Elsa Olivetti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Elsa Olivetti has a total of 263 co-authors. Here are the top co-authors by number of shared publications:
- Rafael Gómez-Bombarelli
Massachusetts Institute of Technology
10 shared publications Richard Roth
Materials Systems Laboratory, Massachusetts Institute of Technology, Cambridge, USA
10 shared publications- Randolph Kirchain
Materials Research Laboratory, Massachusetts Institute of Technology, Cambridge, USA
9 shared publications - Edward Kim
Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
8 shared publications - Daniel Schwalbe-Koda
Department of Materials Science and Engineering, University of California, Los Angeles, USA
7 shared publications - Manuel Moliner
Instituto de Tecnología Química, Universitat Politècnica de València-Consejo Superior de Investigaciones Científicas, Valencia, Spain
7 shared publications
Latest Publications
- Open Access
- 10 November 2026
- Published by Springer Nature in Nature Communications
Electric vehicle battery materials supply disruptions can be mitigated with chemistry changes and recycling
- 10 November 2026
- Published by Springer Nature in Nature Communications
Open AccessElectric vehicle battery materials supply disruptions can be mitigated with chemistry changes and recycling
- Open Access
- 26 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Scaling multimodal materials representation learning with synthetic narratives
Artificial intelligence is increasingly applied to inverse materials design, including crystals and molecules. For molecular systems, multimodal models that integrate chemical structures with natural language have enabled flexible, instruction-driven reasoning. However, approaches for crystalline materials remain limited by the scarcity and imbalanced bias of available crystal datasets and the weak semantic supervision provided by peer-reviewed literature. We introduce a contrastive language-crystals model (CLaC), a multimodal contrastive learning framework that aligns crystal structures with natural language, pre-trained on property-conditioned synthetic narratives of crystal structure-text pairs generated by language models. Here we show that, compared with models trained on literature-derived text, this property-grounded synthetic supervision enables semantic alignment unachievable with existing academic corpora. Embedding-space analyses reveal structured associations between language and crystal structures. These results establish a foundation for zero-shot, instruction-driven reasoning in crystalline materials.
- 26 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessScaling multimodal materials representation learning with synthetic narratives
Artificial intelligence is increasingly applied to inverse materials design, including crystals and molecules. For molecular systems, multimodal models that integrate chemical structures with natural language have enabled flexible, instruction-driven reasoning. However, approaches for crystalline materials remain limited by the scarcity and imbalanced bias of available crystal datasets and the weak semantic supervision provided by peer-reviewed literature. We introduce a contrastive language-crystals model (CLaC), a multimodal contrastive learning framework that aligns crystal structures with natural language, pre-trained on property-conditioned synthetic narratives of crystal structure-text pairs generated by language models. Here we show that, compared with models trained on literature-derived text, this property-grounded synthetic supervision enables semantic alignment unachievable with existing academic corpora. Embedding-space analyses reveal structured associations between language and crystal structures. These results establish a foundation for zero-shot, instruction-driven reasoning in crystalline materials.
- 23 June 2026
- Published by American Chemical Society (ACS) in ACS Energy Letters
- Vol. 11 (7) , 5129-5138
A Mechanically Compliant Tin-Hard Carbon Anode for Sodium Solid-State Batteries
Sodium solid-state batteries (NaSSBs) with alloy anodes can increase cell-level energy density, but they suffer from chemo-mechanical degradation due to volume changes during sodiation and desodiation. Here, we develop a Sn hard carbon composite anode (SnHC), in which HC serves as a mechanically compliant scaffold that buffers alloying-induced stress and helps maintain electrode integrity. Meanwhile, Sn and Na-Sn phases provide coupled ionic and electronic transport pathways for Na+ diffusion and electron percolation. Morphology and pressure monitoring show that SnHC exhibits a 77% reduction in volume change and a 46% reduction in pressure fluctuations compared with Sn upon sodiation. This stress-buffering effect reduces structural degradation during cycling. As a result, SnHC delivers a reversible capacity of 588 mAh g−1 and retains 80% of its capacity over 1000 cycles when paired with NaNi1/3Fe1/3Mn1/3O2. Techno-economic analysis indicates that SnHC can reduce the projected manufacturing cost of NaSSBs by approximately 21% relative to HC counterparts.
