Assessing hyperspectral sensor capabilities: PRISMA vs EnMAP for crop type mapping in a semi-arid region
Bibliographic record
Abstract
Significant advancements are being made through the use of new-generation of hyperspectral sensors to enhance crop type mapping, especially in heterogeneous and fragmented agricultural landscapes. However, the availability and spatial-temporal coverage of hyperspectral satellites such as PRISMA (PRecursore IperSpettrale della Missione Applicativa) and EnMAP (Environmental Mapping and Analysis Program) can pose considerable challenges for crop type mapping. These include limitations in revisit frequency, narrow swath widths, cloud interference, and the relatively recent and still-developing global acquisition strategies, which may result in data gaps over specific agricultural regions during critical crop growth stages. This study presents a comprehensive comparison of EnMAP Level 2A (L2A) and PRISMA level 2D (L2D), acquired on the same day over a semi-arid region in Morocco. To do so, we evaluated two feature selection strategies: Stepwise Discriminant Analysis (SDA) and Recursive Feature Elimination (RFE) and benchmark the performance of four classification models, including Support Vector Machine (SVM), Random Forest (RF), CatBoost, and the transformer-based foundation model for tabular data (TabPFN). Sensor consistency was assessed using spectral correlation metrics and a vegetation index, showing strong agreement between PRISMA and EnMAP in the VNIR and SWIR-1 domains (R 2 > 0.96). Classification results demonstrated that TabPFN outperformed all other models, reaching 93 % overall accuracy with PRISMA and 90 % with EnMAP. These findings highlight the operational value of hyperspectral imaging and foundation models for accurate, scalable crop mapping in complex agricultural settings. The high level of agreement observed between PRISMA and EnMAP in this study further supports the feasibility of synergetic use of multiple hyperspectral missions. This opens the door to constructing dense, multi-sensor hyperspectral time series, which could significantly enhance temporal coverage and support continuous agricultural monitoring and crop dynamics analysis at large scales.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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".