基于形态指纹特征的耕地遥感监测轻量化大模型构建

doi:10.3864/j.issn.0578-1752.2026.01.006

中国农业科学 ›› 2026, Vol. 59 ›› Issue (1): 78-89.doi: 10.3864/j.issn.0578-1752.2026.01.006

• 耕作栽培·生理生化·农业信息技术 • 上一篇下一篇

基于形态指纹特征的耕地遥感监测轻量化大模型构建

唐华俊¹(), 吴文斌¹, 余强毅¹, 史云¹, 段玉林¹, 李文娟¹, 钱建平¹, 宋茜¹, 夏浪¹, 李会宾¹, 苏宝峰², 范蓓蕾³, 胡琼⁴, 叶剑秋⁵, 张帅⁶

¹ 中国农业科学院农业资源与农业区划研究所/北方干旱半干旱耕地高效利用全国重点实验室/农业农村部农业遥感重点实验室，北京 100081
² 西北农林科技大学机械与电子工程学院，陕西杨凌 712100
³ 中国农业科学院农业信息研究所，北京 100081
⁴ 华中师范大学城市与环境科学学院，武汉430070
⁵ 中国热带农业科学院科技信息研究所，海口 571101
⁶ 农业农村部农田建设管理司，北京 100125

收稿日期:2025-08-10 接受日期:2025-11-25 出版日期:2026-01-07 发布日期:2026-01-07
联系方式: 唐华俊，E-mail：tanghuajun@caas.cn
基金资助:
国家农业科技重大项目

Developing a Lightweight Multimodal Model for Cropland Remote Sensing Monitoring

TANG HuaJun¹(), WU WenBin¹, YU QiangYi¹, SHI Yun¹, DUAN YuLin¹, LI WenJuan¹, QIAN JianPing¹, SONG Qian¹, XIA Lang¹, LI HuiBin¹, SU BaoFeng², FAN BeiLei³, HU Qiong⁴, YE JianQiu⁵, ZHANG Shuai⁶

¹ Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences/State Key Laboratory of Efficient Utilization of Arid and Semi-Arid Arable Land/Key Laboratory of Agricultural Remote Sensing, Ministry of Agriculture and Rural Affairs, Beijing 100081
² College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, Shaanxi
³ Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081
⁴ College of Urban and Environmental Sciences, Central China Normal University, Wuhan 430070
⁵ Institute of Scientific and Technical Information Chinese Academy of Tropical Agricultural Sciences, Haikou 571101
⁶ Department of Farmland Construction Management, Ministry of Agriculture and Rural Affairs, Beijing 100125

Received:2025-08-10 Accepted:2025-11-25 Published:2026-01-07 Online:2026-01-07

摘要/Abstract

摘要：

耕地资源及其利用时空动态事关国家粮食安全、资源安全和生态安全。现阶段耕地遥感监测总体沿用了“数据—（模型）—信息”的科学研究范式，注重影像解译与信息提取过程的模型改进与精度提升，面临“信息海量、知识难求、服务受限”的困境，难以满足耕地保护利用实际需求，亟待提升科学研究成果对国家重大需求的支撑服务效能。人工智能（artificial intelligence，AI）技术加速推动数据主动检索与分析向智能化的知识服务与赋能转变，大型多模态模型在文本、图像、音频、视频等多模态数据处理中的突出优势，能够有效挖掘各类遥感监测信息和提供智能知识服务。本文在系统分析国内外最新研究进展、全面梳理耕地遥感监测应用需求的基础上，总结了通过耕地形态认知其结构与功能的核心特点，进而提出基于形态指纹特征的耕地遥感监测轻量化大模型构建思路。首先，针对不同主体分析需求，将耕地遥感监测应用场景归纳为4个方面，包括耕地数量和利用、高标准农田建设、耕地质量退化、耕地农情动态，明晰不同场景对监测信息和知识服务的差异化要求；其次，从人类认知的视角出发，解析耕地形态蕴含的“精细信息”和“宏观知识”特征，为耕地遥感监测大模型构建提供新的切入点；最后，结合多模态遥感数据与通用大语言模型，构建具备感知、推理、学习与执行能力的耕地遥感监测人工智能体（AI Agent），强化注意力机制，集中并抓住耕地形态重要特征，构建基于形态指纹特征的遥感监测轻量化大模型，实现“精细信息—宏观知识—智慧决策”融合，解决数据信息产品多但可用性知识服务不足的现实困境。

