Gully mapping using remote sensing: Case study in KwaZulu-Natal, South Africa
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
At present one of the challenges of soil erosion research in South Africa is the limited information on the location of gullies. This is because traditional techniques for mapping erosion which consists of the manual digitization of gullies from air photos or satellite imagery, is limited to expert knowledge and is very time consuming and costly at a regional scale (50-10000km²). Developing a robust, reliable and accurate means of mapping gullies is a current focus for the Institute for Soil, Climate and Water Conservation (ISCW) of the Agricultural Research Council (ARC) of South Africa. The following thesis attempted to answer the question whether “medium resolution multi-spectral satellite observations, such as Landsat TM, combined with information extraction techniques, such as Vegetation Indices and multispectral classification algorithms, can provide a semi-automatic method of mapping gullies and to what level of accuracy?”. \n \nMore specifically, this thesis investigated the utility of three Landsat TM-derived Vegetation Index (VI) techniques and three classification techniques based on their level of accuracy compared to traditional gully mapping methods applied to SPOT 5 panchromatic imagery at selected scales. The chosen study area was located in the province of KwaZulu-Natal (KZN) South Africa, which is considered to be the province most vulnerable to considerable levels of water erosion, mainly gully erosion. Analysis of the vegetation indices found that Normalized Difference Vegetation Index (NDVI) produced the highest accuracy for mapping gullies at the sub-catchment level while Transformed Soil Adjusted Vegetation Index (TSAVI) was successful at mapping gullies at the continuous gully level. Mapping of gullies using classification algorithms highlighted the spectral complexity of gullies and the challenges faced when trying to identify them from the surrounding areas. The Support Vector Machine (SVM) classification algorithm produced the highest accuracy for mapping gullies in all the tested scales and was the recommended approach to gully mapping using remote sensing
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.
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 it