Towards Unified Vision Language Models for Forest Ecological Analysis in Earth Observation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Xizhe, Zhu, Xiao Xiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917096503377920
author Xue, Xizhe
Zhu, Xiao Xiang
author_facet Xue, Xizhe
Zhu, Xiao Xiang
contents Recent progress in vision language models (VLMs) has enabled remarkable perception and reasoning capabilities, yet their potential for scientific regression in Earth Observation (EO) remains largely unexplored. Existing EO datasets mainly emphasize semantic understanding tasks such as captioning or classification, lacking benchmarks that align multimodal perception with measurable biophysical variables. To fill this gap, we present REO-Instruct, the first unified benchmark designed for both descriptive and regression tasks in EO. REO-Instruct establishes a cognitively interpretable logic chain in forest ecological scenario (human activity,land-cover classification, ecological patch counting, above-ground biomass (AGB) regression), bridging qualitative understanding and quantitative prediction. The dataset integrates co-registered Sentinel-2 and ALOS-2 imagery with structured textual annotations generated and validated through a hybrid human AI pipeline. Comprehensive evaluation protocols and baseline results across generic VLMs reveal that current models struggle with numeric reasoning, highlighting an essential challenge for scientific VLMs. REO-Instruct offers a standardized foundation for developing and assessing next-generation geospatial models capable of both description and scientific inference. The project page are publicly available at \href{https://github.com/zhu-xlab/REO-Instruct}{REO-Instruct}.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16853
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Unified Vision Language Models for Forest Ecological Analysis in Earth Observation
Xue, Xizhe
Zhu, Xiao Xiang
Computer Vision and Pattern Recognition
Recent progress in vision language models (VLMs) has enabled remarkable perception and reasoning capabilities, yet their potential for scientific regression in Earth Observation (EO) remains largely unexplored. Existing EO datasets mainly emphasize semantic understanding tasks such as captioning or classification, lacking benchmarks that align multimodal perception with measurable biophysical variables. To fill this gap, we present REO-Instruct, the first unified benchmark designed for both descriptive and regression tasks in EO. REO-Instruct establishes a cognitively interpretable logic chain in forest ecological scenario (human activity,land-cover classification, ecological patch counting, above-ground biomass (AGB) regression), bridging qualitative understanding and quantitative prediction. The dataset integrates co-registered Sentinel-2 and ALOS-2 imagery with structured textual annotations generated and validated through a hybrid human AI pipeline. Comprehensive evaluation protocols and baseline results across generic VLMs reveal that current models struggle with numeric reasoning, highlighting an essential challenge for scientific VLMs. REO-Instruct offers a standardized foundation for developing and assessing next-generation geospatial models capable of both description and scientific inference. The project page are publicly available at \href{https://github.com/zhu-xlab/REO-Instruct}{REO-Instruct}.
title Towards Unified Vision Language Models for Forest Ecological Analysis in Earth Observation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.16853