Hariprasad Kodamana
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hariprasad Kodamana has a total of 119 co-authors. Here are the top co-authors by number of shared publications:
- Manojkumar Ramteke
Department of Chemical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India
23 shared publications - Naduvath Mana Anoop Krishnan
Department of Civil Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India
19 shared publications - Ravinder Bhattoo
Indian Institute of Technology Delhi
12 shared publications - Sukumaran Sandeep
Centre for Atmospheric Sciences Indian Institute of Technology Delhi New Delhi India
10 shared publications - Bhavik R. Bakshi
Arizona State University
9 shared publications Avan Kumar
7 shared publications
Latest Publications
- 6 November 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
Hierarchical Reinforcement Learning for Degradation-Aware and Coordinated Control of Virtual Power Plants
Virtual Power Plants (VPPs) coordinate distributed energy resources (DERs) under forecast uncertainty and multi-time-scale constraints, while battery and generator wear can erase short-term trading gains. This paper proposes a hierarchical reinforcement learning (HRL) controller that matches aggregator practice: a slow-time-scale manager issues location-level power subgoals together with a continuous autonomy signal, and fast-time-scale workers dispatch devices under local physics. Battery and generator degradation enter the training reward through a three-phase curriculum that activates a throughput-budget penalty and a cycle-depth surcharge, so the policy optimizes profit net of wear rather than arbitrage alone. On a 100-day shared-seed benchmark against two decentralized RL controllers, an open-loop stochastic mixed-integer programming (MIP) day-ahead optimizer, and a closed-loop model predictive control (MPC) baseline that reoptimizes hourly over an 8-h horizon, HRL attains an average daily profit of \$50,264─3.1× MPC and 4.0× MIP─at 50–170 ms per simulated day. HRL is the only method whose throughput-to-cycle-depth ratio exceeds unity (1.18), and it incurs only \$24.6 of cycle-depth-aware wear per \$1,000 of profit (2.5× better than MPC). These results indicate that degradation-aware hierarchical control can outperform both open-loop stochastic optimization and receding-horizon MPC for real-time VPP dispatch.
- 6 November 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
Hierarchical Reinforcement Learning for Degradation-Aware and Coordinated Control of Virtual Power Plants
Virtual Power Plants (VPPs) coordinate distributed energy resources (DERs) under forecast uncertainty and multi-time-scale constraints, while battery and generator wear can erase short-term trading gains. This paper proposes a hierarchical reinforcement learning (HRL) controller that matches aggregator practice: a slow-time-scale manager issues location-level power subgoals together with a continuous autonomy signal, and fast-time-scale workers dispatch devices under local physics. Battery and generator degradation enter the training reward through a three-phase curriculum that activates a throughput-budget penalty and a cycle-depth surcharge, so the policy optimizes profit net of wear rather than arbitrage alone. On a 100-day shared-seed benchmark against two decentralized RL controllers, an open-loop stochastic mixed-integer programming (MIP) day-ahead optimizer, and a closed-loop model predictive control (MPC) baseline that reoptimizes hourly over an 8-h horizon, HRL attains an average daily profit of \$50,264─3.1× MPC and 4.0× MIP─at 50–170 ms per simulated day. HRL is the only method whose throughput-to-cycle-depth ratio exceeds unity (1.18), and it incurs only \$24.6 of cycle-depth-aware wear per \$1,000 of profit (2.5× better than MPC). These results indicate that degradation-aware hierarchical control can outperform both open-loop stochastic optimization and receding-horizon MPC for real-time VPP dispatch.
- 16 September 2026
- Published by American Chemical Society (ACS) in ACS Sustainable Chemistry & Engineering
- Vol. 14  (38) , 17235-17251
Integrated Retrosynthesis and Large Language Modeling for Chemistry-Informed Circular Chemical Reaction Networks
Discovery and development of manufacturing routes that explicitly account for the entire product life cycle are essential for the transformation to a sustainable and circular chemical industry. Retrosynthesis is a promising approach, but operates within a gate-to-gate paradigm, limiting its ability to explicitly integrate end-of-life waste streams into upstream production pathways. We evaluated four reaction discovery strategies that combine human intervention, pattern recognition, retrosynthesis, and large language models (LLM) within a common comparative framework. When evaluated with methanol as a benchmark system, the strategies reveal distinct trade-offs between pathway discovery and technological maturity. Combining LLMs with retrosynthesis achieves the broadest expansion of reaction space with 165 reactions involving 12 unique chemicals and the highest novelty relative to the conventional business-as-usual reference network. The resulting circular chemical reaction network (CCRN) for a more complex molecule, polyethylene, contains more than 1,000 reactions, and human-guided extraction increased the total number of identified reactions by 34–35%, depending on the keyword-search strategy, while recovering additional end-of-life reactions from experimental results. The proposed framework demonstrates that combining language-based knowledge extraction with structure-informed retrosynthetic reasoning enables scalable construction of CCRNs and supports the systematic exploration of candidate circular chemical pathways for subsequent economic and environmental evaluation.
