Parameter-Efficient Multilingual Vision–Language Adaptation for Spatio-Temporal Climate-Risk Interpretation from Satellite Imagery
Remote Sensing · 17.11.2026 · 18 (22) · 3945
DOI: 10.3390/rs18223945 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 17.11.2026. Verfasst von Parita Shah und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Climate-risk monitoring requires models that connect satellite observations with natural-language questions while supporting users working in different languages. We present ClimateRS-VL, a parameter-efficient adaptation of Qwen2.5-VL-3B-Instruct for English, Gujarati, and Hindi climate-risk interpretation. The benchmark combines 7182 regional optical–mask pairs from six districts of Gujarat, 1026 nominal regional temporal pairs, 740 reservoir-year metadata records, 409 reservoir-year image samples, and 178,503 programmatically generated multilingual references. A prompt audit confirms that explicit answer-bearing numerical and categorical variables were absent from all 126,810 training, 25,854 validation, and 25,839 test prompts. On the full 25,839-response test evaluation, English, Gujarati, and Hindi VQA obtain BLEU scores of 83.9230, 80.9125, and 83.2524, with BERTScore-F1 values of 0.9891, 0.9961, and 0.9953. A same-backbone study on a common 3000-response subset yields an average VQA BLEU of 0.5625 for zero-shot Qwen2.5-VL, 1.1138 with contextual prompting but no adaptation, and 85.5191 with contextual prompting and LoRA. Question-aligned cross-lingual consistency is 0.9673, although this metric measures agreement rather than correctness. Class-balanced analysis further shows that raw accuracies above 0.98 on four regional risk questions arise from severe low-risk class prevalence: the model predicts the low-risk class for every sample, yielding a balanced accuracy of 0.5000. The protocol is a temporal holdout over recurring monitoring locations rather than an evaluation of unseen-location generalization. The results support parameter-efficient multilingual adaptation for structured in-domain generation while identifying limitations in numerical visual reasoning, minority-risk discrimination, reference diversity, and spatial generalization.
Zitieren
APA
Shah, P., Satapathy, S., Bhoi, A. K., Barsocchi, P., & Vyas, R. (2026). Parameter-Efficient Multilingual Vision–Language Adaptation for Spatio-Temporal Climate-Risk Interpretation from Satellite Imagery. Remote Sensing, 18(22), 3945. https://doi.org/10.3390/rs18223945
Vancouver
Shah P, Satapathy S, Bhoi AK, Barsocchi P, Vyas R. Parameter-Efficient Multilingual Vision–Language Adaptation for Spatio-Temporal Climate-Risk Interpretation from Satellite Imagery. Remote Sensing. 2026;18(22):3945. doi:10.3390/rs18223945
BibTeX
@article{Shah2026,
author = {Shah, Parita and Satapathy, Santosh and Bhoi, Akash Kumar and Barsocchi, Paolo and Vyas, Ritesh},
title = {Parameter-Efficient Multilingual Vision–Language Adaptation for Spatio-Temporal Climate-Risk Interpretation from Satellite Imagery},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {22},
pages = {3945},
doi = {10.3390/rs18223945}
}
EUVIMED