Tree Ecosystem Services Analysis Platform
Bibliographic record
Abstract
As UBC Electrical and Computer Engineering Capstone Team 117, we worked in collaboration with UBC Campus and Community Planning and UBC SEEDS to develop a project to help support sustainable development policies and goals at UBC. Our project, the Tree Ecosystem Services Analysis Platform (TREESAP), is a tool for analysing and visualizing ecosystem services on the UBC Vancouver campus. We have built a processing pipeline that extracts locations of tree cover on campus from aerial scans, which are in LiDAR and orthophoto formats. Tree clusters are identified in orthophoto by using colour and standard deviation to segment and separate trees from other areas. LiDAR processing consists of a 3D Density-Based Spatial Clustering (DBSCAN) clustering algorithm to identify and separate tree clusters from other points in the scan. These clusters are then smoothed using alpha shape to obtain the optimal outer contour for the cluster. We also provide a desktop app to visualize this data, allowing users to generate reports about ecosystem services, in particular, the carbon sequestration in tonnes/year and the avoided rainwater runoff in litres/year that trees provide. Additionally, shading and cooling information can be gathered by using the interface to calculate the distance between buildings and trees. This app can be used to plan future developments by seeing the potential effects of adding and removing trees. TREESAP provides baseline data for ecosystem services on campus, helping urban planners develop quantitative arboreal sustainability goals. The deliverables of this project are explained in more detail in Appendix 1. Given the limited timeframe of our project, we designed the system with future extensions in mind. We’ve come up with several ideas that future teams could implement: ● Modify or create a new data processing pipeline to use new data sources or new approaches (e.g. machine learning) to provide more or better data. The input to the desktop application is polygons of GeoJson format, so any processing technique that produces valid GeoJson can make use of the desktop application ● Add economic value of the ecosystem services to the desktop application. For example, trees near a cliff may be much more valuable for avoided runoff than those in the middle of campus ● Add more ecosystem services to the desktop application. iTree Canopy1 provides many more ecosystem benefits that depend only on tree cover area, so adding these would work within the architecture of our desktop application. ● Update and scale desktop app so it can be publicly accessible as a tool for public engagement. This may involve some service fees for Google Maps API, for example, on top of usability improvements. Disclaimer: “UBC SEEDS provides students with the opportunity to share the findings of their studies, as well as their opinions, conclusions and recommendations with the UBC community. The reader should bear in mind that this is a student project/report and is not an official document of UBC. Furthermore readers should bear in mind that these reports may not reflect the current status of activities at UBC. We urge you to contact the research persons mentioned in a report or the SEEDS Coordinator about the current status of the subject matter of a project/report.”
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.056 | 0.039 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".