{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T21:39:58Z","timestamp":1777930798936,"version":"3.51.4"},"reference-count":92,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000883","name":"University of Bristol","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000883","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["EP\/Y030796\/1"],"award-info":[{"award-number":["EP\/Y030796\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Ecological Informatics"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.ecoinf.2026.103741","type":"journal-article","created":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:16:36Z","timestamp":1774714596000},"page":"103741","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Forest-Chat: Adapting vision-language agents for interactive forest change analysis"],"prefix":"10.1016","volume":"95","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-4224","authenticated-orcid":false,"given":"James","family":"Brock","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5100-3584","authenticated-orcid":false,"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Nantheera","family":"Anantrasirichai","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.ecoinf.2026.103741_b1","unstructured":"Banerjee, S., Lavie, A., 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. pp. 65\u201372."},{"issue":"9","key":"10.1016\/j.ecoinf.2026.103741_b2","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.3390\/rs16091477","article-title":"Rs-llava: A large vision-language model for joint captioning and question answering in remote sensing imagery","volume":"16","author":"Bazi","year":"2024","journal-title":"Remote. Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b3","series-title":"InternLM2 technical report","author":"Cai","year":"2024"},{"issue":"5","key":"10.1016\/j.ecoinf.2026.103741_b4","doi-asserted-by":"crossref","first-page":"863","DOI":"10.3390\/f14050863","article-title":"Tree recognition and crown width extraction based on novel faster-RCNN in a dense loblolly pine environment","volume":"14","author":"Cai","year":"2023","journal-title":"Forests"},{"key":"10.1016\/j.ecoinf.2026.103741_b5","series-title":"The Europa Directory of International Organizations 2021","first-page":"297","article-title":"Food and agriculture organization of the United Nations\u2014FAO","author":"Canton","year":"2021"},{"key":"10.1016\/j.ecoinf.2026.103741_b6","doi-asserted-by":"crossref","first-page":"6047","DOI":"10.1109\/TIP.2023.3328224","article-title":"Changes to captions: An attentive network for remote sensing change captioning","volume":"32","author":"Chang","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.ecoinf.2026.103741_b7","first-page":"74325","article-title":"Agentboard: An analytical evaluation board of multi-turn llm agents","volume":"37","author":"Chang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b8","first-page":"2039","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","volume":"33","author":"Chen","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b9","series-title":"A change detection reality check","author":"Corley","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b10","series-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103741_b11","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1038\/s41597-024-03384-z","article-title":"A labelled dataset to classify direct deforestation drivers from Earth observation imagery in Cameroon","volume":"11","author":"Debus","year":"2024","journal-title":"Sci. Data"},{"key":"10.1016\/j.ecoinf.2026.103741_b12","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.ecoinf.2026.103741_b13","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Changechat: An interactive model for remote sensing change analysis via multimodal instruction tuning","author":"Deng","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103741_b14","doi-asserted-by":"crossref","first-page":"1729","DOI":"10.5194\/isprs-archives-XLVIII-1-W2-2023-1729-2023","article-title":"Tree-gpt: modular large language model expert system for forest remote sensing image understanding and interactive analysis","volume":"48","author":"Du","year":"2023","journal-title":"Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci."},{"key":"10.1016\/j.ecoinf.2026.103741_b15","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"15046","article-title":"VE-KD: Vocabulary-expansion knowledge-distillation for training smaller domain-specific language models","author":"Gao","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b16","article-title":"Combining SAM with limited data for change detection in remote sensing","author":"Gao","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b17","doi-asserted-by":"crossref","first-page":"5539","DOI":"10.52202\/075280-0242","article-title":"Openagi: When llm meets domain experts","volume":"36","author":"Ge","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b18","series-title":"Global forest watch","author":"Global Forest Watch","year":"2014"},{"key":"10.1016\/j.ecoinf.2026.103741_b19","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.rse.2017.06.031","article-title":"Google earth engine: Planetary-scale geospatial analysis for everyone","volume":"202","author":"Gorelick","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"10.1016\/j.ecoinf.2026.103741_b20","first-page":"93","article-title":"Evaluation of the Nvidia grace superchip in the HPE\/Cray XD isambard 3 supercomputer","volume":"2025","author":"Green","year":"2025","journal-title":"CUG 2025"},{"key":"10.1016\/j.ecoinf.2026.103741_b21","series-title":"IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium","first-page":"11474","article-title":"Remote sensing chatgpt: Solving remote sensing tasks with chatgpt and visual models","author":"Guo","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b22","doi-asserted-by":"crossref","unstructured":"Guo, Z., Wang, T.J., Laaksonen, J., 2022. CLIP4IDC: CLIP for image difference captioning. In: Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). pp. 33\u201342.","DOI":"10.18653\/v1\/2022.aacl-short.5"},{"issue":"3","key":"10.1016\/j.ecoinf.2026.103741_b23","doi-asserted-by":"crossref","first-page":"036502","DOI":"10.1117\/1.JRS.17.036502","article-title":"Multimodal SuperCon: classifier for drivers of deforestation in Indonesia","volume":"17","author":"Hartanti","year":"2023","journal-title":"J. Appl. Remote. Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b24","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"9","key":"10.1016\/j.ecoinf.2026.103741_b25","doi-asserted-by":"crossref","first-page":"160","DOI":"10.3390\/technologies12090160","article-title":"Change detection for forest ecosystems using remote sensing images with siamese attention U-net","volume":"12","author":"Hewarathna","year":"2024","journal-title":"Technologies"},{"key":"10.1016\/j.ecoinf.2026.103741_b26","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.isprsjprs.2025.03.028","article-title":"Rsgpt: A remote sensing vision language model and benchmark","volume":"224","author":"Hu","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b27","series-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b28","doi-asserted-by":"crossref","unstructured":"Ibrahim, A.I., Auwal, A.M., Abba, J.H., 2025. Comparative Evaluation of GPT-4o, Gemini, Llama, and Grok On Remote Sensing Imagery.","DOI":"10.36948\/ijfmr.2025.v07i06.65292"},{"key":"10.1016\/j.ecoinf.2026.103741_b29","unstructured":"Irvin, J.A., Liu, E.R., Chen, J.C., Dormoy, I., Kim, J., Khanna, S., Zheng, Z., Ermon, S., 2025. TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data. In: The Thirteenth International Conference on Learning Representations. URL: https:\/\/openreview.net\/forum?id=pZz0nOroGv."},{"key":"10.1016\/j.ecoinf.2026.103741_b30","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1109\/JSTARS.2020.3034186","article-title":"Deep learning for regular change detection in Ukrainian forest ecosystem with sentinel-2","volume":"14","author":"Isaienkov","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b31","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y., Cipolla, R., 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7482\u20137491.","DOI":"10.1109\/CVPR.2018.00781"},{"key":"10.1016\/j.ecoinf.2026.103741_b32","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al., 2023. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.ecoinf.2026.103741_b33","doi-asserted-by":"crossref","unstructured":"Kuckreja, K., Danish, M.S., Naseer, M., Das, A., Khan, S., Khan, F.S., 2024. Geochat: Grounded large vision-language model for remote sensing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 27831\u201327840.","DOI":"10.1109\/CVPR52733.2024.02629"},{"issue":"8","key":"10.1016\/j.ecoinf.2026.103741_b34","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.3390\/f14081576","article-title":"Detection of pine wilt disease using time series UAV imagery and deep learning semantic segmentation","volume":"14","author":"Lee","year":"2023","journal-title":"Forests"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103741_b35","doi-asserted-by":"crossref","first-page":"166","DOI":"10.3390\/rs18010166","article-title":"Describing land cover changes via multi-temporal remote sensing image captioning using LLM, ViT, and LoRA","volume":"18","author":"Le\u00f3n","year":"2026","journal-title":"Remote. Sens."},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103741_b36","article-title":"A review of remote sensing image segmentation by deep learning methods","volume":"17","author":"Li","year":"2024","journal-title":"Int. J. Digit. Earth"},{"key":"10.1016\/j.ecoinf.2026.103741_b37","article-title":"Cd4c: Change detection for remote sensing image change captioning","author":"Li","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"issue":"2","key":"10.1016\/j.ecoinf.2026.103741_b38","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MGRS.2024.3383473","article-title":"Vision-language models in remote sensing: Current progress and future trends","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Geosci. Remote. Sens. Mag."},{"issue":"3","key":"10.1016\/j.ecoinf.2026.103741_b39","first-page":"362","article-title":"Prospects for AI applications in forest protection: Technologies, challenges, and future developments","volume":"4","author":"Li","year":"2024","journal-title":"Adv. Resour. Res."},{"key":"10.1016\/j.ecoinf.2026.103741_b40","series-title":"UniRS: Unifying multi-temporal remote sensing tasks through vision language models","author":"Li","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b41","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.ecoinf.2026.103741_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2024.102507","article-title":"A model for forest type identification and forest regeneration monitoring based on deep learning and hyperspectral imagery","volume":"80","author":"Lin","year":"2024","journal-title":"Ecol. Inform."