基于Sentinel-2和Landsat卫星时序数据的耕地撂荒识别

doi:10.13474/j.cnki.11-2246.2023.0232

测绘通报 ›› 2023, Vol. 0 ›› Issue (8): 57-62.doi: 10.13474/j.cnki.11-2246.2023.0232

基于Sentinel-2和Landsat卫星时序数据的耕地撂荒识别

欧阳许童^1,2, 张璇^1,2, 李维庆^1,2, 刘娟^1,2, 刘卓圣^1,2

1. 自然资源部第三地理信息制图院, 四川成都 610100;
2. 自然资源部数字制图与国土信息应用重点实验室, 四川成都 610100

收稿日期:2022-11-28 发布日期:2023-09-01
通讯作者: 张璇。E-mail:244037021@qq.com
作者简介:欧阳许童(1995-),女,硕士,主要研究方向为自然资源遥感监测。E-mail:ivyforoy@gmail.com
基金资助:
四川省地理信息测绘局2022年新型基础测绘技术研究补助计划(川测发[2022]46号)

Abandoned land identification based on Sentinel-2 and Landsat satellite time series images

OUYANG Xutong^1,2, ZHANG Xuan^1,2, LI Weiqing^1,2, LIU Juan^1,2, LIU Zhuosheng^1,2

1. The Third Geoinformation Mapping Institute of Ministry of Natural Resources, Chengdu 610100, China;
2. Ministry of Natural Resources Key Laboratory of Digital Cartography and Land Information Application, Chengdu 610100, China

Received:2022-11-28 Published:2023-09-01

摘要/Abstract

摘要： 充足的粮食供应是当下经济发展和社会稳定的重要保障之一,撂荒作为耕地边际化的极端表现,对其开展监测对保障耕地数量和质量至关重要。本文以四川省南充市营山县为研究区域,通过GEE平台,使用Sentinel-2和Landsat 7、8数据构建时序数据集,计算NDVI、EVI、NDWI、BSI、MSI等指数,分别利用支持向量机和随机森林法提取耕地撂荒,总分类精度为73.76%,Kappa系数为0.68,针对耕地撂荒最佳提取效果, F₁ 得分为0.691 1。本文方法对山地丘陵地区耕地撂荒监测有较大的借鉴意义。

关键词: 耕地撂荒, 时间序列, Sentinel-2, Landsat, 支持向量机, 随机森林

Abstract: Adequate food supply is vital to economic development and social stability. With the marginalization of cultivated land, the monitoring of abandoned land is essential to ensure the quantity and quality of cultivated land. This paper takes Yingshan county, Nanchong city, Sichuan province as the research area. GEE platform, Sentinel-2 and Landsat 7、8 data are applied to build a time series dataset, and indices such as NDVI, EVI, NDWI, BSI and MSI are calculated. Machine learning algorithms, support vector machine and random forest are separately used to extract abandoned land, and the overall accuracy is 73.76%, with Kappa coefficients 0.68. The highest F₁ score of abandoned land is 0.691 1. This paper develops an abandoned cultivated land identification method based on time series dataset, which can contribute to monitoring wasteland in hilly areas.

Key words: abandoned cultivated land, time series, Sentinel-2, Landsat, support machine vector, random forest

中图分类号:

P237

欧阳许童, 张璇, 李维庆, 刘娟, 刘卓圣. 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, 0(8): 57-62.

OUYANG Xutong, ZHANG Xuan, LI Weiqing, LIU Juan, LIU Zhuosheng. Abandoned land identification based on Sentinel-2 and Landsat satellite time series images[J]. Bulletin of Surveying and Mapping, 2023, 0(8): 57-62.

