|
Project properties |
|
| Title | Understanding the potential of AI for the development of forestry carbon projects |
| Group | Forest Ecology and Forest Management Group |
| Project type | internship |
| Credits | 24 |
| Supervisor(s) | External: Treevive’s CEO Liesbeth Gort: l.gort@treevive.earth
prof.dr. PA (Pieter) Zuidema |
| Examiner(s) | prof.dr. PA (Pieter) Zuidema |
| Contact info | Liesbeth Gort: l.gort@treevive.earth |
| Begin date | 2024/03/01 |
| End date | |
| Description | Forestry carbon projects typically mitigate or prevent carbon emissions through activities such as reforestation, deforestation prevention, or improved forest management. These efforts generate carbon credits, also known as "carbon offsets," which can be sold on the voluntary carbon market. In simple terms, carbon credits are generated by the difference between net carbon sequestration in the project scenario, minus the net carbon sequestration (or avoided net emissions) in the baseline or without project scenario, minus a couple of deductions covering risk, uncertainty and leakage. The development of a forestry carbon project involves an extensive pre-feasibility phase, primarily aimed at assessing the project's viability. Once proven feasible, the realization of a project design document (PDD) becomes necessary—a process that is costly, requires extensive studies, technical skills and expertise for project to become certified.
Artificial Intelligence (AI) is emerging as a tool to markedly reduce the time and costs associated with creating pre-feasibility studies and Project Design Documents (PDDs). Certain companies are now offering AI-enabled services to forestry project developers at more affordable rates. This raises questions about the quality and relevance of AI-generated documents and data. It also raises concerns about the market position of these companies as well as those that do not embrace AI in their processes. The assignment is about understanding the potential, benefits and challenges of AI-generated PDDs, feasibility studies, data, and carbon projections essential for evaluating the feasibility of forest carbon projects. Specifically, the assignment aims to provide: • Understand the reliability and quality of AI-generated data, especially in feasibility assessments of forestry carbon projects, and; • Understand the risks associated with the use of AI-generated data during project implementation; • Offer recommendations to Treevive on whether and how to integrate AI-generated data during the onboarding of new projects and in assessing the feasibility of its forest carbon projects. Internet page of organization: https://treevive.earth/ https://forminternational.nl/ Keywords to search by: only needed for the search option on the FEM education webpage; in TIP students can search for any word in the whole text! remove in the lists below those that are not applicable. Don’t add your own. Topic(s): Sustainable forest management/ Region(s): America's/ Africa /Asia Climate(s): Tropical zone |
| Used skills | |
| Requirements | Standard for MSc thesis:
- WEC-31806 Ecological Methods I, or a comparable alternative course; - One FEM course (at least), depending on the topic of the thesis: FEM-30306 Forest Ecology and Forest Management, FEM-30806 Resource Dynamics Sustainable Utilization, FEM-32306 Agroforestry, or Models for Ecological Systems FEM-31806 If different: give course code and name Standard for BSc thesis minimal 120 credits |