I am a machine learning research scientist at the National Renewable Energy Lab (NREL). Currently, I am working on developing scientific foundation models. In the past, I have researched advances in deep generative modeling and reinforcement learning. I am broadly interested in applications of AI to clean energy systems.
At NREL, I apply ML to real-world problems such as building energy management, weather and power forecasting, and discovering novel enzymes. NREL is a DOE national lab that uses AI and supercomputing to help tackle the climate crises, which I believe to be one of the most pressing challenges of our time.
[CV][Google scholar] [Github]
Contact: pemami[at]nrel[dot][gov]
News
- August 2024 My paper “Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC” received an NREL directorate Postdoctoral Publication award!
- July 2024 I am serving as a guest editor for the Environmental Data Science <> Climate Change AI special issue. See CFP here
- October 2023 One paper accepted in the journal Neural Computation
- Sept 2023 BuildingsBench is accepted at NeurIPS’23!
Recent Papers
SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems
arXiv preprint
Augmenting surrogate models for complex systems with natural language interfaces.
Augmenting surrogate models for complex systems with natural language interfaces.
Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning
IEEE CDC'23
Framework for learning non-stationary policies in multi-timescale MARL by leveraging periodicity.
Framework for learning non-stationary policies in multi-timescale MARL by leveraging periodicity.
BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting
NeurIPS D&B 2023
Platform for studying large-scale pretraining + zero-shot generalization/finetuning of building load forecasting models.
Platform for studying large-scale pretraining + zero-shot generalization/finetuning of building load forecasting models.
Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC
Machine Learning: Science & Technology, 2023
Also presented at NeurIPS’22 Workshop on Machine Learning in Structural Biology
A fast MCMC sampler for discovering variants by mixing and matching unsupervised evolutionary sequence models with supervised models that map sequence to protein function.
Also presented at NeurIPS’22 Workshop on Machine Learning in Structural Biology
A fast MCMC sampler for discovering variants by mixing and matching unsupervised evolutionary sequence models with supervised models that map sequence to protein function.
See my CV for a complete list including older publications.