For software that relies on machine-learned functionality, model selection is key to finding the right model for the task with desired performance characteristics. Evaluating a model requires developers to i) select from many models (e.g. the Hugging face model repository), ii) select evaluation metrics and training strategy, and iii) tailor trade-offs based on the problem domain. However, current evaluation approaches are either ad-hoc resulting in sub-optimal model selection or brute force leading to wasted compute. In this work, we present GreenRunner, a novel tool to automatically select and evaluate models based on the application scenario provided in natural language. We leverage the reasoning capabilities of large language models to propose a training strategy and extract desired trade-offs from a problem description. GreenRunner features a resource-efficient experimentation engine that integrates constraints and trade-offs based on the problem into the model selection process. Our preliminary evaluation demonstrates that GreenRunner is both efficient and accurate compared to ad-hoc evaluations and brute force. This work presents an important step toward energy-efficient tools to help reduce the environmental impact caused by the growing demand for software with machine-learned functionality. Our tool is available at Figshare GreenRunner.

Meeting the rise of industry demand to incorporate machine learning (ML) components into software systems requires interdisciplinary teams contributing to a shared code base. To maintain consistency, reduce defects and ensure maintainability, developers use code analysis tools to aid them in identifying defects and maintaining standards. With the inclusion of machine learning, tools must account for the cultural differences within the teams which manifests as multiple programming languages, and conflicting definitions and objectives. Existing tools fail to identify these cultural differences and are geared towards software engineering which reduces their adoption in ML projects. In our approach we attempt to resolve this problem by exploring the use of context which includes i) purpose of the source code, ii) technical domain, iii) problem domain, iv) team norms, v) operational environment, and vi) development lifecycle stage to provide contextualised error reporting for code analysis. To demonstrate our approach, we adapt Pylint as an example and apply a set of contextual transformations to the linting results based on the domain of individual project files under analysis. This allows for contextualised and meaningful error reporting for the end user.

One of the main goals in lithium ion battery electrode design is to increase the power density. This requires insight in the relation between the complex heterogeneous microstructure existing of active material, conductive additive and electrolyte providing the required electronic and Li-ion transport. FIB-SEM is used to determine the three phase 3D morphology, and Li-ion concentration profiles obtained with Neutron Depth Profiling (NDP) are compared for two cases, conventional LiFePO₄ electrodes and better performing carbonate templated LiFePO₄ electrodes. This provides detailed understanding of the impact of key parameters such as the tortuosity for electron and Li-ion transport though the electrodes. The created hierarchical pore network of the templated electrodes, containing micron sized pores, appears to be effective only at high rate charge where electrolyte depletion is hindering fast discharge. Surprisingly the carbonate templating method results in a better electronic conductive CB network, enhancing the activity of LiFePO₄ near the electrolyte-electrode interface as directly observed with NDP, which in a large part is responsible for the improved rate performance both during charge and discharge. The results demonstrate that standard electrodes have a far from optimal charge transport network and that significantly improved electrode performance should be possible by engineering the microstructure.