Skip to content
Back to search

remote-sensing-research-radar

Remote Sensing Research Radar is a Codex skill designed for tracking research frontiers in geospatial AI, optical remote sensing, remote sensing big data, and transferable computer vision methods. It helps researchers regularly discover, filter, rank, and summarize recent papers, open-source projects, datasets,

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/limi124--remote-sensing-research-radar/badge.svg)](/listings/limi124--remote-sensing-research-radar)

HTML

<a href="/listings/limi124--remote-sensing-research-radar"><img src="/api/listings/limi124--remote-sensing-research-radar/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install the skill from this repository:

python C:\Users\shuo\.codex\skills\.system\skill-installer\scripts\install-skill-from-github.py --repo limi124/remote-sensing-research-radar --path skills/remote-sensing-research-radar

Restart Codex after installation so the skill can be discovered.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 168 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Remote Sensing Research Radar
  2. [![Codex Skill](https://img.shields.io/badge/Codex-Skill-111827)](#)
  3. [![Research Radar](https://img.shields.io/badge/Research-Frontier%20Radar-2563eb)](#)
  4. [![Remote Sensing](https://img.shields.io/badge/Domain-Remote%20Sensing-059669)](#)
  5. [![No SAR by Default](https://img.shields.io/badge/SAR-Excluded%20by%20Default-b91c1c)](#)
  6. **Language:** English | [中文](README.zh-CN.md)
  7. A Codex skill for tracking research frontiers in **geospatial AI**, **remote sensing big data**, and **transferable computer vision methods**.
  8. This project helps researchers continuously monitor new papers, open-source projects, datasets, benchmarks, and research trends. It focuses on optical remote sensing and geospatial AI, while also scanning computer vision methods that can be transferred into remote sensing research.
  9. > SAR, PolSAR, InSAR, radar-only, microwave-only, and SAR-optical fusion work are excluded by default unless explicitly requested.
  10. ## Why This Skill
  11. Remote sensing research moves quickly across multiple communities: geoscience, computer vision, machine learning, GIScience, and Earth observation. Important ideas often appear first in general CV or ML papers before being adapted to satellite and aerial imagery.
  12. This skill is designed to bridge that gap:
  13. | Need | What the skill does |
  14. | --- | --- |
  15. | Track new papers | Searches recent arXiv, Papers with Code, GitHub, Hugging Face, conference pages, and benchmark pages |
  16. | Find useful CV methods | Screens computer vision papers for remote sensing transfer potential |
  17. | Avoid noisy directions | Filters out SAR-focused work by default |
  18. | Build a reading queue | Ranks papers and projects by novelty, evidence, reproducibility, and fit |
  19. | Generate research ideas | Converts frontier trends into publishable research directions |
  20. | Prepare related work | Produces comparison tables and structured literature summaries |
  21. ## Core Capabilities
  22. - Daily or weekly research radar reports
  23. - Paper and GitHub project screening
  24. - Remote sensing frontier tracking
  25. - Computer-vision-to-remote-sensing transfer analysis
  26. - Related work table generation
  27. - Deep paper reading notes
  28. - Reproducibility planning
  29. - Publishable idea generation
  30. ## Research Scope
  31. ### Remote Sensing and Geospatial AI
  32. | Area | Example Topics |
  33. | --- | --- |
  34. | Earth observation foundation models | MAE, JEPA, contrastive learning, masked modeling, geolocation/time embeddings |
  35. | Optical and multispectral imagery | Sentinel-2, Landsat, aerial RGB, UAV imagery, VHR scene understanding |
  36. | Hyperspectral learning | Spectral-spatial modeling, band selection, domain generalization |
  37. | Multi-temporal modeling | Crop monitoring, land-cover dynamics, urban expansion, ecological time series |
  38. | Change detection | Optical building, land-cover, urban, and ecological change detection |
  39. | Remote sensing VLMs | Captioning, VQA, grounding, open-vocabulary segmentation |
  40. | Cross-domain generalization | Domain adaptation, OOD detection, few-shot learning, spatial bias |
