Case Study Prospectus
Levi Sweet-Breu
- Title
Using ChatGPT to quantify land use/land cover changes between two qualitative rasters
- Research question(s)
Can ChatGPT solve complicated coding problems? Can we develop code that is reproducible and modular?
- Objective(s)
i. Attempt to develop R code that can compare differences between two qualitative rasters.
ii. Document and understand how ChatGPT can understand and solve methodological problems.
iii. Determine if ChatGPT can solve a specific problem, similar to a software engineer.
- Approach
I will ask ChatGPT to create two synthetic land use/land cover rasters representing the same region at different points in time, and then I will ask ChatGPT to quantify the differences between the two rasters, all in R (R Core Team 2024). Each ChatGPT response will be saved to individual text files, and each code response will be saved to individual .R files. I will iterate through this process until I have determined whether ChatGPT can effectively solve the problem. I will measure ChatGPT’s success against an already existing tool in ArcGIS Pro that can perform this operation (ESRI). I will document any revisions I make to ChatGPT-generated code.
- Selected References
Castelvecchi D. 2022. Are ChatGPT and AlphaCode going to replace programmers? Nature. https://www.nature.com/articles/d41586-022-04383-z
ESRI. Compute Change Raster (Image Analyst). From https://pro.arcgis.com/en/pro-app/latest/tool-reference/image-analyst/compute-change-raster.htm
Foroumandi E, Moradkhani H, Sanchez-Vila X, Singha K, Castelletti A, & Destouni G. 2023. ChatGPT in Hydrology and Earth Sciences: Opportunities, Prospects, and Concerns. Water Resources Research, 59(10). https://doi.org/10.1029/2023WR036288
R Core Team. 2024. R: A Language and Environment for Statistical Computing. From https://www.r-project.org/