- 23 June 2026
- Published by American Chemical Society (ACS) in ACS Energy Letters
- Vol. 11 (7) , 5129-5138
A Mechanically Compliant Tin-Hard Carbon Anode for Sodium Solid-State Batteries
Sodium solid-state batteries (NaSSBs) with alloy anodes can increase cell-level energy density, but they suffer from chemo-mechanical degradation due to volume changes during sodiation and desodiation. Here, we develop a Sn hard carbon composite anode (SnHC), in which HC serves as a mechanically compliant scaffold that buffers alloying-induced stress and helps maintain electrode integrity. Meanwhile, Sn and Na-Sn phases provide coupled ionic and electronic transport pathways for Na+ diffusion and electron percolation. Morphology and pressure monitoring show that SnHC exhibits a 77% reduction in volume change and a 46% reduction in pressure fluctuations compared with Sn upon sodiation. This stress-buffering effect reduces structural degradation during cycling. As a result, SnHC delivers a reversible capacity of 588 mAh g−1 and retains 80% of its capacity over 1000 cycles when paired with NaNi1/3Fe1/3Mn1/3O2. Techno-economic analysis indicates that SnHC can reduce the projected manufacturing cost of NaSSBs by approximately 21% relative to HC counterparts.
- Open Access
- 4 May 2026
- Published by Springer Nature in Journal of Industrial Ecology
- Vol. 30 (3) , 1085-1105
Visualizing energy, material and emission flows to understand scale and connections in the physical global economy
- 4 May 2026
- Published by Springer Nature in Journal of Industrial Ecology
- Vol. 30 (3) , 1085-1105
Open AccessVisualizing energy, material and emission flows to understand scale and connections in the physical global economy
- 27 March 2026
- Published by Elsevier in Waste Management
- Vol. 217, 115500
Process-based cost assessment of electrochemical metals recovery from municipal solid waste incineration ash
- 27 March 2026
- Published by Elsevier in Waste Management
- Vol. 217, 115500
Process-based cost assessment of electrochemical metals recovery from municipal solid waste incineration ash
- Open Access
PackFlow: Generative Molecular Crystal Structure Prediction via Reinforcement Learning Alignment
Organic molecular crystals underpin technologies ranging from pharmaceuticals to organic electronics, yet predicting solid-state packing of molecules remains challenging because candidate generation is combinatorial and stability is only resolved after costly energy evaluations. Here we introduce PackFlow, a flow matching framework for molecular crystal structure prediction (CSP) that generates heavy-atom crystal proposals by jointly sampling Cartesian coordinates and unit-cell lattice parameters given a molecular graph. This lattice-aware generation interfaces directly with downstream relaxation and lattice-energy ranking, positioning PackFlow as a scalable proposal engine within standard CSP pipelines. To explicitly steer generation toward physically favourable regions, we propose physics alignment, a reinforcement learning post-training stage that uses machine-learned interatomic potential energies and forces as stability proxies. Physics alignment improves physical validity without altering inference-time sampling. We validate PackFlow's performance against heuristic baselines through two distinct evaluations. First, on a broad unseen set of molecular systems, we demonstrate superior candidate generation capability, with proposals exhibiting greater structural similarity to experimental polymorphs. Second, we assess the full end-to-end workflow on two unseen CSP blind-test case studies, including relaxation and lattice-energy analysis. In both settings, PackFlow outperforms heuristics-based methods by concentrating probability mass in low-energy basins, yielding candidates that relax into lower-energy minima and offering a practical route to amortize the relax-and-rank bottleneck.
Open AccessPackFlow: Generative Molecular Crystal Structure Prediction via Reinforcement Learning Alignment
Organic molecular crystals underpin technologies ranging from pharmaceuticals to organic electronics, yet predicting solid-state packing of molecules remains challenging because candidate generation is combinatorial and stability is only resolved after costly energy evaluations. Here we introduce PackFlow, a flow matching framework for molecular crystal structure prediction (CSP) that generates heavy-atom crystal proposals by jointly sampling Cartesian coordinates and unit-cell lattice parameters given a molecular graph. This lattice-aware generation interfaces directly with downstream relaxation and lattice-energy ranking, positioning PackFlow as a scalable proposal engine within standard CSP pipelines. To explicitly steer generation toward physically favourable regions, we propose physics alignment, a reinforcement learning post-training stage that uses machine-learned interatomic potential energies and forces as stability proxies. Physics alignment improves physical validity without altering inference-time sampling. We validate PackFlow's performance against heuristic baselines through two distinct evaluations. First, on a broad unseen set of molecular systems, we demonstrate superior candidate generation capability, with proposals exhibiting greater structural similarity to experimental polymorphs. Second, we assess the full end-to-end workflow on two unseen CSP blind-test case studies, including relaxation and lattice-energy analysis. In both settings, PackFlow outperforms heuristics-based methods by concentrating probability mass in low-energy basins, yielding candidates that relax into lower-energy minima and offering a practical route to amortize the relax-and-rank bottleneck.
