Remote Sensing-based Socioeconomic Analysis using Task-driven Transfer Learning and Regression
Bibliographic record
Abstract
The economic status of each country varies; some countries are well developed while some are underdeveloped. A lower economic status in any place in the world can lead to hunger, malnutrition, and low life expectancy, especially for children and the older generation. For instance, in Africa, most people live below the international poverty line of 1.25 US dollars per day, according to the World Bank Group. One way of solving this problem is through collecting data and building intelligent models to automatically detect the low economic regions so the organizations, like The United Nations Development Program (UNDP), can allocate vital support systems to save the people there from the severity and help them lead a better life. Unfortunately, obtaining such data through manual surveys takes too long and requires a lot of resources. Thus, this work aims to provide an efficient solution to this problem. It analyzes the socioeconomic status of the underdeveloped regions, primarily a few selected African countries, by using remote sensing (RS), multimodal data exploitation, machine learning, transfer learning, and computer vision technologies. The proposed framework can make accurate prediction on a particular geographic region's standard of living (wealth index) based on the distribution of nightlight intensity that is observed via satellite remote sensing. Exhaustive experiments are carried out using data from the National Oceanic And Atmospheric Administration (NOAA), Demographic and Health Survey (DHS), and Google Static Maps. The experimental results verify that the proposed framework can be used as an effective alternative to the conventional approaches for socioeconomic analysis.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".