关键词: 人工智能, 耕地遥感监测, 应用场景, 形态特征, 注意力机制, 轻量化大模型

Abstract:

The spatio-temporal dynamics of cropland and their utilization are crucial to national food security, resource security and ecological security. Currently, the approach to cropland remote sensing monitoring generally follows the “data - (model) - information” paradigm. However, this paradigm has a significant “innovation-application” gap, with numerous information products but weak knowledge service capabilities, which fail to meet practical application needs of cropland protection and utilization. Artificial intelligence (AI) technology is accelerating the transformation from active data retrieval and analysis to intelligent knowledge services and empowerment. In the new era, the technical system for cropland remote sensing monitoring needs to be restructured. This paper thus proposed an innovative idea for constructing a lightweight multimodal model for cropland remote sensing monitoring. Firstly, it analyzed the demands of different subjects and categorized the application scenarios of cropland remote sensing monitoring into four aspects (cropland area and use, infrastructure, degradation, and crop growth), clarifying the specific requirements for monitoring information and knowledge services in different scenarios. Secondly, from the perspective of human cognition, it analyzed the “macro-level knowledge” and “fine-grained information” characteristics contained in the morphological features of cropland, providing a new entry point for the construction of a multimodal model for cropland remote sensing monitoring. Finally, it combines multi-modal remote sensing data with general large language models to construct an AI agent for cropland remote sensing monitoring, featuring capabilities in perception, reasoning, learning, and execution. It strengthens the attention mechanism to focus on and capture the important features of cropland morphology, and builds a lightweight multimodal model based on these features.

Key words: artificial intelligence, cropland remote sensing monitoring, application scenarios, morphological characteristics, attention mechanism, lightweight multimodal model

唐华俊, 吴文斌, 余强毅, 史云, 段玉林, 李文娟, 钱建平, 宋茜, 夏浪, 李会宾, 苏宝峰, 范蓓蕾, 胡琼, 叶剑秋, 张帅. 基于形态指纹特征的耕地遥感监测轻量化大模型构建[J]. 中国农业科学, 2026, 59(1): 78-89.

TANG HuaJun, WU WenBin, YU QiangYi, SHI Yun, DUAN YuLin, LI WenJuan, QIAN JianPing, SONG Qian, XIA Lang, LI HuiBin, SU BaoFeng, FAN BeiLei, HU Qiong, YE JianQiu, ZHANG Shuai. Developing a Lightweight Multimodal Model for Cropland Remote Sensing Monitoring[J]. Scientia Agricultura Sinica, 2026, 59(1): 78-89.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2026.01.006

https://www.chinaagrisci.com/CN/Y2026/V59/I1/78

图/表 4

图1

表1

耕地遥感监测的主要应用场景、对象主体及需求"

应用场景 Application scenario	主要用户 Main user	精细信息（研究） Information (Research)	宏观知识（应用） Knowledge (Application)
耕地数量和利用监测 Cropland area and use monitoring	政府 Governments	耕地及作物类型的空间分布图；耕地撂荒复种发生的地块；不同地类和作物类型之间的转移矩阵 Maps of cropland area, crop types, abandonment, intensification. Cropland use change transitional matrix	主要的种植作物类型、种植方式；撂荒与“非粮化”总体趋势与预警 Dominant cropland use types; early warning on cropland use change
高标准农田（农田基础设施）监测监管 Farmland infrastructure monitoring	政府、农民、新型经营主体 Governments, farmers, organizations	田块、道路、灌溉、林网等农田基础设施识别提取，农田形态参数估算 Identification of farmland infrastructure (including field plots, roads, irrigation systems, and shelterbelt), and estimation of morphological parameters	区域高标准农田建设实施情况、建设质量情况 The overall implementation and quality of well-facilitated farmland construction programs
耕地质量退化监测 Cropland degradation monitoring	政府、农民、新型经营主体 Governments, farmers, organizations	耕地土壤有机质、含盐量、pH等指标定量反演或预测 Quantitative inversion or prediction of soil properties including organic matter content, salinity, pH etc.	耕地土壤侵蚀、次生盐渍化、酸化等质量退化情况 The overall status of erosion, salinization, and acidification
耕地农情动态监测 Crop growth monitoring	政府、农民、新型经营主体 Governments, farmers, organizations	叶面积、光合有效辐射等作物生长关键参数定量反演 Quantitative inversion of key crop growth parameters including leaf area index and photosynthetically active radiation	作物长势动态状况、与往年同期的差异情况 Crop growth status compared to the normal situation