- 2 February 2026
- Published by Springer Nature in Nature Computational Science
- Vol. 6 (4) , 404-416
DiffSyn: a generative diffusion approach to materials synthesis planning
The synthesis of crystalline materials, such as zeolites, remains a notable challenge owing to a high-dimensional synthesis space, intricate structure–synthesis relationships and time-consuming experiments. Here, considering the ‘one-to-many’ relationship between structure and synthesis, we propose DiffSyn, a generative diffusion model trained on over 23,000 synthesis recipes that span 50 years of literature. DiffSyn generates probable synthesis routes conditioned on a desired zeolite structure and an organic template. DiffSyn a chieves state-of-the-art performance by capturing the multi-modal nature of structure–synthesis relationships. We apply Diffsny to differentiate among competing phases and generate optimal synthesis routes. As a proof of concept, we synthesize a UFI material using DiffSyn-generated synthesis routes. These routes, rationalized by density functional theory binding energies, resulted in the successful synthesis of a UFI material with a high Si/AlICP of 19.0, which is expected to improve thermal stability.
- 2 February 2026
- Published by Springer Nature in Nature Computational Science
- Vol. 6 (4) , 404-416
DiffSyn: a generative diffusion approach to materials synthesis planning
The synthesis of crystalline materials, such as zeolites, remains a notable challenge owing to a high-dimensional synthesis space, intricate structure–synthesis relationships and time-consuming experiments. Here, considering the ‘one-to-many’ relationship between structure and synthesis, we propose DiffSyn, a generative diffusion model trained on over 23,000 synthesis recipes that span 50 years of literature. DiffSyn generates probable synthesis routes conditioned on a desired zeolite structure and an organic template. DiffSyn a chieves state-of-the-art performance by capturing the multi-modal nature of structure–synthesis relationships. We apply Diffsny to differentiate among competing phases and generate optimal synthesis routes. As a proof of concept, we synthesize a UFI material using DiffSyn-generated synthesis routes. These routes, rationalized by density functional theory binding energies, resulted in the successful synthesis of a UFI material with a high Si/AlICP of 19.0, which is expected to improve thermal stability.
- Open Access
- 26 November 2025
- Published by American Chemical Society (ACS) in ACS Applied Materials & Interfaces
- Vol. 17 (51) , 69221-69233
Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials
Inorganic synthesis planning currently relies primarily on heuristic approaches or machine learning models trained on limited data sets, which constrains its generality. We demonstrate that language models (LMs) without task-specific fine-tuning can recall synthesis conditions reported in the scientific literature. Off-the-shelf models, such as GPT-4.1, Gemini 2.0 Flash, and Llama 4 Maverick achieve a Top-1 precursor prediction accuracy of up to 53.8% and a Top-5 performance of 66.8% on a held-out set of 1000 reactions. They also predict calcination and sintering temperatures with mean absolute errors of 7La3Zr2O12 solid-state electrolytes, we demonstrate that SyntMTE reproduces the experimentally observed dopant-dependent sintering trends. Our hybrid workflow enables scalable and data-efficient inorganic synthesis planning.
- 26 November 2025
- Published by American Chemical Society (ACS) in ACS Applied Materials & Interfaces
- Vol. 17 (51) , 69221-69233
Open AccessLanguage Models Enable Data-Augmented Synthesis Planning for Inorganic Materials
Inorganic synthesis planning currently relies primarily on heuristic approaches or machine learning models trained on limited data sets, which constrains its generality. We demonstrate that language models (LMs) without task-specific fine-tuning can recall synthesis conditions reported in the scientific literature. Off-the-shelf models, such as GPT-4.1, Gemini 2.0 Flash, and Llama 4 Maverick achieve a Top-1 precursor prediction accuracy of up to 53.8% and a Top-5 performance of 66.8% on a held-out set of 1000 reactions. They also predict calcination and sintering temperatures with mean absolute errors of 7La3Zr2O12 solid-state electrolytes, we demonstrate that SyntMTE reproduces the experimentally observed dopant-dependent sintering trends. Our hybrid workflow enables scalable and data-efficient inorganic synthesis planning.
