Identification of Cropland Parcels and Evaluation of Cropland Fragmentation Degree in Hilly Areas Based on Deep Learning

doi:10.15933/j.cnki.1004-3268.2026.09.016

Abstract

Abstract: To address low efficiency in cropland extraction and fragmentation evaluation in such hilly areas，this study took Shidong Town，Anju District，Suining City，Sichuan Province—a typical hilly region—as the test area，and adopted the U‑Net+SE model using Gaofen‑2 imagery for cropland patch identification and boundary extraction，respectively.Then，the fragmentation evaluation system was created and implemented from the dimension of parcel area，shape and spatial distribution.Results showed that patch identification achieved higher accuracy［overall accuracy（OA）：92.23%；precision：0.80］than boundary extraction（OA：90.77%；precision：0.77）.Fragmentation assessment presented higher performance using the result of cropland boundary mapping compared with visual interpretation as the reference，which displayed lower difference for the comprehensive index（11.76%），as well as the subindex of area（ 8.51%） and shape（ 13.51%），which was superior to the results derived from cropland patch extraction.

Key words: , Patch identification；Deep learning；Fragmentation assessment；Hilly region；U?Net+SE；High?resolution remote sensing；Boundary extraction

摘要： 针对当前丘陵区耕地识别方法效率低、细碎化程度评估时效性不足的问题，选择典型丘陵区四川省遂宁市安居区石洞镇为试验区，以国产高分二号影像为数据源，采用U-Net+SE模型分别开展耕地田块的斑块识别、边界提取及精度评价；进而构建耕地面积、形状、分布等细碎化评价体系，实现丘陵区耕地细碎化程度评估。结果表明，耕地斑块提取精度更高，其总体精度（OA）为92.23%、准确率（Precision）达0.80，优于耕地边界提取结果（OA为90.77%、Precision为0.77）。利用耕地边界提取结果进行耕地细碎化程度评估更接近目视解译，其面积、形状细碎指数及综合评价指数与目视解译分别仅相差8.51%、13.51%和11.76%，优于耕地斑块提取结果。

关键词: 斑块识别, 深度学习, 耕地细碎化评价, 丘陵区, U-Net+SE模型, 高分辨率遥感, 边界提取

CLC Number:

S127

Xu Haolun, Han Shengbin, Zhang Jianyong, Li Yalong, Gao Yi, Cheng Weidong. Identification of Cropland Parcels and Evaluation of Cropland Fragmentation Degree in Hilly Areas Based on Deep Learning[J]. Journal of Henan Agricultural Sciences, 2026, 55(9): 172-180.

徐浩伦, 韩胜斌, 张建勇, 李亚龙, 高艺, 程维东. 基于深度学习的丘陵区耕地田块识别与细碎化程度评价[J]. 河南农业科学, 2026, 55(9): 172-180.

Figures/Tables 9

References

［1］傅强. 加快推进山地农业理论研究与学科建设［J］. 山地农业研究，2026，1（1）：15‑21.
Fu Q. Accelerating theoretical research and discipline construction of mountain agriculture［J］. Mountain Agriculture Research，2026，1（1）：15‑21.
［2］Deng O，Ran J，Huang S，et al. Managing fragmented croplands for environmental and economic benefits in China［J］. Nature Food，2024，5（3）：230‑240.
［3］刘晶，金晓斌，徐伟义，等. 耕地细碎化对可持续集约利用的影响机理与治理框架［J］. 地理学报，2022，77（11）：2703‑2720.
Liu J，Jin X B，Xu W Y，et al. Influence mechanism of cultivated land fragmentation on sustainable intensification and its governance framework［J］. Acta Geographica Sinica，2022，77（11）：2703‑2720.
［4］欧阳许童，张璇，李维庆，等. 基于Sentinel-2和Landsat卫星时序数据的耕地撂荒识别［J］. 测绘通报，2023（8）：57‑62.
Ouyang X T，Zhang X，Li W Q，et al. Abandoned land identification based on Sentinel‑2 and Landsat satellite time series images［J］. Bulletin of Surveying and Mapping，2023（8）：57‑62.
［5］谢花林，欧阳振益，陈倩茹. 耕地细碎化促进了耕地“非粮化”吗：基于福建丘陵山区农户的微观调查［J］. 中国土地科学，2022，36（1）：47‑56.

Xie H L，Ouyang Z Y，Chen Q R. Does cultivated land fragmentation promote “non‑grain” utilization of cultivated land：based on a micro survey of farmers in the hilly and mountainous areas of Fujian［J］. China Land Science，2022，36（1）：47‑56.