- 16 September 2026
- Published by American Chemical Society (ACS) in ACS Sustainable Chemistry & Engineering
- Vol. 14  (38) , 17235-17251
Integrated Retrosynthesis and Large Language Modeling for Chemistry-Informed Circular Chemical Reaction Networks
Discovery and development of manufacturing routes that explicitly account for the entire product life cycle are essential for the transformation to a sustainable and circular chemical industry. Retrosynthesis is a promising approach, but operates within a gate-to-gate paradigm, limiting its ability to explicitly integrate end-of-life waste streams into upstream production pathways. We evaluated four reaction discovery strategies that combine human intervention, pattern recognition, retrosynthesis, and large language models (LLM) within a common comparative framework. When evaluated with methanol as a benchmark system, the strategies reveal distinct trade-offs between pathway discovery and technological maturity. Combining LLMs with retrosynthesis achieves the broadest expansion of reaction space with 165 reactions involving 12 unique chemicals and the highest novelty relative to the conventional business-as-usual reference network. The resulting circular chemical reaction network (CCRN) for a more complex molecule, polyethylene, contains more than 1,000 reactions, and human-guided extraction increased the total number of identified reactions by 34–35%, depending on the keyword-search strategy, while recovering additional end-of-life reactions from experimental results. The proposed framework demonstrates that combining language-based knowledge extraction with structure-informed retrosynthetic reasoning enables scalable construction of CCRNs and supports the systematic exploration of candidate circular chemical pathways for subsequent economic and environmental evaluation.
- 7 August 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 215
A knowledge graph-embedded large language model to strategize battery recycling technology selection
- 7 August 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 215
A knowledge graph-embedded large language model to strategize battery recycling technology selection
- 23 May 2026
- Published by Elsevier in Chemical Engineering Research and Design
- Vol. 231, 82-101
A framework for computationally efficient process simulation with machine learning aided flash calculations
- 23 May 2026
- Published by Elsevier in Chemical Engineering Research and Design
- Vol. 231, 82-101
A framework for computationally efficient process simulation with machine learning aided flash calculations
- 12 March 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65  (11) , 6375-6392
Thermophysical Property Prediction and Optimization of CO 2 –Binding Organic Liquids Using Kolmogorov–Arnold Networks and Optimized Quantum Descriptors
- 12 March 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65  (11) , 6375-6392
Thermophysical Property Prediction and Optimization of CO 2 –Binding Organic Liquids Using Kolmogorov–Arnold Networks and Optimized Quantum Descriptors
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23  (1545598X) , 1-5
Deep Learning-Based Correction of Decadal Predictions of the PDO and TAG Indices
Conventional multimodel ensemble averages (MME) from hindcasts, such as those from the Decadal Climate Prediction Project component A (DCPP-A), can suffer from diluted predictive skill due to the averaging of models with varying performance. This dilution limits the skillful prediction of key Decadal Climate Variability (DCV) modes, such as the Pacific Decadal Oscillation (PDO) and the Tropical Atlantic SST Gradient (TAG). We propose a Long Short-Term Memory (LSTM) network to correct the ensemble averages of each participating model and hence the MME. The LSTM is trained on individual model ensemble averages and the MME to learn nonlinear relationships, producing a more skillful time series for the PDO and TAG indices, relative to the conventional MME, as quantified by multiple performance metrics. These enhancements include superior temporal accuracy, reduced error, and a closer statistical correspondence in phase, timing, and magnitude with the observations. Our study demonstrates that deep learning can extract a more skillful signal from climate ensembles, offering an approach to more reliable decadal predictions.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23  (1545598X) , 1-5
Deep Learning-Based Correction of Decadal Predictions of the PDO and TAG Indices
Conventional multimodel ensemble averages (MME) from hindcasts, such as those from the Decadal Climate Prediction Project component A (DCPP-A), can suffer from diluted predictive skill due to the averaging of models with varying performance. This dilution limits the skillful prediction of key Decadal Climate Variability (DCV) modes, such as the Pacific Decadal Oscillation (PDO) and the Tropical Atlantic SST Gradient (TAG). We propose a Long Short-Term Memory (LSTM) network to correct the ensemble averages of each participating model and hence the MME. The LSTM is trained on individual model ensemble averages and the MME to learn nonlinear relationships, producing a more skillful time series for the PDO and TAG indices, relative to the conventional MME, as quantified by multiple performance metrics. These enhancements include superior temporal accuracy, reduced error, and a closer statistical correspondence in phase, timing, and magnitude with the observations. Our study demonstrates that deep learning can extract a more skillful signal from climate ensembles, offering an approach to more reliable decadal predictions.