- Open Access
Masked Mineral Modeling: Continent-Scale Mineral Prospecting via Geospatial Infilling
Minerals play a critical role in the advanced energy technologies necessary for decarbonization, but characterizing mineral deposits hidden underground remains costly and challenging. Inspired by recent progress in generative modeling, we develop a learning method which infers the locations of minerals by masking and infilling geospatial maps of resource availability. We demonstrate this technique using mineral data for the conterminous United States, and train performant models, with the best achieving Dice coefficients of $0.31 \pm 0.01$ and recalls of $0.22 \pm 0.02$ on test data at 1$\times$1 mi$^2$ spatial resolution. One major advantage of our approach is that it can easily incorporate auxiliary data sources for prediction which may be more abundant than mineral data. We highlight the capabilities of our model by adding input layers derived from geophysical sources, along with a nation-wide ground survey of soils originally intended for agronomic purposes. We find that employing such auxiliary features can improve inference performance, while also enabling model evaluation in regions with no recorded minerals.Open AccessMasked Mineral Modeling: Continent-Scale Mineral Prospecting via Geospatial Infilling
Minerals play a critical role in the advanced energy technologies necessary for decarbonization, but characterizing mineral deposits hidden underground remains costly and challenging. Inspired by recent progress in generative modeling, we develop a learning method which infers the locations of minerals by masking and infilling geospatial maps of resource availability. We demonstrate this technique using mineral data for the conterminous United States, and train performant models, with the best achieving Dice coefficients of $0.31 \pm 0.01$ and recalls of $0.22 \pm 0.02$ on test data at 1$\times$1 mi$^2$ spatial resolution. One major advantage of our approach is that it can easily incorporate auxiliary data sources for prediction which may be more abundant than mineral data. We highlight the capabilities of our model by adding input layers derived from geophysical sources, along with a nation-wide ground survey of soils originally intended for agronomic purposes. We find that employing such auxiliary features can improve inference performance, while also enabling model evaluation in regions with no recorded minerals. - Open Access
DiffSyn: A Generative Diffusion Approach to Materials Synthesis Planning
The synthesis of crystalline materials, such as zeolites, remains a significant challenge due to a high-dimensional synthesis space, intricate structure-synthesis relationships and time-consuming experiments. Considering the one-to-many relationship between structure and synthesis, we propose DiffSyn, a generative diffusion model trained on over 23,000 synthesis recipes spanning 50 years of literature. DiffSyn generates probable synthesis routes conditioned on a desired zeolite structure and an organic template. DiffSyn achieves state-of-the-art performance by capturing the multi-modal nature of structure-synthesis relationships. We apply DiffSyn to differentiate among competing phases and generate optimal synthesis routes. As a proof of concept, we synthesize a UFI material using DiffSyn-generated synthesis routes. These routes, rationalized by density functional theory binding energies, resulted in the successful synthesis of a UFI material with a high Si/Al$_{\text{ICP}}$ of 19.0, which is expected to improve thermal stability and is higher than that of any previously recorded.
Open AccessDiffSyn: A Generative Diffusion Approach to Materials Synthesis Planning
The synthesis of crystalline materials, such as zeolites, remains a significant challenge due to a high-dimensional synthesis space, intricate structure-synthesis relationships and time-consuming experiments. Considering the one-to-many relationship between structure and synthesis, we propose DiffSyn, a generative diffusion model trained on over 23,000 synthesis recipes spanning 50 years of literature. DiffSyn generates probable synthesis routes conditioned on a desired zeolite structure and an organic template. DiffSyn achieves state-of-the-art performance by capturing the multi-modal nature of structure-synthesis relationships. We apply DiffSyn to differentiate among competing phases and generate optimal synthesis routes. As a proof of concept, we synthesize a UFI material using DiffSyn-generated synthesis routes. These routes, rationalized by density functional theory binding energies, resulted in the successful synthesis of a UFI material with a high Si/Al$_{\text{ICP}}$ of 19.0, which is expected to improve thermal stability and is higher than that of any previously recorded.