Digital Poster/Demo
In session
Postersession No. 1
,
Sept. 3, 2025,
15:45 –
16:30
Exact timing:
15:45 –
16:30
- Hochschule für Nachhaltiche Entwicklung Eberswalde
- Leibniz-Zentrum für Agrarlandschaftsforschung (ZALF)
In forestry, having consistently relevant and correct information is critical towards environmentally conscionable decision making. Consulting commercially available or open-source Large Language Models (LLMs) in this decision-making process can be an effective way towards informed decision making. However, currently LLMs have demonstrated to be deficient in three critical areas: reliable information sources, lack of access to real world data, and ambiguity in their scientific reasoning ability.
To overcome these shortcomings we opted to instantiate a curated knowledgebase containing information from relevant CC-0 research articles. With clearly defined constraints applied to each research article intended for ingestion in the knowledgebase, it becomes possible for the underlying LLM to produce feedback that is correct, concise and accurate. Some of the constraints of the knowledgebase are in place to adhere to European laws regarding the ethical use of AI as well as comply with copyright laws.
Aside from having access to relevant research papers, having access to real world data is one of the cornerstones of the proposed framework. By utilizing calibrated level 1 data from multiple sensors, platforms and measuring devices, we can implement agentic RAG functionality to retrieve information about our area of interest.
Lastly, reasoning abilities in Large Language Models (LLMs) are paramount and are considered an area of continuous research. While in the current state of the art LLMs convey a form of thinking or reasoning process, its efficacy is still hotly debated. In this research, the focus is on a more comprehensive and explainable scientific reasoning framework involving a decision-making AI agent. Wherein the AI agent will have to determine the goal of an input query, devise a logical methodology to resolve that goal, and execute the resolution using an array of pre-defined actions.
This system has the potential to not only provide the end user with real world data but also provide deeper insights from scientific articles, derive scientific reasoning, as well as assist the user in decision making processes.