesting its viability in capturing the nuances of taxonomic hierarchy, particularly at the challenging family and genus levels. Our findings highlight the potential for modern vision-language AI pipelines to support biodiversity conservation initiatives, emphasizing the role of comprehensive data curation and collaboration with citizen science platforms to improve species identification, unknown species characterization and ultimately inform conservation strategies. 

Large, well described gaps exist in both what we know and what we need to know to address the biodiversity crisis. Artificial intelligence (AI) offers new potential for filling these knowledge gaps, but where the biggest and most influential gains could be made remains unclear. To date, biodiversity-related uses of AI have largely focused on tracking and monitoring of wildlife populations. Rapid progress is being made in the use of AI to build phylogenetic trees and species distribution models. However, AI also has considerable unrealized potential in the re-evaluation of important ecological questions, especially those that require the integration of disparate and inherently complex data types, such as images, video, text, audio and DNA. This Review describes the current and potential future use of AI to address seven clearly defined shortfalls in biodiversity knowledge. Recommended steps for AI-based improvements include the re-use of existing image data and the development of novel paradigms, including the collaborative generation of new testable hypotheses. The resulting expansion of biodiversity knowledge could lead to science spanning from genes to ecosystems — advances that might represent our best hope for meeting the rapidly approaching 2030 targets of the Global Biodiversity Framework. 

Mammalian hearing operates on three basic steps: 1) sound capturing, 2) impedance conversion, and 3) frequency analysis. While these canonical steps are vital for acoustic communication and survival in mammals, they are not unique to them. An equivalent mechanism has been described for katydids (Insecta), and it is unique to this group among invertebrates. The katydid inner ear resembles an uncoiled cochlea, and has a length less than 1 mm. Their inner ears contain a hearing organ,crista acustica, which holds tonotopically arranged sensory cells for frequency mapping via travelling waves. Thecrista acusticais located on a curved triangular surface formed by the dorsal wall of the ear canal. While empirical recordings show tonotopic vibrations in the katydid inner ear for frequency analysis, the biophysical mechanism leading to tonotopy remains elusive due to the small size and complexity of the hearing organ. In this study, robust numerical simulations are developed for anin silicoinvestigation of this process. Simulations are based on the precise katydid inner ear geometry obtained by synchrotron-based micro-computed tomography, and empirically determined inner ear fluid properties for an accurate representation of the underlying mechanism. We demonstrate that the triangular structure below the hearing organ drives the tonotopy and travelling waves in the inner ear, and thus has an equivalent role to the mammalian basilar membrane. This reveals a stronger analogy between the inner ear basic mechanical networks of two organisms with ancient evolutionary differences and independent phylogenetic histories. 

Abstract Two-terminal memory elements, or memelements, capable of co-locating signal processing and memory via history-dependent reconfigurability at the nanoscale are vital for next-generation computing materials striving to match the brain’s efficiency and flexible cognitive capabilities. While memory resistors, or memristors, have been widely reported, other types of memelements remain underexplored or undiscovered. Here we report the first example of a volatile, voltage-controlled memcapacitor in which capacitive memory arises from reversible and hysteretic geometrical changes in a lipid bilayer that mimics the composition and structure of biomembranes. We demonstrate that the nonlinear dynamics and memory are governed by two implicitly-coupled, voltage-dependent state variables—membrane radius and thickness. Further, our system is capable of tuneable signal processing and learning via synapse-like, short-term capacitive plasticity. These findings will accelerate the development of low-energy, biomolecular neuromorphic memelements, which, in turn, could also serve as models to study capacitive memory and signal processing in neuronal membranes.