参考文献

[1] 张雪花, 滑永胜, 韩成吉. 耕地资源可持续发展的系统动力学仿真分析[J]. 水土保持通报, 2019, 39(3):144-150.
[2] 李升发,李秀彬. 耕地撂荒研究进展与展望[J]. 地理学报,2016,71(3):370-389.
[3] 徐莉. 城市化进程中如何解决农地抛荒问题:以四川省为例[J]. 农村经济,2010(3):21-24.
[4] REY BENAYAS J M,MARTINS A,NICOLAU J M,et al. Abandonment of agricultural land:an overview of drivers and consequences[J/OL]. CABI Reviews,2007:https://doj.org/10.1019/PAVSNNR20072057.
[5] YIN H,PRISHCHEPOV A V,KUEMMERLE T,et al. Mapping agricultural land abandonment from spatial and temporal segmentation of Landsat time series[J]. Remote Sensing of Environment,2018,210:12-24.
[6] 王玲玉,周忠发,赵馨,等. 基于地块级时序遥感的喀斯特石漠化地区撂荒地时空演变[J]. 水土保持学报,2020,34(1):92-99.
[7] RICHTER R,WANG X J,BACHMANN M,et al. Correction of cirrus effects in Sentinel-2 type of imagery[J]. International Journal of Remote Sensing,2011,32(10):2931-2941.
[8] FOGA S,SCARAMUZZA P L,GUO Song,et al. Cloud detection algorithm comparison and validation for operational Landsat data products[J]. Remote Sensing of Environment,2017,194:379-390.
[9] TUCKER C J. Red and photographic infrared linear combinations for monitoring vegetation[J]. Remote Sensing of Environment,1979,8(2):127-150.
[10] GAO B C. NDWI-a normalized difference water index for remote sensing of vegetation liquid water from space[J]. Remote Sensing of Environment,1996,58(3):257-266.
[11] MCFEETERS S K. The use of the normalized difference water index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing,1996,17(7):1425-1432.
[12] DIEK S,FORNALLAZ F,SCHAEPMAN M E,et al. Barest pixel composite for agricultural areas using landsat time series[J]. Remote Sensing,2017,9(12):1245.
[13] NGUYEN C T,CHIDTHAISONG A,KIEU DIEM P,et al. A modified bare soil index to identify bare land features during agricultural fallow-period in Southeast Asia using landsat 8[J]. Land,2021,10(3):231.
[14] ROY D P,KOVALSKYY V,ZHANG H K,et al. Characterization of Landsat-7 to Landsat-8 reflective wavelength and normalized difference vegetation index continuity[J]. Remote Sensing of Environment,2016,185:57-70.
[15] ZHANG H K,ROY D P,YAN Lin,et al. Characterization of Sentinel-2A and Landsat-8 top of atmosphere,surface,and nadir BRDF adjusted reflectance and NDVI differences[J]. Remote Sensing of Environment,2018,215:482-494.
[16] LI J,CHEN B Z. Global revisit interval analysis of Landsat-8/9 and Sentinel-2A/2B data for terrestrial monitoring[J]. Sensors,2020,20(22):6631.
[17] WULDER M A,MASEK J G,COHEN W B,et al. Opening the archive:how free data has enabled the science and monitoring promise of Landsat[J]. Remote Sensing of Environment,2012,122:2-10.
[18] CORTES C,VAPNIK V. Support-vector networks[J]. Machine Language,1995,20(3):273-297.
[19] MANTERO P,MOSER G,SERPICO S B. Partially supervised classification of remote sensing images through SVM-based probability density estimation[J]. IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):559-570.
[20] BREIMAN L. Random forests[J]. Machine Learning,2001,45(1):5-32.
[21] GREAVES H E,VIERLING L A,EITEL J U H,et al. High-resolution mapping of aboveground shrub biomass in Arctic tundra using airborne LiDAR and imagery[J]. Remote Sensing of Environment,2016,184:361-373.
[22] PAN L,XIA H M,ZHAO X Y,et al. Mapping winter crops using a phenology algorithm,time-series Sentinel-2 and Landsat-7/8 images,and Google Earth Engine[J]. Remote Sensing,2021,13(13):2510.

基于Sentinel-2和Landsat卫星时序数据的耕地撂荒识别

Abandoned land identification based on Sentinel-2 and Landsat satellite time series images

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	钟静, 孙杰, 赖祖龙, 谌一夫. ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量[J]. 测绘通报, 2023, 0(7): 39-43.
[2]	温亚飞, 刘宇, 王光辉, 张秋昭. Landsat 9数据的地表温度反演算法优化[J]. 测绘通报, 2023, 0(7): 74-79.
[3]	李晓彤, 李伟, 颉旭康, 黄宇曈. 考虑多种权重因子的改进叠加滤波方法[J]. 测绘通报, 2023, 0(7): 91-96.
[4]	石银涛, 胡超, 赵钢, 侯婷婷. PS-InSAR技术在长江堤防沉降监测中的应用[J]. 测绘通报, 2023, 0(7): 142-148.
[5]	李鹏, 周虹利, 林是聪, 王厚杰, 李振洪. 海洋塑料垃圾卫星遥感探测方法[J]. 测绘通报, 2023, 0(6): 20-26.
[6]	王冬梅, 吴勇锋, 石一凡, 梁文广, 王轶虹, 潘思远. 利用Sentinel-2遥感影像分析水葫芦时空分布规律[J]. 测绘通报, 2023, 0(6): 44-49.
[7]	张炎, 刘立龙, 何广焕, 徐勇, 蒙金龙. 改进哈里斯鹰优化算法在匹配地面点云孔洞修补中的应用[J]. 测绘通报, 2023, 0(6): 82-87.
[8]	江雪梨, 熊永良, 郭红梅, 赵真, 张莹, 孟雅湉. 改进随机森林模型在人口空间化中的应用[J]. 测绘通报, 2023, 0(6): 155-160.
[9]	程苗苗, 王世东, 张学军, 张合兵. 基于Landsat 8影像的城市蓝色顶面建筑物提取光谱模型构建[J]. 测绘通报, 2023, 0(3): 116-122.
[10]	于浩洋, 董春, 张辉. 融合空间信息和高光谱影像的四旁树自动提取方法[J]. 测绘通报, 2023, 0(2): 65-71.
[11]	唐菲菲, 唐天俊, 朱洪洲, 胡川, 马英, 李昕. 结合注意力机制和Bi-LSTM的降雨型滑坡位移预测[J]. 测绘通报, 2022, 0(9): 74-79,104.
[12]	陈睿哲, 涂伟, 李清泉, 谷宇, 左小清, 高文武. 融合多源测量数据的桥梁挠度异常探测方法[J]. 测绘通报, 2022, 0(9): 105-110.
[13]	孔瑞瑶, 谢涛, 马明, 孔瑞林. CatBoost模型在水深反演中的应用[J]. 测绘通报, 2022, 0(7): 33-37.
[14]	吕峥, 孙群, 温伯威, 马京振. 一种自身全局最优的道路网Stroke生成方法[J]. 测绘通报, 2022, 0(7): 93-99.
[15]	王春霞, 张俊, 李屹旭, 范成成. 一种基于Landsat 8的多波段组合水体指数模型[J]. 测绘通报, 2022, 0(5): 20-25.