表1

图2

图3

参考文献 43

[1]	唐华俊, 吴文斌, 余强毅, 夏天, 杨鹏, 李正国. 农业土地系统研究及其关键科学问题. 中国农业科学, 2015, 48(5): 900-910. doi: 10.3864/j.issn.0578-1752.2015.05.08.
	TANG H J, WU W B, YU Q Y, XIA T, YANG P, LI Z G. Key research priorities for agricultural land system studies. Scientia Agricultura Sinica, 2015, 48(5): 900-910. doi: 10.3864/j.issn.0578-1752.2015.05. 08. (in Chinese)
[2]	陈仲新, 任建强, 唐华俊, 史云, 冷佩, 刘佳, 王利民, 吴文斌, 姚艳敏, 哈斯图亚. 农业遥感研究应用进展与展望. 遥感学报, 2016, 20(5): 748-767.
	CHEN Z X, REN J Q, TANG H J, SHI Y, LENG P, LIU J, WANG L M, WU W B, YAO Y M, HASTUYA. Progress and perspectives on agricultural remote sensing research and applications in China. National Remote Sensing Bulletin, 2016, 20(5): 748-767. (in Chinese) doi: 10.11834/jrs.20166214
[3]	余强毅, 吴文斌, 吴浩, 胡琼, 王心宇, 史舟, 陈颂超, 杜阳, 杨建宇, 高秉博, 赵圆圆, 何亚文, 史文娇, 张帅, 段玉林, 宋茜, 李会宾, 魏妍冰, 李卓, 胡蒙蒙, 李召良. 高标准农田遥感监测技术: 发展现状、差距分析和发展建议. 遥感学报, 2025, 29(5): 1053-1073.
	YU Q Y, WU W B, WU H, HU Q, WANG X Y, SHI Z, CHEN S C, DU Y, YANG J Y, GAO B B, ZHAO Y Y, HE Y W, SHI W J, ZHANG S, DUAN Y L, SONG Q, LI H B, WEI Y B, LI Z, HU M M, LI Z L. Development of a remote sensing-based system for monitoring well-facilitated farmland. National Remote Sensing Bulletin, 2025, 29(5): 1053-1073. (in Chinese) doi: 10.11834/jrs.20253469
[4]	眭海刚, 王建勋, 华丽, 段志强, 许贵林. 遥感耕地监测现状与方法综述. 广西科学, 2022, 29(1): 1-12.
	SUI H G, WANG J X, HUA L, DUAN Z Q, XU G L. Review on the status and methods of remote sensing farmland monitoring. Guangxi Sciences, 2022, 29(1): 1-12. (in Chinese)
[5]	燕琴, 顾海燕, 杨懿, 李海涛, 沈恒通, 刘世琦. 智能遥感大模型研究进展与发展方向. 测绘学报, 2024, 53(10): 1967-1980. doi: 10.11947/j.AGCS.2024.20240053.
	YAN Q, GU H Y, YANG Y, LI H T, SHEN H T, LIU S Q. Research progress and trend of intelligent remote sensing large model. Acta Geodaetica et Cartographica Sinica, 2024, 53(10): 1967-1980. (in Chinese) doi: 10.11947/j.AGCS.2024.20240053.
[6]	李德仁, 张良培, 夏桂松. 遥感大数据自动分析与数据挖掘. 测绘学报, 2014, 43(12): 1211-1216. doi: 10.13485/j.cnki.11-2089.2014.0187
	LI D R, ZHANG L P, XIA G S. Automatic analysis and mining of remote sensing big data. Acta Geodaetica et Cartographica Sinica, 2014, 43(12): 1211-1216. (in Chinese) doi: 10.13485/j.cnki.11-2089.2014.0187
[7]	董金玮, 吴文斌, 黄健熙, 尤南山, 何盈利, 闫慧敏. 农业土地利用遥感信息提取的研究进展与展望. 地球信息科学学报, 2020, 22(4): 772-783. doi: 10.12082/dqxxkx.2020.200192
	DONG J W, WU W B, HUANG J X, YOU N S, HE Y L, YAN H M. State of the art and perspective of agricultural land use remote sensing information extraction. Journal of Geo-Information Science, 2020, 22(4): 772-783. (in Chinese)
[8]	WEISS M, JACOB F, DUVEILLER G. Remote sensing for agricultural applications: A meta-review. Remote Sensing of Environment, 2020, 236: 111402. doi: 10.1016/j.rse.2019.111402
[9]	张素心, 申格, 余强毅, 吴文斌. 中国耕地种植制度遥感探测及其时空特征. 中国农业科学, 2024, 57(8): 1469-1489. doi: 10.3864/j.issn.0578-1752.2024.08.005.
	ZHANG S X, SHEN G, YU Q Y, WU W B. Remote sensing detection of cropping system and its spatial-temporal pattern in China. Scientia Agricultura Sinica, 2024, 57(8): 1469-1489. doi: 10.3864/j.issn.0578-1752.2024.08.005. (in Chinese)
[10]	LIU H, GONG P, WANG J, CLINTON N, BAI Y Q, LIANG S L. Annual dynamics of global land cover and its long-term changes from 1982 to 2015. Earth System Science Data, 2020, 12(2): 1217-1243. doi: 10.5194/essd-12-1217-2020
