Mapping plastic greenhouses with satellite imagery in Valparaiso, Chile: development of a new methodology through data cloud platform
Bibliographic record
Abstract
During the last decades, there has been a strong increase around the globe in the use of plastic greenhouses (PGs) which respond to the need to provide better water security, overcome adverse weather events, or elude pests. The central valley of Chile has not been an exception and the surface covered by greenhouses has also experienced an increase over the years. In the Valparaiso region, the surface increased from 1122 ha to 1180 ha throughout the decade 1997-2007. However, on one hand, there has not been a new PGs census since 2007 and, on the other hand, its spatial distribution has not ever been mapped. Considering that agriculture in this region employs more than 60000 people and moves 4% of regional GPD, this information should be available to be included in land planning and to be incorporated into hydrological, economic, and food security models. To overcome this, we propose a new method for monitoring the variations of the surface covered by PGs based on the intersection of normalized difference indexes and areas excludes by masks. For this, free Landsat 8 multi-temporal cloud-free images were used, from which five indexes were obtained (Modified Soil-adjusted Vegetation Index, Temperature Brightness Index, Normalized Difference Vegetation Index - Green, Normalized Difference Built-up Index, and Plastic Surface Index). These indexes were then reclassified in binary form and added up. Finally, urban areas and high slope zones were excluded to obtain the final output. This procedure was run in Google Earth Engine, which allowed easy replication and automation for longer time series or in other study sites. Results proved this methodology was able to successfully discriminate the 86% of PG, which suppose 1410 ha. This surface is consistent with the agricultural census developed in 2007 and with the increase of more than 900 subsidies granted by the government for installing PGs. Its performance also supports our confidence to discriminate PGs in areas with different land covers such as reservoirs, rural areas, open crops, bare soil, and roads. Future studies will allow us to estimate the surface of plastic greenhouses in Chile, mapping its spatial distribution in all the country, and monitor changes over time.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".