Research And Results

Type: Transformer a novel Transformer variant that replaces noncausal attention weights with causal weights that are reweighted according to a smooth heavy-tailed decay.

Type: Transformer a cascade machine learning forecasting system for 15-day global weather forecast

Type: GAN Raising Awareness about Climate Change by Generating Images of Floods

Type: Multi-Agent Power demand forecasting in an on-policy, cooperative MARL algorithm for voltage control problem in the isolated Microgrid system by incorporating a differentiable, learning-based communication protocol, a spatial discount factor, and an action smoothing scheme.

Type: Transformer Accurate forecasts are of critical importance for Transmission System Operators (TSOs) to match electricity supply and demand.

Type: Transformer Our deterministic model for precise weather forecasting

Type: Foundation Can predict atmospheric variables, such as temperature.

Type: GNN Graph neural network model for predicting wind plant performance. It represents the wind plant a graph with nodes representing individual turbines and wake effects encoded by directed edges.

Type: NN FourCastNet predicts global atmospheric dynamics of various weather / climate variables.

Type: Gradient Boosted Tree It leverages machine learning, satellite imagery, and weather data to predict solar energy output, making it a plug-and-play solution for generating forecasts

Type: CNN A sky image-based deep convolutional neural network for intra-hour solar forecasting

Type: Sparse Retriveal This sparse retrieval model is optimized for nuclear-specific applications. It encodes both queries and documents into high-dimensional sparse vectors, where the non-zero dimensions correspond to specific tokens in the vocabulary, and their values indicate the relative importance of those tokens.

Type: MARL A testbed for the implementation of Multi-Agent Reinforcement Learning (MARL) in building energy coordination and demand response in cities. 

Type: Agent-based The model computes electricity prices endogenously based on the simulation of strategic bidding behavior of prototyped market actors.

Type: Transformer a novel transformer-based framework called GridFormer which serves as a backbone for image restoration under adverse weather conditions.

Type: Foundation Heliophysics model trained on 14 years of observations from NASA’s Solar Dynamics Observatory, helping protect critical infra from space weather.

Type: LLM An instruction model designed specifically for nuclear power domain as a research tool, responds to chats in a chat-based environment based on it's training information.

Type: LLM A base model designed specifically for nuclear power domain as a research tool, responds to chats in a chat-based environment based on it's training information.

Type: LSTM Improving the predictions of power generated using wind energy and we have achieved that using LSTM as machine learning model and performing model optimization on it.

Type: Time Series Modeling a PyTorch implementation of a Transformer-based time series model for forecasting electricity load diagrams (hourly).

Type: LSTM+PPO A hybrid deep learning + reinforcement learning system for power grid optimization in Lauderdale County, AL. The system forecasts demand using a weather-informed LSTM model and trains a PPO-based agent to maintain stability and minimize blackout risk under stress.

Type: RAG GreenChat is a domain-specific RAG model designed to support environmental decision-making across multiple domains relevant to UN SDGs.

Type: GNN Integrating Power Grid Topology in Graph Neural Networks for Power Flow.

Type: Classification An Environmental due diligence classification model, trained on customized environmental Dataset to detect contamination and remediation activities. Identifies the source of contamination, the extent of contamination, the types of contaminants present at the site, the flow of contaminants and their interaction with ground water, surface water and other surrounding water bodies.

Type: Regression This is a custom regression model trained to predict electricity prices ($/kWh) in California, based on a variety of grid-level and environmental features such as EV charging demand, solar/wind production, carbon emissions, and storage indicators.

Type: NN Advanced neural architecture , DMP-PCFC is an interpretable and accurate model for multi-step energy loads prediction in integrated energy systems, or the broader task of time series forecasting.

Type: Transformer This model classifies patents into "green patents" or "no green patents" by their titles.