Periodic Reporting for period 1 - BIG-MAP (Battery Interface Genome - Materials Acceleration Platform)
Período documentado: 2020-09-01 hasta 2022-02-28
Large-scale deployment of intermittent renewable energy and the electrification of the transportation sector critically depend on the availability of low-cost, high-performance, environmentally friendly, and scalable energy storage.
Further development of sustainable, high-performance battery technologies and materials plays a central role in ensuring and accelerating the transition towards a net-zero CO2 emissions. However, the existing battery innovation and development paradigm is too slow and too costly to address the urgency of the societal challenges resulting from global warming.
The ambition of the project is to develop a fully autonomous battery Materials Acceleration Platform (MAP) capable of performing accelerated closed-loop materials discovery, cell design, and manufacturing of sustainable, ultra-high performance batteries in Europe (figure 1). This “MAP” will acquire and utilize data from all parts of the battery value chain, from raw materials to end-users. The "Battery Interface Genome - Materials Acceleration Platform" (BIG-MAP) project represents the ambition to develop a novel “chemistry neutral” methodology and data/research infrastructure.
This will be achieved by:
• Providing an accelerated path to disruptive battery technologies with ultra-high performance, full sustainability, and smart operation.
• Developing a modular, closed-loop infrastructure and methodology to bridge physical insights and data-driven approaches to accelerate the inverse design of future battery chemistries and technologies.
The BIG-MAP project seeks to develop and demonstrate the infrastructural backbone needed to achieve a 5-10 fold acceleration in the discovery process.
Further development of sustainable, high-performance battery technologies and materials plays a central role in ensuring and accelerating the transition towards a net-zero CO2 emissions. However, the existing battery innovation and development paradigm is too slow and too costly to address the urgency of the societal challenges resulting from global warming.
The ambition of the project is to develop a fully autonomous battery Materials Acceleration Platform (MAP) capable of performing accelerated closed-loop materials discovery, cell design, and manufacturing of sustainable, ultra-high performance batteries in Europe (figure 1). This “MAP” will acquire and utilize data from all parts of the battery value chain, from raw materials to end-users. The "Battery Interface Genome - Materials Acceleration Platform" (BIG-MAP) project represents the ambition to develop a novel “chemistry neutral” methodology and data/research infrastructure.
This will be achieved by:
• Providing an accelerated path to disruptive battery technologies with ultra-high performance, full sustainability, and smart operation.
• Developing a modular, closed-loop infrastructure and methodology to bridge physical insights and data-driven approaches to accelerate the inverse design of future battery chemistries and technologies.
The BIG-MAP project seeks to develop and demonstrate the infrastructural backbone needed to achieve a 5-10 fold acceleration in the discovery process.
To facilitate an efficient platform for dissemination, a project website (www.big-map.eu) Twitter (@bigmap_eu) and LinkedIn accounts were created. An animation video describing the vision, approach, and expected impact has also been created (www.youtube.com/watch?v=dc_xluDHnAY).
The BIG-MAP data infrastructure is crucial to ensure a seamless flow of data (figure 2). The foundation of the data infrastructure is a rigorous data management plan (DMP), which has been developed to orchestrate the flow of data. The DMP enables a simple tracking of the data flows across the project, aligns the expectations to the format and size of the exchanged data, and ensures its operability. The BIG-MAP DMP represents one of the first DMPs for a large-scale European research initiative and proposes DMP standards for other projects. For this reason, the DMP itself and the procedure for working it out have been published as a scientific article.
A critical point in making a DMP operational is the development of a shared language or "ontology" to ensure interoperability between simulations and experiments across multiple spatial and temporal scales and different techniques and domains in the battery discovery process. To facilitate battery experts in various fields to convert real-life observations to a standard digital representation an ontology, BattINFO, was developed and made openly available to the community (https://github.com/BIG-MAP/BattINFO). BattINFO supports the description and characterization of key aspects governing battery interface performance, including the formation of interphase layers, passivating layers, active material dissolution, charge transfer reactions, etc.
The development of BattINFO has been closely connected to the development of an electronic laboratory notebook (http://big-map-logbook.eu/) to ensure that data and metadata comply with the overall data infrastructure. The BIG-MAP Notebook is currently accessible to all BIG-MAP partners, where it stores raw (electrochemical) data with a unique DOI to ensure traceability during and after the project. The impact of the notebook goes beyond the BIG-MAP project, as it now serves as a template to share electrochemical data across different BATTERY 2030+ projects.
Finally, the BIG-MAP GitHub registry and App Store (https://big-map.github.io/big-map-registry/) were launched and made openly available to the research community. The BIG-MAP App Store contains 15 apps to date. Two illustrative examples are the automated analysis module, PRISMA, for high-throughput analysis of spectra, and the active learning fast API HELAO for deploying active learning and laboratory automation to a distributed fleet of research instruments. The App Store also includes apps like the CLEASE GUI for running cluster expansion simulations and the FullProfAPP for automated structural analysis of data from large scale facilities.
The BIG-MAP data infrastructure is crucial to ensure a seamless flow of data (figure 2). The foundation of the data infrastructure is a rigorous data management plan (DMP), which has been developed to orchestrate the flow of data. The DMP enables a simple tracking of the data flows across the project, aligns the expectations to the format and size of the exchanged data, and ensures its operability. The BIG-MAP DMP represents one of the first DMPs for a large-scale European research initiative and proposes DMP standards for other projects. For this reason, the DMP itself and the procedure for working it out have been published as a scientific article.
