耦合空间分布模式的复杂山区地块作物遥感分类方法

doi:10.11947/j.AGCS.2025.20240440

测绘学报 ›› 2025, Vol. 54 ›› Issue (7): 1215-1229.doi: 10.11947/j.AGCS.2025.20240440

耦合空间分布模式的复杂山区地块作物遥感分类方法

吴田军¹(), 李曼嘉²^,³, 骆剑承²^,³(), 李子琪²^,³, 胡晓东⁴, 郜丽静², 沈占锋²^,³

^1.长安大学土地工程学院，陕西　西安　710064
^2.中国科学院空天信息创新研究院遥感与数字地球全国重点实验室，北京　100101
^3.中国科学院大学资源与环境学院，北京　100049
^4.浙江科技大学计算机科学与技术学院，浙江　杭州　310023

收稿日期:2024-09-14 修回日期:2025-06-20 出版日期:2025-08-18 发布日期:2025-08-18
通讯作者: 骆剑承 E-mail:tjwu@chd.edu.cn;luojc@aircas.ac.cn
作者简介:吴田军（1986—），男，博士，教授，研究方向为智能遥感与地理时空智能。E-mail：tjwu@chd.edu.cn
基金资助:
国家自然科学基金(42471394);陕西省自然科学基础研究计划(2025JC-QYCX-035);河北省中央引导地方科技发展资金(236Z0104G)

Farmland-parcel-based crop remote sensing classification method in complex mountainous areas via coupling spatial distribution patterns

Tianjun WU¹(), Manjia LI²^,³, Jiancheng LUO²^,³(), Ziqi LI²^,³, Xiaodong HU⁴, Lijing GAO², Zhanfeng SHEN²^,³

^1.School of Land Engineering, Chang'an University, Xi'an 710064, China
^2.State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China
^3.College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China
^4.School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China

Received:2024-09-14 Revised:2025-06-20 Online:2025-08-18 Published:2025-08-18
Contact: Jiancheng LUO E-mail:tjwu@chd.edu.cn;luojc@aircas.ac.cn
About author:WU Tianjun (1986—), male, PhD, professor, majors in intelligent remote sensing and geographic spatio-temporal intelligence. E-mail: tjwu@chd.edu.cn
Supported by:
The National Natural Science Foundation of China(42471394);Natural Science Basic Research Program of Shaanxi(2025JC-QYCX-035);Central Guidance on Local Science and Technology Development Fund of Hebei Province Under Grant(236Z0104G)

摘要/Abstract

摘要：

地块级作物空间分布地图是精准农业应用的迫切需求。然而，在山区地形起伏、耕地结构破碎、作物类型多样、云雨天气频繁的环境条件下，现有仅依托遥感数据驱动的作物分类模型仍无法满足实际要求，究其原因是对山区农地系统复杂性、遥感成像的不确定性及作物种植的时空唯一性缺乏深刻认知，对空间效应关联知识的深层次融入运用不足。对此，本文聚焦复杂地表作物遥感制图的不确定性分析问题，以地块为核心对象，在图谱协同分析框架下开展作物分类方法研究，旨在耦合空间分布模式建立作物种植空间场景解构、作物生长谱序特征重建、作物类型判别模型增强3个创新链环节。西南山地典型区域的综合试验揭示了引入空间分布模式对于不确定性消减的正向作用，明晰地块精细提取、先验知识约束、特征重组拓展、分类器强化等措施的联合对提升山区作物辨识力的促进意义。本文在理论上深化对复杂地表区作物遥感解译机制的探索，在实践上为农业保险、灾害评估等场景生成更高精度、更具解释性的作物类型图提供示范与技术支撑。

关键词: 地块, 作物遥感分类, 山区, 图谱协同, 空间分布模式

Abstract:

Parcel-wise crop spatial distribution maps are currently in urgent need for precision agriculture applications. However, in mountainous areas with undulating topography, fragmented farmland structure, diverse crop types, and rainy climates, existing data-driven models may not fully satisfy the precision demands. Fundamentally, the causes may lie in the cognitive limits of the complicated agricultural systems and the uncertainty in remote sensing imaging, as well as the ignorance of spatial-temporal effect within the calculation. In response, this research focuses on the uncertainty reduction of remote sensing crop mapping, conducting researches on the introduction of spatial patterns to both the object-level decomposition of the targeted planting area, the reconstruction of the parcel-wise temporal spectral signature, and the crop classification process. The spatial and temporal features get adequately collaborated with land parcels received as basic analysis units. The comprehensive experiment of typical mountainous areas in Southwest China reveals the positive effect of introducing spatial distribution patterns on uncertainty reduction. It clarifies the significance of combining measures such as precise extraction of land parcels, prior knowledge constraints, feature recombination and expansion, classifier reinforcement, etc. to enhance crop identification in mountainous areas. In general, this study deepens the theoretical exploration of the remote sensing interpretation in crop mapping under complex terrain conditions and, in practice, provides a practical framework with higher accuracy and greater interpretability for the scenarios such as agricultural insurance and disaster assessment.

