# CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training

arXiv: https://arxiv.org/abs/2607.07292 · HTML: https://mlsanity.com/paper/2607.07292/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 69 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery](https://mlsanity.com/paper/2311.17179/) (2023)
- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning](https://mlsanity.com/paper/2402.01444/) (2024)
- [Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2403.19584/) (2024)
- [Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale](https://mlsanity.com/paper/1704.02965/) (2017)
- [UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction](https://mlsanity.com/paper/2403.16831/) (2024)
- [ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery](https://mlsanity.com/paper/2201.11192/) (2022)
- [FlexiReg: Flexible Urban Region Representation Learning](https://mlsanity.com/paper/2503.09128/) (2025)
- [AddressVLM: Cross-view Alignment Tuning for Image Address Localization using Large Vision-Language Models](https://mlsanity.com/paper/2508.10667/) (2025)
- [Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework](https://mlsanity.com/paper/2509.01910/) (2025)

## Abstract (arXiv)

Accurately estimating urban carbon emissions is critical for sustainable urban planning, yet many existing approaches remain difficult to apply consistently across cities due to data-source heterogeneity and the lack of fine-grained semantic-temporal context in remote sensing data. We propose CarbonCLIP, a task-oriented multimodal distillation framework that improves satellite-based carbon emission prediction by transferring contextual knowledge into a unified satellite representation through dual-branch contrastive learning. Unlike conventional methods that rely on static visual features, CarbonCLIP explicitly bridges the gap between top-down satellite views and ground-level human activities. Specifically, the spatial branch uses fine-grained textual descriptions automatically generated from street-view images by Large Multimodal Models (LMMs) to provide semantic priors reflecting building functions, infrastructure, and urban activities, while the temporal branch employs a month encoder to encode temporal priors associated with monthly emission variation. CarbonCLIP requires multimodal data only during the pretraining phase; during inference, it relies solely on satellite imagery, thereby supporting scalable deployment when ground-level data are unavailable at inference. Experiments on Beijing and Singapore demonstrate that CarbonCLIP outperforms baselines in both study cities. The results validate that our method effectively transfers multimodal knowledge into satellite representations, offering a robust solution for satellite-based urban carbon modeling.