［6］宋曼，张蚌蚌，宋保胜，等. 耕地细碎化、非农就业对农村内部收入差距的影响［J］. 河南农业大学学报，2025，59（4）：735‑745.

Song M， Zhang B B，SONG B S，et al. Impact of fragmented arable land and non‑agricultural employment on the income gap within rural areas［J］. Journal of Henan Agricultural University，2025，59（4）：735‑745.

［7］王迪，曾妍，田甜，等. 基于卫星遥感的耕地质量监测与评价研究进展［J］. 中国农业资源与区划，2025，46（12）：203‑218.

Wang D，Zeng Y，Tian T，et al. Research advances on cultivated land quality monitoring and assessment by remote sensing ［J］. Chinese Journal of Agricultural Resources and Regional Planning，2025，46（12）：203‑218.

［8］孟凤，朱庆伟，董士伟，等. 基于多季相分形特征的Landsat 8 OLI影像耕地信息提取方法［J］. 农业机械学报，2024，55（6）：168‑177.

Meng F，Zhu Q W，Dong S W，et al. Cropland information extraction method of Landsat 8 OLI images based on multi‑seasonal fractal features［J］. Transactions of the Chinese Society for Agricultural Machinery，2024，55（6）：168‑177.

［9］Sun Y，Wang J，Li K，et al. Long‑term spatiotemporal information extraction of cultivated land in the nomadic area：a case study of the Selenge River Basin［J］.Remote Sensing，2025，17（12）：1970.

［10］高圣杰，朱长明，李均力，等. 局部聚焦算法辅助标记的高分遥感影像农田地块智能识别［J］. 农业工程学报，2025，41（16）：164‑172.

Gao S J，Zhu C M，Li J L，et al. Intelligent recognition of farmland geo‑parcels in high resolution remote sensing imagery assisted by local focusing algorithm［J］. Transactions of the Chinese Society of Agricultural Engineering，2025，41（16）：164‑172.

［11］张建勇，赵艳玲，肖武，等. 利用低空无人机摄影测量快速构建矿区线状地物信息［J］. 测绘通报，2017（10）：106‑110.

Zhang J Y，Zhao Y L，Xiao W，et al. Rapid construction of mine line infrastructure using low‑altitude unmanned aerial vehicle photogrammetry［J］. Bulletin of Surveying and Mapping，2017（10）：106‑110.

［12］Wang S Y，Zhou Y N，Yang X Z，et al. BSNet：boundary‑semantic‑fusion network for farmland parcel mapping in high‑resolution satellite images［J］.Computers and Electronics in Agriculture，2023，206：107683.

［13］苟长龙，庞敏，杨扬. 改进的U-Net卷积网络在遥感影像地物分类中的应用［J］. 测绘通报，2025（3）：150‑155.

Gou C L，Pang M，Yang Y. Improved U‑Net convolutional network application for land cover classification in remote sensing images［J］. Bulletin of Surveying and Mapping，2025（3）：150‑155.

［14］Lu R，Wang N，Zhang Y，et al. Extraction of agricultural fields via DASFNet with dual attention mechanism and multi‑scale feature fusion in south Xinjiang，China［J］.Remote Sensing，2022，14（9）：2253.

［15］许玉光，杨钢桥，文高辉. 耕地细碎化对耕地利用效率的影响：基于不同经营规模农户的实证分析［J］. 农业现代化研究，2017，38（4）：688‑695.

Xu Y G，Yang G Q，Wen G H. Impacts of arable land fragmentation on land use efficiency：an empirical analysis based on farms of different scales［J］.Research of Agricultural Modernization，2017，38（4）：688‑695.

［16］李庆东，王秋兵，钱凤魁，等. 农户耕地经营细碎化分析：以辽宁省昌图县为例［J］. 广东农业科学，2010，37（6）：230‑232.

Li Q D，Wang Q B，Qian F K，et al. Analysis on fragmentation of cultivated land in typical region：a case of Changtu County in Liaoning Province［J］.Guangdong Agricultural Sciences，2010，37（6）：230‑232.

［17］陈文彦，李婷，孙俊颖，等. 广东省1990—2020年耕地景观破碎度时空变化特征及其驱动机制［J］. 中国生态农业学报（中英文），2025，33（8）：1480‑1491.

Chen W Y，Li T，Sun J Y，et al. The spatial‑temporal changes of cropland fragmentation and its driving mechanisms in Guangdong Province from 1990 to 2020［J］. Chinese Journal of Eco‑Agriculture，2025，33（8）：1480‑1491.