A critical point in making a DMP operational is the development of a shared language or "ontology" to ensure interoperability between simulations and experiments across multiple spatial and temporal scales and different techniques and domains in the battery discovery process. To facilitate battery experts in various fields to convert real-life observations to a standard digital representation an ontology, BattINFO, was developed and made openly available to the community (https://github.com/BIG-MAP/BattINFO). BattINFO supports the description and characterization of key aspects governing battery interface performance, including the formation of interphase layers, passivating layers, active material dissolution, charge transfer reactions, etc.
The development of BattINFO has been closely connected to the development of an electronic laboratory notebook (http://big-map-logbook.eu/) to ensure that data and metadata comply with the overall data infrastructure. The BIG-MAP Notebook is currently accessible to all BIG-MAP partners, where it stores raw (electrochemical) data with a unique DOI to ensure traceability during and after the project. The impact of the notebook goes beyond the BIG-MAP project, as it now serves as a template to share electrochemical data across different BATTERY 2030+ projects.
Finally, the BIG-MAP GitHub registry and App Store (https://big-map.github.io/big-map-registry/) were launched and made openly available to the research community. The BIG-MAP App Store contains 15 apps to date. Two illustrative examples are the automated analysis module, PRISMA, for high-throughput analysis of spectra, and the active learning fast API HELAO for deploying active learning and laboratory automation to a distributed fleet of research instruments. The App Store also includes apps like the CLEASE GUI for running cluster expansion simulations and the FullProfAPP for automated structural analysis of data from large scale facilities.
Two of the main outputs of BIG-MAP relate to the BIG ML models and the development of the MAP infrastructure. In the first period of the BIG-MAP project, we have focused extensively on developing such fundamental tools and models.
One example in the area of the BIG ML models is the development of an uncertainty-aware deep autoregressive model that with limited training data and only few cycles of observations, can predict the capacity degradation over the entire lifetime with intercell variability while maintaining explainability and learning to differentiate degradation mechanisms in a data-driven manner. This model can substantially reduce how long experiments need to run to test new formulations. Another example in this domain is the work on symbolic regression and HTE-acquired datasets on electrolyte conductivity. Here, we discovered a simple, accurate, consistent, and generalizable governing law. Despite emerging from a purely statistical approach, the expression reflects functional aspects from established thermodynamic limiting laws, indicating our model is grounded on the fundamental physical mechanisms underpinning ionic transport.
In the MAP domain, we operate in the paradigm of integrating combinatorial synthesis, high-throughput characterization, automatic analysis, and ML. Within a MAP, one or multiple autonomous feedback loops may aim to optimize materials for specific functional properties or to generate new insights. The scope of a given experimental campaign is defined by the range of experiment and analysis actions that are integrated into the experiment framework. In HELAO, we present a method for integrating many actions within a hierarchical experimental laboratory automation and orchestration framework. We demonstrate the capability of orchestrating distributed research instruments that can incorporate data from experiments, simulations, and databases. HELAO interfaces laboratory hardware and software distributed across several computers and operating systems for executing experiments, data analysis, provenance tracking, and autonomous planning.
Another important aspect of a MAP is the ability to do automated/autonomous analysis of experimental data, which can be fed to the ML models on-the-fly. We have developed an open-source app called PRISMA to visualize and process hundreds of spectra from operando experiments. The app implements baseline correction and peak fitting methods and a friendly graphical user interface. Users load spectra (or diffraction patterns), tune baseline and peak fitting parameters, run a high-throughput processing step, and export the results in a CSV format within minutes. This approach enables extracting spectroscopic trends that characterize the properties and phenomena inherent to the operation of functional materials.
One example in the area of the BIG ML models is the development of an uncertainty-aware deep autoregressive model that with limited training data and only few cycles of observations, can predict the capacity degradation over the entire lifetime with intercell variability while maintaining explainability and learning to differentiate degradation mechanisms in a data-driven manner. This model can substantially reduce how long experiments need to run to test new formulations. Another example in this domain is the work on symbolic regression and HTE-acquired datasets on electrolyte conductivity. Here, we discovered a simple, accurate, consistent, and generalizable governing law. Despite emerging from a purely statistical approach, the expression reflects functional aspects from established thermodynamic limiting laws, indicating our model is grounded on the fundamental physical mechanisms underpinning ionic transport.
In the MAP domain, we operate in the paradigm of integrating combinatorial synthesis, high-throughput characterization, automatic analysis, and ML. Within a MAP, one or multiple autonomous feedback loops may aim to optimize materials for specific functional properties or to generate new insights. The scope of a given experimental campaign is defined by the range of experiment and analysis actions that are integrated into the experiment framework. In HELAO, we present a method for integrating many actions within a hierarchical experimental laboratory automation and orchestration framework. We demonstrate the capability of orchestrating distributed research instruments that can incorporate data from experiments, simulations, and databases. HELAO interfaces laboratory hardware and software distributed across several computers and operating systems for executing experiments, data analysis, provenance tracking, and autonomous planning.
Another important aspect of a MAP is the ability to do automated/autonomous analysis of experimental data, which can be fed to the ML models on-the-fly. We have developed an open-source app called PRISMA to visualize and process hundreds of spectra from operando experiments. The app implements baseline correction and peak fitting methods and a friendly graphical user interface. Users load spectra (or diffraction patterns), tune baseline and peak fitting parameters, run a high-throughput processing step, and export the results in a CSV format within minutes. This approach enables extracting spectroscopic trends that characterize the properties and phenomena inherent to the operation of functional materials.