Comparison of multi-temporal and multispectral Sentinel-2 and Unmanned Aerial Vehicle imagery for crop type mapping

Detta är en Master-uppsats från Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskap

Sammanfattning: Precision Agriculture aims to maximize crop production and the efficiency of land use to meet the increased demand for food while minimizing environmental impact and economic cost of food production. Crop type maps are needed for Precision Agriculture applications and remote sensing techniques are an efficient way to produce this information. However, at present, there is no single sensor that can provide sufficient data to assess the various growth stages and temporal changes of crops over the growing cycle. Therefore, this study investigated the possibility of combining Sentinel-2A and Unmanned Aerial Vehicle (UAV) data for crop monitoring. We evaluated the potential of the spectral, spatial and temporal information of Sentinel-2A imagery for crop type mapping at the plot level in southern Sweden. We explored the compatibility of spectral bands between MicaSense RedEdge and Sentinel-2A (S2A) to assess the utility of UAV observations in complementing and replacing satellite imagery with cloud-cover and noise. Moreover, we examined the seasonal variation of crops based on an annual time-series of S2A NDVI together with available UAV NDVI data. A supervised Random Forest classifier (RF) was calibrated and validated with ground truth data. We tested the performance of the Variable Selection using Random Forest (VSURF) algorithm to reduce the number of covariates in the classification and to eliminate redundancy in the dataset. We used S2A imagery from 12 dates (from April through July). The number of variables used in the classification was reduced from 145 to 8, with an accuracy of 93% and Kappa of 0.92. Regarding key spectral information, we found that red-edge and shortwave infrared (SWIR) were of high value for crop mapping. Also, the blue band appeared to be important for differentiating crops, together with the maximum NDVI for the growing season. Conversely, bands in the near infrared were amongst the least important for the classification of crops in the study area. Three atmospherically corrected S2A images were compared to three orthomosaics consisting of raw image values and reflectances. The comparison was based on averaged UAV pixels falling into S2A pixel sized cells. The band-by-band analysis evaluated the correlation and mean differences of reflectances and three vegetation indices (NDVI, EVI, and GCC). The results showed that the correlation of reflectances between sensors improved after the radiometric calibration performed by ATLAS. The most correlated bands were red and NIR, closely followed by the green band. However, statistically, significant differences were found in the actual physical units. Similarly, vegetation indices (VI) reduced the variability in the data and showed stronger correlations, although significant differences were also found mostly with EVI. VIs values from S2A imagery were higher in bare soil and lower in green areas compared to those from UAV orthomosaics. The S2A NDVI time-series for crop pixels showed potential to provide seasonality information that can be of high value for various agriculture applications, including crop monitoring. NDVI derived from UAV orthomosaics were used to complement the time-series and to evaluate how well they represent the temporal variation. TIMESAT was used to improve data quality and produce smooth seasonal curves. Results showed that despite absolute differences between the indices obtained from both sensors, UAV observations could provide continuity to the S2A time-series and improve up-scaling of vegetation phenology.

  HÄR KAN DU HÄMTA UPPSATSEN I FULLTEXT. (följ länken till nästa sida)