Key words: farmland-parcel, crop remote sensing classification, mountain area, Tu-Pu collaboration, spatial distribution pattern

中图分类号:

P237

吴田军, 李曼嘉, 骆剑承, 李子琪, 胡晓东, 郜丽静, 沈占锋. 耦合空间分布模式的复杂山区地块作物遥感分类方法[J]. 测绘学报, 2025, 54(7): 1215-1229.

Tianjun WU, Manjia LI, Jiancheng LUO, Ziqi LI, Xiaodong HU, Lijing GAO, Zhanfeng SHEN. Farmland-parcel-based crop remote sensing classification method in complex mountainous areas via coupling spatial distribution patterns[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(7): 1215-1229.

图/表 12

图1

图2

表1

图3

图4

图5

表2

图6

图7

表3

图8

表4

参考文献 40

[1]	赵春江. 农业遥感研究与应用进展[J]. 农业机械学报, 2014, 45(12): 277-293.
	ZHAO Chunjiang. Advances of research and application in remote sensing for agriculture[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(12): 277-293.
[2]	史舟, 梁宗正, 杨媛媛, 等. 农业遥感研究现状与展望[J]. 农业机械学报, 2015, 46(2): 247-260.
	SHI Zhou, LIANG Zongzheng, YANG Yuanyuan, et al. Status and prospect of agricultural remote sensing[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(2): 247-260.
[3]	陈仲新, 任建强, 唐华俊, 等. 农业遥感研究应用进展与展望[J]. 遥感学报, 2016, 20(5): 748-767.
	CHEN Zhongxin, REN Jianqiang, TANG Huajun, et al. Progress and perspectives on agricultural remote sensing research and applications in China[J]. Journal of Remote Sensing, 2016, 20(5): 748-767.
[4]	唐华俊. 农业遥感研究进展与展望[J]. 农学学报, 2018, 8(1): 167-171.
	TANG Huajun. Progress and prospect of agricultural remote sensing research[J]. Journal of Agriculture, 2018, 8(1): 167-171.
[5]	董金玮, 吴文斌, 黄健熙, 等. 农业土地利用遥感信息提取的研究进展与展望[J]. 地球信息科学学报, 2020, 22(4): 772-783.
	DONG Jinwei, WU Wenbin, HUANG Jianxi, et al. State of the art and perspective of agricultural land use remote sensing information extraction[J]. Journal of Geo-information Science, 2020, 22(4): 772-783.
[6]	秦其明, 范闻捷, 任华忠, 等. 农田定量遥感理论、方法与应用[M]. 北京: 科学出版社, 2018.
	QIN Qiming, FAN Wenjie, REN Huazhong, et al. Theory, method and applications of agricultural quantitative remote sensing of farmland[M]. Beijing: Science Press, 2018.
[7]	吴文斌, 胡琼, 陆苗, 等. 农业土地系统遥感制图[M]. 北京: 科学出版社, 2020.
	WU Wenbin, HU Qiong, LU Miao, et al. Remote sensing mapping of agricultural land system[M]. Beijing: Science Press, 2020.
[8]	李爱农, 边金虎, 张正健, 等. 山地遥感主要研究进展、发展机遇与挑战[J]. 遥感学报, 2016, 20(5): 1199-1215.
	LI Ainong, BIAN Jinhu, ZHANG Zhengjian, et al. Progresses, opportunities, and challenges of mountain remote sensing research[J]. Journal of Remote Sensing, 2016, 20(5): 1199-1215.
[9]	杨颖频, 吴志峰, 骆剑承, 等. 时空协同的地块尺度作物分布遥感提取[J]. 农业工程学报, 2021, 37(7): 166-174.
	YANG Yingpin, WU Zhifeng, LUO Jiancheng, et al. Parcel-based crop distribution extraction using the spatiotemporal collaboration of remote sensing data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(7): 166-174.
[10]	吴田军, 骆剑承, 赵馨, 等. 精准地理应用驱动的高分遥感协同计算研究[J]. 武汉大学学报(信息科学版), 2022, 47(8): 1220-1235.
	WU Tianjun, LUO Jiancheng, ZHAO Xin, et al. Collaborative computing of high-resolution remote sensing driven by fine-accurate geographic applications[J]. Geomatics and Information Science of Wuhan University, 2022, 47(8): 1220-1235.
[11]	张冬韵, 吴田军, 李曼嘉, 等. 地块尺度农作物遥感分类及其不确定性分析[J]. 自然资源遥感, 2024, 36(4): 124-134.
	ZHANG Dongyun, WU Tianjun, LI Manjia, et al. Remote sensing-based classification of crops on a farmland parcel scale and uncertainty analysis[J]. Remote Sensing for Natural Resources, 2024, 36(4): 124-134.
[12]	张冬韵, 吴田军, 骆剑承, 等. 时空协同的农业种植结构遥感精细制图[J]. 遥感学报, 2024, 28(8): 2014-2029.