[11]	CHEN J, CHEN J, LIAO A P, CAO X, CHEN L J, CHEN X H, HE C Y, HAN G, PENG S, LU M, ZHANG W W, TONG X H, MILLS J. Global land cover mapping at 30m resolution: A POK-based operational approach. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 103: 7-27. doi: 10.1016/j.isprsjprs.2014.09.002
[12]	匡文慧, 张树文, 杜国明, 颜长珍, 吴世新, 李仁东, 陆灯盛, 潘涛, 宁静, 郭长庆, 董金玮, 包玉海, 迟文峰, 窦银银, 侯亚丽, 尹哲睿, 常丽萍, 杨久春, 谢家丽, 邱娟, 张汉松, 张宇博, 杨仕琪, 萨日盖, 刘纪远. 2015—2020年中国土地利用变化遥感制图及时空特征分析. 地理学报, 2022, 77(5): 1056-1071. doi: 10.11821/dlxb202205002
	KUANG W H, ZHANG S W, DU G M, YAN C Z, WU S X, LI R D, LU D S, PAN T, NING J, GUO C Q, DONG J W, BAO Y H, CHI W F, DOU Y Y, HOU Y L, YIN Z R, CHANG L P, YANG J C, XIE J L, QIU J, ZHANG H S, ZHANG Y B, YANG S Q, SA R G, LIU J Y. Remotely sensed mapping and analysis of spatio-temporal patterns of land use change across China in 2015-2020. Acta Geographica Sinica, 2022, 77(5): 1056-1071. (in Chinese) doi: 10.11821/dlxb202205002
[13]	ZHANG Z X, WANG X, ZHAO X L, LIU B, YI L, ZUO L J, WEN Q K, LIU F, XU J Y, HU S G. A 2010 update of National Land Use/Cover Database of China at 1: 100000 scale using medium spatial resolution satellite images. Remote Sensing of Environment, 2014, 149: 142-154. doi: 10.1016/j.rse.2014.04.004
[14]	XU Y D, YU L, PENG D L, ZHAO J Y, CHENG Y Q, LIU X X, LI W, MENG R, XU X L, GONG P. Annual 30-m land use/land cover maps of China for 1980-2015 from the integration of AVHRR, MODIS and Landsat data using the BFAST algorithm. Science China Earth Sciences, 2020, 63(9): 1390-1407. doi: 10.1007/s11430-019-9606-4
[15]	YANG J, HUANG X. The 30 m annual land cover dataset and its dynamics in China from 1990 to 2019. Earth System Science Data, 2021, 13(8): 3907-3925. doi: 10.5194/essd-13-3907-2021
[16]	LI Z H, ZHANG H Y, LU F X, XUE R Y, YANG G Y, ZHANG L P. Breaking the resolution barrier: A low-to-high network for large-scale high-resolution land-cover mapping using low-resolution labels. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 192: 244-267. doi: 10.1016/j.isprsjprs.2022.08.008
[17]	VAN TRICHT K, DEGERICKX J, GILLIAMS S, ZANAGA D, BATTUDE M, GROSU A, BROMBACHER J, LESIV M, BAYAS J C L, KARANAM S, FRITZ S, BECKER-RESHEF I, FRANCH B, MOLLÀ-BONONAD B, BOOGAARD H, PRATIHAST A K, KOETZ B, SZANTOI Z. WorldCereal: A dynamic open-source system for global-scale, seasonal, and reproducible crop and irrigation mapping. Earth System Science Data, 2023, 15(12): 5491-5515. doi: 10.5194/essd-15-5491-2023
[18]	ZHANG M, WU B F, ZENG H W, HE G J, LIU C, TAO S Q, ZHANG Q, NABIL M, TIAN F Y, BOFANA J, BEYENE A N, ELNASHAR A, YAN N N, WANG Z D, LIU Y L. GCI30: A global dataset of 30 m cropping intensity using multisource remote sensing imagery. Earth System Science Data, 2021, 13(10): 4799-4817. doi: 10.5194/essd-13-4799-2021
[19]	SIEBERT S, DÖLL P, HOOGEVEEN J, FAURES J M, FRENKEN K, FEICK S. Development and validation of the global map of irrigation areas. Hydrology and Earth System Sciences, 2005, 9(5): 535-547. doi: 10.5194/hess-9-535-2005
[20]	QIU B W, WU F Z, HU X, YANG P, WU W B, CHEN J, CHEN X H, HE L Y, JOE B, TUBIELLO F N, QIAN J P, WANG L G. A robust framework for mapping complex cropping patterns: The first national-scale 10 m map with 10 crops in China using Sentinel 1/2 images. ISPRS Journal of Photogrammetry and Remote Sensing, 2025, 224: 361-381. doi: 10.1016/j.isprsjprs.2025.04.012
