Discriminating lithology in arctic environments from Earth orbit, an evaluation of satellite imagery and classification algorithms
Bibliographic record
Abstract
Empirical investigations of classification algorithms for lithological discrimination were performed for field areas on Melville Island, Nunavut, and in the Cape Smith Belt of northern Quebec. These investigations suggest that a neural network classifier (a majority-vote consensus algorithm that combines the classification results of ten feedforward backpropagation neural networks) is capable of consistently producing results that approximate those produced by the best individual neural network execution, and that are equal or superior to those generated by the maximum likelihood and evidential reasoning classifiers. The majority-vote consensus routine serves to eliminate the effect of the natural variability among individual neural network classification results, by producing strong results without necessitating the manual evaluation and ranking of all individual neural network classifications. Two sets of evidential-reasoning classification results were generated based on two different measures of initialevidence: (1) the proportions of training data that contain the image values being classified; and (2) output activations generated by multiple neural network classifications. Evidential-reasoning results produced using the first measure were generally poor, while those produced using the second were frequently comparable to those of the majority-vote neural network consensus algorithm. Empirical investigations of the use of feedforward backpropagation neural networks in the classification of satellite images suggest that: (1) differences in weight initializations between otherwise identical classifications are not sufficient for the generation of sets of error-independent results for use with consensus algorithms; (2) classifications of satellite images are not characterized by over-generalization; (3) the addition of random noise to input vectors during training is not a useful means for supplementing sparse training datasets; (4) commonly applied guidelines for the definition of network topologies are valid; and (5) the absolute and relative magnitudes of output activations may be used as measures of classification confidence. Evaluations of Landsat TM, Radarsat, and IKONOS images, conducted for the Melville Island and Cape Smith Belt regions, demonstrate that: (1) Radarsat images are useful for the discrimination of lithological classes characterized by good correlations with geomorphology and surface roughness, and (2) IKONOS images are good sources of high-resolution information regarding geomorphology, land cover, and lithological units with distinctive weathering characteristics.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".