- 27 October 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64  (44) , 21148-21166
Hierarchical Reinforcement Learning with Dynamic Meta Agent for Adaptive Cut Selection in Integer Programming with Applications to Sensor Network Design
- 27 October 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64  (44) , 21148-21166
Hierarchical Reinforcement Learning with Dynamic Meta Agent for Adaptive Cut Selection in Integer Programming with Applications to Sensor Network Design
- 22 October 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64  (49) , 23220-23233
A Data-Driven Symbolic Regression Framework for Modeling and Multiobjective Optimization of a Microbial Fermentation System
- 22 October 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 64  (49) , 23220-23233
A Data-Driven Symbolic Regression Framework for Modeling and Multiobjective Optimization of a Microbial Fermentation System
- 16 October 2025
- Published by American Chemical Society (ACS) in Environmental Science & Technology
- Vol. 59  (42) , 22533-22543
A Large Language Model-based Framework to Retrieve Life Cycle Inventory and Environmental Impact Data from Scientific Literature
Life cycle assessment (LCA) quantifies environmental impacts from raw material extraction to end-of-life (EoL) treatment, yet its accuracy depends on reliable life cycle inventory (LCI) data. However, obtaining such data is time-consuming and requires an extensive literature review or access to databases that are often behind paywalls that hinder transparent research. This study introduces a systematic framework leveraging a retrained large language model (LLM) to assist LCA practitioners in retrieving LCI data and insightful information about their environmental impact. The framework follows a three-stage process: (i) a fine-tuned classification model identifies relevant documents, (ii) the LLaMA-2-7B model is pretrained on selected texts to inject domain knowledge into its database, and (iii) a fine-tuned Q&A model extracts LCI and environmental impact data from the scientific literature. The resulting LLM is termed as "Sustain-LLaMA". We implement this framework in two cases: methanol production and plastic packaging EoL treatment. After retraining, the classification models achieve high accuracies (0.850 for methanol, 0.952 for plastic packaging) for unseen data, which means effectively distinguishing relevant studies. The Q&A models with Retrieval Augmentated Generation (RAG) yield F1 scores of 0.823 for methanol and 0.855 for plastic studies. The Q&A models' performances are validated against the version of LLaMA-2-7B without retraining, ChatGPT-4o, and the USLCI database, demonstrating comparable or superior accuracy and efficiency. This framework enhances scalability and precision by automating LCI data retrieval, offering a promising tool for guiding the chemical and plastic industries toward sustainability.
- 16 October 2025
- Published by American Chemical Society (ACS) in Environmental Science & Technology
- Vol. 59  (42) , 22533-22543
A Large Language Model-based Framework to Retrieve Life Cycle Inventory and Environmental Impact Data from Scientific Literature
Life cycle assessment (LCA) quantifies environmental impacts from raw material extraction to end-of-life (EoL) treatment, yet its accuracy depends on reliable life cycle inventory (LCI) data. However, obtaining such data is time-consuming and requires an extensive literature review or access to databases that are often behind paywalls that hinder transparent research. This study introduces a systematic framework leveraging a retrained large language model (LLM) to assist LCA practitioners in retrieving LCI data and insightful information about their environmental impact. The framework follows a three-stage process: (i) a fine-tuned classification model identifies relevant documents, (ii) the LLaMA-2-7B model is pretrained on selected texts to inject domain knowledge into its database, and (iii) a fine-tuned Q&A model extracts LCI and environmental impact data from the scientific literature. The resulting LLM is termed as "Sustain-LLaMA". We implement this framework in two cases: methanol production and plastic packaging EoL treatment. After retraining, the classification models achieve high accuracies (0.850 for methanol, 0.952 for plastic packaging) for unseen data, which means effectively distinguishing relevant studies. The Q&A models with Retrieval Augmentated Generation (RAG) yield F1 scores of 0.823 for methanol and 0.855 for plastic studies. The Q&A models' performances are validated against the version of LLaMA-2-7B without retraining, ChatGPT-4o, and the USLCI database, demonstrating comparable or superior accuracy and efficiency. This framework enhances scalability and precision by automating LCI data retrieval, offering a promising tool for guiding the chemical and plastic industries toward sustainability.