[21]	XU Y Y, ZHU Z H, GUO M Q, HUANG Y. Multiscale edge-guided network for accurate cultivated land parcel boundary extraction from remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 1-20.
[22]	ZHANG W, GUO S C, ZHANG P, XIA Z L, ZHANG X G, LIN C, TANG P F, FANG H, DU P J. A novel knowledge-driven automated solution for high-resolution cropland extraction by cross-scale sample transfer. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-16.
[23]	GARCÍA-PEDRERO A, LILLO-SAAVEDRA M, RODRÍGUEZ- ESPARRAGÓN D, GONZALO-MARTÍN C. Deep learning for automatic outlining agricultural parcels: Exploiting the land parcel identification system. IEEE Access, 2019, 7: 158223- 158236. doi: 10.1109/Access.6287639
[24]	SUN H R, WEI Z J, YU W G, YANG G X, SHE J N, ZHENG H B, JIANG C Y, YAO X, ZHU Y, CAO W X, CHENG T, ALI I. SIDEST: A sample-free framework for crop field boundary delineation by integrating super-resolution image reconstruction and dual edge- corrected segment anything model. Computers and Electronics in Agriculture, 2025, 230: 109897. doi: 10.1016/j.compag.2025.109897
[25]	ZHAO H, WU B F, ZHANG M, LONG J, TIAN F Y, XIE Y, ZENG H W, ZHENG Z J, MA Z H, WANG M X, LI J B. A large-scale VHR parcel dataset and a novel hierarchical semantic boundary-guided network for agricultural parcel delineation. ISPRS Journal of Photogrammetry and Remote Sensing, 2025, 221: 1-19. doi: 10.1016/j.isprsjprs.2025.01.034
[26]	李德仁, 郭昊南. 人工智能应用于遥感智能解译的七大准则. 遥感学报, 2025, 29(3): 579-583.
	LI D R, GUO H N. Seven principles for the application of artificial intelligence in remote sensing interpretation. National Remote Sensing Bulletin, 2025, 29(3): 579-583. (in Chinese) doi: 10.11834/jrs.20254568
[27]	DURANTE Z, HUANG Q Y, WAKE N, GONG R, PARK J S, SARKAR B, TAORI R, NODA Y, TERZOPOULOS D, CHOI Y J, IKEUCHI K, VO H, LI F F, GAO J F. Agent AI: Surveying the horizons of multimodal interaction. ArXiv : 2401.03568, 2024.
[28]	PETERS M A, JANDRIĆ P, GREEN B J. The DIKW model in the age of artificial intelligence. Postdigital Science and Education, 2024. doi: 10.1007/s42438-024-00462-8.
[29]	汪寿阳, 刘梦. 以人工智能引领科研范式变革. http://www.xinhuanet.com/politics/20250523/b57a0aafa80042c0a89f55199a7be822/c.html. 2025-05-23.
	WANG S Y, LIU M. Leading scientific research paradigm shifts with artificial intelligence. http://www.xinhuanet.com/politics/20250523/b57a0aafa80042c0a89f55199a7be822/c.html. 2025-05-23. (in Chinese)
[30]	孟瑜, 陈静波, 张正, 刘志强, 赵智韬, 霍连志, 史科理, 刘帝佑, 邓毓弸, 唐娉. 知识与数据驱动的遥感图像智能解译: 进展与展望. 遥感学报, 2024, 28(11): 2698-2718.
	MENG Y, CHEN J B, ZHANG Z, LIU Z Q, ZHAO Z T, HUO L Z, SHI K L, LIU D Y, DENG Y P, TANG P. Knowledge and data driven remote sensing image interpretation: Recent developments and prospects. National Remote Sensing Bulletin, 2024, 28(11): 2698-2718. (in Chinese) doi: 10.11834/jrs.20243547
[31]	PAN Y, WANG X Y, ZHANG L P, ZHONG Y F. E2EVAP: End-to-end vectorization of smallholder agricultural parcel boundaries from high-resolution remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 203: 246-264. doi: 10.1016/j.isprsjprs.2023.08.001
[32]	李德仁, 眭海刚, 张浩, 倪梓轩. 时空智能助力应急监测的思考与探索. 中国减灾, 2025(1): 16-17.
	LI D R, SUI H G, ZHANG H, NI Z X. Reflections and explorations on space-time intelligence for emergency monitoring. Disaster Reduction in China, 2025(1): 16-17. (in Chinese)
