Surface biophysical features fusion in remote sensing for improving land crop/cover classification accuracy

Solmaz Fathololoumi; Mohammad Karimi Firozjaei; Huijie Li; Asim Biswas

doi:10.1016/j.scitotenv.2022.156520

Surface biophysical features fusion in remote sensing for improving land crop/cover classification accuracy

Sci Total Environ. 2022 Sep 10;838(Pt 3):156520. doi: 10.1016/j.scitotenv.2022.156520. Epub 2022 Jun 6.

Authors

Solmaz Fathololoumi¹, Mohammad Karimi Firozjaei², Huijie Li³, Asim Biswas⁴

Affiliations

¹ School of Environmental Sciences, University of Guelph, Canada. Electronic address: sfatholo@uoguelph.ca.
² Department of Remote Sensing and GIS, Faculty of Geography, University of Tehran, Tehran, Iran. Electronic address: mohammad.karimi.f@ut.ac.ir.
³ College of Resources and Environmental Engineering, Ludong University, Yantai, Shandong 264025, China. Electronic address: huijieli88@163.com.
⁴ School of Environmental Sciences, University of Guelph, Canada; College of Resources and Environmental Engineering, Ludong University, Yantai, Shandong 264025, China. Electronic address: biswas@uoguelph.ca.

PMID: 35679933
DOI: 10.1016/j.scitotenv.2022.156520

Abstract

Preparing up-to-date land crop/cover maps is important to study in order to achieve food security. Therefore, the aim of this study was to evaluate the impact of surface biophysical features in the land crop/cover classification accuracy and introduce a new fusion-based method with more accurate results for land crop/cover classification. For this purpose, multi-temporal images from Sentinel 1 and 2, and an actual land crop map prepared by Agriculture and Agri-Food Canada (AAFC) in 2019 were used for 3 test sites in Ontario, Canada. Firstly, surface biophysical features maps were prepared based on spectral indices from Sentinel 2 including Normalized Difference Vegetation Index (NDVI), Index-based Built-up Index (IBI), Wetness, Albedo, and Brightness and co-polarization (VV) and cross-polarization (VH) from Sentinel 1 for different dates. Then, different scenarios were generated; these included single surface biophysical features as well as a combination of several surface biophysical features. Secondly, land crop/cover maps were prepared for each scenario based on the Random Forest (RF). In the third step, based on the voting strategy, classification maps from different scenarios were combined. Finally, the accuracy of the land crop/cover maps obtained from each of the scenario was evaluated. The results showed that the average overall accuracy of land crop/cover maps obtained from individual scenario (one feature) including NDVI, IBI, Wetness, Albedo, Brightness, VV and VH were 66%, 68%, 63%, 60%, 57%, 62% and 58%, respectively, which by the surface biophysical features fusion, the overall accuracy of land crop/cover maps increased to 83%. Also, by combining the classification results obtained from different scenarios based on voting strategy, the overall accuracy increased to 89%. The results of this study indicate that the feature level-based fusion of surface biophysical features and decision level based fusion of land crop/cover maps obtained from various scenarios increases the accuracy of land crop/cover classification.

Keywords: Fusion; Land crop/cover; Random forest; Remote sensing; Surface biophysical features.

MeSH terms

Agriculture
Environmental Monitoring* / methods
Ontario
Remote Sensing Technology* / methods