Hyperspectral Imaging Simulator and Applications for Unmanned Aerial Vehicles
Bibliographic record
Abstract
Mineral exploration utilizing hyperspectral imaging sensors aboard low-altitude airborne platforms is still a relatively new and developing research topic. The main reason is the difficulty of finding the optimal combination of platform, sensor, and survey design for specific targets in various geological settings. This research firstly aims to examine the reliability of an industry-standard workflow for hyperspectral imaging using an unmanned aerial vehicle (UAV) for a mineral exploration target in Cuprite, Nevada. A versatile hyperspectral imaging (HSI) simulator called HYSIMU has been developed that can be used to simulate different scenarios based on customizable flight and target parameters. Random mineral reflectance spectra are assigned to synthetic digital elevation models (DEMs) and several flight scenarios are simulated on those DEMs using different sensors and selectable survey parameters such as altitude, speed, and sun position with options to add spatial noise, spectral noise, and terrain shadow effects. The synthetic hyperspectral data generated from each scenario are further processed using the workflow established earlier in this research to determine the target minerals and to create classification maps. In this study, three ground truth scenarios with different levels of complexity were simulated with varying survey parameters such as altitude (10 to 200 meters), velocity (1 to 100 m/s), and sun elevation (0°, 45°, and 90°). A sensitivity study is performed using four metrics to compare the ground truth data and the obtained classification maps. The results showed that HYSIMU has great potential as a tool to optimize hyperspectral imaging in mineral explorations by finding the right combinations of flight parameters, primarily the altitude and flight speed which affect the survey time and total cost. There are opportunities for further development of HYSIMU to make it more versatile. It was also implemented to test the detectability of agricultural targets in different soil conditions. Lastly, the use of satellite-based Land Surface Temperature (LST) as an earthquake precursor is examined and its potential to be combined with hyperspectral imaging is discussed.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".