[33]	冯芯蕊, 余强毅, 张晓光, 段玉林, 吴文斌. 基于文献计量的“耕地”和“农田”应用场景辨析. 中国农业资源与区划, 2024, 45(11): 229-238.
	FENG X R, YU Q Y, ZHANG X G, DUAN Y L, WU W B. Understanding “cultivated land” and “farmland”: A bibliometric analysis. Chinese Journal of Agricultural Resources and Regional Planning, 2024, 45(11): 229-238. (in Chinese)
[34]	吴文斌, 余强毅, 陆苗, 项铭涛, 谢安坤, 杨鹏, 唐华俊. 耕地复种指数研究的关键科学问题. 中国农业科学, 2018, 51(9): 1681-1694. doi: 10.3864/j.issn.0578-1752.2018.09.006.
	WU W B, YU Q Y, LU M, XIANG M T, XIE A K, YANG P, TANG H J. Key research priorities for multiple cropping systems. Scientia Agricultura Sinica, 2018, 51(9): 1681-1694. doi: 10.3864/j.issn.0578-1752.2018.09.006. (in Chinese)
[35]	WANG C, ZHANG X Y, WANG W J, WEI H D, WANG J Y, LI Z X, LI X N, WU H, HU Q. Understanding the potentials of early-season crop type mapping by using Landsat-8, Sentinel-1/2, and GF-1/6 data. Computers and Electronics in Agriculture, 2024, 224: 109239. doi: 10.1016/j.compag.2024.109239
[36]	王宁静, 王心宇, 潘洋, 卢晓燕, 姚顽强, 钟燕飞, 龚健雅. WHU-RuR: 高分遥感影像农村(高标准农田)道路提取基准数据集. 遥感学报, 2025, 29(4): 857-866.
	WANG N J, WANG X Y, PAN Y, LU X Y, YAO W Q, ZHONG Y F, GONG J Y. WHU-RuR: A high-resolution remote sensing benchmark dataset for rural(high-standard farmland) road extraction. National Remote Sensing Bulletin, 2025, 29(4): 857-866. (in Chinese) doi: 10.11834/jrs.20253491
[37]	GUO X, LAO J W, DANG B, ZHANG Y Y, YU L, RU L X, ZHONG L H, HUANG Z Y, WU K, HU D X, HE H M, WANG J, CHEN J D, YANG M, ZHANG Y J, LI Y S. SkySense: A multi-modal remote sensing foundation model towards universal interpretation for earth observation imagery. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024: 27662-27673.
[38]	ZHANG W, CAI M X, ZHANG T, ZHUANG Y, LI J, MAO X R. EarthMarker: A visual prompting multimodal large language model for remote sensing. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 5604219.
[39]	ZHOU B C, YANG H T, CHEN D R, YE J Y, BAI T Y, YU J H, ZHANG S Y, LIN D H, HE C H, LI W J. UrBench: A comprehensive benchmark for evaluating large multimodal models in multi-view urban scenarios. Proceedings of the AAAI Conference on Artificial Intelligence, 2025, 39(10): 10707-10715.
[40]	YU Q Y, HU Q, WU H, WU W B. View from above: Farmland infrastructure and its impacts on agricultural landscapes. The Innovation Geoscience, 2025, 3(1): 100107. doi: 10.59717/j.xinn-geo.2024.100107
[41]	FRITZ S, SEE L, MCCALLUM I, YOU L Z, BUN A, MOLTCHANOVA E, DUERAUER M, ALBRECHT F, SCHILL C, PERGER C, et al. Mapping global cropland and field size. Global Change Biology, 2015, 21(5): 1980-1992. doi: 10.1111/gcb.12838 pmid: 25640302
[42]	YU Q Y, HU Q, VAN VLIET J, VERBURG P H, WU W B. GlobeLand 30 shows little cropland area loss but greater fragmentation in China. International Journal of Applied Earth Observation and Geoinformation, 2018, 66: 37-45. doi: 10.1016/j.jag.2017.11.002
[43]	周春芳, 赵宇鸾, 文高辉, 龙明顺, 杨顺富, 段雨洁. 耦合地块空间和权属信息的耕地细碎化测度. 地理科学进展, 2025, 44(2): 414-428. doi: 10.18306/dlkxjz.2025.02.015
	ZHOU C F, ZHAO Y L, WEN G H, LONG M S, YANG S F, DUAN Y J. Measurement of cultivated land fragmentation by coupling spatial and tenure information of plots. Progress in Geography, 2025, 44(2): 414-428. (in Chinese) doi: 10.18306/dlkxjz.2025.02.015