	ZHANG Dongyun, WU Tianjun, LUO Jiancheng, et al. Precise crop planting structure mapping method based on spatial-temporal collaboration of remote sensing[J]. National Remote Sensing Bulletin, 2024, 28(8): 2014-2029.
[13]	HONG R, PARK J, JANG S, et al. Development of a parcel-level land boundary extraction algorithm for aerial imagery of regularly arranged agricultural areas[J]. Remote Sensing, 2021, 13(6): 1167.
[14]	刘巍, 吴志峰, 骆剑承, 等. 深度学习支持下的丘陵山区耕地高分辨率遥感信息分区分层提取方法[J]. 测绘学报, 2021, 50(1): 105-116. DOI: . doi: 10.11947/j.AGCS.2021.20190448
	LIU Wei, WU Zhifeng, LUO Jiancheng, et al. A divided and stratified extraction method of high-resolution remote sensing information for cropland in hilly and mountainous areas based on deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(1): 105-116. DOI: . doi: 10.11947/j.AGCS.2021.20190448
[15]	PERSELLO C, TOLPEKIN V A, BERGADO J R, et al. Delineation of agricultural fields in small holder farms from satellite images using fully convolutional networks and combinatorial grouping[J]. Remote Sensing of Environment, 2019, 231: 111253.
[16]	WALDNER F, DIAKOGIANNIS F I. Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network[J]. Remote Sensing of Environment, 2020, 245: 111741.
[17]	WALDNER F, DIAKOGIANNIS F I, BATCHELOR K, et al. Detect, consolidate, delineate: scalable mapping of field boundaries using satellite images[J]. Remote Sensing, 2021, 13(11): 2197.
[18]	LONG Jiang, LI Mengmeng, WANG Xiaoqin, et al. Delineation of agricultural fields using multi-task BsiNet from high-resolution satellite images[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112: 102871.
[19]	PAN Yang, WANG Xinyu, WANG Yu, et al. RBP-MTL: agricultural parcel vectorization via region-boundary-parcel decoupled multitask learning[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 3367850.
[20]	POTT L P, AMADO T J C, SCHWALBERT R A, et al. Satellite-based data fusion crop type classification and mapping in Rio Grande do Sul, Brazil[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 176: 196-210.
[21]	HU Qiong, YIN He, FRIEDL M A, et al. Integrating coarse-resolution images and agricultural statistics to generate sub-pixel crop type maps and reconciled area estimates[J]. Remote Sensing of Environment, 2021, 258: 112365.
[22]	MASKELL G, CHEMURA A, NGUYEN H, et al. Integration of Sentinel optical and radar data for mapping smallholder coffee production systems in Vietnam[J]. Remote Sensing of Environment, 2021, 266: 112709.
[23]	BLICKENSDÖRFER L, SCHWIEDER M, PFLUGMACHER D, et al. Mapping of crop types and crop sequences with combined time series of Sentinel-1, Sentinel-2 and Landsat 8 data for Germany[J]. Remote Sensing of Environment, 2022, 269: 112831.
[24]	何泽, 李世华. 水稻雷达遥感监测研究进展[J]. 遥感学报, 2023, 27(10): 2363-2382.
	HE Ze, LI Shihua. Research progress on radar remote sensing for rice growth monitoring[J]. National Remote Sensing Bulletin, 2023, 27(10): 2363-2382.
[25]	MARTINEZ J A C, LA ROSA L E C, FEITOSA R Q, et al. Fully convolutional recurrent networks for multidate crop recognition from multitemporal image sequences[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 171: 188-201.
[26]	METZGER N, TURKOGLU M O, D'ARONCO S, et al. Crop classification under varying cloud cover with neural ordinary differential equations[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 4404912.
[27]	BROCCA L, ZHAO Wei, LU Hui. High-resolution observations from space to address new applications in hydrology[J]. The Innovation, 2023, 4(3): 100437.