  41. | GIS and raster-vector fusion | Road networks, parcels, POIs, building footprints, topology-aware learning |
  42. | Efficient inference | Tiling, streaming, compression, active learning, uncertainty-aware mapping |
  43. ### Transferable Computer Vision
  44. | CV Direction | Remote Sensing Transfer Path |
  45. | --- | --- |
  46. | Foundation models | Adapt pretrained visual representations to multispectral, high-resolution, or multi-temporal imagery |
  47. | Open-vocabulary segmentation | Map flexible land-cover classes and local taxonomy labels |
  48. | Vision-language models | Support remote sensing VQA, captioning, grounding, and retrieval |
  49. | Video and temporal models | Transfer long-range temporal reasoning to satellite image time series |
  50. | Domain adaptation | Improve cross-city, cross-country, cross-season, and cross-sensor robustness |
  51. | Weak/semi-supervised learning | Reduce annotation cost for large-scale mapping |
  52. | Efficient inference | Handle large remote sensing images with tiled or compressed inference |
  53. ## Scoring Rubric
  54. Candidate papers and projects are ranked by:
  55. | Criterion | Meaning |
  56. | --- | --- |
  57. | Novelty | New problem, method, benchmark, or strong reframing |
  58. | Technical depth | Clear algorithmic or modeling contribution |
  59. | Evidence | Strong experiments, ablations, datasets, and metrics |
  60. | Reproducibility | Code, data, weights, and clean instructions |
  61. | Trend signal | Active authors, labs, stars, benchmarks, or conference attention |
  62. | Transferability | Clear path from CV or ML to remote sensing constraints |
  63. | User fit | Matches non-SAR geospatial remote sensing research goals |
  64. ## Installation
  65. Install the skill from this repository:
  66. ```powershell
  67. python C:\Users\shuo\.codex\skills\.system\skill-installer\scripts\install-skill-from-github.py --repo limi124/remote-sensing-research-radar --path skills/remote-sensing-research-radar
  68. ```
  69. Restart Codex after installation so the skill can be discovered.
  70. ## Recommended Repository Structure
  71. ```text
  72. remote-sensing-research-radar/
  73. ├─ README.md
  74. ├─ README.zh-CN.md
  75. └─ skills/
  76. └─ remote-sensing-research-radar/
  77. ├─ SKILL.md
  78. ├─ agents/
  79. │ └─ openai.yaml
  80. └─ references/
  81. └─ frontier-radar.md
  82. ```
  83. ## Example Prompts
  84. ```text
  85. Use remote-sensing-research-radar to find recent remote sensing foundation model papers and open-source projects from the past month. Exclude SAR.
  86. ```
  87. ```text
  88. Build a weekly geospatial AI research radar. Focus on optical remote sensing, multi-temporal modeling, and transferable computer vision methods.
  89. ```
  90. ```text
  91. Find computer vision papers on open-vocabulary segmentation, VLMs, and domain adaptation that could inspire remote sensing research.
  92. ```
  93. ```text
  94. Based on recent remote sensing and CV frontiers, propose five publishable research ideas for a high-impact paper.
  95. ```
  96. ## Typical Output
  97. ```text
  98. Weekly takeaways
  99. - Trend 1
  100. - Trend 2
  101. - Trend 3
  102. Ranked candidates
  103. | Rank | Title | Source/Date | Task | Data/Modality | Contribution | Code/Data | Score | Why it matters |
  104. Top 3 deep dives
  105. 1. Title
  106. - Core problem:
  107. - Method:
  108. - Evidence:
  109. - Limitations:
  110. - Extension:
  111. CV-to-RS transfer notes
  112. - Paper/project:
  113. - Transferable component:
  114. - Required adaptation:
  115. - Candidate RS datasets:
  116. - First experiment:
  117. - Risk:
  118. Publishable research ideas
  119. 1. Idea name
  120. - Problem:
  121. - Hypothesis:
  122. - Method:
  123. - Datasets/Metrics:
  124. - Baselines:
  125. - First experiment:
  126. ```
  127. ## Notes
  128. - Fresh research reports should use web search because arXiv, GitHub, Papers with Code, and conference pages change frequently.
  129. - English paper titles and technical terms should be preserved even in Chinese reports.
  130. - SAR-related work is excluded by default to keep the radar aligned with optical remote sensing and geospatial AI research.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.