ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913039541862400 |
|---|---|
| author | Elgendy, Hosam Sharshar, Ahmed Aboeitta, Ahmed Guizani, Mohsen |
| author_facet | Elgendy, Hosam Sharshar, Ahmed Aboeitta, Ahmed Guizani, Mohsen |
| contents | Understanding environmental changes from remote sensing imagery is vital for climate resilience, urban planning, and ecosystem monitoring. Yet, current vision language models (VLMs) overlook causal signals from environmental sensors, rely on single-source captions prone to stylistic bias, and lack interactive scenario-based reasoning. We present ChatENV, the first interactive VLM that jointly reasons over satellite image pairs and real-world sensor data. Our framework: (i) creates a 177k-image dataset forming 152k temporal pairs across 62 land-use classes in 197 countries with rich sensor metadata (e.g., temperature, PM10, CO); (ii) annotates data using GPT4o and Gemini 2.0 for stylistic and semantic diversity; and (iii) fine-tunes Qwen-2.5-VL using efficient Low-Rank Adaptation (LoRA) adapters for chat purposes. ChatENV achieves strong performance in temporal and "what-if" reasoning (e.g., BERTF1 0.902) and rivals or outperforms state-of-the-art temporal models, while supporting interactive scenario-based analysis. This positions ChatENV as a powerful tool for grounded, sensor-aware environmental monitoring. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10635 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation Elgendy, Hosam Sharshar, Ahmed Aboeitta, Ahmed Guizani, Mohsen Computer Vision and Pattern Recognition Understanding environmental changes from remote sensing imagery is vital for climate resilience, urban planning, and ecosystem monitoring. Yet, current vision language models (VLMs) overlook causal signals from environmental sensors, rely on single-source captions prone to stylistic bias, and lack interactive scenario-based reasoning. We present ChatENV, the first interactive VLM that jointly reasons over satellite image pairs and real-world sensor data. Our framework: (i) creates a 177k-image dataset forming 152k temporal pairs across 62 land-use classes in 197 countries with rich sensor metadata (e.g., temperature, PM10, CO); (ii) annotates data using GPT4o and Gemini 2.0 for stylistic and semantic diversity; and (iii) fine-tunes Qwen-2.5-VL using efficient Low-Rank Adaptation (LoRA) adapters for chat purposes. ChatENV achieves strong performance in temporal and "what-if" reasoning (e.g., BERTF1 0.902) and rivals or outperforms state-of-the-art temporal models, while supporting interactive scenario-based analysis. This positions ChatENV as a powerful tool for grounded, sensor-aware environmental monitoring. |
| title | ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.10635 |