[28]	盖爽, 张锦水, 朱爽. 深度学习作物分类模型空间泛化能力分析[J]. 遥感学报, 2023, 27(12): 2796-2814.
	GE Shuang, ZHANG Jinshui, ZHU Shuang. Spatial generalization ability analysis of deep learning crop classification models[J]. National Remote Sensing Bulletin, 2023, 27(12): 2796-2814.
[29]	王志华, 杨晓梅, 刘岳明, 等. 遥感影像地学分析的地理学原理及等级斑块建模框架[J]. 遥感学报, 2024, 28(6): 1412-1424.
	WANG Zhihua, YANG Xiaomei, LIU Yueming, et al. Geographical principles of remote sensing image analysis and the hierarchical patch model based analysis framework[J]. National Remote Sensing Bulletin, 2024, 28(6): 1412-1424.
[30]	高松. 地理空间人工智能的近期研究总结与思考[J]. 武汉大学学报(信息科学版), 2020, 45(12): 1865-1874.
	GAO Song. A review of recent researches and reflections on geospatial artificial intelligence[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1865-1874.
[31]	ZHANG Xueliang, XIAO Pengfeng, FENG Xuezhi. Toward combining thematic information with hierarchical multiscale segmentations using tree Markov random field model[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 131: 134-146.
[32]	李新, 刘丰, 方苗. 模型与观测的和弦：地球系统科学中的数据同化[J]. 中国科学：地球科学, 2020, 50(9): 1185-1194.
	LI Xin, LIU Feng, FANG Miao. Harmonizing models and observations: data assimilation in Earth system science[J]. Scientia Sinica (Terrae), 2020, 50(9): 1185-1194.
[33]	刘瑜, 郭浩, 李海峰, 等. 从地理规律到地理空间人工智能[J]. 测绘学报, 2022, 51(6): 1062-1069. DOI: . doi: 10.11947/j.AGCS.2022.20220125
	LIU Yu, GUO Hao, LI Haifeng, et al. A note on GeoAI from the perspective of geographical laws[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(6): 1062-1069. DOI: . doi: 10.11947/j.AGCS.2022.20220125
[34]	杨倩倩, 靳才溢, 李同文, 等. 数据驱动的定量遥感研究进展与挑战[J]. 遥感学报, 2022, 26(2): 268-285.
	YANG Qianqian, JIN Caiyi, LI Tongwen, et al. Research progress and challenges of data-driven quantitative remote sensing[J]. National Remote Sensing Bulletin, 2022, 26(2): 268-285.
[35]	燕琴, 刘纪平, 董春, 等. 地理空间视角下自然资源认知探讨[J]. 测绘科学, 2022, 47(8): 9-17.
	YAN Qin, LIU Jiping, DONG Chun, et al. Natural resources cognition from the perspective of geographic space[J]. Science of Surveying and Mapping, 2022, 47(8): 9-17.
[36]	沈焕锋, 张良培. 地球表层特征参量反演与模拟的机理-学习耦合范式[J]. 中国科学：地球科学, 2023, 53(3): 546-560.
	SHEN Huanfeng, ZHANG Liangpei. Mechanism-learning coupling paradigms for parameter inversion and simulation in earth surface systems[J]. Scientia Sinica (Terrae), 2023, 53(3): 546-560.
[37]	张兵, 杨晓梅, 高连如, 等. 遥感大数据智能解译的地理学认知模型与方法[J]. 测绘学报, 2022, 51(7): 1398-1415. DOI: . doi: 10.11947/j.AGCS.2022.20220279
	ZHANG Bing, YANG Xiaomei, GAO Lianru, et al. Geo-cognitive models and methods for intelligent interpretation of remotely sensed big data[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1398-1415. DOI: . doi: 10.11947/j.AGCS.2022.20220279
[38]	MITCHELL P J, DOWNIE A L, DIESING M. How good is my map? A tool for semi-automated thematic mapping and spatially explicit confidence assessment[J]. Environmental Modelling & Software, 2018, 108: 111-122.
[39]	汪静平, 吴小丹, 马杜娟, 等. 基于机器学习的遥感反演：不确定性因素分析[J]. 遥感学报, 2023, 27(3): 790-801.
	WANG Jingping, WU Xiaodan, MA Dujuan, et al. Remote sensing retrieval based on machine learning algorithm: uncertainty analysis[J]. National Remote Sensing Bulletin, 2023, 27(3): 790-801.
[40]	吴田军, 骆剑承, 李曼嘉, 等. 地理时空数字化底座理论框架构建与应用实践[J]. 地球信息科学学报, 2024, 26(4): 799-830.
	WU Tianjun, LUO Jiancheng, LI Manjia, et al. Theoretical framework construction and application practice of the geographic spatiotemporal digital base[J]. Journal of Geo-information Science, 2024, 26(4): 799-830.