［18］Zhao C，Zhou Y，Jiang J，et al. Spatial characteristics of cultivated land quality accounting for ecological environmental condition：a case study in hilly area of northern Hubei Province，China［J］. Science of the Total Environment，2021，774：145765.

［19］Chen Y，Xie Y，Yao W，et al. U‑MGA：a multi‑module Unet optimized with multi‑scale global attention mechanisms for fine‑grained segmentation of cultivated areas［J］. Remote Sensing，2025，17（5）：760.

［20］田富有，曹玉佩，赵航，等. 结合空间注意力机制与多任务学习的耕地地块分割模型［J］. 遥感学报，2024，28（11）：2850‑2864.

Tian F Y，Cao Y P，Zhao H，et al. Agricultural field segmentation using spatial attention mechanism and multi‑task learning strategy［J］. National Remote Sensing Bulletin，2024，28（11）：2850‑2864.

［21］Lu R，Zhang Y，Huang Q，et al. A refined edge‑aware convolutional neural networks for agricultural parcel delineation［J］. International Journal of Applied Earth Observation and Geoinformation，2024，133：104084.

［22］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 Y P，Wu Z F，Luo J C，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.

［23］陈帷胜，冯秀丽，马仁锋，等. 耕地破碎度评价方法与实证研究：以浙江省宁波市为例［J］. 中国土地科学，2016，30（5）：80‑87.

Chen W S，Feng X L，Ma R F，et al. Method of cultivated land fragmentation evaluation and empirical research：a case of Ningbo City in Zhejiang Province［J］. China Land Sciences，2016，30（5）：80‑87.

［24］王祯，吴金华，白帅，等. 黄土丘陵沟壑区耕地细碎化评价与土地整治工程分区：以吴起县为例［J］. 水土保持研究，2022，29（4）：300‑307.

Wang Z，Wu J H，Bai S，et al. Evaluating of cultivated land fragmentation and land consolidation engineering zoning in the loess hilly and gully region：a case study in Wuqi County［J］. Research of Soil and Water Conservation，2022，29（4）：300‑307.

［25］麦晶晶，冯琦胜，王瑞泾，等. 基于机器学习的高精度耕地识别模型构建：以甘肃省张掖市为例［J］. 草业学报，2025，34（2）：149‑162.

Mai J J，Feng Q S，Wang R J，et al. Construction of a high‑precision cultivated land identification model based on machine learning using Zhangye City，Gansu Province as an example［J］. Acta Prataculturae Sinica，2025，34（2）：149‑162.

［26］Maxwell A E，Warner T A，Fang F. Implementation of machine‑learning classification in remote sensing：an applied review［J］. International Journal of Remote Sensing，2018，39（9）：2784‑2817.

［27］李豪，杜雨秋，肖星竹，等. 基于深度学习的四川盆地丘陵区县域耕地遥感识别研究［J］. 智慧农业（中英文），2024，6（3）：34‑45.

Li H，Du Y Q，Xiao X Z，et al. Remote sensing identification method of cultivated land at hill county of Sichuan Basin based on deep learning［J］. Smart Agriculture，2024，6（3）：34‑45.

［28］毛星，金晶，张欣，等. 基于改进DeepLab v3+模型和迁移学习的高分遥感耕地信息提取方法［J］. 江苏农业学报，2023，39（7）：1519‑1529.

Mao X，Jin J，Zhang X，et al. High‑resolution remote sensing arable land information extraction method based on improved DeepLab v3+ model and transfer learning［J］. Jiangsu Journal of Agricultural Sciences，2023，39（7）：1519‑1529.