},{"key":"10.1016\/j.ecoinf.2026.103741_b43","series-title":"2022 IEEE International Conference on Big Data","first-page":"4528","article-title":"AI applications in forest monitoring need remote sensing benchmark datasets","author":"Lines","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103741_b44","article-title":"Change-agent: Towards interactive comprehensive remote sensing change interpretation and analysis","author":"Liu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b45","series-title":"Auto-lambda: Disentangling dynamic task relationships","author":"Liu","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103741_b46","series-title":"Rsunivlm: A unified vision language model for remote sensing via granularity-oriented mixture of experts","author":"Liu","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b47","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume":"34","author":"Liu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b48","article-title":"Remote sensing spatiotemporal vision\u2013language models: A comprehensive survey","author":"Liu","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Mag."},{"key":"10.1016\/j.ecoinf.2026.103741_b49","first-page":"1","article-title":"Remote sensing image change captioning with dual-branch transformers: A new method and a large scale dataset","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b50","series-title":"JL1-CD: A new benchmark for remote sensing change detection and a robust multi-teacher knowledge distillation framework","author":"Liu","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103741_b51","article-title":"Vision foundation models in remote sensing: A survey","author":"Lu","year":"2025","journal-title":"IEEE Geosci. Remote. Sens. Mag."},{"key":"10.1016\/j.ecoinf.2026.103741_b52","first-page":"1","article-title":"GlobalGeoTree: A multi-granular vision-language dataset for global tree species classification","volume":"2025","author":"Mu","year":"2025","journal-title":"Earth Syst. Sci. Data Discuss."},{"key":"10.1016\/j.ecoinf.2026.103741_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2024.114109","article-title":"Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning","volume":"305","author":"Nguyen","year":"2024","journal-title":"Remote Sens. Environ."},{"key":"10.1016\/j.ecoinf.2026.103741_b54","series-title":"GPT-4v(ision) system card","author":"openai","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103741_b55","doi-asserted-by":"crossref","DOI":"10.1017\/eds.2024.53","article-title":"OpenForest: a data catalog for machine learning in forest monitoring","volume":"4","author":"Ouaknine","year":"2025","journal-title":"Environ. Data Sci."},{"key":"10.1016\/j.ecoinf.2026.103741_b56","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J., 2002. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.ecoinf.2026.103741_b57","article-title":"Deep learning change detection techniques for optical remote sensing imagery: Status, perspectives and challenges","volume":"136","author":"Peng","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.ecoinf.2026.103741_b58","doi-asserted-by":"crossref","DOI":"10.26599\/TST.2025.9010111","article-title":"A fine-grained vision-language pretraining model with progressive freezing and feedback-controlled cropping","author":"Qin","year":"2025","journal-title":"Tsinghua Sci. Technol."},{"key":"10.1016\/j.ecoinf.2026.103741_b59","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.ecoinf.2026.103741_b60","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P., 2020. Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10428\u201310436.","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"10.1016\/j.ecoinf.2026.103741_b61","series-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b62","first-page":"68539","article-title":"Toolformer: Language models can teach themselves to use tools","volume":"36","author":"Schick","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b63","series-title":"Thinkgeo: Evaluating tool-augmented agents for remote sensing tasks","author":"Shabbir","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103741_b64","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3485740","article-title":"A multi-task network and two large scale datasets for change detection and captioning in remote sensing images","author":"Shi","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b65","doi-asserted-by":"crossref","unstructured":"Soni, S., Dudhane, A., Debary, H., Fiaz, M., Munir, M.A., Danish, M.S., Fraccaro, P., Watson, C.D., Klein, L.J., Khan, F.S., et al., 2025. Earthdial: Turning multi-sensory earth observations to interactive dialogues. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 14303\u201314313.","DOI":"10.1109\/CVPR52734.2025.01334"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103741_b66","doi-asserted-by":"crossref","first-page":"162","DOI":"10.3390\/rs17010162","article-title":"Advancements in vision\u2013language models for remote sensing: Datasets, capabilities, and enhancement techniques","volume":"17","author":"Tao","year":"2025","journal-title":"Remote. Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b67","unstructured":"Taylor, R., Dudley, N., Stolton, S., Shapiro, A., 2015. Deforestation fronts: 11 places where most forest loss is projected between 2010 and 2030. In: Proceedings of the XIV World Forestry Congress. Durban, South Africa, pp. 7\u201311."},{"key":"10.1016\/j.ecoinf.2026.103741_b68","series-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103741_b69","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b70","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D., 2015. Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4566\u20134575.","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103741_b71","first-page":"1","article-title":"A multi-scale remote sensing semantic segmentation model with boundary enhancement based on UNetFormer","volume":"15","author":"Wang","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.ecoinf.2026.103741_b72","series-title":"Changeminds: Multi-task framework for detecting and describing changes in remote sensing","author":"Wang","year":"2024"},{"issue":"12","key":"10.1016\/j.ecoinf.2026.103741_b73","doi-asserted-by":"crossref","first-page":"2224","DOI":"10.3390\/rs16122224","article-title":"Potential of earth observation to assess the impact of climate change and extreme weather events in temperate forests\u2014A review","volume":"16","author":"Wegler","year":"2024","journal-title":"Remote. Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b74","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"10883","article-title":"Flowbench: Revisiting and benchmarking workflow-guided planning for llm-based agents","author":"Xiao","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b75","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b76","series-title":"RS-agent: Automating remote sensing tasks through intelligent agent","author":"Xu","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103741_b77","doi-asserted-by":"crossref","unstructured":"Yang, M., Chen, L., Zhou, J., 2025. Change-UP: Advancing Visualization and Inference Capability for Multi-level Remote Sensing Change Interpretation. In: Proceedings of the 33rd ACM International Conference on Multimedia. pp. 15\u201324.","DOI":"10.1145\/3746027.3754706"},{"key":"10.1016\/j.ecoinf.2026.103741_b78","article-title":"Enhancing perception of key changes in remote sensing image change captioning","author":"Yang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.ecoinf.2026.103741_b79","doi-asserted-by":"crossref","first-page":"17052","DOI":"10.1109\/JSTARS.2024.3415729","article-title":"Modality fusion vision transformer for hyperspectral and LiDAR data collaborative classification","volume":"17","author":"Yang","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b80","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., Cao, Y., 2023. React: Synergizing reasoning and acting in language models. In: The Eleventh International Conference on Learning Representations. Publisher Copyright: \u00a9 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.; 11th International Conference on Learning Representations, ICLR 2023 ; Conference date: 01-05-2023 Through 05-05-2023."},{"key":"10.1016\/j.ecoinf.2026.103741_b81","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b82","first-page":"55734","article-title":"Large language model as attributed training data generator: A tale of diversity and bias","volume":"36","author":"Yu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b83","article-title":"Status, advancements and prospects of deep learning methods applied in forest studies","volume":"131","author":"Yun","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.ecoinf.2026.103741_b84","first-page":"1","article-title":"EarthGPT: A universal multimodal large language model for multisensor image comprehension in remote sensing domain","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b85","first-page":"1","article-title":"Bifa: Remote sensing image change detection with bitemporal feature alignment","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.ecoinf.2026.103741_b86","series-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2019"},{"key":"10.1016\/j.ecoinf.2026.103741_b87","series-title":"GeoRSMLLM: A multimodal large language model for vision-language tasks in geoscience and remote sensing","author":"Zhang","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103741_b88","doi-asserted-by":"crossref","unstructured":"Zhang, C., Wang, S., 2024. Good at captioning bad at counting: Benchmarking gpt-4v on earth observation data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7839\u20137849.","DOI":"10.1109\/CVPRW63382.2024.00780"},{"key":"10.1016\/j.ecoinf.2026.103741_b89","first-page":"81204","article-title":"Segment any change","volume":"37","author":"Zheng","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ecoinf.2026.103741_b90","doi-asserted-by":"crossref","unstructured":"Zhu, D., Huang, X., Huang, H., Zhou, H., Shao, Z., 2025. Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 24011\u201324022.","DOI":"10.1109\/CVPR52734.2025.02236"},{"key":"10.1016\/j.ecoinf.2026.103741_b91","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3497338","article-title":"Semantic-cc: Boosting remote sensing image change captioning via foundational knowledge and semantic guidance","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"10.1016\/j.ecoinf.2026.103741_b92","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s13735-025-00375-7","article-title":"Remote sensing image change captioning: A comprehensive review: S. Zou et al","volume":"14","author":"Zou","year":"2025","journal-title":"Int. J. Multimed. Inf. Retr."}],"container-title":["Ecological Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574954126001470?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574954126001470?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T00:24:20Z","timestamp":1777681460000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1574954126001470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":92,"alternative-id":["S1574954126001470"],"URL":"https:\/\/doi.org\/10.1016\/j.ecoinf.2026.103741","relation":{},"ISSN":["1574-9541"],"issn-type":[{"value":"1574-9541","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Forest-Chat: Adapting vision-language agents for interactive forest change analysis","name":"articletitle","label":"Article Title"},{"value":"Ecological Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ecoinf.2026.103741","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103741"}}