作物类型	播种期	苗期	分蘖期	拔节期	抽穗期	灌浆成熟期
水稻	2月下旬至	3月中旬至	4月下旬至	5月下旬至	6月下旬至	7月中旬至
水稻	3月上旬	4月中旬	5月中旬	6月中旬	7月上旬	8月中旬
玉米	2月下旬至	3月下旬至	—	5月中旬至	6月中旬至	7月上旬至
玉米	3月中旬	5月上旬	—	6月上旬	6月下旬	8月中旬

作物类别	OA	正确率	召回率	F₁值	信息熵
水稻	—	0.926	0.907	0.917	－0.634
玉米	—	0.724	0.712	0.718	－0.976
柠檬	—	0.891	0.919	0.905	－0.560
其他	—	0.795	0.816	0.805	－0.895
总体	0.883	0.890	0.885	0.887	－0.757

特征类型	OA	正确率	召回率	F₁值	信息熵
像元级	0.808	0.816	0.812	0.814	－0.885
像元级-地块约束	0.851	0.834	0.838	0.836	－0.733
地块级	0.883	0.890	0.885	0.887	－0.757

地块ID	其他隶属度	水稻隶属度	不确定性	其他隶属度	水稻隶属度	不确定性
目标地块	0.53	0.47	0.997	0.39	0.61	0.967
邻域单元1	0.25	0.75	0.808	0.19	0.81	0.701
邻域单元2	0.61	0.39	0.964	0.58	0.42	0.981
邻域单元3	0.34	0.66	0.925	0.38	0.62	0.958
邻域单元4	0.55	0.45	0.992	0.24	0.76	0.793

耦合空间分布模式的复杂山区地块作物遥感分类方法

Farmland-parcel-based crop remote sensing classification method in complex mountainous areas via coupling spatial distribution patterns

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 40

相关文章 7

编辑推荐

Metrics

本文评价

[1]	李维炼, 朱军, 朱庆, 李佳洛. 耦合数值仿真与时空插值融合的山区桥梁温度场三维建模方法[J]. 测绘学报, 2025, 54(4): 749-759.
[2]	周玉杉, 李新, 郑东海, 任姗姗, 汪赢政, 李志伟. 亚洲高山区冰川厚度变化光学立体和双基SAR卫星监测数据、方法与展望[J]. 测绘学报, 2024, 53(5): 779-800.
[3]	蒋光伟, 王盼龙, 郭春喜, 王斌, 杨元喜. 附加对流层约束的大高差区域短时GNSS网解及其性能[J]. 测绘学报, 2022, 51(11): 2255-2264.
[4]	刘慧敏, 胡文柯, 唐建波, 石岩, 邓敏. 顾及功能语义特征的建筑物空间分布模式识别方法[J]. 测绘学报, 2020, 49(5): 622-631.
[5]	李振豪, 杨春成, 魏斌, 周校东, 何列松, 信睿. 道路与建筑物空间冲突的几何相似性移位算法[J]. 测绘学报, 2016, 45(6): 747-755.
[6]	唐建波, 刘启亮, 邓敏, 黄金彩, 蔡建南. 空间层次聚类显著性判别的重排检验方法[J]. 测绘学报, 2016, 45(2): 233-240.
[7]	吴明光. 一种空间分布模式驱动的空间索引[J]. 测绘学报, 2015, 44(1): 108-115.