基于形态指纹特征的耕地遥感监测轻量化大模型构建

Developing a Lightweight Multimodal Model for Cropland Remote Sensing Monitoring

RichHTML

PDF

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 43

相关文章 10

Metrics

本文评价

推荐阅读 0

[1]	吕旭东, 孙世媛, 李亚楠, 刘玉龙, 王艳群, 付鑫, 张佳英, 宁鹏, 彭正萍. 智能机械化分层施肥对麦田根-土养分分布和小麦产量的影响[J]. 中国农业科学, 2026, 59(1): 129-146.
[2]	唐朝元, 刘韬奋, 吴艳琴, 张启鹏, 李自良, 陈云瑞, 雷长英, 张亚黎, 张旺锋, 杜明伟, 杨明凤, 田景山. 陆地棉与海岛棉铃形态特征与纤维及籽仁品质的关系[J]. 中国农业科学, 2025, 58(15): 2980-2992.
[3]	姚青, 姚波, 吕军, 唐健, 冯晋, 朱旭华. 基于双线性注意力网络的农业灯诱害虫细粒度图像识别研究[J]. 中国农业科学, 2021, 54(21): 4562-4572.
[4]	臧成凤，樊卫国. 供磷水平对铁核桃实生苗生长、形态特征及叶片营养元素含量的影响[J]. 中国农业科学, 2016, 49(2): 319-330.
[5]	杨宁宁1, 3, 孙万仓2, 3, 刘自刚1, 2, 3, 史鹏辉1, 3, 方彦1, 2, 3, 武军艳2, 3, 曾秀存1, 3, 孔德晶1, 3, 鲁美宏1, 3, 王月1, 3. 北方冬油菜抗寒性的形态与生理机制[J]. 中国农业科学, 2014, 47(3): 452-461.
[6]	陈静，刘连涛，孙红春，张永江，王占彪，李存东. 外源NO对缺氮胁迫下棉花幼苗形态及生长的调控效应[J]. 中国农业科学, 2014, 47(23): 4595-4605.
[7]	朱保建,刘朝良,吴宏镇 . 不同发育时期柞蚕雌蛾粘液腺的组织形态学观察[J]. 中国农业科学, 2010, 43(8): 1757-1760 .
[8]	马国胜,高智谋. 烟草黑胫病菌培养性状的研究[J]. 中国农业科学, 2007, 40(3): 512-517 .
[9]	@孙伟$扬州大学畜牧兽医学院!扬州225. 中国部分绵羊群体形态及生态特征多元统计分析[J]. 中国农业科学, 2004, 37(02): 285-285 .
[10]	张弦,严衍录. 用图形图像技术处理作物图像提取作物形态信息[J]. 中国农业科学, 1996, 29(05): 89-93 .