AI in My Research: Practical Lessons Every Academic Should Know

Enhancing Efficiency Without Replacing Expertise

Here, I share practical lessons from my research, where Artificial Intelligence (AI) has become an essential productivity tool. AI enhances efficiency, improves data-driven decision-making, and simplifies the management of complex technical workflows. In research areas like energy systems, hydrogen economy, and decarbonization, AI has become indispensable in supporting design optimization, techno-economic assessments, and policy-related studies.

The Growing Role of AI in Technical Research

Research demands in engineering and sustainability are increasing. The volume of data, the complexity of multidisciplinary systems, and the expectation for actionable and impactful results make it clear that traditional methods, while foundational, require intelligent support. AI has emerged as a practical solution to address these demands by assisting researchers in managing large datasets, improving analytical workflows, and enhancing research efficiency. To me, it feels like AI is no longer a luxury or an optional add-on. For researchers working in technical fields, it is becoming an essential tool that supports rigorous analysis and process optimization. AI allows people to focus on high-level problem-solving while automating data-heavy and repetitive processes.

AI as a Technical Enabler in Modeling, Design, and Analysis

In my research, AI functions as a supportive tool that enhances technical workflows, particularly in design optimization, data management, and analytical assessments. In a recent carbon capture project, an AI-driven data generation framework boosted the accuracy of solvent screening for rotating packed beds from 40% to over 92%, reducing the time and cost needed to identify optimal candidates and accelerating deployment of advanced CO₂ capture systems.

However, the core scientific thinking, critical analysis, and decision-making remain entirely driven by human expertise. AI assists in improving efficiency, but intellectual leadership and scientific rigor always come from the researcher.

Optimizing Design Configurations and Scenario Assessments

Design optimization tasks often involve multiple design variables, complex trade-offs, and scenario evaluations. AI supports these workflows by organizing variable sets and assisting in identifying efficient configurations within defined technical boundaries.

For example, in one liquefied natural gas (LNG) study, an AI-based surrogate model paired with advanced optimization algorithms cut the computational time of process design by over 90 percent, while maintaining near-perfect accuracy in predicting energy use. This approach not only sped up decision-making but also revealed operating conditions that could meaningfully lower greenhouse gas emissions.

AI helps in managing optimization parameters and providing structured comparisons of alternative configurations. However, the final selection of the optimal design, assessment of trade-offs, and alignment with project objectives are determined through in-depth analysis by the researcher.

Enhancing Data Handling and Techno-Economic Evaluations

Techno-economic studies demand managing extensive technical and economic data, modeling various policy scenarios, and evaluating the financial viability of technologies. AI assists in organizing datasets, automating trend analysis, and visualizing results for better clarity. In my research, AI-driven analytics streamline the handling of complex datasets, helping structure the evaluation process more efficiently. However, the interpretation of economic impacts, policy implications, and formulation of strategic conclusions is a process that depends entirely on the researcher’s expertise and critical assessment.

Streamlining Documentation and Review Processes

Research documentation, reporting, and preparation of policy briefs require meticulous attention to detail. AI tools assist in managing references, ensuring formatting consistency, and organizing large documents efficiently. These tools help reduce the time spent on routine documentation tasks, allowing me to dedicate more focus to in-depth content development and technical analysis. However, the creation of research content, the development of arguments, and the final quality review remain the responsibility of the researcher.

Supporting Communication and Ethical Compliance

Communicating research findings effectively, whether in academic publications, policy discussions, or industry engagements, requires clarity, accuracy, and contextual understanding. AI tools support by organizing supporting materials, managing citations, and preparing visual summaries. However, crafting the message, ensuring factual precision, and maintaining ethical standards in communication are tasks that require human oversight and intellectual responsibility. AI organizes information, but the integrity and depth of communication are led by the researcher.