[1]	WANG Fei, LI Xuemeng, YANG Jin, GUO Zhichen, SONG Luyang, QIN Yanhong, WEN Yi, GAO Suxia, LU Shuhao, LIU Qi, QI Hongzhi, LI Shaojian. Evaluation of the Disease Prevention and Growth‑promoting Effects of Bacillus velezensis Bv1‑4 on Three Medicinal Plants and Its Whole Genome Analysis [J]. Journal of Henan Agricultural Sciences, 2025, 54(11): 79-90.
[2]	CHE Yali, WU Sujun, WANG Kunyang, WANG Yanli, ZHANG Kai, QIAO Yake, YUAN Quan. Genome‑wide Association Analysis of Wild Soybean Seedling Traits and Screening of Candidate Cadmium‑tolerant Genes [J]. Journal of Henan Agricultural Sciences, 2025, 54(1): 40-54.
[3]	HUANG Boxuan, ZHENG Cangsong, SUN Miao, SHAO Jingjing, FENG Weina, LI Pengcheng, DONG Helin. Research Progress of Nitrogen Inhibitors [J]. Journal of Henan Agricultural Sciences, 2024, 53(8): 1-10.
[4]	LI Haiyong, LI Mengyu, GAO Chuang, XU Hao, YIN Guihong, DONG Chunhao, NIU Jishan, LI Qiaoyun. Correlation Analysis between the Resisitance of Wheat to Black Point and Leaf Blight at Seedling Stage Caused by Bipolaris sorokiniana [J]. Journal of Henan Agricultural Sciences, 2023, 52(8): 96-104.
[5]	DAI Yurong, LI Yunhong, MU Liqiang, WU jin. Effects of PGPR Combined with Biomass Carbon on Capsicum annuum Growth and Soil Physical and Chemical Properties [J]. Journal of Henan Agricultural Sciences, 2022, 51(5): 62-70.
[6]	GAO Panpan, LI Guoyu, LIU Ruowei, WEI Yujing, FENG Haojie, LOU Yanhong, WANG Hui, YANG Quangang, ZHUGE Yuping, PAN Hong. Effects of Different Modifiers on NH₃ Volatilization and N₂O Emission in Saline Soils [J]. Journal of Henan Agricultural Sciences, 2022, 51(10): 1-8.
[7]	ZHANG Jian, CHEN Jianhua, SUN Yongqiang, DING Shifu, ZHENG Yongtao, DONG Shengjun. Photosynthetic Characteristics and Yield Components of Different Tree Crowns of Armeniaca sibirica [J]. Journal of Henan Agricultural Sciences, 2022, 51(1): 107-115.
[8]	WANG Zicheng, YANG Shuo, GUAN Yang, LIU Baodong. Comparative Study on Gametophyte Development of Phyllitis japonica under Cd²⁺ and Pb²⁺ Stress [J]. Journal of Henan Agricultural Sciences, 2021, 50(9): 128-134.
[9]	QIN Maomao, LIU Yanxi, ZHANG Kun, ZHAO Mengqi, ZHOU Zhengfu, WU Zhengqing, CHEN Feng, LEI Zhensheng. Effect of Late Spring Coldness on Quality of High-Quality Strong Gluten Wheat Zhengmai 366 [J]. Journal of Henan Agricultural Sciences, 2021, 50(3): 42-48.
[10]	LIU Lu, WAN Weijie, ZHENG Tongwen, LONG Xinyu, SUN Zhengxiang, ZHOU Yi. Control Effect of Burkholderia pyrrocinia YZU-S377 on Cotton Verticillium Wilt and Its Growth Promotion Function [J]. Journal of Henan Agricultural Sciences, 2021, 50(3): 91-96.
[11]	PENG Chenglin, YUAN Jiafu, JIA Ping’an, SI Guohan, XU Xiangyu, ZHAO Shujun, LI Jinhua. Effects of Long-term Integrated Rice-crayfish Model on Yield and Nitrogen Use Efficiency of Direct-seeding Rice under Different Nitrogen Application Rates [J]. Journal of Henan Agricultural Sciences, 2020, 49(4): 15-21.
[12]	XU Zhimin, LIU Yanzhen, CHEN Lin, WU Jianfang, LIU Lian, DING Guochang. Effects of Copper and Zinc Combined Stress on Seed Germination and Seedling Growth of 8 Ornamental Grasses [J]. Journal of Henan Agricultural Sciences, 2020, 49(3): 129-137.
[13]	WU Hongqi, LIN Biying, LI Caixia, LIU Xu, ZHANG Zikun, ZHONG Luming. Evaluation of Salt Tolerance of Different Eggplant Varieties at Seedling Stage [J]. Journal of Henan Agricultural Sciences, 2020, 49(10): 92-100.
[14]	LIU Yulan, CHEN Dianyuan, ZHENG Yushi, FAN Wenzhong, LI Yongpeng, SUN Shan, WANG Tao, ZHAI Wenbo. Effects of Interaction of Cutting Seedlings with Planting Density on Growth and Yield of Spring Maize [J]. Journal of Henan Agricultural Sciences, 2019, 48(9): 7-13.
[15]	WANG Liuhang, PENG Ting, XIONG Jiabao, WANG Haibin, LIU Ye, ZHANG Jing, WANG Daizhang, TENG Yongzhong, ZHAO Quanzhi. Effects of Nitrogen Fertilizer on Vascular Bundle Structure in First Internode of Super Hybrid Ｒice [J]. Journal of Henan Agricultural Sciences, 2019, 48(9): 14-22.