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

doi:10.13474/j.cnki.11-2246.2023.0232

Abstract

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

CLC Number:

P237

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.

References

[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.